Showing papers in "Journal of Electrical Engineering & Technology in 2021"
TL;DR: This paper proposes a novel gait event detection system that consists of saliency silhouette detection, a robust body parts model and a 2D stick-model followed by a hierarchical optimization algorithm that outperforms other similarly tasked methods in terms of posture detection and recognition accuracy.
Abstract: To understand daily events accurately, adaptive pose estimation (APE) systems require a robust context-aware model and optimal feature selection methods. In this paper, we propose a novel gait event detection (GED) system that consists of saliency silhouette detection, a robust body parts model and a 2D stick-model followed by a hierarchical optimization algorithm. Furthermore, the most prominent context-aware features such as energy, 0–180° intensity and distinct moveable features are proposed by focusing on invariant and localized characteristics of human postures in different event classes. Finally, we apply Grey Wolf optimization and a genetic algorithm to discriminate complex postures and to provide appropriate labels to each event. In order to evaluate the performance of proposed GED, two public benchmark datasets, UCF101 and YouTube, are examined via the n-fold cross validation method. For the two benchmark datasets, our proposed method detects the human body key points with 82.4% and 83.2% accuracy respectively. Also, it extracts the context-aware features and finally recognizes the gait events with 82.6% and 85.0% accuracy, respectively. Compared with other well-known statistical and state-of-the-art methods, our proposed method outperforms other similarly tasked methods in terms of posture detection and recognition accuracy.
48 citations
TL;DR: At atom search optimization (ASO) with unified power quality conditioner (UPQC) is designed to solve the power quality issues in hybrid renewable energy system (HRES) and compensate load demand in HRES system.
Abstract: Nowadays, the integration of hybrid renewable energy system (HRES) in grid connected load system are encouraged to increase reliability and reduce losses. The HRES system is connected to the grid system to meet required load demand and the integrated design creates the power quality (PQ) issues in the system due to non-linear load, critical load and unbalanced load conditions. Hence, in this paper, atom search optimization (ASO) with unified power quality conditioner (UPQC) is designed to solve the PQ issues in HRES system. The main objective of the work is the mitigation of PQ issues and compensate load demand in HRES system. The PQ issue problems are solved with the help of UPQC device in the system. The UPQC performance is increased by introducing fractional order proportional integral derivative (FOPID) with ASO based controller in series and shunt active power filter to mitigate PQ issues of current and voltage. Initially, HRES is designed with photovoltaic (PV) system, wind turbine (WT) and battery energy storage system (BESS) which connected with the load system. To analysis the presentation of the proposed controller structure, the non-linear load is connected with the system to create PQ issues in the system. The PQ issues are mitigated and load demand is reimbursed with the assistance of HRES system. The proposed method is employed in the MATLAB/Simulink platform and performances were analysed. Three different cases are used to validate the performance of the proposed method such as Sag, Swell, and disturbances. Additionally, total harmonic distortion (THD) is analysed. The proposed method is compared with existing methods of proportional integral (PI) controller, gravitational search algorithm (GSA), biogeography based optimisation (BBO), grey wolf optimization (GWO), extended search algorithm (ESA), random forest algorithm (RFA) and genetic algorithm (GA).
32 citations
TL;DR: In order to reasonably allocate the capacity of distributed generation and realize the goal of stable, economic and clean operation of the system, a multi-objective optimization model with investment cost, environmental protection and power supply quality as indicators has been established, and the multi- objective sparrow search algorithm is used to optimize the solution.
Abstract: In order to reasonably allocate the capacity of distributed generation and realize the goal of stable, economic and clean operation of the system, a multi-objective optimization model with investment cost, environmental protection and power supply quality as indicators has been established, and the multi-objective sparrow search algorithm is used to optimize the solution. Although the multi-objective search algorithm is more efficient than the traditional single objective algorithm, it is easy to fall into local optimum. To this end, the niche optimization technology is used to improve the optimization effect of multi-objective sparrow search algorithm, and the Levy flight strategy is introduced to enhance the ability of multi-objective sparrow search algorithm to jump out of local optimum. The calculation example uses the traditional multi-object search algorithm and the niche multi-objective sparrow search algorithm with levy disturbance to solve the proposed model. The simulation results verify the effectiveness of the multi-objective sparrow search algorithm improved by levy disturbance and niche optimization technology.
30 citations
TL;DR: Constrained Cartesian Genetic Programming (CCGP) is proposed, a variant of CGP to evolve lower order imprecise multipliers and further the higher order multipliers are constructed from them.
Abstract: As most of the real-world problems are imprecise, dedicating a lot of hardware for precise computations is futile for low-power applications and few applications where the precision is not of paramount importance. For such applications an imprecise computational block is sufficient if it has other performance benefits like low power and low area. We propose Constrained Cartesian Genetic Programming (CCGP), a variant of CGP to evolve lower order imprecise multipliers and further the higher order multipliers are constructed from them. Gate-level architectures for 2 × 2, 3 × 2, 3 × 3 and 4 × 4 imprecise multipliers are evolved. Also, we propose few partitioning methodologies for the construction of higher order multipliers using the evolved imprecise lower order multipliers. The constructed evolved-partitioned multiplier (EPM) of orders 8 × 8 and 16 × 16 has significant performance benefits over the existing multiplier architectures in terms of cell area and power. The circuits are synthesized using Cadence SoC Encounter® using TSMC® 180 nm standard cell library. The 16-bit EPMs show a maximum power reduction of 33% compared to other truncated multipliers and an area improvement of 2%.
29 citations
TL;DR: This paper investigates the feasibility of using machine learning (ML) based MPPT techniques, to harness maximum power on a PV system under PSC, and demonstrates that WK-NN performs significantly better when compared with other proposed ML based algorithms.
Abstract: The rapid growth of demand for electrical energy and the depletion of fossil fuels opened the door for renewable energy; with solar energy being one of the most popular sources, as it is considered pollution free, freely available and requires minimal maintenance. This paper investigates the feasibility of using machine learning (ML) based MPPT techniques, to harness maximum power on a PV system under PSC. In this study, certain contributions to the field of PV systems and ML based systems were made by introducing nine (9) ML based MPPT techniques, by presenting three (3) experiments under different weather conditions. Decision Tree (DT), Multivariate Linear Regression (MLR), Gaussian Process Regression (GPR), Weighted K-Nearest Neighbors (WK-NN), Linear Discriminant Analysis (LDA), Bagged Tree (BT), Naive Bayes classifier (NBC), Support Vector Machine (SVM) and Recurrent Neural Network (RNN) performances are validated and proved using MATLAB SIMULINK simulation software. The experimental results demonstrated that WK-NN performs significantly better when compared with other proposed ML based algorithms.
29 citations
TL;DR: A novel Multi Source Cascaded MultileVEL Inverter with a reduced number of switches for the efficient use of DC voltage sources and two Asymmetric Multilevel Inverters Topologies are proposed.
Abstract: Multilevel Inverter integrates several Direct Current (DC) sources to produce a single-phase Alternating Current (AC) waveform that can be used to meet the domestic and commercial power demand. This article introduces a novel Multi Source Cascaded Multilevel Inverter with a reduced number of switches for the efficient use of DC voltage sources. The conversion efficiency can be increased by the presented topology which is simple in design to overcome the significant switching losses in the power electronics devices. Optimal Firing Angle and Phase Opposition Disposition Pulse width Modulation Techniques were used to reduce the harmonics at the desired output of the inverter and also to improve the power quality of the presented topology. This article also proposes two Asymmetric Multilevel Inverter Topologies. A comparison has been made, on the number of switches required and the efficiency of the inverters to differentiate the presented Topologies from other topologies of the multilevel inverter. Finally, the performance characteristics of the presented topologies have been designed and investigated using MATLAB Simulation. Simulation results were validated using an experimental setup.
28 citations
TL;DR: An algorithm for estimating position with sliding mode observer (SMO) based on sigmoid function is proposed, and a sufficient condition that leads SMO into a sliding surface is acquired using Lyapunov stabilization analysis.
Abstract: It is impossible to install or apply position sensors appropriately in some special applications of PMSM. Sensorless PMSM control is an appropriate choice to solve some problems in the control of PMSM. It is necessary to acquire an estimated position precisely and avoid the chattering phenomenon for sensorless PMSM control. This paper proposes an algorithm for estimating position with sliding mode observer (SMO) based on sigmoid function, and a sufficient condition that leads SMO into a sliding surface is acquired using Lyapunov stabilization analysis. The outcome of this study shows that SMO based on sigmoid function for sensorless PMSM control can estimate position with high precision and avoid chattering phenomenon under the condition of different velocity and load. However, the estimated position needs to be compensated for according to load, and the compensating value is in proportion to the value of the current.
26 citations
TL;DR: In this paper, the authors proposed a novel approach for scene understanding that integrates multiple objects detection/segmentation and scene labeling using Geometric features, Histogram of oriented gradient and scale invariant feature transform descriptors.
Abstract: In the recent days, scene understanding has become hot research topic due to its real usage at perceiving, analyzing and recognizing different dynamic scenes coverage during GPS monitoring system, drone’s targets, auto-driving and tourist guide. The goal of scene understanding is to make machines look at like humans do, which means the accurate recognition of the contents in scenes and during location observations. Then, we perform two operations such as (1) to perfectly describe the whole environment and (2) to describe what action is going on in the environment. Due to complex scene analysis, recognition of multiple objects and the relation between the objects remain as a challenging part of the research. In this paper, we have proposed a novel approach for the scene understanding that integrates multiple objects detection/segmentation and scene labeling using Geometric features, Histogram of oriented gradient and scale invariant feature transform descriptors. The complete procedure of the purposed model includes resizing and noise removing of images from the dataset, multiple object segmentation and detection, feature extraction and multiple object recognition using multi-layer kernel sliding perceptron. After that, scene recognition is achieved by using multi-class logistic regression. Finally, two datasets such as MSRC and UIUC sports are used for the experimental evaluation of our proposed method. Our purposed method accurately handles the complex objects physical exclusion and objects occlusion. Therefore, it outperforms in term of accuracy compared with other state-of-the-art approaches.
24 citations
TL;DR: An improved Levy flight based grasshopper optimization algorithm (LGOA) is proposed to estimate the parameters of three PV models, i.e., single diode, double diodes, and PV module to ensure solutions diversity and enhances the exploration and exploitation capabilities.
Abstract: Recently, solar photovoltaic (PV) systems are becoming the tendency theme motivating researchers focus. The appropriate design of PV cells is an important task, challenged by the development of a useful model able to simulate the current vs voltage characteristics of the real solar cell and the accurate estimation of the PV cell’s parameter values. This paper proposes an improved Levy flight based grasshopper optimization algorithm (LGOA) to estimate the parameters of three PV models, i.e., single diode, double diode, and PV module. The incorporation of Levy flight trajectory to the basic grasshopper optimization algorithm (GOA), ensure solutions diversity and enhances the exploration and exploitation capabilities as well. To further validate its effectiveness LGOA is applied to the Sharp ND-R250A5 module under different operating conditions of irradiance and temperature. Experimental results demonstrate that LGOA has the ability to extract the parameters of PV models with high performance and good accuracy compared to the standard GOA.
23 citations
TL;DR: In this article, a new optimization tool-based population parameter called Harris hawks optimizer (HHO) and its application study to fine-tune the gains of well-designed proportional-derivative proportionalintegral (PD-PI) cascade control to suppress the load frequency control (LFC) issues.
Abstract: This paper presents a new optimization tool-based population parameter called Harris hawks optimizer (HHO) and its application study to fine-tune the gains of well-designed proportional-derivative proportional-integral (PD-PI) cascade control to suppress the load frequency control (LFC) issues. The HHO based PID and PD-PI controllers are broadly implemented at two models with many circumstances for each model to ensure the effectiveness and the robustness of the proposed scheme at a high load disturbance, nonlinearity, and some critical parameters associated with the interconnected power system. First, a two-area non-reheat power plant is implemented, and the gains of PID and PD-PI controllers are adjusted using the proposed algorithm. In order to introduce extra realistic challenges, the governor-dead band is also modeled to ensure the robustness of the HHO/PD-PI in handling nonlinearity properties. Furthermore, to guarantee the suitability of the proposed HHO/PD-PI, a model with a mixture of power plants is carried out with and without the HVDC link, which is raised for the practical problems of LFC. Simulation results proved that; the proposed techniques HHO/PID and HHO/PD-PI provide superior performance compared to other reported strategies such as DE/PID, TLBO/PID, IGWO/PID, multi-objective/PID, and TLBO/2DOF-PID controllers. Finally, the dynamic investigation has also been completed using the random load pattern in system model-2, which shows the superior performance of HHO/PID and HHO/PD-PI schemes.
22 citations
TL;DR: A new design of an MPPT controller based on a metaheuristic optimization technique called Crow Search Algorithm (CSA) to attenuate the undesirable effects of partial shading on the tracking performances of standalone PV systems is proposed.
Abstract: The field of research in maximum power point tracking (MPPT) methods is experiencing great progress with a wide range of techniques being suggested, ranging from simple but ineffective methods to more effective but complex ones. Therefore, it is very important to propose a strategy that is both simple and effective in controlling the global maximum power point (GMPP) for a photovoltaic (PV) system under changing weather conditions, especially in partial shading cases (PSCs). This paper proposes a new design of an MPPT controller based on a metaheuristic optimization technique called Crow Search Algorithm (CSA) to attenuate the undesirable effects of partial shading on the tracking performances of standalone PV systems. CSA is a nature-inspired method based on the intelligent skills of the crow in the search process of hidden food places. CSA technique combines efficiency and simplicity using only two tuning parameters. The stability analysis of the proposed system is performed using a Lyapunov function. The simulation results for three different partial shading cases that are zero, weak and severe shading confirm the superior performance of CSA compared to PSO and P&O techniques in term of easy implementation, high efficiency and low power loss, decreasing considerably the convergence time by an average of 38.53%.
TL;DR: A conclusion has been derived that the proposed approach yields superior dynamic performance for BLDC motor based on the results obtained for tuning of PID controller based on of GWO and PSO technique.
Abstract: A BLDC motor is superior to a brushed DC motor, as it replaces the mechanical commutation unit with an electronic one; hence improving the dynamic characteristics, efficiency and reducing the noise level marginally. Maximum BLDC motor drives use PID controller to control the speed of the machine; because it is simple in structure, relatively cheaper and exhibits good performance. But the main problem associated with PID controller is adjusting its parameters during implementation. In recent works, it has been observed that Particle Swarm Optimization (PSO) technique showed good performance in tuning PID controller. For this purpose, in this article, “Grey Wolf Optimization” (GWO) algorithm is introduced; which is used to optimally tune the PID controller parameters. The objective of this article is to compare the results obtained for tuning of PID controller based on of GWO and PSO technique and a conclusion has been derived that the proposed approach yields superior dynamic performance for BLDC motor.
TL;DR: This article investigates modeling and simulation of the off-grid photovoltaic (PV) system, and elimination of harmonic components using an LC passive filter, and determined the output power of the solar inverter, switching frequency, bus voltage etc.
Abstract: This article investigates modeling and simulation of the off-grid photovoltaic (PV) system, and elimination of harmonic components using an LC passive filter. Pulse width modulation (PWM) inverter is used to convert the direct current to alternating current. It is very important in terms of energy quality that the inverter output current total harmonic distortion (THDI) is below the value given by standards. Harmonic components have negatively effect on off-grid PV power system. THDI should be kept below a certain level in order to prevent damage to the equipment in the off-grid system and to ensure a higher quality energy flow to reduce the total harmonic distortion (THD) of the solar inverter output current; LC passive filter must be connected to the output of the PWM inverter. There are many types of passive filters for solar inverters. One of the most widely used filter types is the LC filter. LC filters are used in off-grid systems. LC filter is smaller in size and lower cost than other filters. But it is more complicated to determine the parameters of the LC filter. Therefore, in order for the system to remain in a steady state, the parameters must be accurately calculated and analyzed. In this study, the output power of the solar inverter, switching frequency, bus voltage etc. values were determined and LC filter parameters were calculated. Since high inductance values are used in LC filters, the voltage drop increases in these filters. To reduce the voltage drop, the DC bus voltage must be increased, which increases the switching losses. LC filter is connected between the inverter and the nonlinear load to filter the harmonic components produced by the DC/DC boost converter, DC/AC inverter and non-linear load. Matlab/Simulink program was used in Simulation and analysis of off-grid solar system. Solar inverter output current THD was measured as 91.55%. After the LC filter is connected to the system, this value has dropped to 2.62%.
TL;DR: The electromagnetic analysis aims to determine the average torque and cogging torque of spoke type BLDC motor and a comparative study with respect to Interior Permanent Magnet motor is provided.
Abstract: This paper investigates the electromagnetic and structural characteristics of a spoke type BLDC motor and provides a comparative study with respect to Interior Permanent Magnet motor (IPM).The electromagnetic analysis aims to determine the average torque and cogging torque of spoke type BLDC motor. The natural and induced vibration characteristics of the motor are evaluated by performing structural finite element analysis. The electromagnetic and vibration characteristics are assessed for different slot/pole combination to provide an insight on their influence on the performance of the motor. In addition, thermal analysis is performed to predict the temperature distribution and a comprehensive analysis of spoke type BLDC motor is presented.
TL;DR: The proposed model is developed using a nonlinear Hammerstein–Wiener model to accurately predict the behavior of lithium-ion battery cells and shows that the model is able to predict battery cell behavior with great accuracy.
Abstract: Lithium-ion batteries are a popular electrical storage choice for electric vehicles. This is motivated by their many advantages, such as their high energy density and cycling performance. This article aims to present a nonlinear model for the dynamic behavior of lithium-ion battery cells. For this purpose, we use measurements of electric vehicles at different driving cycles. This allows us to model lithium-ion battery cells using their dynamic behavior in real-world use cases. The proposed model is developed using a nonlinear Hammerstein–Wiener model to accurately predict the behavior of these cells. The proposed model prediction performance is evaluated using mean squared error (MSE), final prediction error (FPE), and goodness of fit between the Hammerstein–Wiener (H–W) model and the measured battery cell output. The results show that the model is able to predict battery cell behavior with great accuracy: The goodness of fit value shows that the presented Hammerstein–Wiener model matches the battery cell data by 93.77% in the identification phase, and by 93.74% in the validation phase for LA-92 drive cycle. In order to show the efficiency of the selected model (H–W), a comparative study is also conducted with other model types including a neural network model, a linear model and an equivalent electrical circuit model using the same measurements. The (H–W) model presented in this paper achieved better results in term of MSE compared to the other models.
TL;DR: In this paper, a combined solution is proposed to compromise the economic and environmental aspects via the Utopia point approach, where the optimal configuration of the hybrid PV/wind along with battery-storage and diesel engine as secondary source is obtained via meta-heuristic optimizers: Genetic Algorithm (GA) and Particle-Swarm Optimization (PSO) and impartial comparison of the results with HOMER software.
Abstract: This paper shows an application of hybrid PV/wind energy and battery storage in the islanded area. This work’s main target allows the distributed energy resources to contribute efficiently in the economic feasibility and enhance the environmental impact of the hybrid renewable energy source. Several factors such as levelized cost of energy (COE), greenhouse gas (GHG) emissions, and loss of power supply probability are studied. A combined solution is to compromise the economic and environmental aspects via the Utopia point approach is investigated. The optimal configuration of the hybrid PV/wind along with battery-storage and diesel engine as secondary source is obtained via meta-heuristic optimizers: Genetic Algorithm (GA) and Particle-Swarm Optimization (PSO) and impartial comparison of the results with HOMER software. The results of Utopia point solution show that the PV (about 46%) and wind turbine (about 13%) are shared significantly as primary renewable sources and battery storage (about 39%) as storage options. Meanwhile, the diesel engine (about 3%) has insignificant sharing in feeding the demand load. The optimal COE and GHG, which are achieved via GA and PSO optimization techniques are 0.182$/kWh and 12076 kg/year, agansit 0.343$/kWh and 17618 kg/year that are obtained via HOMER software, respectively. This corssponing to 47% and 31% reduction in COE and GHG, respectively. Sensitivity studies demonstrate that the variation of the wind energy sharing from 50 to 150% shows that the wind energy has a slight effect considering the GHG emissions. Contrarily, lower PV sharing ratios undesirably raises the levelized COE, however, reduces the GHG emissions.
TL;DR: A simultaneous network reconfiguration and capacitor placement in radial distribution network to minimize the real power losses, operating cost and to improve the bus voltages is proposed.
Abstract: The losses in the distribution networks due to the line resistance decrease the overall efficiency of the power distribution. Reducing the power losses and regulating the voltages within the limits are necessary to provide quality power to the consumers. The power loss can be minimized by optimum network reconfiguration and the placement of the capacitors. Considering independent network reconfiguration and placement of the capacitor is not effective during heavy loading conditions. This paper proposes a simultaneous network reconfiguration and capacitor placement in radial distribution network to minimize the real power losses, operating cost and to improve the bus voltages. The Johnson’s algorithm is used to find the minimal spanning tree during the network reconfiguration and an adaptive whale optimization algorithm is used as an optimization method. The proposed methodology is tested on standard IEEE 33-bus and 69-bus radial distribution systems. The effectiveness of the proposed method is validated by comparing the results with previous result reported in the literature in terms of cost saving and loss reduction.
TL;DR: It is indicated that the proposed method provides maximum profit to GENCOs when compared to other methodologies such as Memory Management Algorithm, Improved Particle Swarm Optimization (PSO), Muller method, Gravitational search algorithm etc.
Abstract: In restructured power system, Generation Companies (GENCOs) has an opportunity to sell power and reserve in power market to earn profit by market clearing process. Defining unit commitment problem in a competitive environment to maximize the profit of GENCOs while satisfying all the network constraints is called Profit Based Unit Commitment problem (PBUC). The main contribution of this paper is modeling and inclusion of Market Clearing Price (MCP) in PBUC problem. In Day market, MCP is determined by market operator which provides maximum social welfare for both GENCOs and Consumers.On other hand this paper proposes a novel combination of solution methodology: Improved Pre-prepared power demand (IPPD) table and Analytical Hierarchy method (AHP) for solving the optimal day ahead scheduling problem as an another contribution. In this method, the status of unit commitment is obtained by IPPD table and AHP provides an optimal solution to PBUC problem. Minimizing total operating cost of thermal units to provide maximum profit to GENCOs is called an optimal day ahead scheduling problem. Also it will be more realistic to redefine this problem to include multiple distributed resources and Electric vehicles with energy storage. Because of any uncertainties or fluctuation of renewable energy resources (RESs), Electric vehicles (EV) can be used as load, energy sources and energy storage. This would reduce cost, emission and to improve system power quality and reliability. So output power of solar (PS), wind output power (PW) and Electric Vehicles power (PEV) are modeled and included into day ahead scheduling problem.The proposed methodology is tested on a standard thermal unit system with or without RESs and EVs. Cost and emission reduction in a smart grid by maximum utilization of EVs and RESs are presented in this literature. It is indicated that the proposed method provides maximum profit to GENCOs when compared to other methodologies such as Memory Management Algorithm, Improved Particle Swarm Optimization (PSO), Muller method, Gravitational search algorithm etc.
TL;DR: In this paper, a regression controller based maximum power point tracking (MPPT) algorithm is developed for maximizing the efficiency of solar Photo Voltaic (PV) system, where the regression controller predicts the duty cycle for boost converter based on stored dataset of PV system output voltage and load, during partial shading effect or rapid isolation for that particular geographic location.
Abstract: Maximum Power Point Tracking (MPPT) algorithm performs for maximizing the efficiency of solar Photo Voltaic (PV) system. The solar photovoltaic system efficiency reduces due to partial shading and ambient atmospheric condition, which varies with geographic locations. Traditional MPPT systems solve the above problem through different soft computing algorithms such as Perturb and observe (P&O), Flower pollination algorithm (FPA) and Particle swarm optimization (PSO). In P&O, FPA and PSO algorithms, duty cycle of boost converter varies to attain MPPT. The soft computing algorithms in MPPT perform less during the partial shading effect or rapid insolation, fluctuation condition of solar energy. The performance of MPPT with traditional algorithms is reduced due to slow convergence speed and oscillations in tracking by computing algorithms. In this paper, Regression controller based MPPT achieve maximum peak voltage during partial shading effect is developed. The regression controller predicts the duty cycle for boost converter based on stored dataset of PV system output voltage and load, during partial shading effect or rapid isolation for that particular geographic location. The regression based duty cycle prediction controller is programmed in MATLAB R2018a Simulink. Furthermore, Regression controller is implemented in PV system test bed. The simulation and hardware results of Regression controller based MPPT perform more of about 20%, 16.96% and 15% in efficiency respectively than PSO, FPA and P&O algorithms during partial shading condition in PV.
TL;DR: A hybrid approach that involves the implementation of the Hilbert–Huang Transform and long short-term memory, recurrent neural networks to detect and classify power quality disturbances and it is possible to show that the ensemble recognition approach using the EEMD yields a better classification accuracy rate compared with the masking signal and the traditional HHT approach.
Abstract: Power quality disturbances are one of the main problems in an electric power system, where deviations in the voltage and current signals can be evidenced. These sudden changes are potential causes of malfunctions and could affect equipment performance at different demand locations. For this reason, a classification strategy is essential to provide relevant information related to the occurrence of the disturbance. Nevertheless, traditional data extraction and detection methods have failed to carry out the classification process with the performance required, in terms of accuracy and efficiency, due to the presence of a non-stationary and non-linear dynamics, specific of these signals. This paper proposes a hybrid approach that involves the implementation of the Hilbert–Huang Transform (HHT) and long short-term memory (LSTM), recurrent neural networks (RNN) to detect and classify power quality disturbances. Nine types of synthetic signals were reproduced and pre-processed taking into account the mathematical models and their specifications established in the IEEE 1159 standard. In order to eliminate the presence of mode mixing, the ensemble empirical decomposition (EEMD) and masking signal methods were implemented. Additionally, based on the successful benefits of LSTM RNNs reported in the literature, associated to the high accuracy rates achieved at learning long short-term dependencies, this classification technique is implemented to analyze the sequences obtained from the HHT. Based on the experimental results, it is possible to show that the ensemble recognition approach using the EEMD yields a better classification accuracy rate (98.85%) compared with the masking signal and the traditional HHT approach.
TL;DR: Comprehensive comparisons are made of the proposed method with the most popular state of the art techniques which show that this method provides more accurate prediction results.
Abstract: The wind power forecasting plays a vital role in renewable energy production. Due to the dynamic and uncertain behavior of wind, it is really hard to catch the actual features of wind for accurate forecasting measures. The patchy and instability of wind leading to the assortment of training samples have a main influence on the forecasting accuracy. For this purpose, an accurate forecasting method is needed. This paper proposed a new hybrid approach of clustering based probabilistic decision tree to forecast wind power efficiently. The collected data is screened for noisy information and selected those variables which mainly contribute in accurate predictions. Then, the wind data is normalized using mean and standard deviation to extract playing level fields for each feature. Based on the similarity of the data behavior, the K-means clustering algorithm is applied to classify the samples into different groups which contain the historical wind data. Further, the Naive Bayes (NB) tree is proposed to extract probabilities for each feature in the clusters. The NB tree is a hybrid model of C4.5 and NB methods that successfully applied on three big real-world wind datasets (hourly, monthly, yearly) collected from National Renewable Energy Laboratory (NREL). The forecasting accuracy exposed that the proposed method could forecast an accurate wind power from hours to years' data. Comprehensive comparisons are made of the proposed method with the most popular state of the art techniques which show that this method provides more accurate prediction results.
TL;DR: The proposed FTC scheme can validate the proposed FTC strategy and guarantee service continuity and the two techniques which are used to illustrate consistency in the proposed approach are the following: the sliding mode with encoder or without encoder-based control and the fuzzy logic control for efficient decision sent to the field-oriented control.
Abstract: The present study seeks to investigate the problem of fault tolerant speed control of the five-phase Permanent Magnet Synchronous Motor (PMSM) in the presence of speed sensor fault. Indeed, the sensors which are the most sensitive elements play a significant role in the closed loop control. In this context, an active Fault Tolerant Control (FTC) is developed based on fuzzy controller. Using the Sliding Mode Observer (SMO), the reconfiguration scheme which alternates between the measured speed value and the estimated one is proposed during failure occurrences so as to preserve the best control performance. The five-phase PMSM is monitored by a fuzzy logic controller to reduce disturbances that can occur under fault conditions. The two techniques which are used to illustrate consistency in the proposed approach are the following: the sliding mode with encoder or without encoder-based control and the fuzzy logic control for efficient decision sent to the field-oriented control. Simulation tests, in terms of the measured and the estimated speed responses, have been carried out on the five phase PMSM drive. The results demonstrate that the proposed FTC scheme can validate the proposed FTC strategy and guarantee service continuity.
TL;DR: The issue of simultaneous planning of electric vehicles and distributed generation resources has received more attention from energy researchers in recent years and a hybrid metaheuristic algorithms (HMA) has been used to obtain the optimal solution.
Abstract: The issue of simultaneous planning of electric vehicles and distributed generation resources has received more attention from energy researchers in recent years. Scattered renewable sources do not have a certain amount of production and, according to research, follow possible mathematical functions. Renewable energy sources are modeled on wind and solar production, both of which are moderately generated per hour. In this study, using, the optimal allocation problem of the electric vehicles parking lots and the optimal operation scheduling of the electric vehicles in a smart distribution network are studied as a novel optimization problem. In the proposed problem, the different factors including the technical and the economic issues are considered for achieving a realistic solution. In terms of technical issues, minimizing network losses, and minimizing voltage drop in feeders, as well as supplying all network demand are considered. Also, the total cost of the charging and discharge at the electric vehicles parking lots, and the total cost paid for purchasing power from upstream network are given as economic issues in the proposed problem. Moreover, the price-based DRP is considered due to the implementation of the demand side management program. To obtain the optimal solution, a hybrid metaheuristic algorithms (HMA) has been used. The proposed problem is simulated on the standard IEEE 69-bus. It is solved by the proposed HMA and is compared with another heuristic method. The obtained results confirm the accuracy and efficiency of the proposed problem. The obtained results show increased to an acceptable level, the voltage profile was improved and network losses were reduced. Finally, the results curves and tables show the efficiency of the proposed method.
TL;DR: An improved metaheuristic optimization algorithm based on the fireflies algorithm, called multidimensional firefly algorithm (MDFA), is presented for solving day-ahead scheduling optimization in a microgrid.
Abstract: In this paper, an improved metaheuristic optimization algorithm based on the firefly algorithm, called multidimensional firefly algorithm (MDFA), is presented for solving day-ahead scheduling optimization in a microgrid. The proposed algorithm takes the output of power generations among a quantity of distributed energy resources during 24 h together rather than a single hour as a firefly separately. The proposed algorithm is combined with strategy of solving equality constraint replacing the use of the penalty-function technique. It is also enhanced by using a novel method in parameters self-adaption instead of applying fixed values, resulting in avoiding tuning frequently the algorithm parameters during the process of optimization. The MDFA is utilized for optimization of energy production cost in a microgrid. The superiority of the MDFA is demonstrated by using the classic test power system proved in the previous literature. The solutions obtained by MDFA are compared with the results found by five famous optimization algorithms. The high performance of MDFA is established by the quality with the minimum total cost, the reliability of gained solutions, the speed of convergence, and the ability to satisfy various constraints.
TL;DR: In this article, the authors found out the teachers' barriers and supports in conducting online learning and recommended three optional solutions to help the teacher facing their barriers in virtual teaching, in terms of students participation in online learning, learning materials, and facilities in supporting the learning activities.
Abstract: The pandemic of COVID-19 situation has converted the teaching and learning process from face-to-face interaction in the classroom into virtual classroom environment. This condition caused challenges for many parties, including teachers as the main agent in the classroom. This study is intended to find out the teachers’ barriers and supports in conducting online learning. A descriptive qualitative method design through an open-ended questionnaire was chosen. Interview were also used to triangulate the data. Twenty-one teachers from sub-urban areas in Cimahi and Bandung were selected as the participants. The findings revealed three issues becoming teachers' challenges, namely, technology, course content, and students. In the first issue, the classic problem of online learning occurred, which was internet connectivity. The second problem was that the teachers had obstacles in making adjustments to design, deliver, and follow-up the material. Then the last issue was the students’ participation as well as technological access. Regarding the supports, the teachers had gained back up from the government, school, and parent in conducting online learning. Furthermore, this study recommended three optional solutions to help the teacher facing their barriers in virtual teaching, in terms of students’ participation in online learning, learning materials, and facilities in supporting the learning activities.
TL;DR: In this paper, the authors proposed two techniques of optimal PID controllers in a hybrid renewable generation energy system, particle swarm optimization (PSO) and lightning attachment procedure optimization (LAPO), to enable renewable energy resources to participate effectively within hybrid micro grids via an optimal proportional integral derivative (PID) controller.
Abstract: The main target of this paper is to allow renewable energy resources (RES) to participate effectively within hybrid micro grids via an optimal proportional integral- derivative (PID) controller. This paper proposes two techniques of optimal PID controllers in a hybrid renewable generation energy system. These techniques are particle swarm optimization (PSO) and lightning attachment procedure optimization (LAPO). The hybrid renewable generation energy system in this study includes a photovoltaic source, wind turbine, and battery storage, which are connected to a point of common coupling via DC/DC boost converters. The controller at the inverter consists of a current controller and voltage source controller, which results in three PID gains at each controller. In order to obtain the PID gains, a time domain objective function is formulated in terms of the voltage, and current errors. The obtained results with the individual advanced optimization LAPO and PSO algorithm are compared. The results display that the developed LAPO algorithms give better results compared to the conventional PSO at the input and output current, voltage, and power. All the results have been taken under several operating conditions of wind turbine (wind speed) and solar sun (changing irradiance and temperature).
TL;DR: This research aimed to estimate the resulting amount of power produced by the hybrid system and mathematical models were submitted and showed the share of the total energy supplying the electricity demand for each part of the network.
Abstract: The assessment of the performance of grid hybrid frameworks depends primarily on the costs and reliability, associated with reduced greenhouse gas (GHG) emissions of the system. In this work, with objectives based on the minimization of two optimization features, namely loss of power supply probability (LPSP) and cost of energy (COE), multi-objective optimization of a grid-connected PV/wind turbine framework was implemented in the Faculty of Engineering in Gharyan, Libya, with the aim of providing adequate electricity, while optimizing the system’s renewable energy fraction (REF) was the third objective. This research also aimed to estimate the resulting amount of power produced by the hybrid system and mathematical models were submitted. The results showed the share of the total energy supplying the electricity demand for each part of the network. This study subsequently explored the interrelationship of the grid and the proposed hybrid system in relation to the capacity of the network to sell or obtain electricity from the hybrid system. In addition, multi-objective bat algorithm (MOBA) findings were divided into three dominant regions: the first region was the economically optimal solution (lowest COE), the second region was the conceptual perspective of utilizing renewable energies (highest REF), and the final region was the optimal solution with optimal environmental effects (lowest GHG emissions).
TL;DR: In this article, the authors proposed a Unified Fault-Tolerant Control System (UFTCS) based on advanced analytical and hardware redundancies for Air-Fuel Ratio (AFR) control of Spark Ignition (SI) Internal Combustion (IC) engines.
Abstract: This paper proposes a Unified Fault-Tolerant Control System (UFTCS) based on advanced analytical and hardware redundancies for Air-Fuel Ratio (AFR) control of Spark Ignition (SI) Internal Combustion (IC) engines. The advanced analytical redundancy part is termed the Hybrid Fault-Tolerant Control System (HFTCS) which consists of both active and passive types. The Lookup Tables (LTs) have been utilized in the active part and a robust proportional feedback controller of high gain with fuel throttle actuator has been implemented in the passive part. Since the failure of any two sensors at the same time or failure of a single actuator causes engine shutdown, an advanced hardware redundancy protocol Modified Triple Modular Redundancy (MTMR) has been suggested for the sensors, and Dual Redundancy (DR) has been proposed for the actuators to prevent the tripping of the engine. MATLAB/Simulink simulation results indicate that the suggested UFTCS is highly robust to the sensor faults in both normal and noisy conditions. The probabilistic reliability analysis for various hardware redundancy schemes also proves the greater overall reliability of UFTCS. Finally, a comparison with the existing AFR control systems is carried out to demonstrate its superior performance.
TL;DR: A new mathematical-based strategy for identifying different types of trading situations considering VPPs effects is proposed in the electricity market to obtain maximum benefit and shows notable profits in both modes.
Abstract: A group of distributed generators (DGs) systems including wind, solar, diesel, energy storage (ES), etc., that are under a central management and control is often considered as virtual power plant (VPP) concept. One of the components of a VPP is ES, whose presence and participation in the electricity market can create business opportunities. In this paper, a new mathematical-based strategy for identifying different types of trading situations considering VPPs effects is proposed in the electricity market to obtain maximum benefit. Also VPP trading between energy and ancillary services is considered and analysed. The presented model considers all limitations of the VPP including network constrains and the structure of VPPs. The optimal management of distributed energy units determines the state of charge (SoC) or discharge of ES resources and the amount of intermittent load for the day ahead electricity market. By implementing the proposed model on the microgrid (MG), two different modes of trading for VPPs are examined and the changes of efficiency related to energy storages are analysed. In order to solve the issue of optimal operation strategy, an intelligent approach based on differential evolution (DE) algorithm is used. The obtained simulation results of both modes are compared with those VPP without energy storage. The results show notable profits in both modes.
TL;DR: A pedestrian detection method with higher accuracy and faster speed based on Faster Regions Convolutional Neural Network (Faster RCNN) method, which is the leading method in the field of target detection.
Abstract: Pedestrian detection in traffic environment requires high accuracy and speed of the algorithm. Traditional methods can meet the speed requirement, but there is a long gap in accuracy. Traditional methods based on convolution neural network have higher accuracy, but the amount of calculation is enormous. Aiming at the problems of background confusion, there are pedestrian ambiguity and pedestrian multi-scale in pedestrian detection, this paper constructs a pedestrian detection method with higher accuracy and faster speed based on Faster Regions Convolutional Neural Network (Faster RCNN) method, which is the leading method in the field of target detection. We have mainly improved three aspects: (1) The design criteria based on the summary and the scale characteristics of pedestrians; (2) The setting of anchor windows and the way of creating regional networks have been adjusted, and the pooling layer of environmental regions has been added; (3) Fusion of different levels of features acquires more comprehensive features. Then, based on the open-source deep learning framework, the network is implemented on the California Institute of Technology pedestrian data set. The experimental results show that our method improves the detection accuracy by 2.9% and the detection speed by 10.1 frames/second compared with the original Faster RCNN on the same data set.