Showing papers in "Iet Generation Transmission & Distribution in 2020"

Probabilistic decomposition-based security constrained transmission expansion planning incorporating distributed series reactor

Abstract: This study presents a probabilistic transmission expansion planning model incorporating distributed series reactors, which are aimed at improving network flexibility. Although the whole problem is a mixed-integer non-linear programming problem, this study proposes an approximation method to linearise it in the structure of the Benders decomposition (BD) algorithm. In the first stage of the BD algorithm, optimal number of new transmission lines and distributed series reactors are determined. In the second stage, the developed optimal power flow problem, as a linear sub-problem, is performed for different scenarios of uncertainties and a set of probable contingencies. The Benders cuts are iteratively added to the first stage problem to decrease the optimality gap below a given threshold. The proposed model utilises the Monte Carlo simulation method to take into account uncertainty of wind generations and demands. Several case studies on three test systems are presented to validate the efficacy of the proposed approach.

Effect of electric vehicles on load frequency control in interconnected thermal and hydrothermal power systems utilising CF-FOIDF controller

Abstract: Load frequency control in modern-complex-uncertain power systems (PSs) assumes significance due to their challenging nature of the operation and hence utilisation of robust controllers is indispensable. In the industry, conventional single-loop controllers may not offer robust behaviour under changed operating conditions. Alternatively, two-loop cascade fuzzy structured controllers can show significant robust performance in dynamic conditions and best suited in systems having non-linearities. Hence, a novel optimal cascade fuzzy-fractional order integral derivative with filter (CF-FOIDF) controller is utilised for 2-area thermal and hydrothermal PSs considering various physical constraints from a practical point of view. As physical constraints mandate an energy storage system, hence in this study, batteries of electric vehicles (EVs) are employed to assist power plants to swiftly arrest oscillations in the system frequency following load demands. A combined model of EV fleets is incorporated in the control areas of PSs. Numerous simulations are conducted to authenticate the robustness and excellence of EVs and the suggested control strategy over existing methods.

Integrated energy hub system based on power-to-gas and compressed air energy storage technologies in the presence of multiple shiftable loads

Abstract: Integrated energy carriers in the framework of energy hub system (EHS) have an undeniable role in reducing operating costs and increasing energy efficiency as well as the system's reliability. Nowadays, power-to-gas (P2G), as a novel technology, is a great choice to intensify the interdependency between electricity and natural gas networks. The proposed strategy of this study is divided into two parts: (i) a conditional value-at-risk-based stochastic model is presented to determine the optimal day-ahead scheduling of the EHS with the coordinated operating of P2G storage and tri-state compressed air energy storage (CAES) system. The main objective of the proposed strategy is to indicate the positive impact of P2G storage and tri-state CAES on lessening the system uncertainties including electricity market price, power generation of the wind turbine, and even electrical, gas, and thermal demands. (ii) A demand response program focusing on day-ahead load shifting is applied to the multiple electrical loads according to the load's activity schedule. The proposed strategy is successfully applied to an illustrative example and is solved by general algebraic modeling system software. The obtained results validate the proposed strategy by demonstrating the considerable diminution in the operating cost of the EHS by almost 4.5%.

Reliability enhancement of electrical power system including impacts of renewable energy sources: a comprehensive review

Abstract: This study presents a comprehensive survey on the reliability evaluation of the electrical network system. The impacts of integration of new and renewable energy sources (electric vehicle, energy storage system, solar, and wind) on the reliability of electrical power system (EPS) are discussed. The impacts of these renewable sources have merits/demerits when these sources are integrated with the conventional electric power system. However, the merits are predominant as it includes unlimited, free, and cost-effective resources. The recent researches depict that the uncertainties of renewable energy resources leads to the probabilistic and reliability analyses of EPS. EPS includes offshore and onshore wind farms, micro-grid, energy storage system, and other high voltage grids. It also contains the failure-prone components related to the power systems. For the accomplishment of these aspects, the handling methods of uncertainty parameters in generation, transmission, and distribution systems are discussed. The incorporation of electric vehicles, wind energy system, and energy storage system for reliability assessment is also discussed briefly. This study also presents the scope of a new research area for the researchers on the reliability assessment of renewable energy integrated power system.

Review on the state-of-the-art multi-objective optimisation of hybrid standalone/grid-connected energy systems

Abstract: Integration of renewable and energy storage components in standalone/grid-connected energy systems, which results in hybrid energy systems, is increasing nowadays. Optimisation of hybrid energy systems is an essential matter for economic, clean, convenient and reliable energy supply. Since the optimal design should satisfy multiple objectives, application of multi-objective optimisation is preferred rather than a single-objective solution. By multi-objective optimisation, a trade-off among different objectives can be obtained. This study presents a timely survey on the state-of-the-art in multi-objective optimal design of hybrid standalone/grid-connected energy systems. The existing literature is categorised by various indices: (i) standalone or grid-connected mode; (ii) number and type of objective functions; (iii) completely renewable-based or diesel-renewable-based hybrid systems; and (iv) multi-energy systems. The applied objective functions, design constraints and decision variables in the optimisation of hybrid energy systems are addressed. It is found that the recent objective functions like customer satisfaction and grid-dependency need further investigation in the multi-objective design procedure.

Wigner distribution function and alienation coefficient-based transmission line protection scheme

Abstract: This study presents an algorithm for detection, classification, and location of transmission line faults. A fault index based on features extracted from current signals using the alienation coefficient and Wigner distribution function has been proposed for the detection and classification of faults. Double line and double line to ground faults have been classified from each other using ground fault index based on negative sequence current. Statistical relations are proposed for the estimation of fault location using peak values of the proposed fault index. The results of different case studies established the effectiveness of the algorithm. The algorithm is found to be effective for providing protection to transmission line against various faults. This is achieved using current signals recorded on one terminal of the line. This makes the protection scheme less complex, fast and more economic due to the elimination of the requirement of communication channel and global positioning system synchronisation. The proposed protection scheme is also validated on a real-time network of transmission utility. The effectiveness of the algorithm is established by comparing performance with reported algorithms.

Integrating layered recurrent ANN with robust control strategy for diverse operating conditions of AGC of the power system

Abstract: This study presents the structural, operational and control aspects of doubly fed induction generator (DFIG) based wind integrated power systems The automatic generation control (AGC) of a meshed power system including DFIG-based wind turbines has been framed and investigations under various system perturbation are presented The two-area system consisting of non-reheat thermal turbines with DFIG and interconnected through parallel AC/DC tie-lines is considered for the study The system non-idealities such as governor lag and generation rate constraints are taken into consideration An AGC strategy using a layered recurrent artificial neural network (ANN) is proposed in this work The gains of the proposed AGC are obtained by effectively training the ANN using a set of reliable data obtained from a widespread range of operating system conditions using robust control strategy The study also incorporates the design of AGC for the power system using the fuzzy logic concept and other AGC actions such as integral (I), proportional–integral (PI) and proportional–integral–derivative (PID) calculated via the means of particle swarm optimization (PSO) The results obtained with the proposed ANN created AGC are linked and demonstrated their superiority over fuzzy logic PI and traditional PSO-based I/PI/PID AGC strategies under numerous system operating conditions

EMD–PSO–ANFIS-based hybrid approach for short-term load forecasting in microgrids

Abstract: Accurate renewable energy generation and electricity demand forecasting tools constitute an essential part of the energy management system functions in microgrids. This study proposes a hybrid approach for short-term load forecasting in microgrids, which integrates empirical mode decomposition (EMD), particle swarm optimisation (PSO) and adaptive network-based fuzzy inference systems (ANFISs). The proposed technique first employs EMD to decompose the complicated load data series into a set of several intrinsic mode functions (IMFs) and a residue, and PSO algorithm is then used to optimise an ANFIS model for each IMF component and the residue. The final short-term electric load forecast value could be obtained by summing up the prediction results from each component model. The performance of the proposed model is examined using load demand dataset of a case study microgrid in Beijing and is compared with four other forecasting methods using the same dataset. The results show that the proposed approach yielded superior performance for short-term forecasting of microgrid load demand compared with the other methods.

Hybrid trading scheme for peer-to-peer energy trading in transactive energy markets

Abstract: This study proposes a hybrid energy trading scheme for peer-to-peer (P2P) energy trading in transactive energy markets. Market players can participate in different markets, including local markets, trading with neighbourhood areas, and traditional trading with the grid. In each local market, a community manager (CM) facilitates energy trading and negotiates with other CMs for neighbourhood trading. Based on the heterogeneous preferences of players of each community, each local market has a different price, which is different from market price for neighbourhood trading and trading with the grid. A distributed market clearing mechanism is presented that incorporates coordination among different markets. Also, a network utilisation charge function is defined to apply price signals to the market players to reflect network constraints in energy trading. These price signals are calculated based on the technical constraints in each market and are applied to the corresponding players based on their contribution to network constraints violation. Performance of the proposed trading scheme is evaluated against different market structures and through several case studies.

Robust UC model based on multi-band uncertainty set considering the temporal correlation of wind/load prediction errors

Abstract: With the increasing proportion of wind power connected to grid, power system dispatching is facing more and more challenges from uncertainty. To cope with this uncertainty, robust optimization has been applied in unit commitment (UC) problem. In this paper, a multi-band uncertainty set considering the temporal correlation (MBUSCTC) of wind/load prediction error is proposed firstly, which has two characteristics: (1) The MBUSCTC rigorously and realistically reflect the distribution characteristics of uncertainties in uncertainty intervals, thereby effectively reducing the conservatism of the traditional singe-band uncertainty set; (2) the temporal correlation constraints of wind power/load prediction errors in MBUSCTC could limit the realization of uncertainties fluctuating frequently in uncertain intervals, thereby eliminating scenarios with lower probability in uncertainty sets. Then the proposed MBUSCTC is applied to UC problem, leading a robust UC model based on MBUSCTC, which is solved by Benders decomposition method and C&CG method. Finally, case studies based on the modified IEEE-118 bus system and an actual power system of China demonstrate that the proposed method can effectively reduce the conservativeness of the robust UC model and ensure the robustness of the unit commitment solution.

Modelling of large-sized electrolysers for real-time simulation and study of the possibility of frequency support by electrolysers

Abstract: Hydrogen as an energy carrier holds promising potential for future power systems. An excess of electrical power from renewables can be stored as hydrogen, which can be used at a later moment by industries, households or the transportation system. The stability of the power system could also benefit from electrolysers as these have the potential to participate in frequency and voltage support. Although some electrical models of small electrolysers exist, practical models of large electrolysers have not been described in literature yet. In this publication, a generic electrolyser model is developed in RSCAD, to be used in real-time simulations on the real-time digital simulator. This model has been validated against field measurements of a 1 MW pilot electrolyser installed in the northern part of The Netherlands. To study the impact of electrolysers on power system stability, various simulations have been performed. These simulations show that electrolysers have a positive effect on frequency stability, as electrolysers are able to respond faster to frequency deviations than conventional generators.

Flexible operation of grid-connected microgrid using ES

Abstract: This study presents a new solution to cope with the intermittent nature of renewable generations (RGs) and facilitate the integration of RGs in the smart active distribution network. Electric spring (ES) as one of the most influential solutions in demand-side management is proposed as a flexible resource for flexible operation of grid-connected microgrid against other sources of uncertainty such as forecasted load demand and energy price as well as the RGs output. This innovative approach has been considered in the context of a stochastic problem by presenting the static model of ES for the first time. The modelling of uncertainties is done by the roulette wheel mechanism as a scenario generation process and backward method for reducing the number of scenarios. In the proposed optimisation problem, the objective function is minimising the operating cost and voltage deviation as well as maximising system flexibility, subject to the AC power flow, ES and RGs constraints and technical system limitations. Finally, the proposed solution is tested on 33-bus IEEE test system by the general algebraic modelling system software. The case studies demonstrate the efficiency of the proposed ES model in different simulation and experimental cases in providing flexi-renewable microgrid.

Review on voltage-violation mitigation techniques of distribution networks with distributed rooftop PV systems

Abstract: The integration of the various types of distributed generators in low-voltage (LV) distribution networks becomes a great concern, especially the rooftop photovoltaic (PV) systems. The negative impacts of the rooftop PVs on the distribution feeder buses' voltage include voltage rise and voltage unbalance (VU). Such a voltage-violation condition depends mainly on the PVs ratings and the network unbalance percentage. This study presents a review for different techniques used to mitigate the voltage violation resulting from PVs integration in a typical three-phase four-wire LV distribution network case study. The voltage-violation mitigation techniques studied in this study are enhancement of the feeder, on-load tap changer, demand-side management, active power curtailment, a reactive power control, static transfer switch, energy storage systems and hybrid strategies. The LV distribution network case study was modelled based on constant power model method using MATLAB software environment. The simulation results demonstrate both voltage regulation and alleviating VU capabilities of each technique.

Deep learning based method for false data injection attack detection in AC smart islands

Abstract: This paper investigates the false data injection attacks (FDIA) in an AC smart island and the detection solution of the attack on distributed energy resources in a smart island. In this study, a new scheme of FDIA detection is proposed based on wavelet singular values as input index of deep learning algorithm. In the proposed method, switching surface based on sliding mode control breaks down for adjusting accurate factors of wavelet transform and then features of wavelet coefficients are extracted by singular value decomposition. Indexes are determined according to the wavelet singular values in switching surface of voltage and current which defines the input indexes of deep machine learning and detecting FDIA. This cyber-protection plan has been put forward for cyber diagnostic and examined in different types of attacks happening in voltage and current signals derivation of measuring sensors as well as sending and receiving data from communication and control systems. The main priority of the suggested detection plan is the high capability to detect FDIA with a high accuracy. To show the effectiveness of the proposed method, simulation studies are performed on AC smart island in MATLAB/Simulink environment.

Implementation of hybrid SSA–SA based three-degree-of-freedom fractional-order PID controller for AGC of a two-area power system integrated with small hydro plants

Abstract: In this work, a comparative study is analysed between the fractional-order controllers such as fractional-order proportional–integral–derivative (FOPID), two-degree-of-freedom proportional–integral–derivative (DOF FOPID) and 3DOF FOPID, and conventional controllers such as proportional–integral–derivative (PID), 2DOF PID and 3DOF PID employed in automatic generation control (AGC) in power system. The proposed 3DOF FOPID controller is validated as superior one among all other controllers. The gains of all the controllers are optimally plucked by novel salp swarm algorithm (SSA). Further, hybrid salp swarm algorithm–simulated annealing (hSSA-SA) algorithm is introduced to enhance the proficiency of 3DOF FOPID controller by sensibly plucking the gain parameters. The proposed approaches are implemented in a two-area thermal-hydro-diesel system. Small hydro plants (SHPs) of similar characteristics are enforced in both areas with their dynamic responses by conceding frequency deviations of each area. Further, sensitivity and robustness analysis of the system with and without SHP are observed by varying some important parameters of the system. Finally, the supremacy of three novel approaches (fractional based controllers, hSSA-SA and SHP) is substantiated gracefully.

Review on generation and transmission expansion co-planning models under a market environment

Abstract: This study presents a review of the state-of-the-art on the coordination of generation and transmission expansion planning. First, the authors present the different investment and operation modelling approaches, with an emphasis on the centralised co-optimisation problem. Second, a comprehensive review of co-planning hierarchical equilibrium models, under a market environment, is carried out. The authors categorise the distinctive market approaches that usually represent the lower level of co-planning problems. They offer an updated and detailed classification of multilevel equilibrium models, based on their hierarchical and regulatory structure versus their equivalent reduced structure. Finally, the authors identify research gaps in the literature of each one of the mentioned model categories.

Hybrid cuckoo search algorithm and grey wolf optimiser-based optimal control strategy for performance enhancement of HVDC-based offshore wind farms

Abstract: The hybridisation of two or more algorithms is recently emerging to detect superior solutions to the optimization troubles. In this study, a new hybrid cuckoo search algorithm and grey wolf optimiser (CSA–GWO) optimisation technique is exercised and exhibited to optimally design and tune the controller parameters installed in the voltage source converter (VSC) of an offshore wind farm (OWF). One of the widely used control strategies for VSC is the proportional–integral (PI) closed-loop control system. The new hybrid optimisation algorithm is used to design and tune the PI controllers' parameters to improve the performance of OWF. It shall be mentioned that these parameters are usually hard to obtain owing to the high level of embedded non-linearity in such energy systems. The performance of such optimally designed PI controllers is presented in both dynamic and transient conditions. To examine the realistic stability of the proposed algorithm, real wind speed pattern has been captured from Egypt wind farm at Zafarrana and simulated. The obtained results from this new hybrid optimisation CSA -GWO control system reflect its superiority over other traditional algorithms, such as genetic algorithm, especially during symmetrical and unsymmetrical faults. CSA–GWO algorithm was examined using MATLAB/Simulink.

Hybrid deep learning for power generation forecasting in active solar trackers

Abstract: To meet the growing electricity demand for consumers, it is necessary to use more efficient systems. The solar trackers stand out among the applications that can improve the efficiency of photovoltaic panel generation by increasing their solar uptake. For solar trackers to be more efficient, they can base their position update on a generation forecast and thus perform the control action only when there is greater efficiency in this update. For generation forecast, the long–short-term memory (LSTM) can handle a large volume of non-linear data. Furthermore, to improve the analysis, it is possible to apply signal filtering techniques. The wavelet energy coefficient is a technique used to reduce signal noise and extract features; this technique performs the filter and preserves the signal characteristic. In this study, the authors present a combination of wavelet energy coefficient and LSTM, defined as wavelet LSTM, to perform photovoltaic power forecasting in the dual-axis solar trackers.

Enhancing the performance of wind energy conversion systems using unified power flow controller

Abstract: Due to the low converters rating and cost of doubly fed induction generator (DFIG) along with its ability to function under variable wind speed, DFIG has been widely employed in wind energy conversion systems (WECSs). Unfortunately, the performance of DFIG is sensitive to the variation in the operating conditions and disturbance events at the grid side. This includes wind gust, voltage fluctuation and faults at the point of common coupling of the DFIG and the grid. In this study, a model-free adaptive control (MFAC) is developed for a unified power flow controller (UPFC) in order to improve the overall dynamic performance of a DFIG-based WECS during wind gusts and enhance the fault ride through capability of the DFIG during various disturbance events. The effective performance of the proposed controller is assessed through a comparison with a conventional proportional–integral (PI) controller optimised by a modified flower pollination algorithm. Results reveal the superiority of the proposed UPFC-MFAC technique over the conventional PI controller currently used in most of the UPFC-WECS applications.

Optimal scheduling of reconfigurable grids considering dynamic line rating constraint

Abstract: Power system automation is an effective tool from both economical and technical aspects to improve the optimal operation of power generators. In this regard, Security Constrained Unit Commitment (SCUC) incorporating Dynamic Thermal Line Rating (DTLR) of overhead transmission lines can boost the system security effectively. Using Transmission Switching (TS) tool in SCUC problems leads to cost reduction. Still, one of the main challenges arisen in TS problems is the excessive number of switching in lines, which decreases the lifespan of power switches. In this paper, an Improved Linear AC Optimal Power Flow (ILACOPF) is proposed by using TS and considering Heat Balance Equation (HBE) as a security constraint. Merging dynamic thermal line rating (considering the weather conditions) in SCUC with TS, besides decreasing the number of switching and increasing the lifespan of power switches, causes a remarkable reduction in operating costs. In this power flow, system losses are modeled by linear formulations. Moreover, a linear approximation of the heat losses due to power flow through lines is proposed. To solve the proposed model, Benders' decomposition approach is applied. The performance of the proposed framework has been evaluated on 6-bus and 118-bus IEEE test systems.

Use of demand response for voltage regulation in power distribution systems with flexible resources

Abstract: In low-voltage power distribution systems with high penetration of photovoltaics (PVs) generation and electric vehicles (EVs), the over-voltage problem arises at times because of large PV generation, and under-voltage problem also arises sometimes because of simultaneous charging of massive EVs. Over- and under-voltage problems lead to more difficulties in achieving voltage regulation. Demand response (DR) is expected to be promising and cost-effective in promoting smart grids, and hence, the utilisation of flexible resources (FRs) through DR can be helpful for distribution system voltage regulation. This study introduces a hierarchical control structure of a community energy management system (CEMS) and multiple sub-CEMSs to apply an FR-based two-stage voltage regulation technique. In the first stage, i.e. the day-ahead scheduling stage, each sub-CEMS optimises the FRs' schedules for minimising customers' electricity cost and network voltage violation times. In the second stage, i.e. the real-time operation stage, the voltage sensitivity-based FRs' shifting method is proposed to eliminate network voltage violations caused by errors of estimated day-ahead data. The proposed models and methods are verified based on a realistic distribution system in Japan, where voltage violations, customer electricity cost and a number of on-load tap changer tap operations are proved to be reduced.

PIDF(1+FOD) controller for load frequency control with SSSC and AC–DC tie-line in deregulated environment

Abstract: In this study, a maiden application of cascade proportional–integral–derivative with filter (PIDF) and one plus fractional-order derivative (1+FOD), i.e. PIDF(1+FOD) controller is proposed for the load frequency control mechanism. The main purpose of the cascade and fractional order controller is to increase the degree of freedom and reject the disturbances faster. A novel attempt has also been made to model a static synchronous series compensator (SSSC) with AC tie-line and HVDC tie-line. Here SSSC and HVDC tie-line are used to regulate and increase the power transfer capabilities between interconnected areas. Furthermore stored energy in the HVDC tie-line is utilised to improve the system dynamics by inertia emulation control strategy. An evolutionary salp swarm algorithm-based optimisation technique is adopted to optimise control parameters. The performance of the proposed controller is tested on a two-area hydro-thermal interconnected power system in deregulated environment. First, the effectiveness AC–DC-SSSC tie line is shown over AC-SSSC and alone AC tie-line with proposed PIDF(1+FOD) controller followed by the supremacy of proposed PIDF(1+FOD) over classical controllers. Finally, sensitivity is analysed by variation in system parameters, which shows the robustness of the proposed controller.

Convolutional Neural Network-Based Intelligent Protection Strategy for Microgrids

Abstract: Microgrids experience significantly different fault currents in different operating scenarios, which make microgrid protection challenging. Existing intelligent protection schemes rely on the extraction of appropriate fault features using statistical parameters. The selection of these features is difficult in a microgrid because of its various operating scenarios. This study develops a convolutional neural network-based intelligent fault protection strategy (CNNBIPS) for microgrids that inherently integrates the feature extraction and classification process. The proposed strategy is directly applicable to three-phase (TP) current signals; thus, it does not require any separate feature extractor. In the proposed CNNBIPS, TP current signals sampled by the protective relays are used as an input to three different CNNs. The CNNs apply convolution and pooling operations to extract the features from the input signals. Then, fully connected layers of the CNNs employ the features to develop fault-type, phase, and location information. To analyse the efficacy of the proposed design, we execute exhaustive simulations on a standard microgrid test system. The results confirm the effectiveness of the proposed strategy in terms of detection accuracy, security, and dependability. Moreover, comparisons with previous methods show that the proposed approach outperforms the existing microgrid protection schemes.

Linear LAV-based state estimation integrating hybrid SCADA/PMU measurements

Abstract: The accuracy of power system state estimation (PSSE), its robustness against bad data and the speed of its algorithm are crucial to economic and secure system operation. On the other hand, observability and redundancy considerations mandate PSSE to take advantage of traditional supervisory control and data acquisition (SCADA) measurements along with available phasor measurement unit (PMU) measurements. This set of hybrid PMU/SCADA inputs has traditionally made the problem formulation non-linear, and hence time-consuming to solve due to the iterative process of solution. This study addresses the foregoing challenges by proposing a novel linear least-absolute-value (LAV) estimation, without the need for an initial guess of the system state. The linearity of the proposed PSSE formulation is guaranteed regardless of whether PMU-only, SCADA-only or hybrid SCADA/PMU measurements are utilised. This facilitates the fast and non-iterative solution of the LAV estimation of system state based on linear programming. The LAV estimator outperforms the weighted-least-squares estimator in dealing with erroneous measurements, by automatically rejecting bad data of any size. An extensive number of simulation studies carried out on test systems of different sizes confirm the superiorities of the proposed method in comparison with other existing PSSE methods.

State-of-the-art review on power system resilience and assessment techniques

Abstract: Modern societies these days are more dependent on electrical energy and they expect a continuous supply as per demand. In this regard, the complex power system is designed to supply electrical energy with a certain level of quality and continuity though it is still susceptible to vandalism, natural disasters, and extreme weather. The black sky event where the power grid goes down is more of a possibility nowadays than ever due to more frequent severe weather events. This in turn has increased the need to study resilience in the context of the power system. This study presents a comprehensive review of the literature on power system resilience from various perspectives. First, well-developed power system safety concepts are discussed and critically reviewed in view of large-scale power outages. Then, the various definitions and confounding features of resilience in the power system domain are presented. Subsequently, several frameworks, resilience curves, and quantitative metrics proposed in recent years for power system resilience are investigated, followed by a summary of hardening strategies. Next, a case study is presented to illustrate how the resilience of a 69-bus system is assessed against a hurricane. Finally, the study highlights challenges and proposes several future works to achieve a resilient power grid.

Mid-term electricity load forecasting by a new composite method based on optimal learning MLP algorithm

Abstract: Electricity load forecasting has been developed as an important issue in the deregulated power system in recent years. Many researchers have been working on the prediction of daily peak load for next month as an important type of mid-term load forecasting (MTLF). Nowadays, MTLF provides useful information for assessing environmental impacts, maintenance scheduling, adequacy assessment, scheduling of fuel supplies and limited energy resources etc. The characteristics of mid-term load signal, such as its non-stationary, volatile and non-linear behaviour, present serious challenges for this forecasting. On the other hand, many input variables and relative parameters can affect the load pattern. In this study, a new composite method based on a multi-layer perceptron neural network and optimisation techniques has been proposed to solve the MTLF problem. The proposed method has an optimal training algorithm composed of two search algorithms (particle swarm optimisation and improved ant lion optimiser) and a multi-layer perceptron neural network. The accuracy of the proposed forecast method is extensively evaluated based on several benchmark datasets.

Deep learning model to detect various synchrophasor data anomalies

Abstract: High-density synchrophasors provide valuable information for power grid situational awareness, operation and control. Unfortunately, due to factors including communication instability and hardware failure, their data quality can be greatly deteriorated by anomalies. Since the anomalies can impact the performance of the synchrophasor applications, it is of paramount significance to propose a model to detect anomalies in synchrophasor. In this study, a convolutional neural network model is established to detect and classify the anomalies in the synchrophasor measurements. Four types of anomalies observed in actual synchrophasors including erroneous patterns, random spikes, missing points and high-frequency interferences are considered in this study. The proposed model is extensively evaluated via field-collected measurements from the synchrophasor network in Jiangsu grid, China. The superior performance of the proposed model indicates the great potential of using deep learning for the detection of abnormal synchrophasor measurements.

Transient stability assessment combined model framework based on cost-sensitive method

Abstract: The real-time transient stability assessment (TSA) is critical for emergency control of power systems. Accurate and fast TSA can provide an important basis for post-fault control of power systems. At present, the accuracy of the evaluation model based on machine learning is very high, but there are still some misjudgements in the results. In order to build a high-accuracy evaluation model, a novel frame based on the cost-sensitive method is proposed. Firstly, a deep belief network (DBN) is applied to build a TSA frame. The DBN is effectively trained by means of pre-training and fine tuning. Secondly, two models with the opposite preference are constructed based on the cost-sensitive method. Based on the output results of the two models, the deterministic or uncertain evaluation results are obtained. The samples that may be misclassified are divided into uncertain evaluation results. Thus, the accuracy of the deterministic evaluation results can be improved greatly. Through this design, the practicability of the evaluation model based on machine learning is greatly improved. The effectiveness of the proposed scheme is verified by the simulation results in the IEEE-39 bus system and a realistic regional system.

Analysis of training techniques of ANN for classification of insulators in electrical power systems

Abstract: Identifying defects in electrical power systems during field inspections is a difficult task, since faults are generally not visible and may be intermittent. To find possible adverse conditions, specific inspection equipment is used. The ultrasound detector is the equipment normally used to inspect outdoor insulating systems; however, using it demands operator experience. To improve the defect condition classification, artificial intelligence techniques are applied to assist the operator in the decision task and thereby facilitate the identification of faulty insulating devices in the grid. The training of artificial neural network (ANN) models is an important step in solving the classification problem. This study aims to evaluate the training capacity in terms of the performance of different optimisation methods for the calculation of the mean square error after convergence. Traditional methods such as Gradient Descent and its variations will be presented, as well as methods that employ high computational effort such as quasi-Newton and Levenberg–Marquardt. In order to base these concepts, a review will be presented on the use of these algorithms and on the problem of classification of insulators in distribution networks. The results show that there is a considerable performance difference between the calculation methods.

1D-CNN based real-time fault detection system for power asset diagnostics

Abstract: Electromagnetic interference (EMI) diagnostics aid in identifying insulation and mechanical faults arising in high voltage (HV) electrical power assets. EMI frequency scans are analysed to detect the frequencies associated with these faults. Time-resolved signals at these key frequencies provide important information for fault type identification and trending. An end-to-end fault classification approach based on real-world EMI time-resolved signals was developed which consists of two classification stages each based on 1D-convolutional neural networks (1D-CNNs) trained using transfer learning techniques. The first stage filters the in-distribution signals relevant to faults from out-of-distribution signals that may be collected during the EMI measurement. The fault signals are then passed to the second stage for fault type classification. The proposed analysis exploits the raw measured time-resolved signals directly into the 1D-CNN which eliminates the need for engineered feature extraction and reduces computation time. These results are compared to previously proposed CNN-based classification of EMI data. The results demonstrate high classification performance for a computationally efficient inference model. Furthermore, the inference model is implemented in an industrial instrument for HV condition monitoring and its performance is successfully demonstrated in tested in both a HV laboratory and an operational power generating site.