The modernisation of the world has significantly reduced the prime sources of energy such as coal, diesel and gas. Thus, alternative energy sources based on renewable energy have been a major focus nowadays to meet the world's energy demand and at the same time to reduce global warming. Among these energy sources, solar energy is a major source of alternative energy that is used to generate electricity through photovoltaic (PV) system. However, the performance of the power generated is highly sensitive on climate and seasonal factors. The unpredictable behaviour of the climate affects the power output and causes an unfavourable impact on the stability, reliability and operation of the grid. Thus an accurate forecasting of PV output is a crucial requirement to ensure the stability and reliability of the grid. This study provides a systematic and critical review on the methods used to forecast PV power output with main focus on the metaheuristic and machine learning methods. Advantages and disadvantages of each method are summarised, based on historical data along with forecasting horizons and input parameters. Finally, a comprehensive comparison between machine learning and metaheuristic methods is compiled to assist researchers in choosing the best forecasting technique for future research.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-rpg.2018.5649

Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques

Recently, multilevel inverters (MLIs) have gained lots of interest in industry and academia, as they are changing into a viable technology for numerous applications, such as renewable power conversion system and drives. For these high power and high/medium voltage applications, MLIs are widely used as one of the advanced power converter topologies. To produce high-quality output without the need for a large number of switches, development of reduced switch MLI (RS MLI) topologies has been a major focus of current research. Therefore, this review paper focuses on a number of recently developed MLIs used in various applications. To assist with advanced current research in this field and in the selection of suitable inverter for various applications, significant understanding on these topologies is clearly summarized based on the three categories, i.e., symmetrical, asymmetrical, and modified topologies. This review paper also includes a comparison based on important performance parameters, detailed technical challenges, current focus, and future development trends. By a suitable combination of switches, the MLI produces a staircase output with low harmonic distortion. For a better understanding of the working principle, a single-phase RS MLI topology is experimentally illustrated for different level generation using both fundamental and high switching frequency techniques which will help the readers to gain the utmost knowledge for advance research.

/pdf/recently-developed-reduced-switch-multilevel-inverter-for-4lxrfejht6.pdf

Recently Developed Reduced Switch Multilevel Inverter for Renewable Energy Integration and Drives Application: Topologies, Comprehensive Analysis and Comparative Evaluation

http://dspace.uniten.edu.my/jspui/bitstream/123456789/13396/1/Gridconnected-renewable-energy-sources-Review-of-the-recent-integration-requirements-and-control-methodsJournal-of-Cleaner-Production.pdf

Grid-connected renewable energy sources: Review of the recent integration requirements and control methods

In this paper, hybrid brain-computer interface (hBCI) technologies for improving classification accuracy and increasing the number of commands are reviewed. Hybridization combining more than two modalities is a new trend in brain imaging and prosthesis control. Electroencephalography (EEG), due to its easy use and fast temporal resolution, is most widely utilized in combination with other brain/non-brain signal acquisition modalities, for instance, functional near-infrared spectroscopy (fNIRS), electromyography (EMG), electrooculography (EOG), eye tracker, etc. Three main purposes of hybridization are to increase the number of control commands, improve classification accuracy, and reduce the signal detection time. Currently, such combinations of EEG+fNIRS and EEG+EOG are most commonly employed. Four principal components (i.e., hardware, paradigm, classifiers, features) relevant to accuracy improvement are discussed. In the case of brain signals, motor imagination/movement tasks are combined with cognitive tasks to increase active BCI accuracy. Active and reactive tasks sometimes are combined: motor imagination with steady-state evoked visual potentials (SSVEP), and motor imagination with P300, etc. In the case of reactive tasks, SSVEP is most widely combined with P300 to increase the number of commands. Passive BCIs, however, are rare. After discussing the hardware and strategies involved in the development of hBCI, the second part examines the approaches used to increase the number of control commands and to enhance classification accuracy. The future prospects and the extension of hBCI in real-time applications for daily life scenarios are provided.

/pdf/hybrid-brain-computer-interface-techniques-for-improved-x6kgxccccc.pdf

Hybrid Brain-Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review.

Multilevel inverters (MLIs) are a great development for industrial and renewable energy applications due to their dominance over conventional two-level inverter with respect to size, rating of switches, filter requirement, and efficiency. A new single-phase cascaded MLI topology is suggested in this paper. The proposed MLI topology is designed with the aim of reducing the number of switches and the number of dc voltage sources with modularity while having a higher number of levels at the output. For the determination of the magnitude of dc voltage sources and a number of levels in the cascade connection, three different algorithms are proposed. The optimization of the proposed topology is aimed at achieving a higher number of levels while minimizing other parameters. A detailed comparison is made with other comparable MLI topologies to prove the superiority of the proposed structure. A selective harmonic elimination pulse width modulation technique is used to produce the pulses for the switches to achieve high-quality voltage at the output. Finally, the experimental results are provided for the basic unit with 11 levels and for cascading of two such units to achieve 71 levels at the output.

/pdf/optimal-design-of-a-new-cascaded-multilevel-inverter-92toxxo1kk.pdf

Optimal Design of a New Cascaded Multilevel Inverter Topology With Reduced Switch Count

There is a growing interest of research being conducted on detecting eye blink to assist physically impaired people for verbal communication and controlling devices using electroencephalogram (EEG) signal. One particular eye blink can be determined from use of peak points. Therefore, the purpose of peak detection algorithm is to distinguish an actual peak location from a list of peak candidates. The need of a good peak model is important in ensuring a satisfy classification performance. In general, there are various peak models available in literature, which have been tested in several peak detection algorithms. In this study, performance evaluation of the existing peak models is conducted based on Artificial Neural Network (ANN) with particle swarm optimization (PSO) as learning algorithm. This study evaluates the performance of eye blink EEG signal peak detection algorithm for four different peak models which are Dumpala's, Acir's, Liu's, and Dingle's peak models. To generalize the performance evaluation, two case studies of eye blink EEG signal are considered, which are single and double eye blink signals. It has been observed that the best test performance, in average, is 91.94% and 87.47% for single and double eye blink signals, respectively. These results indicate that the Acir's peak model offers high accuracy of peak detection for the two eye blink EEG signals as compared to other peak models. The result of statistical analysis also indicates that the Acir's peak model is better than Dingle's and Dumpala's peak models.

/pdf/evaluation-of-different-peak-models-of-eye-blink-eeg-for-sqp3kn2fh9.pdf

Evaluation of different peak models of eye blink EEG for signal peak detection using artificial neural network

Growing electricity demand, the deployment of renewable energy sources and the widespread use of smart home appliances provide new opportunities for home energy management systems (HEMSs), which can be defined as systems that improve the overall energy production and consumption of residential buildings by controlling and scheduling the use of household equipment. By saving energy, reducing residential electricity costs, optimizing the utilization rate and reliability of utility companies’ power systems, and reducing air pollution for society, HEMSs lead to an enhancement in the socioeconomic development of low-carbon economies. This review aims to systematically analyze and summarize the development trends and challenges of HEMSs in recent years. This paper reviews the development history of the HEMS architecture and discusses the characteristics of several major communication technologies in the current HEMS infrastructure. In addition, the common objectives and constraints related to scheduling optimization are classified, and several optimization methods in the literature, including various intelligent algorithms, have been introduced, compared, and critically analyzed. Furthermore, experimental studies and challenges in the real world are also summarized and recommendations are given. This paper reveals the trend from simple to complex in the architecture and functionality of HEMSs, discusses the challenges for future improvements in modeling and scheduling, and shows the development of various modeling and scheduling methods. Based on this review, researchers can gain a comprehensive understanding of current research trends in HEMSs and open up ideas for developing new modeling and scheduling approaches by gaining insight into the trade-offs between optimum solutions and computational complexity.

Home Energy Management Systems: A Review of the Concept, Architecture, and Scheduling Strategies

This study presents the improved phase disposition pulse width modulation (PDPWM) technique control for MMCs, which is flexible for fault-tolerant capability. Fault tolerance improves converter reliability, which is one of the important issues of half-bridge MMCs with considerable switching devices. In this study, MMC with a fault condition has been analyzed. So, a modulation control for the fault-tolerant method has been presented as well as described in simulation model. The proposed method bypasses the faulty SM when the malfuntioning occurs. This method does not produce interfere the reference signal and using only one single carrier form which reduces the software requirement. Simulation is contained to validate the fault-tolerant capability of the proposed modulation strategy for MMCs.

Modular Multilevel Converter Modulation Technique with Fault-tolerant Capability

This paper presents a performance evaluation of a novel Vector Evaluated Gravitational Search Algorithm II (VEGSAII) for multi-objective optimization problems. The VEGSAII algorithm uses a number of populations of particles. In particular, a population of particles corresponds to one objective function to be minimized or maximized. Simultaneous minimization or maximization of every objective function is realized by exchanging a variable between populations. The results shows that the VEGSA is outperformed by other multi-objective optimization algorithms and further enhancements are needed before it can be employed in any application.

Performance Evaluation of Vector Evaluated Gravitational Search Algorithm II

A simple noise-speech discrimination method in time domain is presented. The random signal noise characteristics were studied in time domain. Using the characteristics information, in real time processing, a simple algorithm to detect starting and ending point of speech samples in time domain is being demonstrated. Out of 100 attempts, about 94% of successful attempts of noise-speech discrimination have been obtained with white noise background by choosing the critical thresholds values.

http://eprints.um.edu.my/6134/1/Real_time_noise%2Dspeech_discrimination_in_time_domain_for_speech_recognition_application.pdf

Marizan Mubin

Papers

Evaluation of different peak models of eye blink EEG for signal peak detection using artificial neural network

Home Energy Management Systems: A Review of the Concept, Architecture, and Scheduling Strategies

Modular Multilevel Converter Modulation Technique with Fault-tolerant Capability

Performance Evaluation of Vector Evaluated Gravitational Search Algorithm II

Real time noise-speech discrimination in time domain for speech recognition application