In an electrical power network linear and non-linear models are used for directional overcurrent relay (DOCR) coordination issue by applying different heuristic techniques. Nature inspired algorithms (NIA) have found great interest in power system optimization issues. This article proposes the recently developed meta-heuristic technique known as Firefly Algorithm (FA) that mimics the flashing behavior of fireflies. The implementation of the proposed algorithm has been utilized to solve the coordination of Directional Over-current Relay (DOCR) problems. The main aim of this work is to find out the optimum values of the Time Dial Setting (TDS) to minimize the relay operating time. The modifications to original FA has been implemented in this paper to solve the DOCR coordination issues. Self-adaptive weight and experience-based learning strategy are added in the original FA, named as improved firefly algorithm (IFA). In IFA, a self-adaptive weight is presented to change the propensity of moving the best solution and ignoring the worst solution. In addition, an experience-based learning system is created and utilized arbitrarily to keep up the populace-assorted variety and improve the exploration capacity. The IFA has been tested on IEEE 6 and 30-bus systems and tested on IEEE 9-bus system for numerical DOCRs and the results had been verified by a comparative study with other optimization techniques. The obtained results show that the IFA provides efficient and promising results compared to other meta-heuristic techniques mentioned in the literature. The IFA has been successfully implemented on MATLAB software programming.

The directional overcurrent relays (DOCRs) coordination is a useful tool in guaranteeing the safe protection of the power system by the proper coordination of primary and backup protection systems. The optimization model of this problem is non-linear and highly constrained. The main objective of this paper is to develop a hybridized version of the Whale optimization algorithm referred to as HWOA for the optimal coordination of the DOCRs. The hybridization is done by deploying the simulated annealing (SA) in the WOA algorithm in order to improve the best solution found after each iteration and enhance the exploitation by searching the most promising regions located by the WOA algorithm, which leads toward a globally optimum solution. The proposed algorithm has been applied to five test systems, including the IEEE 3-bus, 8-bus, 9-bus, 15-bus, and 30-bus test systems. Furthermore, the results obtained using the proposed HWOA are compared with those obtained using the traditional WOA and a number of up-to-date algorithms. The obtained results show the effectiveness of the proposed HWOA in minimizing the relay operating time for the optimal coordination of the DOCRs.

In this study, recently proposed JAYA algorithm is implemented on the economic load dispatch problmes (ELDPs). Different from most of the other meta-heuristics, JAYA algorithm needs no algorithm-specific parameters, and only two common parameters are required for effective execution, which makes the implementation simple and effective. Simultaneously, considering the non-convex, non-linear and non-smooth characteristics of the ELDPs, multi-population (MP) method is introduced to improve the population diversity. However, the introduction of MP method adds extra parameters to JAYA algorithm, hence a self-adaptive strategy (SAS) is used to cope with the tuning problem for extra parameters. Moreover, to avoid being trapped by local optima, Lévy flight distribution is incorporated into the population iteration phase. Finally, a self-adaptive multi-population JAYA algorithm with Lévy flights (AML-JAYA) is proposed, it is evaluated by ELDPs with different constraints including power balance constraints, generating capacity limits, ramp rate limits, prohibited operating zones (POZs), valve-point effects and multi-fuel options. The comparisons with state-of-the-art methods indicate that AML-JAYA algorithm can generate more competitive results for solving the ELDPs.

The world is shifting towards renewable energy sources due to the harmful effects of fossils fuel-based power generation in the form of global warming and climate change. When it comes to renewable energy sources, solar-based power generation remains on top of the list as a clean and carbon cutting alternative to the fossil fuels. Naturally, the sites chosen for installing solar parks to generate electricity are the ones that get maximum solar radiance throughout the year. Consequently, such sites offer challenges for the solar panels such as increased temperature, humidity and high dust levels that negatively affect their power generation capability. In this work, we are more concerned with the detection of dust from the images of the solar panels so that the cleaning process can be done in time to avoid power loses due to dust accumulation on the surface of solar panels. To this end, we utilize state-of-art deep learning-based image classification models and evaluate them on a publicly available dataset to identify the one that gives maximum classification accuracy for dusty solar panel detection. We utilize pre-trained models of 20 deep learning models to encode the images that are then used to train and validate four variants of a support vector machine. Among the 20 models, we get the maximum classification of 86.79% when the images are encoded with the pre-trained model of DenseNet169 and then use these encodings with a linear SVM for image classification.

The relay coordination problem is of dire importance as it is critical to isolate the faulty portion in a timely way and thus ensure electrical network security and reliability. Meanwhile a relay protection optimization problem is highly constraint and complicated problem to be addressed. To fulfill this purpose, Harris Hawk Optimization (HHO) is adapted to solve the optimization problem for Directional Over-current Relays (DOCRs) and numerical relays. As it is inspired by the intelligent and collegial chasing and preying behavior of hawks for capturing the prey, it shows quite an impressive result for finding the global optimum values. Two decision variables; Time Dial Settings (TDS) and Plug Settings (PS) are chosen as the decision variables for minimization of overall operating time of relays. The proposed algorithm is implemented on three IEEE test systems. In comparison to other state-of-the-art nature inspired and traditional algorithms, the results demonstrate the superiority of HHO.

Due to an increase in penetration of intermittent distributed energy resources (DERs) in conjunction with load demand escalation, the electric power system will confront more and more challenges in terms of stability and reliability. Furthermore, the adoption of electric vehicles (EVs) is increasing day by day in the personal automobile market. The sudden rise in load demand due to EV load might cause overloading of the potential transformer, undue circuit faults and feeder congestion. The objective of this paper is to develop a strategy for distribution feeder management to support the implementation of emergency demand response (EDR) during contingency and overload conditions. The proposed methodology focuses on management of smart home appliances along with EVs by considering demand rebound and consumer convenience indices, in order to reduce network stress, congestion and demand rebound. The developed scheme ensures that the load profile is retained below a certain level during a demand response event while mitigating demand rebound impacts. Simultaneously, the mitigation of consumers’ convenience level violation, information of smart loads and homeowners’ objective of serving critical loads are also considered during the event. The effectiveness of the developed approach is assessed by simulating a node of a distribution network of 300kW, consisting of 9 distribution transformers serving the associated homes. In this study, the smart loads such as an air conditioner/heater, an EV, a clothes dryer, and a water heater are also modeled and simulated. Furthermore, the simulation results are compared with an already developed de-centralized approach, and a simple fair distribution approach to evaluate and validate the effectiveness of the designed methodology. It is exhibited by the analysis of the results that the developed approach reduced the demand rebound following a demand response event and minimized the congestion at distribution transformer during overloading condition while maintaining the consumers’ comfort.