Voltage source converter based multi – terminal DC grids (VSC – MTDC) are widely used for integration of renewable resources. Control of these grids requires vector control method, which includes inner and outer current controllers, tuning of these controllers is very important. Conventionally used tuning methods consider approximated linear model to tune the proportional – integral (PI) parameters of voltage source converter (VSC) which fails to produce optimum disturbance rejection results. In this research an Ant Colony Optimization (ACO) technique is used to get the optimum parameters of inner and outer power control layers for multi – terminal DC system. ACO is applied simultaneously on inner and outer control layers and results are compared with classical tuning method and well established meta - herustic technique, Particle Swarm Optimization (PSO) using MATLAB software. Dynamic models of VSC – MTDC are developed in PSCAD/EMTDC to exalt the qualities of the presented tuning method. In this paper, a four terminal VSC – MTDC has been used under different sequence of events of disturbances e.g. load change on AC side, active power reference change for inverter and rectifier mode and disconnection of one terminal to evaluate the robustness of ACO algorithm with respect to classical method. The proposed tuning method gives superior results under different disturbance compared to conventional method.

This research work proposes an Improved Supervised Learning (ISL)-based Deep Neural Network (DNN) for accurately forecasting the load demand of Electric Vehicles (EVs). This work incorporates Gated Recurrent Unit (GRU), Long Short Term Memory (LSTM), Recurrent Neural Network (RNN), Fully Connected (FC), and Convolutional Neural Network (CNN) architectures. The proposed ISL technique enhances prediction performance by refining the training process with additional features and information. Using a real-world EV charging dataset from Boulder City, USA, the simulations demonstrate consistent improvements in the GRU, LSTM, RNN, FC, and CNN models with the proposed ISL technique. Further, the proposed technique reduces the Normalised Root Mean Square Error (NRMSE) and Normalised Mean Absolute Error (NMAE) values. The accurate load demand predictions facilitated by the proposed models with ISL have significant implications for the planning and management of EV charging stations. This enables stakeholders to optimize resource allocation, effectively plan infrastructure capacity, and ensure the sustainable and reliable operation of grids in the face of increasing EV adoption. By leveraging deep learning architectures and incorporating the ISL technique, this research contributes to advancing load forecasting models for EVs, providing practical solutions for efficient management and planning in the evolving electric mobility landscape.

Increased adoption of the electric vehicle (EV) needs the proper charging infrastructure integrated with suitable energy management schemes. However, the available literature on this topic lacks in providing a comparative survey on different aspects of this field to properly guide the people interested in this area. To mitigate this gap, this research survey is an effort to provide know-how about the important aspects of the overall EV charging setup with 239 relevant references. It reviews the achievements of energy management systems in terms of improving fuel consumption efficiency and reducing carbon dioxide emissions in EV charging systems. State-of-the-art and most up-to-date standards of EV technology and charging infrastructure are presented. EV charging schemes based on standard grid and renewable energy resources are introduced with a brief comparison of the standard grid and photovoltaic-grid charging systems. Moreover, this article describes centralized and decentralized control configurations of EV charging. A comparative survey of different energy management algorithms is presented while highlighting the benefits and drawbacks of each algorithm. The work presented in this review will help frame future research needs. It is anticipated that the material gathered in this article will become a valuable source of information for the researchers working on this area of study.

This paper presents a modified and novel form of the conventional short-term hydrothermal scheduling problem by incorporating the effects of adding the photovoltaic energy source to the conventional grid. A photovoltaic energy source is intermittent in nature, therefore, to determine the optimal power contribution of the photovoltaic source towards the economic dispatch problem, a detailed strategy is presented in this paper. The proposed design method includes the forecasting of the photovoltaic system’s parameters using the Auto-Regressive Integrated Moving Average (ARIMA) model. The analytical model is developed based on the fractional integral polynomials for studying the characteristics of the single photovoltaic module. The optimization of power allocation in the system consisting of conventional and non-conventional energy sources is highly non-linear and classical deterministic methods can not be guaranteed to determine the optimal solution for economic power dispatch. The global optima of such non-linear and non-convex problems can be determined using swarm-based intelligence techniques. This paper presents accelerated particle swarm optimization and the firefly algorithm to determine a solution for short-term non-linear scheduling problems. The multiple test cases have been presented to demonstrate the effectiveness of the proposed solution over classical methods. The overall generation cost of the selected hybrid system is reduced using the proposed methods while meeting the generation constraints of each energy source. Moreover, due to the stochastic nature of the meta-heuristic techniques, a comprehensive statistical comparison, based on the independent T-test results, is also presented to highlight the algorithm which performs better for selected scheduling problems. It has been demonstrated that accelerated particle swarm optimization gives lower mean generation cost of the system whereas the execution time of the firefly algorithm is better compared to its counterpart.

Short term hydrothermal scheduling (STHTS) is a non-linear, multi-modal and very complex constrained optimization problem which has been solved using several conventional and modern metaheuristic optimization algorithms. A number of research articles have been published addressing STHTS using different techniques. This article presents a comprehensive review of research published for solving the STHTS problem in the last four decades.