A reasonable dataset, which is an essential factor of renewable energy forecasting model development, sometimes is not directly available. Waiting for a substantial amount of training data creates a delay for a model to participate in the electricity market. Also, inappropriate selection of dataset size may lead to inaccurate modeling. Besides, in a multivariate environment, the impact of different variables on the output is often neglected or not adequately addressed. Therefore, in this work, a novel Mode Adaptive Artificial Neural Network (MAANN) algorithm has been proposed using Spearman’s rank-order correlation, Artificial Neural Network (ANN), and population-based algorithms for the dynamic learning of renewable energy sources power generation forecasting model. The proposed algorithm has been trained and compared with three population-based algorithms: Advanced Particle Swarm Optimization (APSO), Jaya Algorithm, and Fine-Tuning Metaheuristic Algorithm (FTMA). Also, the gradient descent algorithm is considered as a base case for comparing with the population-based algorithms. The proposed algorithm has been applied in predicting the power output of a Solar Photovoltaic (PV) and Wind Turbine Energy System (WTES). Using the proposed methodology with FTMA, the error was reduced by 71.261% and 80.514% compared to the conventional fixed-sized dataset gradient descent-based training approach for Solar PV and WTES, respectively.

To meet up fluctuations of the real-time electric load demands, many electricity markets have gone for the real-time-market-based operation. To do so, online forecasting of the real-time load demand is necessary. Due to changes in the relation between impacting variables and output over time, a continuous-learning-based approach is highly desired. A fixed data set-based training may perform accurately for a certain amount of time, but as the load pattern and impact of different external variables change, the performance of such a model may decrease. Thus, to overcome such an inherent problem of fixed-sized databased forecasting model development, in this work, a novel simultaneous online learning and feature-engineering-based appropriate time-delay neural network has been proposed. The data for developing a forecasting model are collected through different sensors available in the Internet of Things (IoT)-based networks. To develop an optimal-cost-effective IoT network and a parsimonious model for load forecasting, variable type-dependent correlation considering the multicollinearity has been performed in online training. The proper choice of the model has been also proved using the numerical analysis with the help of time-delay embedding theory. Interestingly, it is found that, with the proper choice of inputs and their lagged variables, the proposed model performs better over general feedforward, general regression neural networks, and several deep learning and advanced models, including recurrent neural networks, fully connected deep neural networks, and dendritic neuron model.

Implementation of demand side management (DSM) ensures a dynamic energy management for residential domain by permitting consumers to initiate early informed decisions concerning their energy utilization, which facilitates the utility providers to scale down the peak load demand and remodel the load curve, rather than constructing new generation and transmission units. Consequently, a better sustainability and decrement of net operational cost along with carbon emission level is achieved. DSM can be expanded by applying various optimization methods to handle large scale appliances of disparate power ratings. In this paper, for a residential community a unique DSM algorithm is proposed, where the Peak to Average Ratio (PAR) reduction is the foremost focus, which will eventually escalate the efficiency of Smart Grid and also reduce the cost of electricity consumption. Regarding this, a framework of DSM is suggested utilizing load shifting and peak clipping techniques, which is mathematically formulated and optimized by implementing the proposed algorithm in MATLAB. From this methodology, utility providers and consumers could reach to a mutually beneficial agreement; moreover, achieve significant savings and reduction in peak period requirement.

Recently, the penetration of electric vehicle (EV) has increased, and several motor companies have declared a paradigm shift to EVs. However, most existing studies focusing on EV charging scheduling in power system operations neglect the integrated operation of transportation and distribution systems. Because EVs affect both systems, it is necessary to consider the grid operation and the individual EV’s preferences (charging cost and time) simultaneously. In this study, an integrated power-transportation system structure and operation algorithms are developed to analyze the impact of EVs on the distribution system. In addition, this study proposes an optimal EV driving model that consists of two driving patterns: routine driving and long-distance driving. For routine driving patterns, the Markov chain model is implemented considering the mileage and conditions of individual EVs. Subsequently, long-distance driving patterns are developed to select the optimal route through reinforcement learning. In addition, the EV aggregator structure of EV charging stations can effectively predict local charge demands and perform charge control in real-time. An integrated power-transportation system is developed using the IEEE RBTS system and the integrated system architecture and algorithms are developed using MATLAB. It utilizes the ACOPPF function of MATPOWER to evaluate systematic stability and derive DLMP (Distributed Locational Marginal Price). This study conducts performance verification in various scenarios, confirming the effect of charging control of EV aggregators considering system stability, loss reduction, and cost reduction of the entire system.