This paper addresses a hybrid solution methodology integrating particle swarm optimization (PSO) algorithm with the sequential quadratic programming (SQP) method for the reserve constrained dynamic economic dispatch problem (RCDEDP) of generating units considering the valve-point effects. The cost function of the generating units exhibits the nonconvex characteristics, as the valve-point effects are modeled and imposed as rectified sinusoid components. The hybrid method incorporates the PSO algorithm as the main optimizer and SQP as the local optimizer to fine-tune the solution region whenever the PSO algorithm discovers a better solution region in the progress of its run. Thus, the SQP guides PSO for better performance in the complex solution space. To validate the feasibility of the proposed method, a ten-unit system is taken and studied under three different load patterns. The effectiveness and computation performance of the proposed method for the RCDEDP of units with valve-point effects is shown in general.

The immense growth and penetration of electric vehicles has become a major component of smart transport systems; thereby decreasing the greenhouse gas emissions that pollute the environment. With the increased volumes of electric vehicles (EV) in the past few years, the charging demand of these vehicles has also become an immediate requirement. Due to which, the prediction of the demand of electric vehicle charging is of key importance so that it minimizes the burden on the electric grids and also offers reduced costs of charging. In this research study, an attempt is made to develop a novel deep learning (DL)-based long-short term memory (LSTM) recurrent neural network predictor model to carry out the forecasting of electric vehicle charging demand. The parameters of the new deep long-short term memory (DLSTM) neural predictor model are tuned for its optimal values using the classic arithmetic optimization algorithm (AOA) and the input time series data are decomposed so as to maintain their features using the empirical mode decomposition (EMD). The novel EMD—AOA—DLSTM neural predictor modeled in this study overcomes the vanishing and exploding gradients of basic recurrent neural learning and is tested for its superiority on the EV charging dataset of Georgia Tech, Atlanta, USA. At the time of simulation, the best results of 97.14% prediction accuracy with a mean absolute error of 0.1083 and a root mean square error of 2.0628 × 10⁻⁵ are attained. Furthermore, the mean absolute error was evaluated to be 0.1083 and the mean square error pertaining to 4.25516 × 10⁻¹⁰. The results prove the efficacy of the prediction metrics computed with the novel deep learning LSTM neural predictor for the considered dataset in comparison with the previous techniques from existing works.

This paper presents a new hybrid approach integrating the cross-entropy (CE) algorithm and the sequential quadratic programming (SQP) technique to solve the economic load dispatch (ELD) problem related to electrical power generating units. Due to the introduction of the valve-point effect in the ELD objective function, the optimization task requires tools appropriate for a nonconvex optimization landscape. In this respect, we employ the CE approach, which constructs a random sequence of solutions probabilistically converging to a near-optimal solution and, thus, facilitating the exploration capability. Additionally, to fine-tune the solution in promising basins of attraction, the SQP algorithm is invoked, which performs a local search. Despite its reliance on a global heuristic scheme, CE-SQP is vested with fast convergence capability, which may entail its use for online power dispatch. The effectiveness and the robustness of the proposed method in comparison with several state-of-the-art approaches have been demonstrated with four standard test systems that are widely reported in the ELD literature.