Hybrid PSO–ACO–ANN Optimization for Cost-Effective and Low-Carbon Energy Management in Renewable Microgrids

Abstract

The smart management of electrical energy in the micro grid is one of the most significant aspect of the modern energy system. Micro grif (MGs) based on renewable energy sources (RES),such as solar photovoltaic (PV) panels, wind turbines (WT), battery energy storage system (BESS) and the main grid are becoming widespread.These MGs have advantages in terms of economy and environmental friendliness, but at the same time, they have a set of problems related to the variability of RES. The current optimization methods are no longer able to address the issue of finding optimal solutions considering the trade-offs between the MG operation cost, carbon dioxide emission, battery state of charge, and reliability of the system. This paper aims to propose Hybrid Particle Swarm Optimization-Ant Colony Optimization Artificial Neural Network (PSO-ACO-ANN) for optimal MG scheduling using MATLAB. This strategy includes two types of optimization algorithms and artificial intelligence for learning patterns in electrical load and RES production. The proposed method was tested on the basis of a program written in the MATLAB environment, which simulates the MG functioning within a selected time interval, considering the interaction between PV, WT, BESS, and the main grid. The operating cost of the MG, the use of RES, and the state of charge of the battery were considered as optimization criteria. In addition, the convergence and speed of calculation of the proposed method were compared with similar methods of optimization algorithms known from the literature, namely, PSO and GA optimization algorithms and Ant Colony Optimization (ACO) and Whale Optimization Algorithm (WOA).