Premium
Analysis of power management and cost minimization in MG—A hybrid GOAPSNN technique
Author(s) -
Roy Kallol
Publication year - 2019
Publication title -
international journal of numerical modelling: electronic networks, devices and fields
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.249
H-Index - 30
eISSN - 1099-1204
pISSN - 0894-3370
DOI - 10.1002/jnm.2624
Subject(s) - particle swarm optimization , photovoltaic system , microgrid , computer science , minification , automotive engineering , turbine , state of charge , diesel generator , artificial neural network , energy management , mathematical optimization , engineering , power (physics) , battery (electricity) , renewable energy , diesel fuel , algorithm , energy (signal processing) , electrical engineering , mathematics , artificial intelligence , mechanical engineering , statistics , physics , quantum mechanics
This paper presents a hybrid technique for optimal power flow management and production cost minimization of microgrid (MG)‐connected system with renewable energy sources (RES). The hybrid technique is the joint execution of both the particle swarm optimization (PSO)–aided artificial neural network (ANN) and grasshopper optimization algorithm (GOA) named as GOAPSNN technique. The proposed technique is concerned with the mathematical optimization problems that involve more than one objective function to be optimized. At first, the PSO‐ANN technique predicts the load demand in the MG‐connected system by using the inputs of MG‐connected system like photovoltaic (PV) system, wind turbine (WT), microturbine (MT), diesel engine (DE), and battery. According to the load demand, GOA is utilized to choose an optimal configuration of MG, ie, fuel cost minimization, emission factors, operating, and maintenance cost. The proposed technique is executed in MATLAB/Simulink platform and compared with the existing strategies, such as squirrel optimization with gravitational search–aided neural network (SOGSNN), adaptive neuro‐fuzzy interference system and advanced salp swam optimization algorithm (ANFASO). In this paper, the maximum generated power of PV, WT, MT, and battery is 7.9, 9.8, 15.7, and 4.56 kW, respectively. The state of charge (SoC) of the proposed technique is investigated, which is around 83%. In light of the load demand, the proposed approach has less production cost.