Open AccessSpider monkey optimization technique–based allocation of distributed generation for demand side management
Author(s) -
Deb Gagari,
Chakraborty Kabir,
Deb Sumita
Publication year - 2019
Publication title -
international transactions on electrical energy systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.428
H-Index - 42
ISSN - 2050-7038
DOI - 10.1002/2050-7038.12009
Subject(s) - learning vector quantization , computer science , voltage , energy management system , distributed generation , electric power system , smart grid , genetic algorithm , renewable energy , energy management , artificial intelligence , power (physics) , engineering , machine learning , energy (signal processing) , artificial neural network , mathematics , statistics , physics , quantum mechanics , electrical engineering
Summary Recent research indicates that future power networks will witness a major enhancement in renewable energy–based distributed generation (DG). The impact of DG and distribution management system (DMS) action can be directly and easily implemented in the distribution networks for the improvement of its voltage security states. In the first phase of this paper, the voltage security state of the distribution network is identified using combined Kohonen's self‐organizing feature map (SOFM) and learning vector quantization (LVQ) algorithm. Two indicators namely voltage stability index (VSI) and distribution system stability indicator (DSSI) are used in this paper for verification of classification result. To ensure voltage security, it is essential to improve the voltage profile of the system. In the next phase, genetic algorithm (GA) and spider monkey optimization (SMO) techniques have been applied to find the optimal location and size of DG for voltage security state improvement of the reconfigured distribution system. Accurate allocation of DG can help in demand side management (DSM) for providing better service to the consumers in real time in smart grid scenario. This methodology has been tested on IEEE 33 bus, IEEE 69 bus, and Indian 85 bus practical radial distribution system. Result shows that the proposed methodology can successfully and appropriately identify the voltage security states of power system by combined SOFM and LVQ algorithms, and utilization of suitable amount of DGs at best locations as obtained from SMO algorithm can improve the operating states of distribution network in terms of voltage security.