Green Economic Load Dispatch: A Review and Implementation

TL;DR

This paper reviews modern AI techniques for green economic load dispatch, focusing on minimizing fuel costs and emissions in power systems, and compares PSO and GA methods on a benchmark system.

Contribution

It provides a comprehensive review of AI methods for eco-friendly load dispatch and demonstrates their application and comparison on a standard power system model.

Findings

PSO and GA effectively optimize dispatch with emission considerations

AI techniques outperform classical methods in complex, multi-objective scenarios

Results show significant cost and emission reductions using AI algorithms

Abstract

The economic dispatch of generators is a major concern in thermal power plants that governs the share of each generating unit with an objective of minimizing fuel cost by fulfilling load demand. This problem is not as simple as it looks because of system constraints that cannot be neglected practically. Moreover, increased awareness of clean technology imposes another important limit on the emission of pollutants obtained from burning of fossil fuels. Classical optimization methods lack the ability of solving such a complex and multi-objective problem. Hence, various modern artificial intelligence (AI) techniques based on evolution and social behaviour of organisms are being used to solve such problems because they are easier to implement, give accurate results and take less computational time. In this work, a study is done on most of the contemporary basic AI techniques being used in literature for power systems in general and combined economic emission dispatch (CEED) in particular. The dispatch problem is implemented on IEEE 30-bus benchmarked system in MATLAB for different load demands considering all gases (COX, NOX and SOX) using particle swarm optimization (PSO) and genetic algorithm (GA) and their results are compared with each other.