Enhanced Multiobjective Evolutionary Algorithm based on Decomposition for Solving the Unit Commitment Problem

TL;DR

This paper introduces an advanced multi-objective evolutionary algorithm combining hybrid strategies and parallel models to effectively solve the complex unit commitment problem considering both cost and emission objectives.

Contribution

It proposes a novel hybrid MOEA/D framework with hybrid genetic and differential evolution, non-uniform weight vector distribution, and parallel island models for improved UC problem solving.

Findings

Outperforms existing algorithms in convergence speed.

Provides more uniformly distributed trade-off solutions.

Effectively balances cost and emission objectives.

Abstract

The unit commitment (UC) problem is a nonlinear, high-dimensional, highly constrained, mixed-integer power system optimization problem and is generally solved in the literature considering minimizing the system operation cost as the only objective. However, due to increasing environmental concerns, the recent attention has shifted to incorporating emission in the problem formulation. In this paper, a multi-objective evolutionary algorithm based on decomposition (MOEA/D) is proposed to solve the UC problem as a multi-objective optimization problem considering minimizing cost and emission as the multiple objec- tives. Since, UC problem is a mixed-integer optimization problem consisting of binary UC variables and continuous power dispatch variables, a novel hybridization strategy is proposed within the framework of MOEA/D such that genetic algorithm (GA) evolves the binary variables while differential evolution (DE) evolves the continuous variables. Further, a novel non-uniform weight vector distribution strategy is proposed and a parallel island model based on combination of MOEA/D with uniform and non-uniform weight vector distribution strategy is implemented to enhance the performance of the presented algorithm. Extensive case studies are presented on different test systems and the effectiveness of the proposed hybridization strategy, the non-uniform weight vector distribution strategy and parallel island model is verified through stringent simulated results. Further, exhaustive benchmarking against the algorithms proposed in the literature is presented to demonstrate the superiority of the proposed algorithm in obtaining significantly better converged and uniformly distributed trade-off solutions.