返回
θ-Multiobjective Teaching-Learning-Based Optimization for Dynamic Economic Emission Dispatch
DOI:10.1109/JSYST.2012.2183276.png)
摘要
En 中文
This paper presents a theta-multiobjective-teaching-learning-based optimization algorithm to solve the dynamic economic emission dispatch problem. Teaching-learning-based-optimization (TLBO) algorithm works on the effect of a teacher on learners. This paper proposes several modifications on the basic TLBO. In the suggested method, the optimization process is done based on the phase angles, instead of the design variables themselves whereby the nonlinear characteristics of the problem are considered more efficiently. To avoid entrapping into local optima, a new learning method is proposed. Moreover, several metaheuristic techniques are applied to make a satisfactory multiobjective optimization method. A new approach is employed to select the population; thereby uniformly distributed Pareto-optimal front as well as the extreme points of the tradeoff surface can be achieved. Furthermore, a niching mechanism is applied to direct the individuals to seek the lesser explored regions. A fuzzy clustering approach is utilized to handle the size of the repository and obtain profitable solutions from the decision maker's point of view. To involve the decision maker's favor through the search process perfectly, a min-max approach is developed to select the best candidate solutions for the next generation. The applicability of the method is validated on three test systems, including 5-unit, 10-unit, and 120-unit test systems.
Keyword:
Dynamic economic emission dispatch (DEED)
theta-multiobjective-teaching-learning-based optimization (theta-mTL-BO)
Pareto dominance
ramp-rate limits
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
2.4
论文数:
4.5K
被引数:
387

