Optimization Of Unit Commitment And Economic Dispatch In Microgrids Based On Genetic Algorithm And Mixed Integer Linear Programming

Optimization of Unit Commitment and Economic Dispatch in Microgrids Based on Genetic Algorithm and Mixed Integer Linear Programming

Energy Management System (EMS) applications of modern power networks like microgrids have to respond to a number of stringent challenges due to current energy revolution. Optimal resource dispatch tasks must be handled with specific regard to the addition of new resource types and the adoption of novel modeling considerations. In addition, due to the comprehensive changes concerning the multi cell grid structure, new policies should be fulfilled via microgrids’ EMS. At the same time achieving a variety of conflicting goals in different microgrids requires a universal and a multi criteria optimization tool. In this work two dispatch-optimizers based on genetic algorithm and mixed integer linear programming for a centralized EMS are introduced which can schedule the unit commitment and economic dispatch of microgrid units. In the proposed methods, different network restrictions like voltages and equipment loadings and unit constraints have been considered.

Optimization of Unit Commitment and Economic Dispatch in Microgrids Based on Genetic Algorithm and Mixed Integer Linear Programming

Nature Inspired Computing for Data Science

This book discusses the current research and concepts in data science and how these can be addressed using different nature-inspired optimization techniques. Focusing on various data science problems, including classification, clustering, forecasting, and deep learning, it explores how researchers are using nature-inspired optimization techniques to find solutions to these problems in domains such as disease analysis and health care, object recognition, vehicular ad-hoc networking, high-dimensional data analysis, gene expression analysis, microgrids, and deep learning. As such it provides insights and inspiration for researchers to wanting to employ nature-inspired optimization techniques in their own endeavors.