Distributed Neuro-Dynamic Optimization for Multi-Objective Power Management Problem in Micro-Grid

This paper focuses on a multi-objective power management problem considering demand response in micro grid. The multi-objective problem consists of four conflicting objective functions: the average efficiency function of DG (Diesel Generation) unit, the emission of micro-grid, the dissatisfaction ca...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 362; S. 51 - 59
Hauptverfasser: Liang, Xiaowei, He, Xing, Huang, Tingwen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 14.10.2019
Schlagworte:
Demand response
Micro-grid
Multi-objective optimization
Neuro-dynamic algorithm
Micro-grid
Multi-objective optimization
Demand response
Neuro-dynamic algorithm
ISSN:0925-2312, 1872-8286
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper focuses on a multi-objective power management problem considering demand response in micro grid. The multi-objective problem consists of four conflicting objective functions: the average efficiency function of DG (Diesel Generation) unit, the emission of micro-grid, the dissatisfaction caused by demand response and the total profit function. A single-objective product formulation is applied to convert the multi-objective optimization problem into a single-objective optimization problem. It is shown that the optimal solution of single-objective problem is a pareto optimal point of the original multi-objective problem. Then, using a logarithmic obstacle penalty parameter to deal with the inequality constraint, a distributed neuro-dynamic algorithm is proposed for the aforementioned single-objective optimization problem. Lasalle’s invariance principle and Lyapunov function are used to prove that the proposed algorithm can converge to the optimal solution. Finally, the numerical simulation in the micro-grid illustrates the feasibility of the proposed algorithm.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2019.05.096