2013 | OriginalPaper | Chapter
Multi-Objective Evolutionary Algorithm with Node-Depth Encoding and Strength Pareto for Service Restoration in Large-Scale Distribution Systems
Authors : Marcilyanne Moreira Gois, Danilo Sipoli Sanches, Jean Martins, João Bosco A. London Junior, Alexandre Cláudio Botazzo Delbem
Published in: Evolutionary Multi-Criterion Optimization
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
The network reconfiguration for service restoration in distribution systems is a combinatorial complex optimization problem that usually involves multiple non-linear constraints and objectives functions. For large networks, no exact algorithm has found adequate restoration plans in real-time, on the other hand, Multi-objective Evolutionary Algorithms (MOEA) using the Node-depth enconding (MEAN) is able to efficiently generate adequate restorations plans for relatively large distribution systems. An MOEA for the restoration problem should provide restoration plans that satisfy the constraints and reduce the number of switching operations in situations of one fault. For diversity of real-world networks, those goals are met by improving the capacity of the MEAN to explore both the search and objective spaces. This paper proposes a new method called MEA2N with Strength Pareto table (MEA2N-STR) properly designed to restore a feeder fault in networks with significant different bus sizes: 3 860 and 15 440. The metrics
R
2
,
R
3
, Hypervolume and
ε
-indicators were used to measure the quality of the obtained fronts.