Multiobjective service restoration of distribution systems using fuzzy cause-effect networks

This paper proposes the use of a fuzzy cause-effect (FCE) network to achieve the multiobjective service restoration of distribution systems. Service restoration is a complicated combinatorial optimization problem that often has a great number of candidate solutions to be evaluated by the operators. To tackle the problem of service restoration with multiple objectives, the weighted sum strategy is employed to convert these objectives into a single objective function by giving relative weighting values. The weighting factor of each objective is assessed via the analytical hierarchy process (AHP) approach. Since the operators´ needs and heuristic rules are often expressed in imprecise linguistic terms, the FCE networks are then built to represent the related knowledge and inference scheme regarding the task of restoration. The proposed FCE networks were practically tested on a typical distribution system of the Taiwan Power Company (TPC). The flexibility and effectiveness of the FCE networks have validated it for use as decision support in restoration scheduling of distribution systems.