Bio-inspired algorithms like Genetic Algorithms and Fuzzy Inference Systems(FIS) are nowadays widely adopted as hybrid techniques in commercial andindustrial environment. In this paper we present an interesting application ofthe fuzzy-GA paradigm to Smart Grids. The main aim consists in performingdecision making for power flow management tasks in the proposed microgrid modelequipped by renewable sources and an energy storage system, taking into accountthe economical profit in energy trading with the main-grid. In particular, thisstudy focuses on the application of a Hierarchical Genetic Algorithm (HGA) fortuning the Rule Base (RB) of a Fuzzy Inference System (FIS), trying to discovera minimal fuzzy rules set in a Fuzzy Logic Controller (FLC) adopted to performdecision making in the microgrid. The HGA rationale focuses on a particularencoding scheme, based on control genes and parametric genes applied to theoptimization of the FIS parameters, allowing to perform a reduction in thestructural complexity of the RB. This approach will be referred in thefollowing as fuzzy-HGA. Results are compared with a simpler approach based on aclassic fuzzy-GA scheme, where both FIS parameters and rule weights are tuned,while the number of fuzzy rules is fixed in advance. Experiments shows how thefuzzy-HGA approach adopted for the synthesis of the proposed controlleroutperforms the classic fuzzy-GA scheme, increasing the accounting profit by67\% in the considered energy trading problem yielding at the same time asimpler RB.
展开▼
