Genetically Evolved Fuzzy Predictor for Photovoltaic Power Output Estimation

Abstract

Fuzzy sets and fuzzy logic can be used for efficient data mining, classification, and value prediction. We propose a genetically evolved fuzzy predictor to estimate the output of a Photovoltaic Power Plant. Photovoltaic Power Plants (PVPPs) are classified as power energy sources with unstable supply of electrical energy. It is necessary to back up power energy from PVPPs for stable electric network operation. An optimal value of back up power can be set with reliable prediction models and significantly contribute to the robustness of the electric network and therefore help in the building of intelligent power grids.

Evolutionary prediction of photovoltaic power plant energy production

“…The extended fuzzy rule is used to estimate the amount of energy produced by a real world PVPP. This paper is extending the initial research presented in [16]. In this study, the fuzzy rules are evolved over a more comprehensive data set describing longer term operations of a real PVPP in the Czech Republic.…”

Soft identification of experts in DBLP using FCA and fuzzy rules

“…The same method was earlier used for data classification [19], [20] and for photovoltaic power plant output prediction [21]. When compared to more complex fuzzy classifier systems, a fuzzy rule can be seen as a sole symbolic expression that maps data features onto a real value from the range [0,1].…”

“…The genetic programming used for the evolution of the fuzzy rule was executed with the following parameters: population size 100, number of generations 10000, mutation probability 0.04. The F-score measure with β = 1 was used as fitness function (for details see [19]- [21]). The best fuzzy rule found by the genetic programming is shown in Fig.…”

Value estimation of the use case parameters using SOM and fuzzy rules

“…The predictor was earlier used for data classification in [6,5] and photovoltaic power plant output prediction [4]. When compared to more complex fuzzy classifier systems, it can be seen as a sole fuzzy rule that maps data features onto a real value from the range [0, 1].…”