Neuro-fuzzy resource forecast in site suitability assessment for wind and solar energy: A mini review

Site suitability problems in renewable energy studies have taken a new turn since the advent of geographical information system (GIS). GIS has been used for site suitability analysis for renewable energy due to its prowess in processing and analyzing attributes with geospatial components. Multi criteria decision-making (MCDM) tools are further used for criteria ranking in the order of influence on the study. Upon location of most appropriate sites, the need for intelligent resource forecast to aid in strategic and operational planning becomes necessary if viability of the investment will be enhanced and resource variability will be better understood. One of such intelligent models is the adaptive neuro-fuzzy inference system (ANFIS) and its variants. This study presents a mini-review of GIS-based MCDM facility location problems in wind and solar resource site suitability analysis and resource forecast using ANFISbased models. Also,a framework for the integration of the two concepts in wind and solar energy studies was presented. Various MCDM techniques for decision making with their strengths and weaknesses were presented. Country specific studies that apply GIS-based method in site suitability were presented with the criteria considered. Similarly, country-specific studies in ANFIS-based resource forecasts for wind and solar energy were also presented. From our findings, there has been no technically valid range of values for spatial criteria in site suitability process for wind and solar resource exploration and the analytical hierarchical process (AHP) has been commonly used for criteria ranking, thus, leaving other MCDM techniques less explored. Also, hybrid ANFIS models are more effective compared to standalone ANFIS models in resource forecast, and ANFIS optimized with population-based models has been mostly used. Finally, we present a roadmap for integrating GIS-MCDM site suitability studies with ANFIS-based modeling for improved strategic and operational planning. (C) 2020 Elsevier Ltd. All rights reserved.