|Abstract: ||When a large percentage of energy (>90%) is still generated by fossil fuel, carbon dioxide emission, the greenhouse effect, and subsequent environmental damages remain to be major problems for many countries. Therefore, renewable, sustainable, and economically viable energy sources are sought after as alternatives to fossil fuels. The advantages of using renewable energy are that it will never run out, emits nearly no carbon dioxide, and has little negative effect on the eco-system. However, the facility and installation cost for generating renewable energy is much higher than the cost of fossil fuel generated energy. Thus, governments should form effective policies, regulations, and incentive programs to promote the usage of renewable energy. Renewable energy can be classified into different categories, e.g., offshore and onshore wind power, photovoltaic solar, and geothermal. The policies used for promoting specific categories vary significantly. These policies consist of the policy goals, regulations, taxations, incentives and promotional schemes. The purpose of this study is to apply data mining techniques to analyze types of renewable energies and their attributes with respect to economic factors, energy resource and supply, and environmental effects. The study provides a scientific outlook to help governments plan their renewable energy policies. In our specific case study, the data from Taiwan’s renewable energy statistics are related to photovoltaic, wind farms, ocean thermal energy conversion, geothermal, hydro power, and solid wastes. The research has two major results and findings, i.e., 1. Develop analytical models for the decision support of renewable energy policy using intelligent data mining techniques.
2. Four clusters of renewable energy sources in Taiwan are identified for the future planning of suitable promotional schemes.