Solar Intensity Characterization Using Data-Mining to Support Solar Forecasting
The increase of renewable based generation as alternative power source brings an added uncertainty to power systems. The intermittent nature of renewable resources, such as wind speed and solar intensity, requires the use of adequate forecast methodologies to support the management and integration of this type of energy resources. This paper proposes a clustering methodology to group historic data according to the data correlation and relevance for different contexts of use. Using the clustering process as a data filter only the most adequate data is used for the training process of forecasting methodologies. Artificial Neural Networks and Support Vector Machines are used to test and compare the quality of forecasts when using the proposed methodology to select the training data. Data from the Brazilian city of Florianópolis, Santa Catarina, has been used, including solar irradiance components and other meteorological variables, e.g. temperature, wind speed and humidity. Experimental findings show that using the proposed method to filter data used for training ANN and SVM achieved promising results, outperforming the approaches without clustering.
KeywordsArtificial Neural Network Clustering Data Mining Machine Learning Solar Forecasting Support Vector Machine
Unable to display preview. Download preview PDF.
- 1.European Commission, The 2020 climate and energy package, http://ec.europa.eu/clima/policies/package/index.en.htm (last accessed December 2014)
- 3.Pinto, T., et al.: Dynamic Artificial Neural Network for Electricity Market Prices Forecast. In: IEEE 16th Int. Conference on Intelligent Engineering Systems, Portugal (June 2012)Google Scholar
- 4.Pereira, R., Sousa, T.M., Pinto, T., Praça, I., Vale, Z., Morais, H.: Strategic Bidding for Electricity Markets Negotiation Using Support Vector Machines. In: Bajo Perez, J., et al. (eds.) Trends in Practical Applications of Heterogeneous Multi-agent Systems. The PAAMS Collection. AISC, vol. 293, pp. 9–18. Springer, Heidelberg (2014)CrossRefGoogle Scholar
- 5.Kopp, G., Lean, J.L.: A new, lower value of total solar irradiance: Evidence and climate significance. Geophysical Research Letters 38, L01706 (2011)Google Scholar
- 7.Pelland, S., et al.: Photovoltaic and Solar Forecasting: State of the Art. International Energy Agency Photovoltaic Power Systems Programme (2013)Google Scholar
- 10.Ioakimidis, C.S., et al.: Solar Production Forecasting Based on Irradiance Forecasting Using Artificial Neural Networks. In: IEEE Industrial Electronics Society Conference (2013)Google Scholar
- 11.Quan, H., et al.: Short-Term Load and Wind Power Forecasting Using Neural Network-Based Prediction Intervals. IEEE Trans. NN and Learning Systems 25(2) (February 2014)Google Scholar
- 12.Xu, R., et al.: Short-term Photovoltaic Power Forecasting with Weighted Support Vector Machine. In: IEEE International Conference on Automation and Logistics (August 2012)Google Scholar
- 17.Abreu, S.L., et al.: Qualificação e Recuperação de Dados de Radiação Solar Medidos em Florianópolis – SC. In: 8th Brazilian Congress of Thermal Engineering and Sciences, Porto Alegre (2000)Google Scholar