@article{article_455941, title={A Comparison of the Performance of Classification Methods and Artificial Neural Networks for Electricity Load Forecasting}, journal={The Eurasia Proceedings of Science Technology Engineering and Mathematics}, pages={233–238}, year={2018}, author={Tuna, Gurkan and Vatansever, Ahmet and Das, Resul}, keywords={Load-Forecasting plan,Artificial neural networks,Regression analysis,Support vector machine,Prediction techniques}, abstract={<p> <span style="font-size: 10pt; line-height: 115%; font-family: "Times New Roman", serif;">Electricity load forecasting plays a key role for utility companies. Short-term and medium-term electricity load forecasting processes allow the utility companies to retain reliable operation and high energy efficiency. On the other hand, long-term electricity load forecasting allows the utility companies to minimize the risks. Long-term forecasting also helps the utility companies to plan and make feasible decisions in regard to generation and transmission investments. Since there are commercial and technical implications of electricity load forecasting, the accuracy of the electricity forecasting is important not only to the utility companies but also to the consumers. In this paper, we carry out a performance evaluation study to evaluate the accuracy of different classification approaches for electricity load forecasting. As shown with the results of the performance evaluation study, some of the investigated approaches can successfully achieve high accuracy rates and therefore can be used for short-, mid-, or long-term electricity load forecasting.  </span> <br> </p>}, number={2}, publisher={ISRES Publishing}