PROJECT TITLE :
Novel Hybrid Market Price Forecasting Method With Data Clustering Techniques for EV Charging Station Application
Over and above providing charging service, an electric vehicle charging station equipped with a distributed energy storage system can also participate in the deregulated market to optimize the value of operation. To support this perform, it's necessary to realize sufficient accuracy on the forecasting of energy resources and market costs. The deregulated market price prediction presents challenges since the incidence and magnitude of the value spikes are troublesome to estimate. This paper proposes a hybrid technique for terribly short term market value forecasting to improve prediction accuracy on both nonspike and spike wholesale market prices. First, support vector classification is disbursed to predict spike worth occurrence, and support vector regression is employed to forecast the magnitude for each nonspike and spike market prices. Additionally, 3 clustering techniques together with classification and regression trees, K-means that, and stratification ways are introduced to mitigate high error spike magnitude estimation. The performance of the proposed hybrid technique is validated with the electric Reliability Commission of Texas wholesale market price. The results from the proposed methodology show a significant improvement over typical approaches.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here