Abstract
Accurate day-ahead load prediction plays a significant role to electric companies because decisions on power system generations depend on future behavior of loads. This paper presents a strategy for short-term load forecasting that utilizes support vector regression machines. Proper data preparation, model implementation and model validation methods were introduced in this study. The SVRM model being implemented is composed of specific features, parameters, data architecture and kernel to achieve accurate pattern discovery. The developed model was implemented into an electric load forecasting system using the java open source library called LibSVM. To confirm the effectiveness of the proposed model, the performance of the developed model is evaluated through the validation set of the study and compared to other published models. The created SVRM model produced the lowest Mean Average Percentage Error (MAPE) of 1.48% and was found to be a viable forecasting technique for a day-ahead electric load forecasting system.
Highlights
Accurate day-ahead load prediction demand plays a very significant role to electric companies because operation decisions in power systems such as unit commitment, contingency analysis, field scheduling, reducing spinning reserve, reliability analysis, load flow, and scheduling device maintenance depend on future behavior of loads [1]-[3]
The data used as input for the SVRM models is the attribute kilowatt delivered (KW_DEL) for the reason that it is the column considered by power utilities in determining forecasted load values for the day
This paper proposed a short term electric load forecasting strategy using SVRM by executing data preparation and by implementing an SVRM model in LIBSVM
Summary
Accurate day-ahead load prediction demand plays a very significant role to electric companies because operation decisions in power systems such as unit commitment, contingency analysis, field scheduling, reducing spinning reserve, reliability analysis, load flow, and scheduling device maintenance depend on future behavior of loads [1]-[3]. SVRM was utilized to analyze and predict day-ahead load forecasting using the historical load data that a power utility company has accumulated with the aim to solve the long term problem of managing the supply and demand of the locality’s power system. Electric transmission and distribution system [1], [4] Because of this existing limitation, utility companies invest greatly in load prediction to ensure that the basis of their operational
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
