Various Electricity Load Forecasting Techniques with Pros and Cons
Mandeep Singh1, Raman Maini2
1Mandeep Singh, Research Scholar, Punjabi University, Patiala, India.
2Dr. Raman Maini, Professor, Punjabi University, Patiala, India.
Manuscript received on February 12, 2020. | Revised Manuscript received on February 21, 2020. | Manuscript published on March 30, 2020. | PP: 220-229 | Volume-8 Issue-6, March 2020. | Retrieval Number: F6997038620/2020©BEIESP | DOI: 10.35940/ijrte.F6997.038620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The rapid growth of stored information in the demand forecasting, associated with data analysis provoked an utmost need for generating a powerful tool which must be capable of extracting hidden and vital knowledge of load forecasting from available vast data sets. Being a promising sub domain of computer science, numerous data mining techniques suits the solution to this problem very well. This paper presents a vast, rigorous and comparable survey of tremendous data mining techniques useful in forecasting the electricity load demand of different geographic area. Based upon the rigorous survey, primary challenges involved in the current technologies and future goals are also discussed.
Keywords: Load Forecasting, Regression, Time Series and Artificial Neural Networks.
Scope of the Article: Artificial Neural Networks