Short‐term electric power load forecasting using factor analysis and long short‐term memory for smart cities

• Published in: International journal of circuit theory and applications Vol. 49; no. 6; pp. 1678 - 1703
• Main Authors: Veeramsetty, Venkataramana, Chandra, D. Rakesh, Salkuti, Surender Reddy
• Format: Journal Article
• Language: English
• Published: Bognor Regis Wiley Subscription Services, Inc 01.06.2021
• Subjects: Computer architecture; day ahead market; Electric power systems; Electrical loads; Electricity substations; Factor analysis; load forecasting; long short‐term memory; Machine learning; mean absolute error; self‐adaptive Adam optimizer; Short term
• ISSN: 0098-9886; 1097-007X
• DOI: 10.1002/cta.2928

Summary Electric load estimation is an important activity for electrical power system operators to operate the system stably and optimally. This paper develops a machine learning model with a long short‐term memory and a factor analysis to predict the load at a specific hour of the day on an electrical power substation. Historical load data from the 33‐/11‐kV substation near Kakatiya University in Warangal are taken at each hour of the day for the period from September 2018 to November 2018. A new long short‐term memory architecture with factor analysis is being designed based on the approach used to predict substation loads by simulation in Microsoft Azure Notebooks. Based on the study, it was found that the proposed design predicts loads with good accuracy. The versions of the LSTM, i.e., LSTM‐HAM‐Model1 and LSTM‐DAM‐Model1, have been designed to forecast loads with reasonable precision relative to current simple neural networks so that utilities can trade energy efficiently. The lightweight models, e.g., LSTM‐HAM‐Model2 and LSTMDAM‐Model2, were developed by reducing input features using factor analysis. These lightweight models predict the load with almost same precision as the initial models. In the smart cities, the proposed models will help power utilities trade electricity efficiently.