|
 |
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
 |
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
|
09 May 2023, Volume 38 Issue 3
|
|
|
Abstract
Residential electricity usage is drastically rising on account of population growth and the utilization of the latest appliances. Electricity demand is the electricity required for power consumption in the residence division. Prediction of residential electrical energy usage is very important to make future power grids more reliable. The load forecasting problem is tougher because of the unpredictability found in the individual residential consumers. Accurate forecasting activities are essential for the planning of electrical resources and for maintaining supply and demand equilibrium. This paper reviews different categories of techniques to forecast residential electricity consumption, which includes both single and hybrid models. There are numerous categories of residential forecasting models like deep learning, machine learning, statistical as well as hybrid techniques. The techniques are further categorized into sub-techniques and into individual models. Each and every category of the model is analyzed in terms of input parameters, output parameters, error type and timeframe of forecasting.
Keyword
Electricity forecasting, deep learning models, residential area, time series analysis
PDF Download (click here)
|
|
|
|
|