Study on Time Series Forecasting Algorithm of Power Users’ Electricity Charges Based on Support Vector Machine

DOI

10.2991/978-94-6463-308-5_6How to use a DOI?

Keywords

Support vector machine; Time series of electricity charges of power users; Decomposition treatment; Combined with decomposition; Electric load; Chaotic phase space; Maximum Lyapunov exponent

Abstract

When forecasting the electricity charges of power users, the accuracy of the forecast results is low because of the correlation between the actual electricity consumption time series. Therefore, the research on the time series forecasting algorithm of power users’ electricity charges based on support vector machine is proposed. In order to ensure the reliability of the forecast results, the time series of electricity tariff data is decomposed from the perspectives of long-term trend, periodicity, randomness, comprehensiveness, stability and short-term. Combined with the decomposition results, the power consumption load of users at different times is regarded as the phase point in the chaotic phase space, and the chaotic characteristics of the time series data of power users’ electricity consumption behavior are determined by using the maximum Lyapunov exponent. After training the support vector machine through the phase point and reconstructing the phase space of all users’ electricity consumption load at different times with the help of historical load data, In the test results, the difference between the predicted results of the overall electricity bill and the actual electricity bill is always stable within 15.0 yuan.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sha Liu
AU  - Rui Guo
AU  - Xianying Mu
PY  - 2023
DA  - 2023/12/11
TI  - Study on Time Series Forecasting Algorithm of Power Users’ Electricity Charges Based on Support Vector Machine
BT  - Proceedings of the 2023 8th International Conference on Engineering Management (ICEM 2023)
PB  - Atlantis Press
SP  - 48
EP  - 55
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-308-5_6
DO  - 10.2991/978-94-6463-308-5_6
ID  - Liu2023
ER  -