Customer short term load forecasting by using ARIMA transfer function model
- National Kaohsiung Inst. of Tech. (Taiwan, Province of China). Dept. of Electrical Engineering
- National Sun Yat-Sen Univ., Kaohsiung (Taiwan, Province of China). Dept. of Electrical Engineering
Short-term load forecasting plays an important role in electric power system operation and planning. An accurate load forecasting not only reduces the generation cost in a power system, but also provides a good principle of effective operation. In this paper, the ARIMA model and transfer function model are applied to the short-term load forecasting by considering weather-load relationship. For four types of customer in Taiwan power (Taipower) system, residential load, commercial load, office load and industrial load customers, the summer ARIMA model transfer function model have been derived to proceed the short-term load forecasting during one week. To demonstrate the effectiveness of the proposed method, this paper compares the results of the transfer function model and the univariate ARIMA model with conventional regression. Besides, the transfer function model`s accuracy of the load forecast on weekday and weekend is thoroughly investigated. To improve the accuracy level of load forecast, the temperature effect is considered in the transfer function. According to the short-term load forecasting for these four customer classes, it is concluded that the proposed method can achieve better accuracy of load forecast than ARIMA model by considering the causality between power consumption and temperature.
- OSTI ID:
- 433836
- Report Number(s):
- CONF-951136-; ISBN 0-7803-2981-3; TRN: IM9709%%270
- Resource Relation:
- Conference: 1995 International conference on energy management and power delivery, Singapore (Singapore), 21-23 Nov 1995; Other Information: PBD: 1995; Related Information: Is Part Of 1995 international conference on energy management and power delivery: Proceedings. Volume 1; PB: 479 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Power system yearly peak load forecasting: A grey system modeling approach
Compensated Box-Jenkins transfer function for short term load forecast