Research on Electricity Demand Combination Forecasting Model in Beijing-Tianjin-Hebei Region Based on Shapley Value
Yuqing Wang, Chenjun Sun, Lilin Peng, Yang Liu, Ming Zeng
Available Online September 2016.
- https://doi.org/10.2991/iccia-16.2016.88How to use a DOI?
- Shapley value; Combined model; Electricity demand forecasting.
- Due to the electricity power is the foundation of economic development, reasonable and accurate electricity demand forecasting not only helps to develop electricity power planning scientifically, but also has important reference value to the economic development planning. In order to integrate different forecast models' strengths as well as improve the forecast accuracy, this paper puts forward the electricity demand forecasting model based on Shapley value. First, it chooses one-dimensional linear regression model, Holt two-parameter linear exponential smoothing model and ARIMA model for electricity demand forecasting respectively, and through the game theory Shapley value theory determines the weight of single model in the portfolio model, and then the combined forecasting result is obtained; Second, it analyzes the electricity demand data in Beijing-Tianjin-Hebei Region and the results show that the proposed method has high forecast accuracy; Finally, it forecasts electricity demand in Beijing-Tianjin-Hebei Region during "13th five-year" period and provides decision-making basis for the economic development planning of Beijing, Tianjin Hebei province during "13th five-year" period.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Yuqing Wang AU - Chenjun Sun AU - Lilin Peng AU - Yang Liu AU - Ming Zeng PY - 2016/09 DA - 2016/09 TI - Research on Electricity Demand Combination Forecasting Model in Beijing-Tianjin-Hebei Region Based on Shapley Value BT - 2016 International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2016) PB - Atlantis Press SP - 481 EP - 486 SN - 2352-538X UR - https://doi.org/10.2991/iccia-16.2016.88 DO - https://doi.org/10.2991/iccia-16.2016.88 ID - Wang2016/09 ER -