A Novel Combined Model for Short-Term Electric Load Forecasting Based on Whale Optimization Algorithm
- PDF / 2,480,825 Bytes
- 26 Pages / 439.37 x 666.142 pts Page_size
- 110 Downloads / 213 Views
A Novel Combined Model for Short-Term Electric Load Forecasting Based on Whale Optimization Algorithm Zhihao Shang1 · Zhaoshuang He2 · Yanru Song2 · Yi Yang2 · Lian Li2 · Yanhua Chen1 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Stable electric load forecasting plays a significant role in power system operation and grid management. Improving the accuracy of electric load forecasting is not only a hot topic for energy managers and researchers of the power system, but also a fair challenging and difficult task due to its complex nonlinearity characteristics. This paper proposes a new combination model, which uses the least squares support vector machine, extreme learning machine, and generalized regression neural network to predict the electric load in New South Wales, Australia. In addition, the model employs a heuristic algorithm–whale optimization algorithm to optimize the weight coefficient. To verify the usability and generalization ability of the model, this paper also applies the proposed combined model to electricity price forecasting and compares it with the benchmark method. The experimental results demonstrate that the combined model not only can get accurate results for shortterm electric load forecasting, but also achieves fine accuracy for the same period of electricity price forecasting. Keywords Short-term electric load forecasting · Electricity price forecasting · LSSVM · ELM · GRNN · WOA
1 Introduction Short-term electric load forecasting is an important part of the power system, which can help managers to make right decisions on the power market. The operations of the power system provide a guarantee for people’s normal life. Proper operations can significantly reduce the loss of auxiliary power and save a lot of money for other scientific research, eventually enhance the security and stability of the electrical power system [1]. However, the power source cannot be stored in a large amount resulting in low resource utilization. To achieve dynamic balance of electricity and power generation, short-term electric load
* Zhaoshuang He [email protected] 1
School of Information Engineering, Zhengzhou University, Zhengzhou 450000, People’s Republic of China
2
School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, People’s Republic of China
13
Vol.:(0123456789)
Z. Shang et al.
forecasting is particularly irreplaceable and has become an important research topic of the power system. Many scholars and experts have proposed various short-term electric load forecasting methods to overcome the influence of various external factors in the prediction process. In the early stage of electric load forecasting, some traditional statistical methods are used. Traditional statistical methods include trend extrapolation method [2, 3], exponential smoothing [4, 5], Kalman filtering [6] and ARIMA [7–9]. These methods have the advantages of fast speed and small calculation amount. They are effective in dealing with linear forecasting problems a
Data Loading...
