Chaotic Dynamics of Power Load and Its Short-Term Forecasting
Due to the temporal and spatial variation, in皍ence of meteorological factors, and uncertainties associated with initial and boundary conditions, power load exhibits complicated and irregular fluctuations and it is very difficult to model and forecast. This paper investigates whether the power load time series can be modeled as the output of a low dimensional chaotic dynamical system based on dynamical systems theory, as well as prediction analysis. The model is constructed by creating a multidimensional phase space from actual load time series. Prediction accuracy is used as a diagnostic tool to characterize the nature of load, stochastic vs. chaotic. To demonstrate the effectiveness of this diagnostic tool, the proposed method is first applied to time series with known characteristics. Results for load time series suggest that it can be characterized as a low-dimensional chaotic system. Therefore phase space model can be used for short-term load forecasting. The performances of the proposed model and optimum autoregressive (AR) model are compared for one-hour and one-day ahead predictions. The ability of the proposed model to identify the inherent characteristics makes it a powerful tool to characterize and predict power load.
Rengcun Fang Jianzhong Zhou Junjie Yang Qingqing Li
School of Hydropower and Information Engineering Huazhong University of Science and Technology Wuhan, China 430074
国际会议
南宁
英文
2007-07-20（万方平台首次上网日期，不代表论文的发表时间）