Random vector functional link network for short-term electricity load demand forecasting

详细信息    查看全文

• 作者：Ye Ren^a ; ^{re0003ye@ntu.edu.sg" class="auth_mail" title="E-mail the corresponding author} ; P.N. Suganthan ; ^a ; ^{epnsugan@ntu.edu.sg" class="auth_mail" title="E-mail the corresponding author} ; ; N. Srikanth^b ; ^{nsrikanth@ntu.edu.sg" class="auth_mail" title="E-mail the corresponding author} ; Gehan Amaratunga^c ; ^{gaja1@hermes.cam.ac.uk" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Random weights ; Random vector functional link ; Neural network ; Time series forecasting ; Electricity load demand forecasting
• 刊名：Information Sciences
• 出版年：2016
• 出版时间：1 November 2016
• 年：2016
• 卷：367-368
• 期：Complete
• 页码：1078-1093
• 全文大小：827 K

文摘

Short-term electricity load forecasting plays an important role in the energy market as accurate forecasting is beneficial for power dispatching, unit commitment, fuel allocation and so on. This paper reviews a few single hidden layer network configurations with random weights (RWSLFN). The RWSLFN was extended to eight variants based on the presence or absence of input layer bias, hidden layer bias and direct input–output connections. In order to avoid mapping the weighted inputs into the saturation region of the enhancement nodes’ activation function and to suppress the outliers in the input data, a quantile scaling algorithm to re-distribute the randomly weighted inputs is proposed. The eight variations of RWSLFN are assessed using six generic time series datasets and 12 load demand time series datasets. The result shows that the RWSLFNs with direct input–output connections (known as the random vector functional link network or RVFL network) have statistically significantly better performance than the RWSLFN configurations without direct input–output connections, possibly due to the fact that the direct input–output connections in the RVFL network emulate the time delayed finite impulse response (FIR) filter. However the RVFL network has simpler training and higher accuracy than the FIR based two stage neural network. The RVFL network is also compared with some reported forecasting methods. The RVFL network overall outperforms the non-ensemble methods, namely the persistence method, seasonal autoregressive integrated moving average (sARIMA), artificial neural network (ANN). In addition, the testing time of the RVFL network is the shortest while the training time is comparable to the other reported methods. Finally, possible future research directions are pointed out.