Multi-Scale Convolutional Neural Network With Time-Cognition for Multi-Step Short-Term Load Forecasting

Electric load forecasting has always been a key component of power grids. Many countries have opened up electricity markets and facilitated the participation of multiple agents, which create a competitive environment and reduce costs to consumers. In the electricity market, multi-step short-term load forecasting becomes increasingly significant for electricity market bidding and spot price calculation, but the performances of traditional algorithms are not robust and unacceptable enough. In recent years, the rise of deep learning gives us the opportunity to improve the accuracy of multi-step forecasting further. In this paper, we propose a novel model multi-scale convolutional neural network with time-cognition (TCMS-CNN). At first, a deep convolutional neural network model based on multi-scale convolutions (MS-CNN) extracts different level features that are fused into our network. In addition, we design an innovative time coding strategy called the periodic coding strengthening the ability of the sequential model for time cognition effectively. At last, we integrate MS-CNN and periodic coding into the proposed TCMS-CNN model with an end-to-end training and inference process. With ablation experiments, the MS-CNN and periodic coding methods had better performances obviously than the most popular methods at present. Specifically, for 48-step point load forecasting, the TCMS-CNN had been improved by 34.73%, 14.22%, and 19.05% on MAPE than the state-of-the-art methods recursive multi-step LSTM (RM-LSTM), direct multi-step MS-CNN (DM-MS-CNN), and the direct multi-step GCNN (DM-GCNN), respectively. For 48-step probabilistic load forecasting, the TCMS-CNN had been improved by 3.54% and 6.77% on average pinball score than the DM-MS-CNN and the DM-GCNN. These results show a great promising potential applied in practice.

[1]  S. M. Moghaddas-Tafreshi,et al.  A linear regression-based study for temperature sensitivity analysis of Iran electrical load , 2008, 2008 IEEE International Conference on Industrial Technology.

[2]  Wenhu Tang,et al.  Deep Learning for Daily Peak Load Forecasting–A Novel Gated Recurrent Neural Network Combining Dynamic Time Warping , 2019, IEEE Access.

[3]  Souhaib Ben Taieb,et al.  A gradient boosting approach to the Kaggle load forecasting competition , 2014 .

[4]  G. Jang,et al.  Short-term load forecasting for the holidays using fuzzy linear regression method , 2005, IEEE Transactions on Power Systems.

[5]  Lili Su,et al.  Hybrid Forecasting Approach Based on GRNN Neural Network and SVR Machine for Electricity Demand Forecasting , 2017 .

[6]  David J. Hill,et al.  Short-Term Residential Load Forecasting Based on Resident Behaviour Learning , 2018, IEEE Transactions on Power Systems.

[7]  S. A. Soliman,et al.  Short-term electric load forecasting based on Kalman filtering algorithm with moving window weather and load model , 2004 .

[8]  George Edwards,et al.  A Review of Deep Learning Methods Applied on Load Forecasting , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[9]  Gregory D. Hager,et al.  Temporal Convolutional Networks for Action Segmentation and Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Ning Zhang,et al.  Probabilistic individual load forecasting using pinball loss guided LSTM , 2019, Applied Energy.

[11]  T. Brailsford,et al.  An evaluation of volatility forecasting techniques , 1996 .

[12]  Saifur Rahman,et al.  Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques , 2019, Applied Energy.

[13]  Tao Hong,et al.  Modeling and forecasting hourly electric load by multiple linear regression with interactions , 2010, IEEE PES General Meeting.

[14]  Riccardo Bonetto,et al.  Parallel multi-step ahead power demand forecasting through NAR neural networks , 2016, 2016 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[15]  Tao Hong,et al.  Probabilistic electric load forecasting: A tutorial review , 2016 .

[16]  Bo Zhong,et al.  BP neural network with rough set for short term load forecasting , 2009, Expert Syst. Appl..

[17]  S. Soliman,et al.  Fuzzy short-term electric load forecasting using Kalman filter , 2006 .

[18]  B. De Moor,et al.  Electric Load Forecasting , 2007, IEEE Control Systems.

[19]  W. R. Christiaanse.  Short-Term Load Forecasting Using General Exponential Smoothing , 1971 .

[20]  Yann Dauphin,et al.  Language Modeling with Gated Convolutional Networks , 2016, ICML.

[21]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[22]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[23]  Ning Jin,et al.  Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy , 2018, Energies.

[24]  Borhan M. Sanandaji,et al.  Short-term residential electric load forecasting: A compressive spatio-temporal approach , 2016 .

[25]  Alex Graves,et al.  Neural Machine Translation in Linear Time , 2016, ArXiv.

[26]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[27]  Hiroyuki Mori,et al.  Optimal regression tree based rule discovery for short-term load forecasting , 2001, 2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194).

[28]  Liang Guo,et al.  A Short-Term User Load Forecasting with Missing Data , 2018, DEStech Transactions on Engineering and Technology Research.

[29]  Ömer Faruk Ertuğrul,et al.  Forecasting electricity load by a novel recurrent extreme learning machines approach , 2016 .

[30]  Li Wei,et al.  Based on Time Sequence of ARIMA Model in the Application of Short-Term Electricity Load Forecasting , 2009, 2009 International Conference on Research Challenges in Computer Science.

[31]  Jianzhou Wang,et al.  Short-term load forecasting using a kernel-based support vector regression combination model , 2014 .

[32]  Zachary Chase Lipton.  A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.

[33]  G. Juberias,et al.  A new ARIMA model for hourly load forecasting , 1999, 1999 IEEE Transmission and Distribution Conference (Cat. No. 99CH36333).

[34]  Xiaobo Zhang,et al.  Short-term electric load forecasting based on singular spectrum analysis and support vector machine optimized by Cuckoo search algorithm , 2017 .

[35]  Wei-Chiang Hong,et al.  Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artific , 2011 .

[36]  Tao Hong,et al.  Energy Forecasting: Past, Present, and Future , 2013 .

[37]  Ljupco Kocarev,et al.  Deep belief network based electricity load forecasting: An analysis of Macedonian case , 2016 .

[38]  Song Li,et al.  Short-term load forecasting by wavelet transform and evolutionary extreme learning machine , 2015 .

[39]  Yun Lu,et al.  Short-term Load Forecasting Based on Grey Model and Correction System , 2005, 2005 IEEE/PES Transmission & Distribution Conference & Exposition: Asia and Pacific.