Recurrent inception convolution neural network for multi short-term load forecasting

被引:166
作者
Kim, Junhong [1 ]
Moon, Jihoon [2 ]
Hwang, Eenjun [2 ]
Kang, Pilsung [1 ]
机构
[1] Korea Univ, Sch Ind Management Engn, Seoul 136701, South Korea
[2] Korea Univ, Sch Elect Engn, Seoul 136701, South Korea
基金
新加坡国家研究基金会;
关键词
Recurrent inception convolution neural network; Deep learning; Recurrent neural network; Convolution neural network; Load forecasting; SUPPORT VECTOR REGRESSION; ELECTRICITY CONSUMPTION; ENERGY-CONSUMPTION; BUILDINGS; PREDICTION; SYSTEM; MODELS; ANN; STRATEGY; WEATHER;
D O I
10.1016/j.enbuild.2019.04.034
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Smart grid and microgrid technology based on energy storage systems (ESS) and renewable energy are attracting significant attention in addressing the challenges associated with climate change and energy crises. In particular, building an accurate short-term load forecasting (STLF) model for energy management systems (EMS) is a key factor in the successful formulation of an appropriate energy management strategy. Recent recurrent neural network (RNN)-based models have demonstrated favorable performance in electric load forecasting. However, when forecasting electric load at a specific time, existing RNN-based forecasting models neither use a predicted future hidden state vector nor the fully available past information. Therefore, once a hidden state vector has been incorrectly generated at a specific prediction time, it cannot be corrected for enhanced forecasting of the following prediction times. To address these problems, we propose a recurrent inception convolution neural network (RICNN) that combines RNN and 1-dimensional CNN (1-D CNN). We use the 1-D convolution inception module to calibrate the prediction time and the hidden state vector values calculated from nearby time steps. By doing so, the inception module generates an optimized network via the prediction time generated in the RNN and the nearby hidden state vectors. The proposed RICNN model has been verified in terms of the power usage data of three large distribution complexes in South Korea. Experimental results demonstrate that the RICNN model outperforms the benchmarked multi-layer perception, RNN, and 1-D CNN in daily electric load forecasting (48-time steps with an interval of 30 min). (C) 2019 Elsevier B.V. All rights reserved.
引用
收藏
页码:328 / 341
页数:14
相关论文
共 79 条
[1]   Accurate photovoltaic power forecasting models using deep LSTM-RNN [J].
Abdel-Nasser, Mohamed ;
Mahmoud, Karar .
NEURAL COMPUTING & APPLICATIONS, 2019, 31 (07) :2727-2740
[2]   A review on applications of ANN and SVM for building electrical energy consumption forecasting [J].
Ahmad, A. S. ;
Hassan, M. Y. ;
Abdullah, M. P. ;
Rahman, H. A. ;
Hussin, F. ;
Abdullah, H. ;
Saidur, R. .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2014, 33 :102-109
[3]   Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption [J].
Ahmad, Muhammad Waseem ;
Mourshed, Monjur ;
Rezgui, Yacine .
ENERGY AND BUILDINGS, 2017, 147 :77-89
[4]   A Review of Deep Learning Methods Applied on Load Forecasting [J].
Almalaq, Abdulaziz ;
Edwards, George .
2017 16TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2017, :511-516
[5]   Electricity consumption forecasting models for administration buildings of the UK higher education sector [J].
Amber, K. P. ;
Aslam, M. W. ;
Hussain, S. K. .
ENERGY AND BUILDINGS, 2015, 90 :127-136
[6]  
[Anonymous], P 3 INT C LEARNING R
[7]  
[Anonymous], 2015, ARXIV PREPRINT ARXIV
[8]  
[Anonymous], ARXIV160505101
[9]  
[Anonymous], 2017 25 EUR SIGN PRO
[10]  
[Anonymous], 24 INT C EL DISTR 20