GRU-based Encoder-Decoder for Short-term CHP Heat Load Forecast

International Conference on Manufacturing Technology, Materials and Chemical Engineering

机械制造;材料科学;化学工业

Lu, Kuan^1 ; Meng, Xiang Rong^1 ; Sun, Wen Xue^2 ; Zhang, Rong Gui^3 ; Han, Ying Kun^1 ; Gao, Song^1 ; Su, Dongliang^4

State Grid Shandong Electric Power Research Institute, Shandong, Jinan, China^1

State Grid Zhangqiu Power Supply Company, Jinan, Shandong, China^2

Shandong Luneng Software Technology Co. LTD, Jinan, Shandong, China^3

Shandong Zhongshi Yitong Group Co. LTD., Jinan, Shandong, China^4

关键词: Combined heat and power;    Encoder-decoder;    Load forecast;    Load forecasting;    Load predictions;    Load-time series;    Network-based;    Shandong province;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/392/6/062173/pdf
DOI  :  10.1088/1757-899X/392/6/062173

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

A gated recurrent units (GRU) network based encoder-decoder (E-D) model is proposed for combined heat and power (CHP) heat load forecasting. First, we use the GRU based E-D model as an auto-encoder to map the historical CHP heat load time series into a fixed length representation. Then, concatenate the representation with weather forecasting information as a new input to another multiple GRUs network for heat load prediction. Data collected from Rizhao, Shandong province is used to verify the conclusions. Results illustrate that GRU-based E-D model can give a more accurate forecast to the short-term CHP heat load compared with non-auto-encoded RNN model.