Heating Load Forecasting for Combined Heat and Power Plants Via Strand-Based LSTM
Heating load forecasting is the premise for guiding heating operation management and dispatching. Heating load forecasting is a time series prediction problem which requires us to predict the real-time heating loads in the next 24 hours using available historical records and weather information. In...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8986613/ |
id |
doaj-fc7919de40be4d55b4ac265d3e712a9a |
---|---|
record_format |
Article |
spelling |
doaj-fc7919de40be4d55b4ac265d3e712a9a2021-03-30T02:03:01ZengIEEEIEEE Access2169-35362020-01-018333603336910.1109/ACCESS.2020.29723038986613Heating Load Forecasting for Combined Heat and Power Plants Via Strand-Based LSTMJunyu Liu0https://orcid.org/0000-0002-9290-3762Xiao Wang1https://orcid.org/0000-0003-0508-3039Yan Zhao2https://orcid.org/0000-0002-5768-2802Bin Dong3https://orcid.org/0000-0003-1295-3362Kuan Lu4https://orcid.org/0000-0003-2693-3995Ranran Wang5https://orcid.org/0000-0002-5498-4864Academy of Advanced Interdisciplinary Studies, Peking University, Beijing, ChinaAcademy of Advanced Interdisciplinary Studies, Peking University, Beijing, ChinaState Grid Shandong Electric Power Research Institute, Jinan, ChinaBeijing International Center for Mathematical Research, Peking University, Beijing, ChinaState Grid Shandong Electric Power Research Institute, Jinan, ChinaBeijing Institute of Big Data Research, Beijing, ChinaHeating load forecasting is the premise for guiding heating operation management and dispatching. Heating load forecasting is a time series prediction problem which requires us to predict the real-time heating loads in the next 24 hours using available historical records and weather information. In this paper, we propose a model for short-term heating load forecasting based on a properly designed strand-based long short term memory (LSTM) recurrent neural network. We present how the data are pre-processed, and the loss function is designed to improve the model's performance. Furthermore, an ensemble strategy is incorporated with the LSTM model to enhance its generalization and robustness. On offline (historical) testing data, the proposed model performs satisfactory predictions which meet the requirements of the local power plant. In addition to offline tests, we also implement the model to an online system of a power plant in Shandong province, China. The model made continuous forecasting without human interference for four months during the heating season of 2018. The model reported satisfactory online testing results that were comparable with the offline experiments using historical data.https://ieeexplore.ieee.org/document/8986613/Deep learningload forecastingrecurrent neural networkstime series |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Junyu Liu Xiao Wang Yan Zhao Bin Dong Kuan Lu Ranran Wang |
spellingShingle |
Junyu Liu Xiao Wang Yan Zhao Bin Dong Kuan Lu Ranran Wang Heating Load Forecasting for Combined Heat and Power Plants Via Strand-Based LSTM IEEE Access Deep learning load forecasting recurrent neural networks time series |
author_facet |
Junyu Liu Xiao Wang Yan Zhao Bin Dong Kuan Lu Ranran Wang |
author_sort |
Junyu Liu |
title |
Heating Load Forecasting for Combined Heat and Power Plants Via Strand-Based LSTM |
title_short |
Heating Load Forecasting for Combined Heat and Power Plants Via Strand-Based LSTM |
title_full |
Heating Load Forecasting for Combined Heat and Power Plants Via Strand-Based LSTM |
title_fullStr |
Heating Load Forecasting for Combined Heat and Power Plants Via Strand-Based LSTM |
title_full_unstemmed |
Heating Load Forecasting for Combined Heat and Power Plants Via Strand-Based LSTM |
title_sort |
heating load forecasting for combined heat and power plants via strand-based lstm |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Heating load forecasting is the premise for guiding heating operation management and dispatching. Heating load forecasting is a time series prediction problem which requires us to predict the real-time heating loads in the next 24 hours using available historical records and weather information. In this paper, we propose a model for short-term heating load forecasting based on a properly designed strand-based long short term memory (LSTM) recurrent neural network. We present how the data are pre-processed, and the loss function is designed to improve the model's performance. Furthermore, an ensemble strategy is incorporated with the LSTM model to enhance its generalization and robustness. On offline (historical) testing data, the proposed model performs satisfactory predictions which meet the requirements of the local power plant. In addition to offline tests, we also implement the model to an online system of a power plant in Shandong province, China. The model made continuous forecasting without human interference for four months during the heating season of 2018. The model reported satisfactory online testing results that were comparable with the offline experiments using historical data. |
topic |
Deep learning load forecasting recurrent neural networks time series |
url |
https://ieeexplore.ieee.org/document/8986613/ |
work_keys_str_mv |
AT junyuliu heatingloadforecastingforcombinedheatandpowerplantsviastrandbasedlstm AT xiaowang heatingloadforecastingforcombinedheatandpowerplantsviastrandbasedlstm AT yanzhao heatingloadforecastingforcombinedheatandpowerplantsviastrandbasedlstm AT bindong heatingloadforecastingforcombinedheatandpowerplantsviastrandbasedlstm AT kuanlu heatingloadforecastingforcombinedheatandpowerplantsviastrandbasedlstm AT ranranwang heatingloadforecastingforcombinedheatandpowerplantsviastrandbasedlstm |
_version_ |
1724185925847613440 |