Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting
Residential load forecasting is important for many entities in the electricity market, but the load profile of single residence shows more volatilities and uncertainties. Due to the difficulty in producing reliable point forecasts, probabilistic load forecasting becomes more popular as a result of c...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/9147545 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832550477220282368 |
|---|---|
| author | Zhuofu Deng Binbin Wang Heng Guo Chengwei Chai Yanze Wang Zhiliang Zhu |
| author_facet | Zhuofu Deng Binbin Wang Heng Guo Chengwei Chai Yanze Wang Zhiliang Zhu |
| author_sort | Zhuofu Deng |
| collection | DOAJ |
| description | Residential load forecasting is important for many entities in the electricity market, but the load profile of single residence shows more volatilities and uncertainties. Due to the difficulty in producing reliable point forecasts, probabilistic load forecasting becomes more popular as a result of catching the volatility and uncertainty by intervals, density, or quantiles. In this paper, we propose a unified quantile regression deep neural network with time-cognition for tackling this challenging issue. At first, a convolutional neural network with multiscale convolution is devised for extracting more behavioral features from the historical load sequence. In addition, a novel periodical coding method marks the model to enhance its ability of capturing regular load pattern. Then, features generated from both subnetworks are fused and fed into the forecasting model with an end-to-end manner. Besides, a globally differentiable quantile loss function constrains the whole network for training. At last, forecasts of multiple quantiles are directly generated in one shot. With ablation experiments, the proposed model achieved the best results in the AQS, AACE, and inversion error, and especially the average of the AACE is grown by 34.71%, 75.22%, and 32.44% compared with QGBRT, QCNN, and QLSTM, respectively, indicating that our method has excellent reliability and robustness rather than the state-of-the-art models obviously. Meanwhile, great performances of efficient time response demonstrate that our proposed work has promising prospects in practical applications. |
| format | Article |
| id | doaj-art-3562ebf67c4041a486a2cd3cbf88dc11 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-3562ebf67c4041a486a2cd3cbf88dc112025-02-03T06:06:42ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/91475459147545Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load ForecastingZhuofu Deng0Binbin Wang1Heng Guo2Chengwei Chai3Yanze Wang4Zhiliang Zhu5College of Software, Northeastern University, Shenyang 110169, ChinaCollege of Software, Northeastern University, Shenyang 110169, ChinaCollege of Software, Northeastern University, Shenyang 110169, ChinaCollege of Software, Northeastern University, Shenyang 110169, ChinaKuandian Electric Power Supply Company, State Grid Liaoning Electric Power Supply Co., Ltd., Kuandian 118200, Liaoning, ChinaCollege of Software, Northeastern University, Shenyang 110169, ChinaResidential load forecasting is important for many entities in the electricity market, but the load profile of single residence shows more volatilities and uncertainties. Due to the difficulty in producing reliable point forecasts, probabilistic load forecasting becomes more popular as a result of catching the volatility and uncertainty by intervals, density, or quantiles. In this paper, we propose a unified quantile regression deep neural network with time-cognition for tackling this challenging issue. At first, a convolutional neural network with multiscale convolution is devised for extracting more behavioral features from the historical load sequence. In addition, a novel periodical coding method marks the model to enhance its ability of capturing regular load pattern. Then, features generated from both subnetworks are fused and fed into the forecasting model with an end-to-end manner. Besides, a globally differentiable quantile loss function constrains the whole network for training. At last, forecasts of multiple quantiles are directly generated in one shot. With ablation experiments, the proposed model achieved the best results in the AQS, AACE, and inversion error, and especially the average of the AACE is grown by 34.71%, 75.22%, and 32.44% compared with QGBRT, QCNN, and QLSTM, respectively, indicating that our method has excellent reliability and robustness rather than the state-of-the-art models obviously. Meanwhile, great performances of efficient time response demonstrate that our proposed work has promising prospects in practical applications.http://dx.doi.org/10.1155/2020/9147545 |
| spellingShingle | Zhuofu Deng Binbin Wang Heng Guo Chengwei Chai Yanze Wang Zhiliang Zhu Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting Complexity |
| title | Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting |
| title_full | Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting |
| title_fullStr | Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting |
| title_full_unstemmed | Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting |
| title_short | Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting |
| title_sort | unified quantile regression deep neural network with time cognition for probabilistic residential load forecasting |
| url | http://dx.doi.org/10.1155/2020/9147545 |
| work_keys_str_mv | AT zhuofudeng unifiedquantileregressiondeepneuralnetworkwithtimecognitionforprobabilisticresidentialloadforecasting AT binbinwang unifiedquantileregressiondeepneuralnetworkwithtimecognitionforprobabilisticresidentialloadforecasting AT hengguo unifiedquantileregressiondeepneuralnetworkwithtimecognitionforprobabilisticresidentialloadforecasting AT chengweichai unifiedquantileregressiondeepneuralnetworkwithtimecognitionforprobabilisticresidentialloadforecasting AT yanzewang unifiedquantileregressiondeepneuralnetworkwithtimecognitionforprobabilisticresidentialloadforecasting AT zhiliangzhu unifiedquantileregressiondeepneuralnetworkwithtimecognitionforprobabilisticresidentialloadforecasting |