Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy
Electric power consumption short-term forecasting for individual households is an important and challenging topic in the fields of AI-enhanced energy saving, smart grid planning, sustainable energy usage and electricity market bidding system design. Due to the variability of each household’...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/11/11/3089 |
| _version_ | 1811278105366495232 |
|---|---|
| author | Ke Yan Xudong Wang Yang Du Ning Jin Haichao Huang Hangxia Zhou |
| author_facet | Ke Yan Xudong Wang Yang Du Ning Jin Haichao Huang Hangxia Zhou |
| author_sort | Ke Yan |
| collection | DOAJ |
| description | Electric power consumption short-term forecasting for individual households is an important and challenging topic in the fields of AI-enhanced energy saving, smart grid planning, sustainable energy usage and electricity market bidding system design. Due to the variability of each household’s personalized activity, difficulties exist for traditional methods, such as auto-regressive moving average models, machine learning methods and non-deep neural networks, to provide accurate prediction for single household electric power consumption. Recent works show that the long short term memory (LSTM) neural network outperforms most of those traditional methods for power consumption forecasting problems. Nevertheless, two research gaps remain as unsolved problems in the literature. First, the prediction accuracy is still not reaching the practical level for real-world industrial applications. Second, most existing works only work on the one-step forecasting problem; the forecasting time is too short for practical usage. In this study, a hybrid deep learning neural network framework that combines convolutional neural network (CNN) with LSTM is proposed to further improve the prediction accuracy. The original short-term forecasting strategy is extended to a multi-step forecasting strategy to introduce more response time for electricity market bidding. Five real-world household power consumption datasets are studied, the proposed hybrid deep learning neural network outperforms most of the existing approaches, including auto-regressive integrated moving average (ARIMA) model, persistent model, support vector regression (SVR) and LSTM alone. In addition, we show a <i>k</i>-step power consumption forecasting strategy to promote the proposed framework for real-world application usage. |
| first_indexed | 2024-04-13T00:28:43Z |
| format | Article |
| id | doaj.art-47f47960d24844399a9916f313071b4f |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-13T00:28:43Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-47f47960d24844399a9916f313071b4f2022-12-22T03:10:31ZengMDPI AGEnergies1996-10732018-11-011111308910.3390/en11113089en11113089Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning StrategyKe Yan0Xudong Wang1Yang Du2Ning Jin3Haichao Huang4Hangxia Zhou5Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaDepartment of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaState Grid Zhejiang Electric Power Co., Ltd, Hangzhou 310007, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaElectric power consumption short-term forecasting for individual households is an important and challenging topic in the fields of AI-enhanced energy saving, smart grid planning, sustainable energy usage and electricity market bidding system design. Due to the variability of each household’s personalized activity, difficulties exist for traditional methods, such as auto-regressive moving average models, machine learning methods and non-deep neural networks, to provide accurate prediction for single household electric power consumption. Recent works show that the long short term memory (LSTM) neural network outperforms most of those traditional methods for power consumption forecasting problems. Nevertheless, two research gaps remain as unsolved problems in the literature. First, the prediction accuracy is still not reaching the practical level for real-world industrial applications. Second, most existing works only work on the one-step forecasting problem; the forecasting time is too short for practical usage. In this study, a hybrid deep learning neural network framework that combines convolutional neural network (CNN) with LSTM is proposed to further improve the prediction accuracy. The original short-term forecasting strategy is extended to a multi-step forecasting strategy to introduce more response time for electricity market bidding. Five real-world household power consumption datasets are studied, the proposed hybrid deep learning neural network outperforms most of the existing approaches, including auto-regressive integrated moving average (ARIMA) model, persistent model, support vector regression (SVR) and LSTM alone. In addition, we show a <i>k</i>-step power consumption forecasting strategy to promote the proposed framework for real-world application usage.https://www.mdpi.com/1996-1073/11/11/3089electric power consumptionmulti-step forecastinglong short term memoryconvolutional neural network |
| spellingShingle | Ke Yan Xudong Wang Yang Du Ning Jin Haichao Huang Hangxia Zhou Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy Energies electric power consumption multi-step forecasting long short term memory convolutional neural network |
| title | Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy |
| title_full | Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy |
| title_fullStr | Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy |
| title_full_unstemmed | Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy |
| title_short | Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy |
| title_sort | multi step short term power consumption forecasting with a hybrid deep learning strategy |
| topic | electric power consumption multi-step forecasting long short term memory convolutional neural network |
| url | https://www.mdpi.com/1996-1073/11/11/3089 |
| work_keys_str_mv | AT keyan multistepshorttermpowerconsumptionforecastingwithahybriddeeplearningstrategy AT xudongwang multistepshorttermpowerconsumptionforecastingwithahybriddeeplearningstrategy AT yangdu multistepshorttermpowerconsumptionforecastingwithahybriddeeplearningstrategy AT ningjin multistepshorttermpowerconsumptionforecastingwithahybriddeeplearningstrategy AT haichaohuang multistepshorttermpowerconsumptionforecastingwithahybriddeeplearningstrategy AT hangxiazhou multistepshorttermpowerconsumptionforecastingwithahybriddeeplearningstrategy |