Combined electricity-heat-cooling-gas load forecasting model for integrated energy system based on multi-task learning and least square support vector machine

Abstract Accurate forecasting of the combined loads of electricity, heat, cooling and gas in the integrated energy system is the key to improve the comprehensive efficiency and gain more economic benefits of various types of energy. As an important part of the new generation of energy systems, the integrated energy system contains energy subsystems such as electricity, heat, cooling and gas, and each subsystem employs energy supply, conversion and storage equipment. This form of energy system achieves the coupling of different types of energy in different links. Based on this, this paper firstly combs the coupling relations among different integrated energy subsystems. Secondly, with the help of the weight sharing mechanism in the multi-task learning and the idea of least square support vector machine, a combined forecasting model of electricity, heat, cooling and gas loads based on the multi-task learning and least square support vector machine is constructed. Finally, in order to verify the effectiveness of the forecasting model proposed in this paper, the actual data from the integrated energy system in Suzhou Industrial Park are selected for a case study. The results show that: (1) the combined forecasting model based on multi-task learning and least square support vector machine can accurately predict the electricity, heat, cooling and gas loads of the park integrated energy system. (2) Compared with extreme learning machine and least square support vector machine, the combined forecasting model based on the multi-task learning and least square support vector machine increased the forecasting accuracy of a workday and a weekend by 18.00% and 19.19%, and the average forecasting accuracy increased by 18.60%. (3) Compared with extreme learning machine and least square support vector machine, the combined forecasting model can effectively shorten the training time which is reduced by 58.1% and 35.22%. The results further reflect the application effect of the multi-task learning in energy demand forecasting of the integrated energy system and have a very broad reference value.

[1]  Arun Kumar Sangaiah,et al.  Smart grid load forecasting using online support vector regression , 2017, Comput. Electr. Eng..

[2]  Ali Abbas,et al.  A novel modeling approach to optimize oxygen–steam ratios in coal gasification process , 2015 .

[3]  Erik Delarue,et al.  Integrating short term variations of the power system into integrated energy system models: A methodological review , 2017 .

[4]  Xi Zhang,et al.  Iterative multi-task learning for time-series modeling of solar panel PV outputs , 2018 .

[5]  Davy Geysen,et al.  Thermal load forecasting in district heating networks using deep learning and advanced feature selection methods , 2018, Energy.

[6]  Yanfeng Liu,et al.  Comparison of support vector machine and copula-based nonlinear quantile regression for estimating the daily diffuse solar radiation: A case study in China , 2020, Renewable Energy.

[7]  Worarat Krathu,et al.  Enhancing metabolic event extraction performance with multitask learning concept , 2019, J. Biomed. Informatics.

[8]  Chi-Keong Goh,et al.  Co-evolutionary multi-task learning for dynamic time series prediction , 2017, Appl. Soft Comput..

[9]  Keisuke Fujii,et al.  Supervised dynamic mode decomposition via multitask learning , 2019, Pattern Recognit. Lett..

[10]  Qinghua Hu,et al.  Correlation aware multi-step ahead wind speed forecasting with heteroscedastic multi-kernel learning , 2018 .

[11]  Davy Geysen,et al.  Operational thermal load forecasting in district heating networks using machine learning and expert advice , 2017, ArXiv.

[12]  C. van Treeck,et al.  Data-driven heating and cooling load predictions for non-residential buildings based on support vector machine regression and NARX Recurrent Neural Network: A comparative study on district scale , 2018, Energy.

[13]  Dan Wang,et al.  Review of key problems related to integrated energy distribution systems , 2018, CSEE Journal of Power and Energy Systems.

[14]  Alireza Bahadori,et al.  On the estimation of viscosities and densities of CO2-loaded MDEA, MDEA + AMP, MDEA + DIPA, MDEA + MEA, and MDEA + DEA aqueous solutions , 2017 .

[15]  Guido Carpinelli,et al.  Short-term industrial reactive power forecasting , 2019, International Journal of Electrical Power & Energy Systems.

[16]  Beyzanur Cayir Ervural,et al.  Using machine learning tools for forecasting natural gas consumption in the province of Istanbul , 2019, Energy Economics.

[17]  A. Mohammadi,et al.  Group contribution methods for estimating CO2 absorption capacities of imidazolium and ammonium-based polyionic liquids , 2018, Journal of Cleaner Production.

[18]  Gejirifu De,et al.  Forecasting China’s Natural Gas Consumption Based on AdaBoost-Particle Swarm Optimization-Extreme Learning Machine Integrated Learning Method , 2018, Energies.

[19]  Chongqing Kang,et al.  Review and prospect of integrated demand response in the multi-energy system , 2017 .

[20]  Yi-Ming Wei,et al.  Forecasting China’s regional energy demand by 2030: A Bayesian approach , 2017 .

[21]  Enrico Gerding,et al.  A comparison of multitask and single task learning with artificial neural networks for yield curve forecasting , 2019, Expert Syst. Appl..

[22]  YanYing Li,et al.  Subsampled support vector regression ensemble for short term electric load forecasting , 2018, Energy.

[23]  Xuan Yang,et al.  Short-term electricity load forecasting based on feature selection and Least Squares Support Vector Machines , 2019, Knowl. Based Syst..

[24]  Dacheng Tao,et al.  On Better Exploring and Exploiting Task Relationships in Multitask Learning: Joint Model and Feature Learning , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Lin Li,et al.  Multi-output least-squares support vector regression machines , 2013, Pattern Recognit. Lett..

[26]  Ertuğrul Çam,et al.  Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines , 2015 .

[27]  J. Suykens,et al.  Indefinite kernels in least squares support vector machines and principal component analysis , 2017 .

[28]  Manohar Singh,et al.  Protection challenges under bulk penetration of renewable energy resources in power systems: A review , 2017 .

[29]  A. Mohammadi,et al.  Modeling of stability conditions of natural gas clathrate hydrates using least squares support vector machine approach , 2016 .

[30]  Pan Jian,et al.  The re-optimization strategy of multi-layer hybrid building’s cooling and heating load soft sensing technology research based on temperature interval and hierarchical modeling techniques , 2018 .

[31]  Pan Dongmei,et al.  Forecasting performance comparison of two hybrid machine learning models for cooling load of a large-scale commercial building , 2019, Journal of Building Engineering.

[32]  Ting Zhang,et al.  Evaluation of renewable power sources using a fuzzy MCDM based on cumulative prospect theory: A case in China , 2018 .

[33]  Shuo Xu,et al.  Multi-task least-squares support vector machines , 2014, Multimedia Tools and Applications.

[34]  Cong Li,et al.  Multitask Classification Hypothesis Space With Improved Generalization Bounds , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[35]  Fredrik Wallin,et al.  Analysis of Key Factors in Heat Demand Prediction with Neural Networks , 2017 .

[36]  Fuwei Zhang,et al.  Planning and operation method of the regional integrated energy system considering economy and environment , 2019, Energy.

[37]  Li Li,et al.  Energy performance certification in mechanical manufacturing industry: A review and analysis , 2019, Energy Conversion and Management.

[38]  Hongjie Jia,et al.  A Brief Review to Integrated Energy System and Energy Internet 综合能源系统与能源互联网简述 , 2016 .

[39]  Shun Jia,et al.  Task-Oriented Energy Benchmark of Machining Systems for Energy-Efficient Production , 2020, International Journal of Precision Engineering and Manufacturing-Green Technology.

[40]  Chi-Keong Goh,et al.  Co-evolutionary multi-task learning with predictive recurrence for multi-step chaotic time series prediction , 2017, Neurocomputing.

[41]  Ping Zhong,et al.  Semi-supervised matrixized least squares support vector machine , 2017, Appl. Soft Comput..

[42]  Yachao Zhang,et al.  A novel combination forecasting model for wind power integrating least square support vector machine, deep belief network, singular spectrum analysis and locality-sensitive hashing , 2019, Energy.

[43]  Yandong Yang,et al.  Power load probability density forecasting using Gaussian process quantile regression , 2017 .

[44]  Alireza Bahadori,et al.  Computational intelligent strategies to predict energy conservation benefits in excess air controlled gas-fired systems , 2016 .

[45]  A. Mohammadi,et al.  An accurate CSA-LSSVM model for estimation of densities of ionic liquids , 2016 .

[46]  Shanlin Yang,et al.  A deep learning model for short-term power load and probability density forecasting , 2018, Energy.

[47]  Alireza Baghban,et al.  Insight into the experimental and modeling study of process intensification for post-combustion CO2 capture by rotating packed bed , 2019, Journal of Cleaner Production.

[48]  Chao Feng,et al.  The impact of environmental regulation on fossil energy consumption in China: Direct and indirect effects , 2017 .

[49]  Xiaolei Li,et al.  Traffic Flow Forecasting by a Least Squares Support Vector Machine with a Fruit Fly Optimization Algorithm , 2016 .