Cited By
View all- Yu HWang ZXie YWang G(2024)A multi-granularity hierarchical network for long- and short-term forecasting on multivariate time series dataApplied Soft Computing10.1016/j.asoc.2024.111537157(111537)Online publication date: May-2024
Short-term Load Forecasting With Clustered Hybrid Models Based On Hour Granularity
Authors: 
Eleftherios Kouloumpris, Athina Konstantinou, 
Stamatis Karlos, 
Grigorios Tsoumakas, Ioannis VlahavasAuthors Info & Claims
Article No.: 42, Pages 1 - 10
Abstract
Although the recent technological achievements have noticeable impact on several aspects of daily life, more and more challenges are raised in practice. As it concerns the Energy field, the need for accurate predictions over time-dependent use cases of large scale remains high. Deep learning approaches have already found great acceptance in energy time-series signals, but there is still much space for improvement. Contributing to the task of short-term load forecasting we compose a hybrid method; first it exploits the statistical profiling of input raw-signals validating them through various complexity metrics; then a series of feature-engineering processes are applied, before fitting a specified recurrent neural network (RNN) architecture. During the first stage, we use time series clustering to separate time periods in order to capture better temporal patterns. We evaluate our approach using a public dataset that regards the total load consumption of Spain, thus supporting our assumptions about the benefits of leveraging hybrid models for short-term load forecasting. The proposed method outperforms other competitors, including a different RNN architecture and some representative Machine Learning regressors.
References
[1]
Juan A Acero, Elliot J K Koh, Gloria Pignatta, and Leslie K Norford. 2020. Clustering weather types for urban outdoor thermal comfort evaluation in a tropical area. Theoretical and Applied Climatology 139, 1 (2020), 659–675. https://doi.org/10.1007/s00704-019-02992-9
[2]
Ernesto Aguilar Madrid and Nuno Antonio. 2021. Short-Term Electricity Load Forecasting with Machine Learning. Information 12, 2 (2021). https://doi.org/10.3390/info12020050
[3]
Songpu Ai, Antorweep Chakravorty, and Chunming Rong. 2019. Household Power Demand Prediction Using Evolutionary Ensemble Neural Network Pool with Multiple Network Structures. Sensors 19, 3 (2019). https://doi.org/10.3390/s19030721
[4]
Mohanad S. Al-Musaylh, Ravinesh C. Deo, Jan F. Adamowski, and Yan Li. 2018. Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia. Advanced Engineering Informatics 35 (2018), 1–16. https://doi.org/10.1016/j.aei.2017.11.002
[5]
Duong Tuan Anh and Le Huu Thanh. 2015. An efficient implementation of k-means clustering for time series data with DTW distance. International Journal of Business Intelligence and Data Mining 10, 3(2015), 213–232.
[6]
Phil Aupke, Andreas Kassler, Andreas Theocharis, Magnus Nilsson, and Michael Uelschen. 2021. Quantifying Uncertainty for Predicting Renewable Energy Time Series Data Using Machine Learning. Engineering Proceedings 5, 1 (2021). https://doi.org/10.3390/engproc2021005050
[7]
Rosangela Ballini and Ronald R. Yager. 2014. OWA filters and forecasting models applied to electric power load time series. Evol. Syst. 5, 3 (2014), 159–173. https://doi.org/10.1007/s12530-014-9112-2
[8]
Karol Bot, Antonio Ruano, and Maria da Graça Ruano. 2020. Forecasting Electricity Consumption in Residential Buildings for Home Energy Management Systems. In Information Processing and Management of Uncertainty in Knowledge-Based Systems, Marie-Jeanne Lesot, Susana Vieira, Marek Z. Reformat, João Paulo Carvalho, Anna Wilbik, Bernadette Bouchon-Meunier, and Ronald R. Yager (Eds.). Springer International Publishing, Cham, 313–326.
[9]
Moulay Larbi Chalal, Medjdoub Benachir, Michael White, and Raid Shrahily. 2016. Energy planning and forecasting approaches for supporting physical improvement strategies in the building sector: A review. Renewable and Sustainable Energy Reviews 64, C (2016), 761–776. https://doi.org/10.1016/j.rser.2016.06.04
[10]
Cristina Heghedus, Antorweep Chakravorty, and Chunming Rong. 2018. Energy Load Forecasting Using Deep Learning. In 2018 IEEE International Conference on Energy Internet (ICEI). 146–151. https://doi.org/10.1109/ICEI.2018.00-23
[11]
Benedikt Heidrich, Marian Turowski, Nicole Ludwig, Ralf Mikut, and Veit Hagenmeyer. 2020. Forecasting energy time series with profile neural networks. In e-Energy ’20: The Eleventh ACM International Conference on Future Energy Systems, Virtual Event, Australia, June 22-26, 2020. ACM, 220–230. https://doi.org/10.1145/3396851.3397683
[12]
Benedikt Heidrich, Marian Turowski, Nicole Ludwig, Ralf Mikut, and Veit Hagenmeyer. 2020. Forecasting energy time series with profile neural networks. In Proceedings of the Eleventh ACM International Conference on Future Energy Systems. 220–230.
[13]
Julia Hidalgo and Renaud Jougla. 2018. On the use of local weather types classification to improve climate understanding: An application on the urban climate of Toulouse. PLOS ONE 13, 12 (12 2018), 1–21. https://doi.org/10.1371/journal.pone.0208138
[14]
Tareq Hossen, Arun Sukumaran Nair, Radhakrishnan Angamuthu Chinnathambi, and Prakash Ranganathan. 2018. Residential Load Forecasting Using Deep Neural Networks (DNN). In 2018 North American Power Symposium (NAPS). 1–5. https://doi.org/10.1109/NAPS.2018.8600549
[15]
Jun Huang, Baohua Yu, Cong-Cong Xing, Tomas Cerny, and Zhaolong Ning. 2021. Online Energy Scheduling Policies in Energy Harvesting Enabled D2D Communications. IEEE Transactions on Industrial Informatics 17, 8 (2021), 5678–5687. https://doi.org/10.1109/TII.2020.3005440
[16]
Junhong Kim, Jihoon Moon, Eenjun Hwang, and Pilsung Kang. 2019. Recurrent inception convolution neural network for multi short-term load forecasting. Energy and Buildings 194(2019), 328–341. https://doi.org/10.1016/j.enbuild.2019.04.034
[17]
Weicong Kong, Zhao Yang Dong, Youwei Jia, David J. Hill, Yan Xu, and Yuan Zhang. 2019. Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network. IEEE Transactions on Smart Grid 10, 1 (2019), 841–851. https://doi.org/10.1109/TSG.2017.2753802
[18]
Irena Koprinska, Dengsong Wu, and Zheng Wang. 2018. Convolutional Neural Networks for Energy Time Series Forecasting. In 2018 International Joint Conference on Neural Networks, IJCNN 2018, Rio de Janeiro, Brazil, July 8-13, 2018. IEEE, 1–8. https://doi.org/10.1109/IJCNN.2018.8489399
[19]
Muralitharan Krishnan, Yoon Mo Jung, and Sangwoon Yun. 2020. Prediction of Energy Demand in Smart Grid using Hybrid Approach. In 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC). 294–298. https://doi.org/10.1109/ICCMC48092.2020.ICCMC-00055
[20]
Brecht Laperre, Jorge Amaya, and Giovanni Lapenta. 2020. Dynamic Time Warping as a New Evaluation for Dst Forecast with Machine Learning. CoRR abs/2006.04667(2020). arXiv:2006.04667https://arxiv.org/abs/2006.04667
[21]
Jian Li, Daiyu Deng, Junbo Zhao, Dongsheng Cai, Weihao Hu, Man Zhang, and Qi Huang. 2021. A Novel Hybrid Short-Term Load Forecasting Method of Smart Grid Using MLR and LSTM Neural Network. IEEE Transactions on Industrial Informatics 17, 4 (2021), 2443–2452. https://doi.org/10.1109/TII.2020.3000184
[22]
Yanfei Li, Haiping Wu, and Hui Liu. 2018. Multi-step wind speed forecasting using EWT decomposition, LSTM principal computing, RELM subordinate computing and IEWT reconstruction. Energy Conversion and Management 167 (2018), 203–219. https://doi.org/10.1016/j.enconman.2018.04.082
[23]
Jun Lin, Jin Ma, Jianguo Zhu, and Yu Cui. 2022. Short-term load forecasting based on LSTM networks considering attention mechanism. International Journal of Electrical Power & Energy Systems 137 (2022), 107818. https://doi.org/10.1016/j.ijepes.2021.107818
[24]
Daniel L. Marino, Kasun Amarasinghe, and Milos Manic. 2016. Building energy load forecasting using Deep Neural Networks. In IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society. 7046–7051. https://doi.org/10.1109/IECON.2016.7793413
[25]
Meinard Müller. 2007. Dynamic time warping. Information retrieval for music and motion(2007), 69–84.
[26]
Christoforos Nalmpantis, Odysseas Krystalakos, and Dimitris Vrakas. 2018. Energy profile representation in vector space. In Proceedings of the 10th Hellenic Conference on Artificial Intelligence, SETN 2018, Patras, Greece, July 09-12, 2018. ACM, 22:1–22:5. https://doi.org/10.1145/3200947.3201050
[27]
Slobodan Petrovic. 2006. A comparison between the silhouette index and the davies-bouldin index in labelling ids clusters. In Proceedings of the 11th Nordic Workshop of Secure IT Systems, Vol. 2006. Citeseer, 53–64.
[28]
Steven M Pincus. 1991. Approximate entropy as a measure of system complexity.Proceedings of the National Academy of Sciences 88, 6 (1991), 2297–2301.
[29]
M Pumperla. 2017. Hyperas: a very simple convenience wrapper around hyperopt for fast prototyping with Keras model. Accessed: Apr 30(2017), 2019.
[30]
Jason Runge and Radu Zmeureanu. 2019. Forecasting Energy Use in Buildings Using Artificial Neural Networks: A Review. Energies 12, 17 (2019). https://doi.org/10.3390/en12173254
[31]
Bikash Kumar Sahu. 2018. Wind energy developments and policies in China: A short review. Renewable and Sustainable Energy Reviews 81 (2018), 1393–1405. https://doi.org/10.1016/j.rser.2017.05.183
[32]
Xingjian Shi, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai-Kin Wong, and Wang-chun Woo. 2015. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett (Eds.). 802–810. https://proceedings.neurips.cc/paper/2015/hash/07563a3fe3bbe7e3ba84431ad9d055af-Abstract.html
[33]
Amanpreet Singh, Narina Thakur, and Aakanksha Sharma. 2016. A review of supervised machine learning algorithms. In 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom). Ieee, 1310–1315.
[34]
Angela Stallone, Antonio Cicone, and Massimo Materassi. 2020. New insights and best practices for the successful use of Empirical Mode Decomposition, Iterative Filtering and derived algorithms. Scientific Reports 10, 1 (2020), 15161. https://doi.org/10.1038/s41598-020-72193-2
[35]
Marina Theodosiou. 2011. Forecasting monthly and quarterly time series using STL decomposition. International Journal of Forecasting 27, 4 (2011), 1178–1195.
[36]
Nicolai Bo Vanting, Zheng Ma, and Bo Nørregaard Jørgensen. 2021. A scoping review of deep neural networks for electric load forecasting. Energy Informatics 4, 2 (2021), 49. https://doi.org/10.1186/s42162-021-00148-6
[37]
Zhaohua Wu and Norden E. Huang. 2009. Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method. Adv. Data Sci. Adapt. Anal. 1, 1 (2009), 1–41. https://doi.org/10.1142/S1793536909000047
[38]
Hong Bo Zhou and Jun Tao Gao. 2014. Automatic method for determining cluster number based on silhouette coefficient. In Advanced Materials Research, Vol. 951. Trans Tech Publ, 227–230.
Index Terms
- Short-term Load Forecasting With Clustered Hybrid Models Based On Hour Granularity
Recommendations
Short-term load forecasting using lifting scheme and ARIMA models
Research highlights Short-term load forecasting is achieved using a lifting scheme and autoregressive integrated moving average (ARIMA) models. Lifting scheme is embedded into the ARIMA models to enhance forecasting accuracy. The Coeflet 12 wavelet is ...
Application of a Hybrid Model to Short-Term Load Forecasting
ISME '10: Proceedings of the 2010 International Conference of Information Science and Management Engineering - Volume 01Short-term load forecasting has been viewed as an important problem for its wide application. Grey forecasting model is tested by using electric load data sampled from SA for short-term load forecasting in this paper. Then by regarding the electric load ...
Neural networks for pattern-based short-term load forecasting
In this work several univariate approaches for short-term load forecasting based on neural networks are proposed and compared. They include: multilayer perceptron, radial basis function neural network, generalized regression neural network, fuzzy ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2022
450 pages
ISBN:9781450395977
DOI:10.1145/3549737
Copyright © 2022 ACM.
Publication rights licensed to ACM. ACM acknowledges that this contribution was authored or co-authored by an employee, contractor or affiliate of a national government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only.
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 09 September 2022
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- Operational Program Competitiveness, Entrepreneurship and Innovation
Conference
SETN 2022
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 47Total Downloads
- Downloads (Last 12 months)14
- Downloads (Last 6 weeks)0
Reflects downloads up to 28 Dec 2024
Other Metrics
Citations
Cited By
View all- Yu HWang ZXie YWang G(2024)A multi-granularity hierarchical network for long- and short-term forecasting on multivariate time series dataApplied Soft Computing10.1016/j.asoc.2024.111537157(111537)Online publication date: May-2024
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format