{"type":"ScholarlyArticle","title":"Hierarchical Electricity Time Series Forecasting for Integrating Consumption Patterns Analysis and Aggregation Consistency","authors":[{"name":"Yue Pang","slug":"yue-pang","given":"Yue","family":"Pang","affiliation":"School of Computer Science , Fudan University , Shanghai , China; {ypang15 ,"},{"name":"Bo Yao","slug":"bo-yao","given":"Bo","family":"Yao","affiliation":"School of Computer Science , Fudan University , Shanghai , China; {ypang15 ,"},{"name":"Xiangdong Zhou","slug":"xiangdong-zhou","given":"Xiangdong","family":"Zhou","affiliation":"School of Computer Science , Fudan University , Shanghai , China; {ypang15 ,"},{"name":"Yong Zhang","slug":"yong-zhang","given":"Yong","family":"Zhang","affiliation":"State Grid Shanghai Municipal Electric Power Company , Shanghai , China"},{"name":"Yiming Xu","slug":"yiming-xu","given":"Yiming","family":"Xu","affiliation":"School of Computer Science , Fudan University , Shanghai , China; {ypang15 ,"},{"name":"Zijing Tan","slug":"zijing-tan","given":"Zijing","family":"Tan","affiliation":"School of Computer Science , Fudan University , Shanghai , China; {ypang15 ,"}],"abstract":"Electricity demand forecasting is a very important problem for energy supply and environmental protection. It can be formalized as a hierarchical time series forecasting problem with the aggregation constraints according to the geographical hierarchy, since the sum of the prediction results of the disaggregated time series should be equal to the prediction results of the aggregated ones. However in most previous work, the aggregation consistency is ensured at the loss of forecast accuracy. In this paper, we propose a novel clustering-based hierarchical electricity time series forecasting approach. Instead of dealing with the geographical hierarchy directly, we explore electricity consumption patterns by clustering analysis and build a new consumption pattern based time series hierarchy. We then present a novel hierarchical forecasting method with consumption hierarchical aggregation constraints to improve the electricity demand predictions of the bottom level, followed by a ``bottom-up\" method to obtain forecasts of the geographical higher levels. Especially, we observe that in our consumption pattern based hierarchy the reconciliation error of the bottom level time series is ``correlated\" to its membership degree of the corresponding cluster (consumption pattern), and hence apply this correlations as the regularization term in our forecasting objective function. Extensive experiments on real-life datasets verify that our approach achieves the best prediction accuracy, compared with the state-of-the-art  methods.","doi":"10.24963/ijcai.2018/487","url":"https://ijcai.org/proceedings/2018/487","pdf":"https://ijcai.org/proceedings/2018/0487.pdf","markdown":"https://ijcai.org/proceedings/2018/487.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/487","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning Applications","track":"Main track","number":487,"pages":{"first":3506,"last":3512},"keywords":["Machine Learning Applications: Other Applications","Machine Learning: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Athanasopoulos et al., 2009] George Athanasopoulos, Ro- man A Ahmed, and Rob J Hyndman. Hierarchical fore- casts for australian domestic tourism. International Jour- nal of Forecasting, 25(1):146-166, 2009.","title":"Hierarchical forecasts for australian domestic tourism","authors":"Athanasopoulos","year":"2009","venue":"International Journal of Forecasting","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Athanasopoulos et al., 2015] George Athanasopoulos, Rob J Hyndman, Nikolaos Kourentzes, and Fotios Petropoulos. Forecasting with temporal hierarchies. Working paper 16/15, Department of Econometrics and Business Statistics, Monash University, 2015.","title":"Forecasting with temporal hierarchies","authors":"George Athanasopoulos, Rob J Hyndman, Nikolaos Kourentzes, Fotios Petropoulos","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Box and Jenkins, 1976] George EP Box and Gwilym M Jenkins. Time series analysis: forecasting and control, revised ed. Holden-Day, 1976.","title":"Time series analysis: forecasting and control","authors":"Jenkins Box","year":"1976","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[De Livera et al., 2011] Alysha M De Livera, Rob J Hyn- dman, and Ralph D Snyder. Forecasting time series with complex seasonal patterns using exponential smooth- ing. Journal of the American Statistical Association, 106(496):1513-1527, 2011.","title":"Forecasting time series with complex seasonal patterns using exponential smoothing","authors":"Alysha M De Livera, Rob J Hyndman, Ralph D Snyder","year":"2011","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hastie et al., 2015] Trevor Hastie, Robert Tibshirani, and Martin Wainwright. Statistical learning with sparsity: the lasso and generalizations. CRC press, 2015.","title":"Statistical learning with sparsity: the lasso and generalizations","authors":"Trevor Hastie, Robert Tibshirani, Martin Wainwright","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hotelling, 1933] Harold Hotelling. Analysis of a complex of statistical variables into principal components. Journal of educational psychology, 24(6):417, 1933.","title":"Harold Hotelling. Analysis of a complex of statistical variables into principal components","authors":"Hotelling","year":"1933","venue":"Journal of educational psychology","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Huber et al., 2017] Jakob Huber, Alexander Gossmann, and Heiner Stuckenschmidt. Cluster-based hierarchical de- mand forecasting for perishable goods. Expert systems with applications, 76:140-151, 2017.","title":"Cluster-based hierarchical demand forecasting for perishable goods","authors":"Huber","year":"2017","venue":"Expert systems with applications","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hyndman et al., 2008] Rob Hyndman, Anne B Koehler, J Keith Ord, and Ralph D Snyder. Forecasting with ex- ponential smoothing: the state space approach. Springer Science & Business Media, 2008.","title":"Forecasting with exponential smoothing: the state space approach","authors":"Rob Hyndman, Anne B Koehler, J Keith Ord, Ralph D Snyder","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hyndman et al., 2011] Rob J Hyndman, Roman A Ahmed, George Athanasopoulos, and Han Lin Shang. Optimal combination forecasts for hierarchical time series. Com- putational Statistics & Data Analysis, 55(9):2579-2589, 2011.","title":"Optimal combination forecasts for hierarchical time series","authors":"Rob J Hyndman, Roman A Ahmed, George Athanasopoulos, Han Lin Shang","year":"2011","venue":"Computational Statistics & Data Analysis","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hyndman et al., 2016] Rob J Hyndman, Alan J Lee, and Earo Wang. Fast computation of reconciled forecasts for hierarchical and grouped time series. Computational S- tatistics & Data Analysis, 97:16-32, 2016.","title":"Fast computation of reconciled forecasts for hierarchical and grouped time series","authors":"Rob J Hyndman, Alan J Lee, Earo Wang","year":"2016","venue":"Computational Statistics & Data Analysis","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kariya and Kurata, 2004] Takeaki Kariya and Hiroshi Ku- rata. Generalized least squares. John Wiley & Sons, 2004.","title":"Generalized least squares","authors":"Kurata ; Hiroshi Kariya, Kurata","year":"2004","venue":"Takeaki Kariya and","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2012] Der-Chiang Li, Che-Jung Chang, Chien- Chih Chen, and Wen-Chih Chen. Forecasting short-term electricity consumption using the adaptive grey-based ap- proachłan asian case. Omega, 40(6):767-773, 2012.","title":"Forecasting short-term electricity consumption using the adaptive grey-based approachłan asian case","authors":"Li","year":"2012","venue":"Omega","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Park and Nassar, 2014] Mijung Park and Marcel Nassar. Variational bayesian inference for forecasting hierarchical time series. In ICML Workshop, 2014.","title":"Mijung Park and Marcel Nassar. Variational bayesian inference for forecasting hierarchical time series","authors":"Nassar Park","year":"2014","venue":"ICML Workshop","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Pelleg et al., 2000] Dan Pelleg, Andrew W Moore, et al. X- means: Extending k-means with efficient estimation of the number of clusters. In ICML, volume 1, pages 727-734, 2000.","title":"Xmeans: Extending k-means with efficient estimation of the number of clusters","authors":"Dan Pelleg, Andrew W Moore","year":"2000","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ramchurn et al., 2012] Sarvapali D Ramchurn, Perukrish- nen Vytelingum, Alex Rogers, and Nicholas R Jennings. Putting the'smarts' into the smart grid: a grand challenge for artificial intelligence. Communications of the ACM, 55(4):86-97, 2012.","title":"Putting the'smarts' into the smart grid: a grand challenge for artificial intelligence","authors":"Ramchurn","year":"2012","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Raw and Ross, 2011] GJ Raw and DI Ross. Energy demand research project: Final analysis. 2011.","title":"Energy demand research project: Final analysis","authors":"Ross Raw","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Siano, 2014] Pierluigi Siano. Demand response and smart gridsła survey. Renewable and Sustainable Energy Re- views, 30:461-478, 2014.","title":"Demand response and smart gridsła survey","authors":"Pierluigi Siano","year":"2014","venue":"Renewable and Sustainable Energy Reviews","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Snyman, 2005] Jan Snyman. Practical mathematical opti- mization: an introduction to basic optimization theory and classical and new gradient-based algorithms, volume 97. Springer Science & Business Media, 2005.","title":"Practical mathematical optimization: an introduction to basic optimization theory and classical and new gradient-based algorithms","authors":"Jan Snyman, Snyman","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Taieb et al., 2017] Souhaib Ben Taieb, Jiafan Yu, Mateus N- eves Barreto, and Ram Rajagopal. Regularization in hier- archical time series forecasting with application to elec- tricity smart meter data. In AAAI, pages 4474-4480, 2017.","title":"Regularization in hierarchical time series forecasting with application to electricity smart meter data","authors":"Taieb","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Taylor, 2012] James W Taylor. Short-term load forecasting with exponentially weighted methods. IEEE Transactions on Power Systems, 27(1):458-464, 2012.","title":"Short-term load forecasting with exponentially weighted methods","authors":"James W Taylor","year":"2012","venue":"IEEE Transactions on Power Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wickramasuriya et al., 2015] Shanika L Wickramasuriya, George Athanasopoulos, Rob J Hyndman, et al. Fore- casting hierarchical and grouped time series through trace minimization. Department of Econometrics and Business Statistics, Monash University, 2015.","title":"Forecasting hierarchical and grouped time series through trace minimization","authors":"George Shanika L Wickramasuriya, Rob J Athanasopoulos, Hyndman","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wijaya et al., 2015] Tri Kurniawan Wijaya, Matteo Vasir- ani, Samuel Humeau, and Karl Aberer. Cluster-based ag- gregate forecasting for residential electricity demand using smart meter data. In Big Data (Big Data), 2015 IEEE In- ternational Conference on, pages 879-887. IEEE, 2015.","title":"Cluster-based aggregate forecasting for residential electricity demand using smart meter data","authors":"Tri Kurniawan Wijaya, Matteo Vasirani, Samuel Humeau, Karl Aberer","year":"2015","venue":"IEEE International Conference on","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Williams et al., 2016] John K Williams, Peter P Neilley, Joseph P Koval, and Jeff McDonald. Adaptable regres- sion method for ensemble consensus forecasting. In AAAI, pages 3915-3921, 2016.","title":"Adaptable regression method for ensemble consensus forecasting","authors":"Peter P John K Williams, Joseph P Neilley, Jeff Koval, Mcdonald","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang et al., 2015] Dazhi Yang, Gary SW Goh, Siwei Jiang, Allan N Zhang, and Orkan Akcan. Forecast upc-level fm- cg demand, part ii: Hierarchical reconciliation. In Big Data (Big Data), 2015 IEEE International Conference on, pages 2113-2121. IEEE, 2015.","title":"Forecast upc-level fmcg demand, part ii: Hierarchical reconciliation","authors":"Dazhi Yang, S W Gary, Siwei Goh, Allan N Jiang, Orkan Zhang, Akcan","year":"2015","venue":"IEEE International Conference on","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yang et al., 2017] Dazhi Yang, Hao Quan, Vahid R Disfani, and Licheng Liu. Reconciling solar forecasts: Geographi- cal hierarchy. Solar Energy, 146:276-286, 2017.","title":"Reconciling solar forecasts: Geographical hierarchy","authors":"Dazhi Yang, Hao Quan, Licheng Vahid R Disfani, Liu","year":"2017","venue":"Solar Energy","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zheng et al., 2013] Jixuan Zheng, David Wenzhong Gao, and Li Lin. Smart meters in smart grid: An overview. In Green Technologies Conference, 2013 IEEE, pages 57-64. IEEE, 2013.","title":"Smart meters in smart grid: An overview","authors":"Zheng","year":"2013","venue":"Green Technologies Conference","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}