{"type":"ScholarlyArticle","title":"NeuCast: Seasonal Neural Forecast of Power Grid Time Series","authors":[{"name":"Pudi Chen","slug":"pudi-chen","given":"Pudi","family":"Chen","affiliation":"Beijing Key Lab of Intelligent Telecommunications Software and Multimedia; Beijing University of Posts and Telecommunications"},{"name":"Shenghua Liu","slug":"shenghua-liu","given":"Shenghua","family":"Liu","affiliation":"CAS Key Laboratory of Network Data Science and Technology; Institute of Computing Technology , Chinese Academy of Sciences"},{"name":"Chuan Shi","slug":"chuan-shi","given":"Chuan","family":"Shi","affiliation":"Beijing Key Lab of Intelligent Telecommunications Software and Multimedia; Beijing University of Posts and Telecommunications"},{"name":"Bryan Hooi","slug":"bryan-hooi","given":"Bryan","family":"Hooi","affiliation":"School of Computer Science , Carnegie Mellon University"},{"name":"Bai Wang","slug":"bai-wang","given":"Bai","family":"Wang","affiliation":"Beijing Key Lab of Intelligent Telecommunications Software and Multimedia; Beijing University of Posts and Telecommunications"},{"name":"Xueqi Cheng","slug":"xueqi-cheng","given":"Xueqi","family":"Cheng","affiliation":"CAS Key Laboratory of Network Data Science and Technology; Institute of Computing Technology , Chinese Academy of Sciences"}],"abstract":"In the smart power grid, short-term load forecasting (STLF) is a crucial step in scheduling and planning for future load, so as to improve the reliability, cost, and emissions of the power grid. Different from traditional time series forecast, STLF is a more challenging task, because of the complex demand of active and reactive power from numerous categories of electrical loads and the effects of environment. Therefore, we propose NeuCast, a seasonal neural forecasting method, which dynamically models various loads as co-evolving time series in a hidden space, as well as extra weather conditions, in a neural network structure. NeuCast captures seasonality and patterns of the time series by integrating factor modeling and hidden state recognition. NeuCast can also detect anomalies and forecast under different temperature assumptions. Extensive experiments on 134 real-word datasets show the improvements of NeuCast over the stateof-the-art methods.","doi":"10.24963/ijcai.2018/460","url":"https://ijcai.org/proceedings/2018/460","pdf":"https://ijcai.org/proceedings/2018/0460.pdf","markdown":"https://ijcai.org/proceedings/2018/460.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/460","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":460,"pages":{"first":3315,"last":3321},"keywords":["Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications","Machine Learning: Time-series;Data Streams","Machine Learning: Data Mining"],"videos":[],"references":[{"position":1,"raw":"[Baliyan et al., 2015] Arjun Baliyan, Kumar Gaurav, and Sudhansu Kumar Mishra. A review of short term load forecasting using artificial neural network models. Pro- cedia Computer Science, 48:121-125, 2015.","title":"A review of short term load forecasting using artificial neural network models","authors":"Arjun Baliyan, Kumar Gaurav, Sudhansu Kumar, Mishra","year":"2015","venue":"Procedia Computer Science","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Box et al., 2015] George E. P. Box, Gwilym M. Jenkins, Gregory C. Reinsel, and Greta M. Ljung. Time series anal- ysis: Forecasting and control, 5th edition. Journal of the Operational Research Society, 22(2):199-201, 2015.","title":"Time series analysis: Forecasting and control, 5th edition","authors":"E P George, Box, M Gwilym, Gregory C Jenkins, Greta M Reinsel, Ljung","year":"2015","venue":"Journal of the Operational Research Society","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bryan Hooi and Faloutsos, 2018] Amritanshu Pandey Marko Jereminov Larry Pileggi Bryan Hooi, Hyun Ah Song and Christos Faloutsos. Streamcast: Fast and online mining of power grid time sequences. In The 2018 SIAM International Conference on Data Mining, 2018.","title":"Streamcast: Fast and online mining of power grid time sequences","authors":"Bryan Hooi, Faloutsos ; Amritanshu Pandey, Marko Jereminov, Larry Pileggi, Bryan Hooi, Hyun, Ah Song, Christos Faloutsos","year":"2018","venue":"The 2018 SIAM International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Daneshi and Daneshi, 2008] H. Daneshi and A. Daneshi. Real time load forecast in power system. In 2008 Third International Conference on Electric Utility Deregulation and Restructuring and Power Technologies, pages 689- 695, 2008.","title":"Real time load forecast in power system","authors":"H Daneshi, A Daneshi","year":"2008","venue":"2008 Third International Conference on Electric Utility Deregulation and Restructuring and Power Technologies","doi":null,"url":null,"internal_url":null},{"position":5,"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":6,"raw":"[Dudek, 2016] Grzegorz Dudek. Pattern-based local lin- ear regression models for short-term load forecasting. 130:139-147, 2016.","title":"Pattern-based local linear regression models for short-term load forecasting","authors":"Grzegorz Dudek","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fan et al., 2016] Guo-Feng Fan, Li-Ling Peng, Wei-Chiang Hong, and Fan Sun. Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. 173:958-970, 2016.","title":"Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression","authors":"Guo-Feng Fan, Li-Ling Peng, Wei-Chiang Hong, Fan Sun","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ganguly et al., 2017] Piyali Ganguly, Akhtar Kalam, and Aladin Zayegh. Short term load forecasting using fuzzy logic. In International Conference on Research in Educa- tion and Science, 2017.","title":"Short term load forecasting using fuzzy logic","authors":"Piyali Ganguly, Akhtar Kalam, Aladin Zayegh","year":"2017","venue":"International Conference on Research in Education and Science","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gers et al., 1999] Felix A Gers, Jürgen Schmidhuber, and Fred Cummins. Learning to forget: Continual prediction with lstm. 1999.","title":"Learning to forget: Continual prediction with lstm","authors":"Jürgen Felix A Gers, Fred Schmidhuber, Cummins","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Godfrey and Gashler, 2017] Luke B Godfrey and Michael S Gashler. Neural decomposition of time-series data for ef- fective generalization. IEEE transactions on neural net- works and learning systems, 2017.","title":"Neural decomposition of time-series data for effective generalization","authors":"Godfrey, Gashler ; Luke, B Godfrey, Michael S Gashler","year":"2017","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gross and Galiana, 1987] George Gross and Francisco D Galiana. Short-term load forecasting. Proceedings of the IEEE, 75(12):1558-1573, 1987.","title":"Short-term load forecasting","authors":"Galiana Gross, George Gross, Francisco D Galiana","year":"1987","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2017] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collabo- rative filtering. pages 173-182. ACM Press, 2017.","title":"Neural collaborative filtering","authors":"He","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jereminov et al., 2017] M Jereminov, A Pandey, HA Song, B Hooi, C Faloutsos, and L Pileggi. Linear load model for robust power system analysis. IEEE PES Innovative Smart Grid Technologies (2017, p.(submitted)) Google Scholar, 2017. [Letchner et al., 2009] Julie Letchner, Christopher Re, Mag- dalena Balazinska, and Matthai Philipose. Access meth- ods for markovian streams. In Data Engineering, 2009. ICDE'09. IEEE 25th International Conference on, pages 246-257. IEEE, 2009.","title":"Linear load model for robust power system analysis","authors":"Jereminov, H A Pandey, B Song, C Hooi, L Faloutsos, Pileggi","year":"2009","venue":"ICDE'09. IEEE 25th International Conference on","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Maas et al., 2013] Andrew L Maas, Awni Y Hannun, and Andrew Y Ng. Rectifier nonlinearities improve neural net- work acoustic models. In Proc. ICML, volume 30, 2013.","title":"Rectifier nonlinearities improve neural network acoustic models","authors":"Awni Y Andrew L Maas, Andrew Y Hannun, Ng","year":"2013","venue":"Proc. ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Matsubara and Sakurai, 2016] Yasuko Matsubara and Ya- sushi Sakurai. Regime shifts in streams: Real-time fore- casting of co-evolving time sequences. In KDD, pages 1045-1054, 2016.","title":"Regime shifts in streams: Real-time forecasting of co-evolving time sequences","authors":"Yasuko Matsubara, Yasushi Sakurai","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Matsubara et al., 2014] Yasuko Matsubara, Yasushi Saku- rai, and Christos Faloutsos. AutoPlait: automatic min- ing of co-evolving time sequences. pages 193-204. ACM Press, 2014.","title":"AutoPlait: automatic mining of co-evolving time sequences","authors":"Yasuko Matsubara, Yasushi Sakurai, Christos Faloutsos","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Matsubara et al., 2015] Yasuko Matsubara, Yasushi Saku- rai, and Christos Faloutsos. The web as a jungle: Non- linear dynamical systems for co-evolving online activi- ties. In Proceedings of the 24th International Conference on World Wide Web, pages 721-731. International World Wide Web Conferences Steering Committee, 2015.","title":"The web as a jungle: Nonlinear dynamical systems for co-evolving online activities","authors":"Yasuko Matsubara, Yasushi Sakurai, Christos Faloutsos","year":"2015","venue":"Proceedings of the 24th International Conference on World Wide Web","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Salvador and Chan, 2007] Stan Salvador and Philip Chan. Toward accurate dynamic time warping in linear time and space. Intelligent Data Analysis, 11(5):561-580, 2007.","title":"Toward accurate dynamic time warping in linear time and space","authors":"Salvador, Chan ;, Stan Salvador, Philip Chan","year":"2007","venue":"Intelligent Data Analysis","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Selakov et al., 2014] A Selakov, D Cvijetinović, L Milović, S Mellon, and D Bekut. Hybrid pso-svm method for short- term load forecasting during periods with significant tem- perature variations in city of burbank. Applied Soft Com- puting, 16:80-88, 2014.","title":"Hybrid pso-svm method for shortterm load forecasting during periods with significant temperature variations in city of burbank","authors":"Selakov, L Cvijetinović, S Milović, Mellon, Bekut","year":"2014","venue":"Applied Soft Computing","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shahidehpour et al., 2002] Mohammad Shahidehpour, Ha- tim Yamin, and Zuyi Li. Market Operations in Electric Power Systems, New York, NY: IEEE. Wiley-Interscience, John Wiley & Sons, Inc, 2002.","title":"Market Operations in Electric Power Systems","authors":"Mohammad Shahidehpour, Hatim Yamin, Zuyi Li","year":"2002","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Shen and Li, 2015] Zhushi Shen and Defu Li. Electrici- ty power load yesterday hit a new high to 29.82 mil- lion kilowatts. http://wwww.zhhome.com/news/detail/id- 2930.html, 2015.","title":"Electricity power load yesterday hit a new high to 29.82 million kilowatts","authors":"Li ; Shen, Zhushi Shen, Defu Li","year":"2015","venue":null,"doi":null,"url":"http://wwww.zhhome.com/news/detail/id-2930.html,2015","internal_url":null},{"position":22,"raw":"[Song et al., 2017] Hyun Ah Song, Bryan Hooi, Marko Jereminov, Amritanshu Pandey, Larry Pileggi, and Chris- tos Faloutsos. PowerCast: Mining and forecasting power grid sequences. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 606-621. Springer, 2017.","title":"PowerCast: Mining and forecasting power grid sequences","authors":"Hyun Ah Song, Bryan Hooi, Marko Jereminov, Amritanshu Pandey, Larry Pileggi, Christos Faloutsos","year":"2017","venue":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sudheer and Suseelatha, 2015] G Sudheer and A Susee- latha. Short term load forecasting using wavelet transform combined with holt-winters and weighted nearest neigh- bor models. International Journal of Electrical Power & Energy Systems, 64:340-346, 2015.","title":"Short term load forecasting using wavelet transform combined with holt-winters and weighted nearest neighbor models","authors":"G Sudheer, Suseelatha","year":"2015","venue":"International Journal of Electrical Power & Energy Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zheng et al., 2017] Jian Zheng, Cencen Xu, Ziang Zhang, and Xiaohua Li. Electric load forecasting in smart grids using long-short-term-memory based recurrent neural net- work. In Information Sciences and Systems (CISS), 2017 51st Annual Conference on, pages 1-6. IEEE, 2017.","title":"Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network","authors":"Jian Zheng, Cencen Xu, Ziang Zhang, Xiaohua Li","year":"2017","venue":"Information Sciences and Systems (CISS)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}