Abstract
Smart cities can be viewed as large-scale Cyber-Physical Systems (CPS) where different sensors and devices record the cyber and physical indicators of the city systems. The collected data are used for improving urban life by offering services such as accurate electric load forecasting, and more efficient traffic management. Traditional monitoring for electricity and transportation networks generally do not provide full observability due to their limited coverage as well as high implementation and maintenance costs. For example, continuous traffic data collection is mostly limited to major highways only in big cities, whereas local roadways are usually covered once or twice a year. Also, there are no high-fidelity and real-time electric monitoring systems in all parts of power distribution networks. Combining the limited data from each of the urban systems together (e.g., electricity, transportation, environment, etc.) provides a better picture of the energy flow in a city. Furthermore, a city should be considered as a collection of the layers of tangled infrastructure networks, which connects people, places, and resources. Therefore, the study of traffic or electricity consumption forecasting should go beyond the transportation and electricity networks and merge with each other and even with other city networks such as environmental networks. As such, this article proposes a Bayesian spatiotemporal Gaussian Process model that employs the most informative spatiotemporal interdependency among different interconnected networks (in this case, electricity, transportation, and weather). The proposed load forecasting method is compared with other state-of-the-art methods using real-life data obtained from the City of Tallahassee in Florida. Results show that the proposed Bayesian spatiotemporal Gaussian Process model outperforms state-of-the-art methods.
- Juan Aparicio, Justinian Rosca, Markus Mediger, Alexander Essl, Klaus Arzig, and Chris Develder. 2014. Exploiting road traffic data for very short term load forecasting in smart grids. In Proceedings of the 2014 IEEE PES Innovative Smart Grid Technologies Conference (ISGT’14) (Feb. 2014). DOI:https://doi.org/10.1109/ISGT.2014.6816498Google ScholarCross Ref
- Khandoker Shuvo Bakar. 2012. Bayesian Analysis of Daily Maximum Ozone Levels. Ph.D. Dissertation. University of Southampton.Google Scholar
- Khandoker Shuvo Bakar and Sujit K. Sahu. 2015b. spTimer: Spatio-temporal bayesian modeling using R. J. Stat. Softw. 63, 15 (Feb. 2015), 1--32. http://www.jstatsoft.org/v63/i15/.Google ScholarCross Ref
- Khandoker Shuvo Bakar and Sujit K. Sahu. 2015a. spTimer: Spatio-temporal bayesian modeling using R. R package version 2.0-1. J. Stat. Softw. 63, 15 (Feb. 2015), 1–32. DOI:https://doi.org/10.18637/jss.v063.i15Google ScholarCross Ref
- U.S. Census Bureau. 2018. U.S. Census Bureau QuickFacts: Tallahassee city, Florida. Retrieved from https://www.census.gov/quickfacts/fact/table/tallahasseecityflorida/IPE120216.Google Scholar
- Ervin Ceperic, Vladimir Ceperic, and Adrijan Baric. 2013. A strategy for short-term load forecasting by support vector regression machines. IEEE Trans. Power Syst. 28, 4 (Jul. 2013), 4356--4364. DOI:https://doi.org/10.1109/TPWRS.2013.2269803Google ScholarCross Ref
- Mohamed Chaouch. 2014. Clustering-based improvement of nonparametric functional time series forecasting: Application to intra-day household-level load curves. IEEE Trans. Smart Grid 5, 1 (Sept. 2014), 411--419. DOI:https://doi.org/10.1109/TSG.2013.2277171Google ScholarCross Ref
- Shin-Tzo Chen, David C. Yu, and A. R. Moghaddamjo. 1992. Weather sensitive short-term load forecasting using nonfully connected artificial neural network. IEEE Trans. Power Syst. 7, 3 (Aug. 1992), 1098--1105. DOI:https://doi.org/10.1109/59.207323Google ScholarCross Ref
- T. W. S. Chow and C. T. Leung. 1996. Neural network based short-term load forecasting using weather compensation. IEEE Trans. Power Syst. 11, 4 (Nov. 1996), 1736--1742. DOI:https://doi.org/10.1109/59.544636Google ScholarCross Ref
- Mario Cools, Elke Moons, Lieve Creemers, and Geert Wets. 2010. Changes in travel behavior in response to weather conditions do type of weather and trip purpose matter? J. Transport. Res. Board 2157, 1 (Dec. 2010), 22--28. DOI:https://doi.org/10.3141/2157-03Google ScholarCross Ref
- Jose Cordova, Lalitha Madhavi K. S., Ayberk Kocatepe, Yuxun Zhou, Eren E. Ozguven, and Reza Arghandeh. 2018. Combined electricity and traffic short-term load forecasting using bundled causality engine. (unpublished).Google Scholar
- M. Davies. 1959. The relationship between weather and electricity demand. In Proceedings of the IEEE, Part C: Monographs (IEEE’59), Vol. 106. IET, 27--37. DOI:https://doi.org/10.1049/pi-c.1959.0007Google ScholarCross Ref
- Wen Deng, Hao Lei, and Xuesong Zhou. 2013. Traffic state estimaton and uncertainty quantification based on heterogeneous data sources: A three detector approach. Transport. Res. 57, 1 (Nov. 2013), 132--157. DOI:https://doi.org/10.1016/j.trb.2013.08.015Google ScholarCross Ref
- Nour-Eddin El-Faouzi. 2010. Real-time Monitoring, Surveillance and Control of Road Networks Under Adverse Weather Conditions: Effects of Weather on Traffic and Pavement: State of the Art and Best Practices. INRETS.Google Scholar
- Damien Fay and John V. Ringwood. 2010. On the influence of weather forecast errors in short-term load forecasting models. IEEE Trans. Power Syst. 25, 3 (Feb. 2010), 1751--1758. DOI:https://doi.org/10.1109/TPWRS.2009.2038704Google ScholarCross Ref
- Alan E. Gelfand. 2012. Hierarchical modeling for spatial data problems, spatial statistics. Spatial Stat. 1, 1 (Feb. 2012), 30--39. DOI:https://doi.org/10.1016/j.spasta.2012.02.005Google ScholarCross Ref
- Andrew Gelman, John B. Carlin, Hal S. Stern, David B. Dunson, Aki Vehtari, and Donald B. Rubin. 2004. Bayesian Data Analysis (3rd ed.). Chapman 8 Hall/CRC.Google Scholar
- Mahmoud Ghofrani, M. Hassanzadeh, Mehdi Etezadi-Amoli, and M. Sami Fadali. 2011. Smart meter based short-term load forecasting for residential customers. In Proceedings of the IEEE North American Power Symposium (NAPS’11), 99--118. DOI:https://doi.org/10.1109/NAPS.2011.6025124Google Scholar
- Juan C. Herrera, Daniel B. Work, Ryan Herring, Xuegang Ban, Quinn Jacobson, and Alexandre M. Bayen. 2010. Evaluation of traffic data obtained via GPS-enabled mobile phones: The mobile century field experiment.Transport. Res. 18, 4 (Dec. 2010), 568--583. DOI:https://doi.org/10.1016/j.trc.2009.10.006Google Scholar
- Aude Hofleitner, Ryan Herring, Pieter Abbeel, and Alexandre Bayen. 2012. Learning the dynamics of arterial traffic from probe data using a dynamic Bayesian network. IEEE Trans. Intell. Transport. Syst. 13, 4 (Dec. 2012), 1679--1693. DOI:https://doi.org/10.1109/TITS.2012.2200474Google ScholarDigital Library
- Yu-Hsiang Hsiao. 2015. Household electricity demand forecast based on context information and user daily schedule analysis from meter data. IEEE Trans. Industr. Inf. 11, 1 (Oct. 2015), 33--43. DOI:https://doi.org/10.1109/TII.2014.2363584Google ScholarCross Ref
- Samuel Humeau, Tri Kurniawan Wijaya, Matteo Vasirani, and Karl Aberer. 2013. Electricity load forecasting for residential customers: Exploiting aggregation and correlation between households. Sustainable Internet and ICT for Sustainability (SustainIT). 1–6. DOI:https://doi.org/10.1109/SustainIT.2013.6685208Google Scholar
- Jarod C. Kelly, Tulga Ersal, Chiao-Ting Li, Brandon M. Marshall, Soumya Kundu, Gregory A. Keoleian, Huei Peng, Ian A. Hiskens, and Jeffrey L. Stein. 2015. Sustainability, resiliency, and grid stability of the coupled electricity and transportation infrastructures: Case for an integrated analysis. J. Infrastruct. Syst. 21, 4 (Feb. 2015), 04015001.Google ScholarCross Ref
- Weicong Kong, Zhao Yang Dong, David J. Hill, Fengji Luo, and Yan Xu. 2017. Short-term residential load forecasting based on resident behaviour learning. IEEE Trans. Power Syst. 33, 1 (Mar. 2017), 1087–1088. DOI:https://doi.org/10.1109/TPWRS.2017.2688178Google Scholar
- Lalitha Madhavi K. S., Mostafa Gilanifar, Yuxun Zhou, Eren E. Ozguven, and Reza Arghandeh. 2018. Multivariate deep causal network for time series forecasting in independent networks. In Proceedings of the 57th IEEE Conference on Decision and Control.Google Scholar
- Sharad Kumar, Shashank Mishra, and Shashank Gupta. 2016. Short term load forecasting using ANN and multiple linear regression. In Proceedings of the Second International Conference on Computational Intelligence and Communication Technology (CICT’16). DOI:https://doi.org/10.1109/CICT.2016.44Google ScholarCross Ref
- K. S. Lalitha Madhavi, Jose Cordova, Mehmet Baran Ulak, Michael Ohlsen, Eren E. Ozguven, Reza Arghandeh, and Ayberk Kocatepe. 2017. Advanced electricity load forecasting combining electricity and transportation network. In Proceedings of the IEEE Conference of the 2017 North American Power Symposium (NAPS’17). DOI:https://doi.org/10.1109/NAPS.2017.8107312Google ScholarCross Ref
- K. S. Lalitha Madhavi, Mostafa Gilanifar, Yuxun Zhou, Eren E. Ozguven, and Reza Arghandeh. 2019. Causal Markov Elman network for load forecasting in multi network systems. IEEE Trans. Industr. Electr. 66, 2 (Feb. 2019), 1434--1442. DOI:https://doi.org/10.1109/TIE.2018.2851977Google Scholar
- Benjamin Marti. 2006. Integrated Analysis of Energy and Transportation Systems. Master’s thesis. Swiss Federal Institute of Technology (ETH) Zurich, Zurich.Google Scholar
- Bertil Matern. 1986. Spatial Variation (2nd ed.). Springer-Verlag, New York.Google Scholar
- Alfredo Nantes, Dong Ngoduy, Ashish Bhaskar, Marc Miska, and Edward Chung. 2016. Real-time traffic state estimation in urban corridors from heterogeneous data. Transport. Res. 66, 1 (May 2016), 99--118. DOI:https://doi.org/10.1016/j.trc.2015.07.005Google Scholar
- Hung Nguyen and Christian K. Hansen. 2017. Short-term electricity load forecasting with time series analysis. In Proceedings of the 2017 IEEE International Conference onPrognostics and Health Management (ICPHM’17). DOI:https://doi.org/10.1109/ICPHM.2017.7998331Google ScholarCross Ref
- Julien Ostermann and Falko Koetter. 2016. Energy-management-as-a-service: Mobility aware energy management for a shared electric vehicle fleet. In Proceedings of the 2016 5th International Conference on Smart Cities and Green ICT Systems (SMARTGREENS’16).Google ScholarDigital Library
- Davide Pinzan, Ayberk Kocatepe, Mostafa Gilanifar, Mehmet B. Ulak, Eren E. Ozguven, and Reza Arghandeh. 2018. Data-driven and hurricane-focused metrics for combined transportation and power networks resilience. In Proceedings of the 2018 Transportation Research Board Annual Meeting (TRB’18).Google Scholar
- Christian Rudloff, Maximilian Leodolter, Dietmar Bauer, Roland Auer, Werner Brög, and Knud Kehnscherper. 2015. Influence of weather on transport demand: A case study from the Vienna region. J. Transport. Res. Board 24821, 1 (Jan. 2015), 110–116. DOI:https://doi.org/10.3141/2482-14Google Scholar
- Slobodan Ruzic, Aca Vuckovic, and Nikola Nikolic. 2003. Weather sensitive method for short term load forecasting in electric power utility of serbia. IEEE Trans. Power Sys. 18, 4 (Nov. 2003), 1581--1586. DOI:https://doi.org/10.1109/TPWRS.2003.811172Google ScholarCross Ref
- Rijurekha Sen, Andrew Cross, Aditya Vashistha, Venkata N. Padmanabhan, Edward Cutrell, and William Thies. 2013. Accurate speed and density measurement for road traffic in India. In Proceedings of the 3rd ACM Symposium on Computing for Development (ACM DEV’13). ACM, 1--10. DOI:https://doi.org/10.1145/2442882.2442901Google ScholarDigital Library
- James W. Taylor and Roberto Buizza. 2002. Neural network load forecasting with weather ensemble predictions. IEEE Trans. Power Syst. 17, 3 (Nov. 2002), 626--632. DOI:https://doi.org/10.1109/TPWRS.2002.800906Google ScholarCross Ref
- WeatherSTEM. 2018. WeatherSTEM.Leon County. Retrieved from https://leon.weatherstem.com.Google Scholar
- Young-Min Wi, Sung-Kwan Joo, and Kyung-Bin Song. 2012. Holiday load forecasting using fuzzy polynomial regression with weather feature selection and adjustment. IEEE Trans. Power Syst. 27, 2 (Dec. 2012), 596--603. DOI:https://doi.org/10.1109/TPWRS.2011.2174659Google ScholarCross Ref
- Daniel B. Work, Sebastien Balndin, Olli-Pekka Tossavainen, Benedetto Piccoli, and Alexandre M. Bayen. 2010. A traffic model for velocity data assimilation. Appl. Math. Res. Express (Apr. 2010), 1--35. DOI:https://doi.org/10.1093/amrx/abq002.Google Scholar
- Tao Xing, Xuesong Zhou, and Jeffrey Taylor. 2013. Designing heterogeneous sensor networks for estimating and predicting path travel time dynamics: An information-theoretic modeling approach. Transport. Res. 57, 1 (Nov. 2013), 66--90. DOI:https://doi.org/10.1016/j.trb.2013.09.007Google ScholarCross Ref
- Desheng Zhang, Juanjuan Zhao, Fan Zhang, Tian He, Haengju Lee, and Sang H. Son. 2017. Heterogeneous model integration for multi-source urban infrastructure data. ACM Trans. Cyber-Phys. Syst. 1, 1 (Feb. 2017). DOI:https://doi.org/10.1145/2967503Google ScholarDigital Library
- Yu Zheng, Licia Capra, Ouri Wolfson, and Hai Yang. 2014. Urban computing: Concepts, methodologies, and applications. ACM Trans. Intell. Syst. Technol. 5, 3 (Sept. 2014). DOI:https://doi.org/10.1145/2629592Google ScholarDigital Library
Index Terms
- Bayesian Spatiotemporal Gaussian Process for Short-term Load Forecasting Using Combined Transportation and Electricity Data
Recommendations
Online SARIMA applied for short-term electricity load forecasting
AbstractShort-term Load Forecasting (STLF) plays a crucial role in balancing the supply and demand of load dispatching operations and ensures stability for the power system. With the advancement of real-time smart sensors in power systems, it is of great ...
Short-term load forecasting using a Gaussian process model: The influence of a derivative term in the input regressor
Intelligent technologies for planning and decision making under uncertaintyThis paper establishes a regressive methodology, applied to the electrical distribution sector, to predict the next hour load. The approach followed is based on a Gaussian process model. To create a simple structure for the input regressor only a few ...
Short-term natural gas consumption forecasting
ASM '07: The 16th IASTED International Conference on Applied Simulation and ModellingThe natural gas market requires forecasting for the optimisation of leasing additional storage capacities. Consequently, natural gas distribution companies have an economic stimulus to accurately forecast their future gas consumption. A method for short-...
Comments