Using Large-Scale Social Media Networks as a Scalable Sensing System for Modeling Real-Time Energy Utilization Patterns

The hypothesis of this paper is that topics, expressed through large-scale social media networks, approximate electricity utilization events (e.g., using high power consumption devices such as a dryer) with high accuracy. Traditionally, researchers have proposed the use of smart meters to model device-specific electricity utilization patterns. However, these techniques suffer from scalability and cost challenges. To mitigate these challenges, we propose a social media network-driven model that utilizes large-scale textual and geospatial data to approximate electricity utilization patterns, without the need for physical hardware systems (e.g., such as smart meters), hereby providing a readily scalable source of data. The methodology is validated by considering the problem of electricity use disaggregation, where energy consumption rates from a nine-month period in San Diego, coupled with 1.8 million tweets from the same location and time span, are utilized to automatically determine activities that require large or small amounts of electricity to accomplish. The system determines 200 topics on which to detect electricity-related events and finds 38 of these to be valid descriptors of energy utilization. In addition, a comparison with electricity consumption patterns published by domain experts in the energy sector shows that our methodology both reproduces the topics reported by experts, while discovering additional topics. Finally, the generalizability of our model is compared with a weather-based model, provided by the U.S. Department of Energy.

[1]  Sven G. Bilen,et al.  Increasing the veracity of event detection on social media networks through user trust modeling , 2014, 2014 IEEE International Conference on Big Data (Big Data).

[2]  Lawrence V. Snyder,et al.  Control Mechanisms for Residential Electricity Demand in SmartGrids , 2010, 2010 First IEEE International Conference on Smart Grid Communications.

[3]  I. Ayres,et al.  Evidence from Two Large Field Experiments that Peer Comparison Feedback Can Reduce Residential Energy Usage , 2009 .

[4]  Dane Petersen,et al.  WattBot: a residential electricity monitoring and feedback system , 2009, CHI Extended Abstracts.

[5]  Cécile Viboud,et al.  Reassessing Google Flu Trends Data for Detection of Seasonal and Pandemic Influenza: A Comparative Epidemiological Study at Three Geographic Scales , 2013, PLoS Comput. Biol..

[6]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[7]  M. Kwan The Uncertain Geographic Context Problem , 2012 .

[8]  Douglas W. Caves,et al.  Econometric analysis of residential time-of-use electricity pricing experiments , 1980 .

[9]  Christian Bauckhage,et al.  More influence means less work: fast latent dirichlet allocation by influence scheduling , 2011, CIKM '11.

[10]  M.T.O. Amanullah,et al.  Network Security Vulnerabilities in SCADA and EMS , 2005, 2005 IEEE/PES Transmission & Distribution Conference & Exposition: Asia and Pacific.

[11]  Sherif Sakr,et al.  Cloud Data Management , 2014, Springer International Publishing.

[12]  Inês L. Azevedo,et al.  Residential and Regional Electricity Consumption in the U.S. and EU: How Much Will Higher Prices Reduce CO2 Emissions? , 2011 .

[13]  Maximilian Auffhammer,et al.  IMPACTS OF CLIMATE CHANGE ON RESIDENTIAL ELECTRICITY CONSUMPTION: EVIDENCE FROM BILLING DATA , 2011 .

[14]  Marcel Salathé,et al.  Validating models for disease detection using twitter , 2013, WWW.

[15]  Stephen B. Wicker,et al.  A Privacy-Aware Architecture for Demand Response Systems , 2011, 2011 44th Hawaii International Conference on System Sciences.

[16]  J. Zico Kolter,et al.  REDD : A Public Data Set for Energy Disaggregation Research , 2011 .

[17]  Marcel Salathé,et al.  On the ground validation of online diagnosis with Twitter and medical records , 2014, WWW.

[18]  R. Guha,et al.  What are we ‘tweeting’ about obesity? Mapping tweets with topic modeling and Geographic Information System , 2013, Cartography and geographic information science.

[19]  Jácint Szabó,et al.  Latent dirichlet allocation in web spam filtering , 2008, AIRWeb '08.

[20]  Gregor Heinrich Parameter estimation for text analysis , 2009 .

[21]  Zhiwei Li,et al.  LogisticLDA: Regularizing Latent Dirichlet Allocation by Logistic Regression , 2009, PACLIC.

[22]  Yiming Yang,et al.  A re-examination of text categorization methods , 1999, SIGIR '99.

[23]  Peter Palensky,et al.  Simulating Cyber-Physical Energy Systems: Challenges, Tools and Methods , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[24]  Kathleen M. Carley,et al.  Social Network Modeling and Agent-Based Simulation in Support of Crisis De-Escalation , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[25]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[26]  C. Granger Some recent development in a concept of causality , 1988 .

[27]  Steven B. Wicker,et al.  Decreased time delay and security enhancement recommendations for AMI smart meter networks , 2010, 2010 Innovative Smart Grid Technologies (ISGT).

[28]  Russell Smyth,et al.  Multivariate Granger causality between electricity generation, exports, prices and GDP in Malaysia , 2010 .

[29]  Ward Jewell,et al.  Wireless AMI application and security for controlled home area networks , 2011, 2011 IEEE Power and Energy Society General Meeting.

[30]  Yutaka Matsuo,et al.  Earthquake shakes Twitter users: real-time event detection by social sensors , 2010, WWW '10.

[31]  M. Parti,et al.  The Total and Appliance-Specific Conditional Demand for Electricity in the Household Sector , 1980 .

[32]  Martin F. Porter,et al.  An algorithm for suffix stripping , 1997, Program.

[33]  Iraklis Varlamis,et al.  A Trust-Aware System for Personalized User Recommendations in Social Networks , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[34]  Wolfgang Lehner,et al.  pEDM: online-forecasting for smart energy analytics , 2013, CIKM.

[35]  Stephen B. Wicker,et al.  Inferring Personal Information from Demand-Response Systems , 2010, IEEE Security & Privacy.

[36]  Todd R. Andel,et al.  A Trust-Management Toolkit for Smart-Grid Protection Systems , 2014, IEEE Transactions on Power Delivery.

[37]  David W. S. Wong The Modifiable Areal Unit Problem (MAUP) , 2004 .

[38]  J. Dobson,et al.  Conservation Effect of Immediate Electricity Cost Feedback on Residential Consumption Behaviour , 2009 .

[39]  Mark Steyvers,et al.  Finding scientific topics , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[40]  Matthew A. Russell,et al.  Mining the Social Web: Data Mining Facebook, Twitter, LinkedIn, Google+, GitHub, and More , 2018 .

[41]  R. J. Moe,et al.  Residential energy use and improved building thermal efficiency: an econometric analysis , 1983 .

[42]  Marcel Salathé,et al.  Discovering health-related knowledge in social media using ensembles of heterogeneous features , 2013, CIKM.

[43]  Susumu Horiguchi,et al.  Learning to classify short and sparse text & web with hidden topics from large-scale data collections , 2008, WWW.

[44]  ChengXiang Zhai,et al.  Mining causal topics in text data: iterative topic modeling with time series feedback , 2013, CIKM.

[45]  Wattanapong Rakwichian,et al.  The impacts of climatic and economic factors on residential electricity consumption of Bangkok Metropolis , 2008 .

[46]  Yiming Yang,et al.  RCV1: A New Benchmark Collection for Text Categorization Research , 2004, J. Mach. Learn. Res..

[47]  C. Bennett,et al.  Networking AMI Smart Meters , 2008, 2008 IEEE Energy 2030 Conference.

[48]  R. Larson,et al.  The Energy Box: Locally Automated Optimal Control of Residential Electricity Usage , 2009 .

[49]  D. Kammen,et al.  Letting the (energy) Gini out of the bottle: Lorenz curves of cumulative electricity consumption and Gini coefficients as metrics of energy distribution and equity , 2005 .

[50]  松川 勇 The Effects of Information on Residential Demand for Electricity , 2002 .

[51]  Maximilian Auffhammer,et al.  The Impact of State Level Building Codes on Residential Electricity Consumption , 2011 .

[52]  Ross Maciejewski,et al.  Understanding Twitter data with TweetXplorer , 2013, KDD.

[53]  Massimo Filippini,et al.  Short- and long-run time-of-use price elasticities in Swiss residential electricity demand , 2011 .

[54]  D. Perron,et al.  Evolution of Residential Electricity Demand by End-Use in Quebec 1979-1989: A Conditional Demand Analysis , 1994 .

[55]  Jian-Yun Nie,et al.  Originator or propagator?: incorporating social role theory into topic models for twitter content analysis , 2013, CIKM.