Modeling industrial loads in non-residential buildings

Industrial loads in non-residential buildings have significantly contributed in total energy use throughout the world. This paper aims to develop a data-driven risk-based framework to predict and optimally control industrial loads in non-residential buildings. In the proposed framework, first, a set of predictive analytics tools are employed to identify the patterns of industrial loads over time. This also includes a high-dimensional clustering model to allocate industrial load profiles into smaller groups with less variability and same patterns. Once the patterns of industrial loads are identified, then a classification model is implemented to estimate the best class that matches with any new load profiles. Ultimately, the proposed framework provides a risk-based model to calculate and evaluate the total risk of energy decisions for the next day. This is coupled with a utility function structure to help decision makers to take best demand-side actions. The efficiency of the proposed model is investigated through a real world use case.

[1]  F. Hartwig,et al.  Exploratory Data Analysis , 2008, Using Science in Cybersecurity.

[2]  Mohsen A. Jafari,et al.  A multi-scale adaptive model of residential energy demand , 2015 .

[3]  Yan Lu,et al.  Modeling and forecasting of cooling and electricity load demand , 2014 .

[4]  A. Agresti,et al.  Categorical Data Analysis , 1991, International Encyclopedia of Statistical Science.

[5]  Waqar Mahmood,et al.  Application of NARX based FFNN, SVR and ANN Fitting models for long term industrial load forecasting and their comparison , 2012, 2012 IEEE International Symposium on Industrial Electronics.

[6]  Ozan Erdinc,et al.  Economic impacts of small-scale own generating and storage units, and electric vehicles under different demand response strategies for smart households , 2014 .

[7]  Jiming Chen,et al.  Smart temperature monitoring for data center energy efficiency , 2013, Proceedings of 2013 IEEE International Conference on Service Operations and Logistics, and Informatics.

[8]  Mohsen A. Jafari,et al.  Integration of Demand Dynamics and Investment Decisions on Distributed Energy Resources , 2016, IEEE Transactions on Smart Grid.

[9]  C. Bouveyron,et al.  HDclassif: an R Package for Model-Based Clustering and Discriminant Analysis of High-Dimensional Data , 2012 .

[10]  William N. Venables,et al.  Modern Applied Statistics with S , 2010 .

[11]  Charles Bouveyron,et al.  Simultaneous model-based clustering and visualization in the Fisher discriminative subspace , 2011, Statistics and Computing.

[12]  John W. Tukey,et al.  Exploratory Data Analysis. , 1979 .

[13]  Roberto Lamberts,et al.  The use of simplified weather data to estimate thermal loads of non-residential buildings , 2004 .

[14]  Barry O'Sullivan,et al.  Analyzing the impact of electricity price forecasting on energy cost-aware scheduling , 2014, Sustain. Comput. Informatics Syst..

[15]  Sila Kiliccote,et al.  Statistical analysis of baseline load models for non-residential buildings , 2009 .

[16]  S. Ashok,et al.  Load-management applications for the industrial sector , 2000 .

[17]  Ali Azadeh,et al.  Annual electricity consumption forecasting by neural network in high energy consuming industrial sectors , 2008 .

[18]  Carina Lansing,et al.  Nationwide buildings energy research enabled through an integrated data intensive , 2014 .

[19]  Katherine E. Seiferlein.  Annual Energy Review 2004 , 2005 .

[20]  Jonathan Cagan,et al.  Quantifying Aesthetic Form Preference in a Utility Function , 2009 .

[21]  Ahmet Palazoglu,et al.  Operational optimization and demand response of hybrid renewable energy systems , 2015 .

[22]  Charles Bouveyron,et al.  Model-based clustering of high-dimensional data: A review , 2014, Comput. Stat. Data Anal..

[23]  Esfandyar Mazhari,et al.  Integrated analysis of high-penetration PV and PHEV with energy storage and demand response , 2013 .

[24]  Yan Lu,et al.  A Hybrid Physics-Based and Data Driven Approach to Optimal Control of Building Cooling/Heating Systems , 2016, IEEE Transactions on Automation Science and Engineering.

[25]  Massimo Paolucci,et al.  Energy-aware scheduling for improving manufacturing process sustainability: A mathematical model for flexible flow shops , 2012 .

[26]  Eric Siegel,et al.  Predictive analytics: The power to predict who will click, buy, lie, or die , 2013, Journal of Marketing Analytics.

[27]  Yoseba K. Penya,et al.  Short-term load forecasting in air-conditioned non-residential Buildings , 2011, 2011 IEEE International Symposium on Industrial Electronics.

[28]  Rodney Anthony Stewart,et al.  RAINWATER TANK END USAGE AND ENERGY DEMAND: A PILOT STUDY , 2011 .

[29]  V. Bianco,et al.  Analysis and forecasting of nonresidential electricity consumption in Romania , 2010 .

[30]  Johanna L. Mathieu,et al.  Variability in automated responses of commercial buildings and industrial facilities to dynamic elec , 2011 .

[31]  Mohammed H. Albadi,et al.  Demand Response in Electricity Markets: An Overview , 2007, 2007 IEEE Power Engineering Society General Meeting.

[32]  H. Houthakker.  Revealed Preference and the Utility Function , 1950 .

[33]  Athulan Vijayaraghavan,et al.  Automated energy monitoring of machine tools , 2010 .

[34]  Cordelia Schmid,et al.  High-dimensional data clustering , 2006, Comput. Stat. Data Anal..

[35]  Ale Smidts,et al.  The Shape of Utility Functions and Organizational Behavior , 2002, Manag. Sci..

[36]  Pascal Bouvry,et al.  Multi-objective evolutionary algorithms for energy-aware scheduling on distributed computing systems , 2014, Appl. Soft Comput..