Time Series-Based GHG Emissions Prediction for Smart Homes

Smart homes play a crucial role in reducing the residential sector electricity consumption and Greenhouse Gases (GHG) emissions. In this work, we present a time series approach to predict GHG emissions to be integrated into smart home management systems. More specifically, we used Long Short-Term Memory (LSTM), a variant of Recurrent Neural Networks. The prediction results get mean absolute percentage error (MAPE) close to 2 percent when the region under study has an energy matrix mostly based on fossil fuels, less intermittent. For regions in which more renewable sources are present, the MAPE is around 12 percent. However, in either case, LSTM can predict the hours well with smaller emissions among the next 24 hours. Such day-ahead information brings awareness to the users and allows the scheduling of appliances to work in the hours in which the emissions are minimal, reducing them without significantly affecting the consumers’ behavior.

[1]  Anna Fensel,et al.  SESAME-S: Semantic Smart Home System for Energy Efficiency , 2013, Informatik-Spektrum.

[2]  Alexander Rassau,et al.  Impact of dynamic energy pricing schemes on a novel multi-user home energy management system , 2015 .

[3]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[4]  Ioannis P. Panapakidis,et al.  Day-ahead electricity price forecasting via the application of artificial neural network based models , 2016 .

[5]  J. Contreras,et al.  ARIMA Models to Predict Next-Day Electricity Prices , 2002, IEEE Power Engineering Review.

[6]  Frank Hutter,et al.  SGDR: Stochastic Gradient Descent with Restarts , 2016, ArXiv.

[7]  Aditya Mishra,et al.  Energy Optimizations for Smart Buildings and Smart Grids , 2015 .

[8]  Hermann Ney,et al.  LSTM Neural Networks for Language Modeling , 2012, INTERSPEECH.

[9]  Jeannie R. Albrecht,et al.  Smart * : An Open Data Set and Tools for Enabling Research in Sustainable Homes , 2012 .

[10]  Mehdi Rahmani-Andebili,et al.  Energy Scheduling for a Smart Home Applying Stochastic Model Predictive Control , 2016, 2016 25th International Conference on Computer Communication and Networks (ICCCN).

[11]  Mohammed Hassan Ahmed,et al.  Smart Home Activities: A Literature Review , 2014 .

[12]  Réjean Samson,et al.  Modelling of Electricity Mix in Temporal Differentiated Life-Cycle-Assessment to Minimize Carbon Footprint of a Cloud Computing Service , 2014, ICT4S.

[13]  Réjean Samson,et al.  Consideration of marginal electricity in real-time minimization of distributed data centre emissions , 2017 .

[14]  Pia Stoll,et al.  Scheduling residential electric loads for green house gas reductions , 2011, 2011 2nd IEEE PES International Conference and Exhibition on Innovative Smart Grid Technologies.

[15]  Cheng Hao Jin,et al.  Short‐term electricity load and price forecasting based on clustering and next symbol prediction , 2015 .

[16]  C. Sims,et al.  Vector Autoregressions , 1999 .

[17]  Jukka Lassila,et al.  Electric vehicle smart charging aims for CO2 emission reduction? , 2016, 2016 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe).

[18]  Frank Hutter,et al.  SGDR: Stochastic Gradient Descent with Warm Restarts , 2016, ICLR.

[19]  Pierre-Olivier Pineau,et al.  Influence of wind power on hourly electricity prices and GHG (greenhouse gas) emissions: Evidence that congestion matters from Ontario zonal data , 2014 .

[20]  Eric Jones,et al.  SciPy: Open Source Scientific Tools for Python , 2001 .

[21]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Ari Nissinen,et al.  Hourly-based greenhouse gas emissions of electricity – cases demonstrating possibilities for households and companies to decrease their emissions , 2017 .

[23]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[24]  Réjean Samson,et al.  Real-time environmental assessment of electricity use: a tool for sustainable demand-side management programs , 2018, The International Journal of Life Cycle Assessment.

[25]  S Adams,et al.  President's Page. , 1968, Bulletin of the Medical Library Association.

[26]  Jim Kurose,et al.  GreenCharge: Managing RenewableEnergy in Smart Buildings , 2013, IEEE Journal on Selected Areas in Communications.

[27]  Yonghong Kuang,et al.  Smart home energy management systems: Concept, configurations, and scheduling strategies , 2016 .

[28]  Yang Wang,et al.  Estimating hourly marginal emission in real time for PJM market area using a machine learning approach , 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[29]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[30]  Deepa Singhal,et al.  Electricity price forecasting using artificial neural networks , 2011 .

[31]  Ksenia Petrichenko,et al.  Towards zero-emission efficient and resilient buildings.: Global Status Report , 2016 .

[32]  A. Chiu,et al.  A bibliometric review: Energy consumption and greenhouse gas emissions in the residential sector , 2017 .

[33]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[34]  Sung-Kwan Joo,et al.  Electric vehicle charging method for smart homes/buildings with a photovoltaic system , 2013, IEEE Transactions on Consumer Electronics.

[35]  Gulnar Mehdi,et al.  Electricity Consumption Constraints for Smart-home Automation: An Overview of Models and Applications☆ , 2015 .

[36]  Rob J Hyndman,et al.  Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing , 2011 .

[37]  Janssens-Maenhout Greet,et al.  Covenant of Mayors for Climate and Energy: Default emission factors for local emission inventories – Version 2017 , 2017 .

[38]  Santiago Grijalva,et al.  Modeling for Residential Electricity Optimization in Dynamic Pricing Environments , 2012, IEEE Transactions on Smart Grid.

[39]  Mohammad Kazem Sheikh-El-Eslami,et al.  An annual framework for clustering-based pricing for an electricity retailer , 2010 .

[40]  Grzegorz Dudek Multivariate Regression Tree for Pattern-Based Forecasting Time Series with Multiple Seasonal Cycles , 2017, ISAT.

[41]  D. Dijk,et al.  Forecasting Day-Ahead Electricity Prices: Utilizing Hourly Prices , 2013 .

[42]  Christian R. Prause,et al.  The Energy Aware Smart Home , 2010, 2010 5th International Conference on Future Information Technology.

[43]  Yu Peng,et al.  A review on electric vehicles interacting with renewable energy in smart grid , 2015 .

[44]  Mohamed Cheriet,et al.  Statistical-based method to determine the best hour of the day regarding GHG emissions for a smart home appliance , 2017, 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI).

[45]  Gregory A Keoleian,et al.  Comparative Assessment of Models and Methods To Calculate Grid Electricity Emissions. , 2016, Environmental science & technology.