Developing a Mixed Neural Network Approach to Forecast the Residential Electricity Consumption Based on Sensor Recorded Data

In this paper, we report a study having as a main goal the obtaining of a method that can provide an accurate forecast of the residential electricity consumption, refining it up to the appliance level, using sensor recorded data, for residential smart homes complexes that use renewable energy sources as a part of their consumed electricity, overcoming the limitations of not having available historical meteorological data and the unwillingness of the contractor to acquire such data periodically in the future accurate short-term forecasts from a specialized institute due to the implied costs. In this purpose, we have developed a mixed artificial neural network (ANN) approach using both non-linear autoregressive with exogenous input (NARX) ANNs and function fitting neural networks (FITNETs). We have used a large dataset containing detailed electricity consumption data recorded by sensors, monitoring a series of individual appliances, while in the NARX case we have also used timestamps datasets as exogenous variables. After having developed and validated the forecasting method, we have compiled it in view of incorporating it into a cloud solution, being delivered to the contractor that can provide it as a service for a monthly fee to both the operators and residential consumers.

[1]  Fredrik Wallin,et al.  Evaluation of classification methodologies and Features selection from smart meter data , 2017 .

[2]  M. Lytras,et al.  Smart Cities in Taiwan: A Perspective on Big Data Applications , 2018 .

[3]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[4]  Navid Ghavami,et al.  Occupancy based household energy disaggregation using ultra wideband radar and electrical signature profiles , 2017 .

[5]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[6]  Ion Lungu,et al.  PREDICTION INTELLIGENT SYSTEM IN THE FIELD OF RENEWABLE ENERGIES THROUGH NEURAL NETWORKS , 2016 .

[7]  T. Vafeiadis,et al.  Machine Learning Based Occupancy Detection via the Use of Smart Meters , 2017, 2017 International Symposium on Computer Science and Intelligent Controls (ISCSIC).

[8]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[9]  Fabio Rinaldi,et al.  Data analytics for energy disaggregation: methods and applications , 2017 .

[10]  Arne J. Berre,et al.  Energy Analytics - Opportunities for Energy Monitoring and Prediction with smart Meters , 2017 .

[11]  Fabio Rinaldi,et al.  Machine Learning based Short-term Prediction of Air-conditioning Load through Smart Meter Analytics , 2017 .

[12]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[13]  Francisco Martínez-Álvarez,et al.  A Survey on Data Mining Techniques Applied to Electricity-Related Time Series Forecasting , 2015 .

[14]  Saurabh Chanana,et al.  Smart operations of smart grids integrated with distributed generation: A review , 2018 .

[15]  Aurelio Tommasetti,et al.  A Review of Smart Cities Based on the Internet of Things Concept , 2017 .

[16]  Ion Lungu,et al.  A Two-step Forecasting Solution and Upscaling Technique for Small Size Wind Farms Located in Hilly Areas of Romania , 2016 .

[17]  Daniel L. Marino,et al.  Building energy load forecasting using Deep Neural Networks , 2016, IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society.

[18]  Jose I. Bilbao,et al.  Recent advances in the analysis of residential electricity consumption and applications of smart meter data , 2017 .

[19]  Adela Bâra,et al.  Devising Hourly Forecasting Solutions Regarding Electricity Consumption in the Case of Commercial Center Type Consumers , 2017 .

[20]  Tudor Edu,et al.  Purchasing behaviour patterns : evidence from large surface stores in Romania , 2014 .

[21]  Yu Hao,et al.  Forecasting residential electricity demand in provincial China , 2017, Environmental Science and Pollution Research.

[22]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[23]  Anzar Mahmood,et al.  Prosumer based energy management and sharing in smart grid , 2018 .

[24]  Costel Emil Cotet,et al.  Smart City Platform Development for an Automated Waste Collection System , 2017 .

[25]  Maria del Carmen Pegalajar Jiménez,et al.  An Application of Non-Linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings , 2016 .

[26]  Shihab S Asfour,et al.  Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs , 2017 .

[27]  Mehmet Kurban,et al.  Short-term load forecasting without meteorological data using AI-based structures , 2015 .

[28]  Nikos E. Mastorakis,et al.  Short Term Load Forecasting in Electric Power Systems with Artificial Neural Networks , 2015 .

[29]  O. Kisi,et al.  Comparison of three back-propagation training algorithms for two case studies , 2005 .

[30]  Ana S. Mestre,et al.  Daily electricity consumption profiles from smart meters - Proxies of behavior for space heating and cooling , 2017 .

[31]  O. Tor,et al.  ACCURACY OF ANN BASED DAY-AHEAD LOAD FORECASTING IN TURKISH POWER SYSTEM: DEGRADING AND IMPROVING FACTORS , 2015 .