A global monitoring system for electricity consumption and production of household roof-top PV systems in Madeira

This paper describes recent work on the development of a wireless-based remote monitoring system for household energy consumption and generation in Madeira Island, Portugal. It contains three different main sections: (1) a monitoring system for consumed and produced energy of residencies equipped with photovoltaic (PV) systems, (2) developing a tool to predict the electricity production, (3) and proposing a solution to detect the PV system malfunctions. With the later tool, the user (owner) or the energy management system can monitor its own PV system and make an efficient schedule use of electricity at the consumption side. In addition, currently, the owners of PV systems are notified about a failure in the system only when they receive the bill, whereas using the proposed method conveniently would notify owners prior to bill issue. The artificial neural network was employed as a tool together with the hardware-based monitoring system which allows a daily analysis of the performance of the system. The comparison of the predicted value of the produced electricity with the actual production for each day shows the validity of the method.

[1]  F. Hocaoglu,et al.  Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks , 2008 .

[2]  K. Sopian,et al.  Predicting average energy conversion of photovoltaic system in Malaysia using a simplified method , 2004 .

[3]  Bangyin Liu,et al.  Online 24-h solar power forecasting based on weather type classification using artificial neural network , 2011 .

[4]  Wolfgang Lehner,et al.  First Steps Towards a Systematical Optimized Strategy for Solar Energy Supply Forecasting , 2013 .

[5]  E. Izgi,et al.  Short–mid-term solar power prediction by using artificial neural networks , 2012 .

[6]  Mini S. Thomas,et al.  Smart home energy management by Demand Response controller design , 2014, 2014 IEEE 6th India International Conference on Power Electronics (IICPE).

[7]  Hao Yu,et al.  Levenberg—Marquardt Training , 2011 .

[8]  T. Funabashi,et al.  Application of Recurrent Neural Network to Short-Term-Ahead Generating Power Forecasting for Photovoltaic System , 2007, 2007 IEEE Power Engineering Society General Meeting.

[9]  Sandy Rodrigues,et al.  Development of an ANN model to predict the electricity produced by small scale roof-top PV systems in Madeira Island , 2017, 2017 International Conference in Energy and Sustainability in Small Developing Economies (ES2DE).

[10]  Henrik Madsen,et al.  Online short-term solar power forecasting , 2009 .

[11]  Henry D. Jacoby,et al.  The future of the (US) electric grid , 2013 .

[12]  Fabio Nardecchia,et al.  Home smart grid device for energy saves and failure monitoring , 2015, 2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC).

[13]  Marco Zennaro,et al.  SOLAR MONITORING SYSTEM IN MALAWI , 2011 .

[14]  Francesco Grimaccia,et al.  Hybrid Predictive Models for Accurate Forecasting in PV Systems , 2013 .

[15]  F. Faria,et al.  Economic feasibility analysis of small scale PV systems in different countries , 2016 .

[16]  A. Dolara,et al.  Comparison of different physical models for PV power output prediction , 2015 .

[17]  Tom E. Baldock,et al.  Feasibility analysis of renewable energy supply options for a grid-connected large hotel , 2009 .

[18]  Montserrat Mendoza-Villena,et al.  Short-term power forecasting system for photovoltaic plants , 2012 .

[19]  Adel Mellit,et al.  Performance prediction of 20 kWp grid-connected photovoltaic plant at Trieste (Italy) using artificial neural network , 2010 .