Electrical Energy Consumption Forecast Using External Facility Data

Recent changes in the power systems gives place to the active consumers participation. The participation in demand response programs requires consumers to undertake strategic management of their consumption. Small and medium players should have the capability of performing day-ahead and hour-ahead load management which requires forecasting techniques applied to the consumption and generation. A good forecasting accuracy is very important for the quality of the management results but also very difficult to achieve. This paper proposes an artificial neural network based methodology to forecast the consumption in an office building. The considered building is equipped with a Supervisory Control and Data Acquisition (SCADA) system that stores data every 10 seconds. The stored data are used together with additional data, such as, the temperature and the solar radiation.

[1]  Paul A. Fishwick,et al.  Feedforward Neural Nets as Models for Time Series Forecasting , 1993, INFORMS J. Comput..

[2]  H. Morais,et al.  Using data mining techniques to support DR programs definition in smart grids , 2011, 2011 IEEE Power and Energy Society General Meeting.

[3]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[4]  A. K. Rigler,et al.  Accelerating the convergence of the back-propagation method , 1988, Biological Cybernetics.

[5]  Zita Vale,et al.  Demand response programs definition supported by clustering and classification techniques , 2011, 2011 16th International Conference on Intelligent System Applications to Power Systems.

[6]  Ganesh Kumar Venayagamoorthy,et al.  One Step Ahead: Short-Term Wind Power Forecasting and Intelligent Predictive Control Based on Data Analytics , 2012, IEEE Power and Energy Magazine.

[7]  Geoffrey E. Hinton,et al.  Learning representations of back-propagation errors , 1986 .

[8]  M. Paun,et al.  Smart grids and networks of the future - Eurelectric views , 2009 .

[9]  L. Pazvakawambwa,et al.  Forecasting methods and applications. , 2013 .

[10]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[11]  Steven C. Wheelwright,et al.  Forecasting: Methods and Applications, 3rd Ed , 1997 .

[12]  Hieu Minh Trinh,et al.  Exponential Stabilization of Neural Networks With Various Activation Functions and Mixed Time-Varying Delays , 2010, IEEE Transactions on Neural Networks.

[13]  F. S. Wong,et al.  Time series forecasting using backpropagation neural networks , 1991, Neurocomputing.

[14]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[15]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[16]  Zita Vale,et al.  Contextual and environmental awareness laboratory for energy consumption management , 2015, 2015 Clemson University Power Systems Conference (PSC).

[17]  Worawat Nakawiro,et al.  A novel optimization algorithm for optimal reactive power dispatch: A comparative study , 2011, 2011 4th International Conference on Electric Utility Deregulation and Restructuring and Power Technologies (DRPT).

[18]  Jeff Heaton,et al.  Introduction to Neural Networks for C#, 2nd Edition , 2008 .

[19]  István Erlich,et al.  Hybrid Approach for Power System Operational Planning With Smart Grid and Small-Signal Stability Enhancement Considerations , 2013, IEEE Transactions on Smart Grid.

[20]  Heaton T. Jeff,et al.  Introduction to Neural Networks with Java , 2005 .

[21]  Jens Fortmann,et al.  New Generic Model of DFG-Based Wind Turbines for RMS-Type Simulation , 2014, IEEE Transactions on Energy Conversion.

[22]  Pedro Faria,et al.  Distributed, Agent-Based Intelligent System for Demand Response Program Simulation in Smart Grids , 2014, IEEE Intelligent Systems.

[23]  Kevin N. Gurney,et al.  An introduction to neural networks , 2018 .