The application of the data mining in the integration of RES in the smart grid: Consumption and generation forecast in the I3RES project

Accurate models for predicting generation, demand, prices, and storage under uncertainties are essential for managing safe, sustainable and reliable electric grids. In this investigation, the use of data-mining methods for building models of electrical consumption and renewable generation aimed at integrating renewable generation for smart grid control is studied. The results presented are part of the I3RES project that aims at building future energy solutions for smart electric grids considering the typical uncertainties of the renewable generation. Our results indicate that the data-mining techniques are able to provide forecasts with reasonable accuracy in the presence of uncertainties. Furthermore, such forecasts are useful in building controllers that can perform control actions such as demand side management in smart grids.

[1]  Z. Huang,et al.  Use of time-series analysis to model and forecast wind speed , 1995 .

[2]  David G. Stork,et al.  Pattern Classification , 1973 .

[3]  Damminda Alahakoon,et al.  Minority report in fraud detection: classification of skewed data , 2004, SKDD.

[4]  Athanasios Sfetsos,et al.  A comparison of various forecasting techniques applied to mean hourly wind speed time series , 2000 .

[5]  Georges Kariniotakis,et al.  Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering. , 2005 .

[6]  Jing Shi,et al.  Bayesian adaptive combination of short-term wind speed forecasts from neural network models , 2011 .

[7]  Chi-Yo Huang,et al.  Short Term Wind Speed Predictions by Using the Grey Prediction Model Based Forecast Method , 2011, 2011 IEEE Green Technologies Conference (IEEE-Green).

[8]  Henrik Madsen,et al.  Adaptive modelling and forecasting of offshore wind power fluctuations with Markov‐switching autoregressive models , 2012 .

[9]  Pierluigi Siano,et al.  Exploiting maximum energy from variable speed wind power generation systems by using an adaptive Takagi-Sugeno-Kang fuzzy model , 2009 .

[10]  Li Lingling,et al.  Wind Power Forecasting Based on Time Series and Neural Network , 2009 .

[11]  Y Lu,et al.  A Sequential Learning Scheme for Function Approximation Using Minimal Radial Basis Function Neural Networks , 1997, Neural Computation.

[12]  Alireza Khotanzad,et al.  ANNSTLF-Artificial Neural Network Short-Term Load Forecaster- generation three , 1998 .

[13]  Andrew Kusiak,et al.  Wind farm power prediction: a data‐mining approach , 2009 .

[14]  Birgitte Bak-Jensen,et al.  ARIMA-Based Time Series Model of Stochastic Wind Power Generation , 2010, IEEE Transactions on Power Systems.

[15]  John C. Platt.  A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.

[16]  Wenzhong Gao,et al.  Wind power plant prediction by using neural networks , 2012, 2012 IEEE Energy Conversion Congress and Exposition (ECCE).

[17]  A. Kusiak,et al.  Short-Term Prediction of Wind Farm Power: A Data Mining Approach , 2009, IEEE Transactions on Energy Conversion.

[18]  Mohamed Benbouzid,et al.  Hilbert Transform-Based Bearing Failure Detection in DFIG-Based Wind Turbines , 2011 .

[19]  George Stavrakakis,et al.  Wind power forecasting using advanced neural networks models , 1996 .

[20]  Marcelo Gradella Villalva,et al.  Comprehensive Approach to Modeling and Simulation of Photovoltaic Arrays , 2009, IEEE Transactions on Power Electronics.