Applying machine learning techniques for forecasting flexibility of virtual power plants

Previous and existing evaluations of available flexibility using small device demand response have typically been done with detailed information of end-user systems. With these large numbers, having lower level information has both privacy and computational limitations. We propose a black box approach to investigating the longevity of aggregated response of a virtual power plant using historic bidding and aggregated behaviour with machine learning techniques. The two supervised machine learning techniques investigated and compared in this paper are, multivariate linear regression and single hidden layer artificial neural network (ANN). Both techniques are used to model a relationship between the aggregator portfolio state and requested ramp power to the longevity of the delivered flexibility. Using validated individual household models, a smart controlled aggregated virtual power plant is simulated. A hierarchical market-based supply-demand matching control mechanism is used to steer the heating devices in the virtual power plant. For both the training and validation set of clusters, a random number of households, between 200 and 2000, is generated with day ahead profile scaled accordingly. Further, a ramp power (power deviation) is assigned at various hours of the day and requested to hold for the remainder of the day. Using only the bidding functions and the requested ramp powers, the ramp longevity is estimated for a number of different cluster setups for both the artificial neural network as well as the multi-variant linear regression. It is found that it is possible to estimate the longevity of flexibility with machine learning. The linear regression algorithm is, on average, able to estimate the longevity with a 15% error. However, there was a significant improvement with the ANN algorithm achieving, on average, a 5.3% error. This is lowered 2.4% when learning for the same virtual power plant. With this information it would be possible to accurately offer residential VPP flexibility for market operations to safely avoid causing further imbalances and financial penalties.

[1]  L.A.L. de Almeida,et al.  Demand side management using artificial neural networks in a smart grid environment , 2015 .

[2]  Pamela MacDougall,et al.  Mitigation of wind power fluctuations by intelligent response of demand and distributed generation , 2011, 2011 2nd IEEE PES International Conference and Exhibition on Innovative Smart Grid Technologies.

[3]  Geert Deconinck,et al.  Quantifying the flexibility of residential electricity demand in 2050: a bottom-up approach , 2015, 2015 IEEE Eindhoven PowerTech.

[4]  G. Venekamp,et al.  Dynamic pricing by scalable energy management systems — Field experiences and simulation results using PowerMatcher , 2012, 2012 IEEE Power and Energy Society General Meeting.

[5]  G. Strbac,et al.  Distribution System State Estimation Using an Artificial Neural Network Approach for Pseudo Measurement Modeling , 2012, IEEE Transactions on Power Systems.

[6]  Pamela MacDougall,et al.  Quantifying flexibility for smart grid services , 2013, 2013 IEEE Power & Energy Society General Meeting.

[7]  Sen Guo,et al.  A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm , 2013, Knowl. Based Syst..

[8]  M. Zerner,et al.  A Broyden—Fletcher—Goldfarb—Shanno optimization procedure for molecular geometries , 1985 .

[9]  Alireza Bahmanyar,et al.  Power system voltage stability monitoring using artificial neural networks with a reduced set of inputs , 2014 .

[10]  Geert Deconinck,et al.  Demand response flexibility and flexibility potential of residential smart appliances: Experiences from large pilot test in Belgium , 2015 .

[11]  Hany M. Hasanien,et al.  Reduction of frequency fluctuation for wind farm connected power systems by an adaptive artificial neural network controlled energy capacitor system , 2012 .

[12]  Anna Magdalena Kosek,et al.  Contextual anomaly detection for cyber-physical security in Smart Grids based on an artificial neural network model , 2016, 2016 Joint Workshop on Cyber- Physical Security and Resilience in Smart Grids (CPSR-SG).