PROJECT TITLE :

Genetic Optimal Regression of Relevance Vector Machines for Electricity Pricing Signal Forecasting in Smart Grids

ABSTRACT:

Price-directed demand in good grids operating within deregulated electricity markets requires real-time forecasting of the value of electricity for the aim of scheduling demand at the nodal level (e.g., appliances, machines, and devices) during a means that minimizes energy cost to the consumer. During this paper, a completely unique hybrid methodology for electricity value forecasting is introduced and applied on a group of real-world historical information taken from the New England area. The proposed approach is implemented in 2 steps. In the first step, a set of relevance vector machines (RVMs) is adopted, where every RVM is used for individual ahead-of-time worth prediction. In the second step, individual predictions are aggregated to formulate a linear regression ensemble, whose coefficients are obtained as the solution of one objective optimization problem. Therefore, an optimal solution to the problem is found by employing the micro-genetic algorithm and the optimized ensemble is used for computing the ultimate value forecast. The performance of the proposed methodology is compared with performance of autoregressive-moving-average and naïve forecasting ways, further as to that taken from each individual RVM. Results clearly demonstrate the superiority of the hybrid methodology over the other tested methods with regard to mean absolute error for electricity signal pricing forecasting.