Petra Vrablecová

TL;DR: This work demonstrates the suitability of online support vector regression (SVR) method to short term power load forecasting and thoroughly explore its pros and cons, and presents a comparison of ten state-of-the-art forecasting methods in terms of accuracy on public Irish CER dataset.

TL;DR: For energy consumption forecasting, an improvement of incremental adaptive power load forecasting methods is presented by performing cluster analysis prior to forecasts by carrying out the cluster analysis before applying predictive techniques.

TL;DR: Despite the fact that utilization of the method does not necessarily improve the speed of the domain model creation nor does it reduce the overall difficulty of the task, a significant improvement in the quality of resulting domain models has been observed.

TL;DR: This chapter presents one way of incorporating computational intelligence into smart grid environment by involving advanced methods of data analysis and optimization and proposes solutions, which deal with stream and online processing as well as adaptivity of the proposed solutions.

TL;DR: Different weighting schemes of predictive base models including biologically inspired genetic algorithm (GA) and particle swarm optimization (PSO) in the domain of electricity consumption are investigated to improve the performance of ensemble learning in the presence of different types of concept drift that naturally occur in electricity load measurements.