Predictive analytics beyond time series: Predicting series of events extracted from time series data

Realizing carbon neutral energy generation creates the challenge of accurately predicting time-series data for long-term capacity planning and short-term operational decisions. The key challenges adopting data-driven decision-making, specifically predictive analytics, can be attributed to volume velocity. Data poses storage retrieval. velocity processing near real time decisions or building. This manuscript proposes a novel prediction method tackle above two by using an event-based in place traditional series methods. central concept is extract meaningful information, denoted events, from use these events analysis. These extracted retain information required analytics while significantly reducing data; consequently, present at glance, effectively enabling decision-making. applied set consisting six years historical wind power factor temperature measurements. Deploying five deep learning models, comparison drawn between classical predictions based on computational several error metrics. analysis results are presented graphical format comparative discussion results. indicate that proposed obtains same better accuracy volume.