Abstract
Given the impact of renewable sources in the overall energy production, accurate predictions are becoming essential, with machine learning becoming a very important tool in this context. In many situations, the prediction problem can be divided into several tasks, more or less related between them but each with its own particularities. Multitask learning (MTL) aims to exploit this structure, training several models at the same time to improve on the results achievable either by a common model or by task-specific models. In this paper, we show how an MTL approach based on support vector regression can be applied to the prediction of photovoltaic and wind energy, problems where tasks can be defined according to different criteria. As shown experimentally with three different datasets, the MTL approach clearly outperforms the results of the common and specific models for photovoltaic energy, and are at the very least quite competitive for wind energy.
Highlights
There is a worldwide energy transition towards renewable sources, with a particular emphasis in wind and solar generation, which implies, among other things, a great demand by transmission system operators, wind and solar farm managers or market agents, of accurate energy forecasts to be made at the time horizons of interest for each actor
We first observe that the common task learning SVR (ctlSVR) approach in this problem obtains much better results than those of any independent task learning SVR (itlSVR) model
Machine learning (ML) offers a useful tool in this context, allowing to estimate the future energy production using as input information numerical weather predictions (NWPs)
Summary
There is a worldwide energy transition towards renewable sources, with a particular emphasis in wind and solar generation, which implies, among other things, a great demand by transmission system operators, wind and solar farm managers or market agents, of accurate energy forecasts to be made at the time horizons of interest for each actor. These go from the very short (up to one hour), short (up to a few hours), or medium-long (from one to several days ahead). In short-term prediction one can use past energy production values and/or real-time meteorological information, if available; on the other hand, for medium–long forecasts the features more widely used are those derived from numerical weather predictions (NWPs) provided by entities such as the European Centre for Medium-Range
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
