New MATRYCS Publication in Nature Scientific Reports "Transfer learning strategies for solar power forecasting under data scarcity"
We are truly proud about the new MATRYCS publication entitled “Transfer learning strategies for solar power forecasting under data scarcity”! MATRYCS congratulates the authors from NTUA and HOLISTIC, Elissaios Sarmas, Nikos Dimitropoulos, Vangelis Marinakis, Zoi Mylona and Haris Doukas for their work which is published in Nature Scientific Reports, the 5th most-cited journal in the world, with more than 696,000 citations in 2021.
Accurately forecasting solar plants production is critical for balancing supply and demand and for scheduling distribution networks operation in the context of inclusive smart cities and energy communities. However, the problem becomes more demanding, when there is insufficient amount of data to adequately train forecasting models, due to plants being recently installed or because of lack of smart-meters.
Transfer learning (TL) offers the capability of transferring knowledge from the source domain to different target domains to resolve related problems. This paper uses the stacked Long Short-Term Memory (LSTM) model with three TL strategies to provide accurate solar plant production forecasts. TL is exploited both for weight initialization of the LSTM model and for feature extraction, using different freezing approaches. The presented TL strategies are compared to the conventional non-TL model, as well as to the smart persistence model, at forecasting the hourly production of 6 solar plants.
You can download the publication and read more by clicking here.