Advances in Time Series Forecasting Development for Power Systems’ Operation with MLOps

• Published in: Forecasting Vol. 4; no. 2; pp. 501 - 524
• Main Authors: Gürses-Tran, Gonca, Monti, Antonello
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.06.2022
• Subjects: Accuracy; congestion management; Convexity; Decision making; Economic forecasting; Energy; Energy consumption; Forecasting; grid operation; Machine learning; Mathematical models; MLOps; Neural networks; Optimization; probabilistic load forecasting; Solution space; Task scheduling; Time series; uncertainty; Wind power
• ISSN: 2571-9394; 2571-9394
• DOI: 10.3390/forecast4020028

Forecast developers predominantly assess residuals and error statistics when tuning the targeted model’s quality. With that, eventual cost or rewards of the underlying business application are typically not considered in the model development phase. The analysis of the power system wholesale market allows us to translate a time series forecast method’s quality to its respective business value. For instance, near real-time capacity procurement takes place in the wholesale market, which is subject to complex interrelations of system operators’ grid activities and balancing parties’ scheduling behavior. Such forecasting tasks can hardly be solved with model-driven approaches because of the large solution space and non-convexity of the optimization problem. Thus, we generate load forecasts by means of a data-driven based forecasting tool ProLoaF, which we benchmark with state-of-the-art baseline models and the auto-machine learning models auto.arima and Facebook Prophet.