This book takes an approach that leverages methods using time series analysis, machine learning, and stochastic models to effectively forecast solar power. The goal of this book is not only to produce an accurate forecast but also to make it conducive to being used for decision-making. Solar Power Forecasting: Using Time Series and Machine Learning combines traditional forecasting with recent advances in machine learning and data science. It uses a decision-making-oriented approach and provides probabilistic forecasts and methods as well as explains the analytical underpinnings of accuracy metrics in detail. As it illustrates through examples of how forecasting can be used in planning and operations, the book also delivers a systems-level approach. This comprehensive resource covers various aspects of solar forecasting, including data science methods, computational techniques, and mathematical foundations. It serves as a valuable tool for practitioners, students, and experienced researchers, both in the solar power industry and in the broader field of forecasting. Color figures can be found on Routledge.com/9781032515328 and in the eBook version.
This book takes an approach that leverages methods using time series analysis, machine learning, and stochastic models to effectively forecast solar power. The goal of this book is not only to produce an accurate forecast but also to make it conducive to being used for decision-making.
