Achieving significant cost reduction in solar through the targeted use of AI and Machine Learning

Autor: M. Ghiassi, Andy Skumanich
Rok vydání: 2021
Předmět:
Zdroj: 2021 IEEE 48th Photovoltaic Specialists Conference (PVSC).
DOI: 10.1109/pvsc43889.2021.9518872
Popis: The current DOE targets for solar are to achieve 50 year lifetimes, and 50% cost reductions (50/50) by 2030. These goals are challenging from both a fundamental physics mode as well as from an implementation aspect. To achieve these goals it will be necessary to address not only the hardware and BoS types of costs, but also the execution costs. In this regard, it will be essential to have AI and Machine Learning as key components for development and for optimization. This paper will outline the critical role that AI/ML will play in the various segments of the value chain and indicate the modes where the targeted use will lead to achieving the challenging goals.This paper will describe the following: (1) the key advantages of AI/ML, along with the current issues, (2) the need for AI/ML to achieve the DOE goals of 50-year lifetimes, and 50% cost reductions, and (3) a potential AI/ML approach which can support some of the necessary developments.
Databáze: OpenAIRE