Artificial Intelligence (AI) based algorithms for predictive maintenance using NOAA data-sets for renewable energy assets

This research aims to develop decision support tools for better maintenance and planning of renewable energy generation and storage assets using atmospheric, local weather, and on-ground environmental data blended with site-, regional- and national-generation data. The study will use a combination of these data to understand the relationship between non-cloud cover based atmospheric conditions and the impact on renewable energy generation and storage which will then be used to develop models for planning and decision support for operations. Research will be conducted across multiple renewable generation and storage sites with diverse environmental conditions to validate and verify the existing model developed during Phase I of this research. The expected results of this research include a better understanding of the relationship between atmospheric conditions and the impact on renewable energy generation and storage, the development of a decision support tool for proactive and reactionary operations and maintenance, and the potential for commercialization of the model and tools. This research will significantly impact the clean energy generation and storage community by providing real-time insights and accurate, useful predictions that, when leveraged properly, will help clean energy operations & maintenance (O&M) managers ensure optimized operational revenues in both generation and storage asset performance.