Posters
Come meet the poster presenters to ask them questions and discuss their work
We would like to invite you to come and see the posters at our upcoming conference. The posters will showcase a diverse range of research topics, and will give delegates an opportunity to engage with the authors and learn more about their work. Whether you are a seasoned researcher or simply curious about the latest developments in your field, we believe that the posters will offer something of interest to everyone. So please join us at the conference and take advantage of this opportunity to learn and engage with your peers in the academic community. We look forward to seeing you there!
PO010: Implementation of an AI cloud-based energy management layer for two EV second life batteries integration in a wind power plant
Andoni Saez-de-Ibarra, Senior Researcher, Ikerlan
Abstract
In this industrial project, artificial intelligence (AI) based optimization algorithms have been developed and implemented in a cloud system for storage systems integration within a wind power plant. Going into detail, a Google Cloud Platform (GCP) has been used where several models have been developed and implemented for i) estimating electricity markets prices; ii) estimating storage systems degradation behavior; and iii) optimizing the renewable wind plant market participation. This implementation is based on the data of two commercial EV second life batteries, which are highly monitored and have the capability to upload all their operation data to their own cloud. All these data have also been shared with the IA4BAT cloud, a cloud developed in the GCP environment between Capital Energy and Ikerlan Technology Research Centre. Based on this data, already in the IA4BAT cloud, the storage system degradation model has estimated the upcoming degradation of each of the two storage systems. Moreover, other data have been considered as an input in the cloud platform, which are the Iberian electricity markets prices, wind and solar photovoltaic generation predictions and demand estimations, and storage systems degradation data, from which the electricity markets prices are also estimated. From those degradation and electricity market prices estimations, and from the wind plant generation predictions, the market participation optimization model has been executed, calculating the optimal operation for the wind power plant together with the two storage systems. This output is communicated again from the IT world to the OT of the renewable plant, and its physical HW control has distributed the required commands between the two storage systems. Therefore, considering the storage systems' data acquisition, data analysis, AI model training, AI model application, operation decision, setpoints communication and system operation, the complete information loop is closed.
