Presentation Details
| Automated Performance Evaluation Frameworks: Leveraging Large Language Models for Scalable Service Delivery in Multi-Tiered Solar Asset Management André M.Nobre1, Carlos Alberto Severiano Jr.2, Manav Gupta1, Yi Zhen Zhou1. 1PV Doctor, Singapore, Singapore.2Instituto Federal de Minas Gerais, Sabará, Brazil |
Abstract
Managing distributed photovoltaic portfolios spanning thousands of systems across multiple countries presents unprecedented service delivery challenges. This work presents an intelligent framework leveraging Large Language Models to automate performance advisory services. We manage 1,609 systems (1.43 GWp) across 21 countries, with an additional 1.5 GWp being onboarded by mid-2026. The framework integrates LLM-powered interfaces with messaging platforms (WhatsApp, LINE) and employs Retrieval-Augmented Generation with vector search for context-aware triage across three client tiers. Implementation is underway, with field results to be presented at the conference.
No part of this publication may be reproduced, distributed, or transmitted in any form or by any means, including photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the author.
No part of this publication may be reproduced, distributed, or transmitted in any form or by any means, including photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the author.
Content Locked. Log into a registered attendee account to access this presentation.