Conversational Agents for Building Energy Efficiency -- Advising Housing Cooperatives in Stockholm on Reducing Energy Consumption
Shadaab Ghani, Anne Håkansson, Oleksii Pasichnyi, Hossein Shahrokni
TL;DR
The paper addresses the challenge of energy efficiency in Swedish housing cooperatives (BRFs) facing aging buildings and limited owner knowledge, in the context of stringent EU EPBD targets. It introduces SPARA, a Retrieval-Augmented Generation-based conversational agent powered by GPT-4o, which leverages a knowledge base of energy-advisor emails and building data within Azure storage and a vector store to deliver context-grounded retrofit guidance. Key findings show high semantic and lexical alignment of SPARA's responses with expert references and 85% accuracy on building-level queries during pilot testing, suggesting SPARA can enhance stakeholder support and streamline retrofit planning while reducing reliance on external consultants. The work also notes limitations around reliability for highly specialized or dynamic data and emphasizes the need for ongoing evaluation of trustworthiness and stability before broader deployment.
Abstract
Housing cooperative is a common type of multifamily building ownership in Sweden. Although this ownership structure grants decision-making autonomy, it places a burden of responsibility on cooperative's board members. Most board members lack the resources or expertise to manage properties and their energy consumption. This ignorance presents a unique challenge, especially given the EU directives that prohibit buildings rated as energy classes F and G by 2033. Conversational agents (CAs) enable human-like interactions with computer systems, facilitating human-computer interaction across various domains. In our case, CAs can be implemented to support cooperative members in making informed energy retrofitting and usage decisions. This paper introduces a Conversational agent system, called SPARA, designed to advise cooperatives on energy efficiency. SPARA functions as an energy efficiency advisor by leveraging the Retrieval-Augmented Generation (RAG) framework with a Language Model(LM). The LM generates targeted recommendations based on a knowledge base composed of email communications between professional energy advisors and cooperatives' representatives in Stockholm. The preliminary results indicate that SPARA can provide energy efficiency advice with precision 80\%, comparable to that of municipal energy efficiency (EE) experts. A pilot implementation is currently underway, where municipal EE experts are evaluating SPARA performance based on questions posed to EE experts by BRF members. Our findings suggest that LMs can significantly improve outreach by supporting stakeholders in their energy transition. For future work, more research is needed to evaluate this technology, particularly limitations to the stability and trustworthiness of its energy efficiency advice.