Grant: Alliance Grants
Lakehead University
$56,000.00
Reinforcement-based large language models to enhance energy management platform
EF 2024-25
Résumé
The current research introduces "CoPilot," a pioneering energy management platform leveraging the strengths of Reinforcement Learning (RL) in Large Language Models (LLMs). CoPilot will be designed to dynamically engage customers through interaction-based triggers on its portal, thereby transforming each customer into an active agent contributing to the model's evolution. At the heart of CoPilot will be an advanced RL algorithm, which adapts over time based on customer interactions, enabling the platform to learn from a diverse pool of users and significantly enhancing its predictive capabilities.
The innovative aspect of CoPilot will lie in its use of a long-chain model that integrates existing AI knowledge. It will be programmed to generate comprehensive responses and prompts in real-time as customers make inquiries or submit requests. This feature will be crucial for maintaining an interactive and intuitive user experience.
A key strength of CoPilot will be the extensive data it draws from, contributed by numerous energy managers over a substantial period. This wealth of information will allow the platform to train its model more effectively, aiming to achieve an accuracy of at least 90% in energy management scenarios.
The research objectives of this proposal include developing and training LLMs for energy management, refining RL algorithms to improve decision-making processes in dynamic energy environments, and integrating IoT and Edge Computing to respond to changing energy use patterns. The project also aims to validate and implement AI-driven strategies through pilot tests and real-world applications, demonstrating the practical effectiveness of the developed technologies.
CoPilot's approach is not just about immediate responses but also about shaping a sustainable future. By combining cost efficiency with a significant reduction in emissions, the platform aligns with contemporary environmental goals. It stands as a testament to the potential of AI in transforming how we manage and conserve energy resources, making it an indispensable tool for both individuals and organizations striving for a greener future.
Programme
Alliance Grants
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
597740-2024
Name nom
Ameli, Amir A
Department département
Electrical Engineering
Organization id
25
Institution établissement
Lakehead University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
56000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
306
Area of application group en
Energy resources
Area of application group fr
Ressources d'énergie
Area of application en
Energy efficiency
Area of application fr
Efficacité énergétique
Research subject code
2516
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Energy conversion and distribution
Research subject fr
Conversion et distribution de l'énergie
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Reinforcement-based large language models to enhance energy management platform
Keywords
edge computing; energy management; internet of things; large language models; reinforcement learning
Application summary
The current research introduces "CoPilot," a pioneering energy management platform leveraging the strengths of Reinforcement Learning (RL) in Large Language Models (LLMs). CoPilot will be designed to dynamically engage customers through interaction-based triggers on its portal, thereby transforming each customer into an active agent contributing to the model's evolution. At the heart of CoPilot will be an advanced RL algorithm, which adapts over time based on customer interactions, enabling the platform to learn from a diverse pool of users and significantly enhancing its predictive capabilities.
The innovative aspect of CoPilot will lie in its use of a long-chain model that integrates existing AI knowledge. It will be programmed to generate comprehensive responses and prompts in real-time as customers make inquiries or submit requests. This feature will be crucial for maintaining an interactive and intuitive user experience.
A key strength of CoPilot will be the extensive data it draws from, contributed by numerous energy managers over a substantial period. This wealth of information will allow the platform to train its model more effectively, aiming to achieve an accuracy of at least 90% in energy management scenarios.
The research objectives of this proposal include developing and training LLMs for energy management, refining RL algorithms to improve decision-making processes in dynamic energy environments, and integrating IoT and Edge Computing to respond to changing energy use patterns. The project also aims to validate and implement AI-driven strategies through pilot tests and real-world applications, demonstrating the practical effectiveness of the developed technologies.
CoPilot's approach is not just about immediate responses but also about shaping a sustainable future. By combining cost efficiency with a significant reduction in emissions, the platform aligns with contemporary environmental goals. It stands as a testament to the potential of AI in transforming how we manage and conserve energy resources, making it an indispensable tool for both individuals and organizations striving for a greener future.