Work

A Game‐Theoretic Reinforcement Learning Approach for Multiobjective Optimization of Building HVAC Systems Subject to Unmeasurable Disturbances

Year: 2025

Type: article

Source: International Journal of Robust and Nonlinear Control

DOI: 10.1002/rnc.8056

Authors: Junaid Anwar, Syed Ali Asad Rizvi, Zongli Lin

Institutions: Tennessee Technological University, University of Virginia

Language: English

Topic: Building Energy and Comfort Optimization

Subfield: Building and Construction

Field: Engineering

Domain: Physical Sciences

Open Access status: closed

Funder: National Institute of Standards and Technology

Award: PURPOSE: THE OBJECTIVE OF THIS PROJECT IS TO DEVELOP A DISTRIBUTED LEARNING, OPTIMIZATION, AND CONTROL FRAMEWORK SUITABLE FOR HEATING, VENTILATING, AND AIR-CONDITIONING EQUIPMENT USED IN COMMERCIAL BUILDINGS BY ADOPTING MATHEMATICAL DESIGN TOOLS FROM GAME THEORY AND REINFORCEMENT LEARNING CONTROL.ACTIVITIES TO BE PERFORMED: THIS RESEARCH PROJECT WILL APPLY RECENT THEORETICAL DEVELOPMENTS AT THE INTERSECTION OF GAME THEORY AND REINFORCEMENT LEARNING TO DEVELOP ALGORITHMS FOR DISTRIBUTING TASKS OVER SEVERAL INTELLIGENT AGENTS CAPABLE OF COOPERATING WITH EACH OTHER TO MEETING THE LEARNING, OPTIMIZATION, AND CONTROL OBJECTIVES. THIS FRAMEWORK AND REINFORCEMENT LEARNING EMPOWERS THE INDIVIDUAL AGENTS TO LEARN OPTIMAL CONTROL SEQUENCES WITHOUT HAVING THE NEED TO PERFORM EQUIPMENT LEVEL IDENTIFICATION.EXPECTED OUTCOMES: THE RESULTS OF THIS RESEARCH ARE EXPECTED TO RESULT IN A NEW GENERATION OF BUILDING CONTROL PRODUCTS THAT IMPROVE BOTH OCCUPANT COMFORT AND THE OPERATIONAL EFFICIENCY OF BUILDING SYSTEMS. INTENDED BENEFICIARIES: THE OWNERS, OPERATORS, AND USERS OF COMMERCIAL AND INSTITUTIONAL BUILDINGS.SUBRECIPIENT ACTIVITIES: THE RECIPIENT DOES NOT INTEND TO SUBAWARD FUNDS.

OpenAlex ID: W4410792901

FWCI: 0.429

Cites: 29

Cited by: 1

Related to: 10