Multi-Agent-Based CBR Recommender System for Intelligent Energy Management in Buildings

Abstract

This paper proposes a novel case-based reasoning (CBR) recommender system for intelligent energy management in buildings. The proposed approach recommends the amount of energy reduction that should be applied in a building in each moment, by learning from previous similar cases. The k-nearest neighbor clustering algorithm is applied to identify the most similar past cases, and an approach based on support vector machines is used to optimize the weight of different parameters that characterize each case. An expert system composed by a set of ad hoc rules guarantees that the solution is adequate and applicable to the new case scenario. The proposed CBR methodology is modeled through a dedicated software agent, thus enabling its integration in a multi-agent systems society for the study of energy systems. Results show that the proposed approach is able to provide suitable recommendations on energy reduction, by comparing its results with a previous approach based on particle swarm optimization and with the real reduction in past cases. The applicability of the proposed approach in real scenarios is also assessed through the application of the results provided by the proposed approach on a house energy resources management system. Index Terms-Building energy management, case-based reasoning (CBR), energy efficiency, multi-agent systems (MAS).

Energy Management in Smart Buildings and Homes: Current Approaches, a Hypothetical Solution, and Open Issues and Challenges

“…The results are promising which show the significant energy reductions the proposed approach might achieve in the future. CBR and SCADA are used in conjunction with multi-agent systems (MAS) based societies in [21]. The MAS can model the energy usage on different parts of a building and share it with other agents to 5 create an energy usage model for the entire building.…”

The emergence of explainability of intelligent systems: Delivering explainable and personalized recommendations for energy efficiency

“…This can be regarded as a strategy to distribute/optimize the use of power in households and avoid peak electricity demand. A case‐based reasoning recommendation system is introduced in Reference [11]. The system knowledge (cases) are historic related examples which map a usage behavior to an energy saving plan.…”

Recommendation of Workplaces in a Coworking Building: A Cyber-Physical Approach Supported by a Context-Aware Multi-Agent System

“…Multi-agent systems (MAS) can also be used to benefit recommender systems [ 20 , 21 , 22 ]. MAS are commonly used as contributors or enablers for the recommender systems or contextual data acquisition, and not to make direct recommendations to the user.…”