The Adaptive and Intelligent Edge Computing Based Building Energy Management System (AI-BEMS) project team meeting took place last week to finalize the design of its system. The meeting was held in Qatar to conclude the final phase of the specifications. Juan Manuel Corchado attended as a representative of the BISITE Research Group of the University of Salamanca and participated along with other researchers from Iberdrola Innovation Middle East and Hamad Bin Khalifa University.
AI-BEMS will provide the ability to dynamically optimize consumption patterns and recommend energy efficiency (EE) measures using a comprehensive edge computing architecture for BEMS. It will also capture data from IoT devices located in homes and businesses and any other heterogeneous source of information. This will include assessing the feasibility of virtual organizations that leverage social computing technology to recommend energy efficiency solutions that take into account users’ tastes, convenience and the opinions of other customers.
The new system is based on an edge computing model, rather than a conventional architecture. It uses virtual organizations with distributed Explainable Artificial Intelligence (XAI) algorithms to improve performance.
The project also plans to explore innovative neuro symbolic XAI algorithms to significantly reduce energy consumption and facilitate model interpretation, as well as build a secure framework to ensure user data privacy.
About AI-BEIMS
In this project, a plug-and-play adaptive intelligent building energy management system (AI-BEMS) will be researched, designed and validated by conducting two pilot tests in a real environment. It will be based on a secure and scalable 3-tier edge computing architecture supported by virtual organizations that will orchestrate distributed XAI algorithms for DR and EE optimization, integrating local generation and storage systems, enabling demand-side management with dynamic and demand-dependent tariffs.
AI-BEMS overcomes some of the drawbacks of existing cloud computing-based IoT systems related to network bandwidth, security weaknesses and service scalability. It implements cost-effective, high-performance prediction of demand flexibility and autonomic power consumption optimization techniques. In addition, this device will have greater business insight, offering added value to DNOs and improved performance for end users.
This article was made possible by the thirteenth (13th) cycle NPRP-Standard (NPRP-S) grant no. 13S-0128-200187 from the Qatar National Research Fund (a member of Qatar Foundation). It is expected to have a significant impact on future building energy management systems.
