Systematic Review on Deep Reinforcement Learning-Based Energy Management for Different Building Types

Abstract

Owing to the high energy demand of buildings, which accounted for 36% of the global share in 2020, they are one of the core targets for energy-efficiency research and regulations. Hence, coupled with the increasing complexity of decentralized power grids and high renewable energy penetration, the inception of smart buildings is becoming increasingly urgent. Data-driven building energy management systems (BEMS) based on deep reinforcement learning (DRL) have attracted significant research interest, particularly in recent years, primarily owing to their ability to overcome many of the challenges faced by conventional control methods related to real-time building modelling, multi-objective optimization, and the generalization of BEMS for efficient wide deployment. A PRISMA-based systematic assessment of a large database of 470 papers was conducted to review recent advancements in DRL-based BEMS for different building types, their research directions, and knowledge gaps. Five building types were identified: residential, offices, educational, data centres, and other commercial buildings. Their comparative analysis was conducted based on the types of appliances and systems controlled by the BEMS, renewable energy integration, DR, and unique system objectives other than energy, such as cost, and comfort. Moreover, it is worth considering that only approximately 11% of the recent research considers real system implementations.

A Review of Generative Models for 3D Vehicle Wheel Generation and Synthesis

“…As for the findings of [31], a generative design method rooted in deep learning was developed for 2D wheel design. The primary objective of this research is to broaden the applicability of the generative design method to address the 3D wheel design challenges in industrial settings, showcasing its viability within the automotive industry [86]. This study presents an efficient deep learning-based CAD/CAE system that includes advanced technologies, generative design, and CAD/CAE automation.…”

Design of proactive management system for residential buildings by using smart equipment

“…Energy consumption by buildings is up to 40 % of global demand, and total greenhouse gas emissions are about 35 % of the total volume. Moreover, the residential and communal sector is characterized by a high percentage of energy losses because of low quality of management [1]. In this context, strategies and tools for improved consumption structure management, planning and implementation of energy saving measures in buildings have significant potential.…”

PV-Optimized Heat Pump Control in Multi-Family Buildings Using a Reinforcement Learning Approach

“…RL is potentially model-free, i.e., unlike the mixed-integer (non)linear programming (MI(N)LP) approaches, which are most commonly used for MPC; there is no need for models of the building energy system. Forecasts for weather and heat/electricity demand are also not required but can be implemented and will improve the results [9][10][11][12].…”

“…As the statistics in several publications [9,12,[14][15][16] show, the number of publications on (deep) reinforcement learning for building energy-system control has been increasing significantly since approximately 2013.…”

“…Shaqour and Hagishima [12] analyzed a database of 470 publications on DRL-based building energy-management systems (BEMS) for different building types and reviewed recent advances, research directions, and knowledge gaps. Their selection resulted in 31 publications focused on residential buildings, of which only three used thermal energy storage and investigated RL approaches on a single-family home or district level.…”