scholarly journals Reinforcement Learning-Based School Energy Management System

Energies ◽  
2020 ◽  
Vol 13 (23) ◽  
pp. 6354
Author(s):  
Yassine Chemingui ◽  
Adel Gastli ◽  
Omar Ellabban

Energy efficiency is a key to reduced carbon footprint, savings on energy bills, and sustainability for future generations. For instance, in hot climate countries such as Qatar, buildings are high energy consumers due to air conditioning that resulted from high temperatures and humidity. Optimizing the building energy management system will reduce unnecessary energy consumptions, improve indoor environmental conditions, maximize building occupant’s comfort, and limit building greenhouse gas emissions. However, lowering energy consumption cannot be done despite the occupants’ comfort. Solutions must take into account these tradeoffs. Conventional Building Energy Management methods suffer from a high dimensional and complex control environment. In recent years, the Deep Reinforcement Learning algorithm, applying neural networks for function approximation, shows promising results in handling such complex problems. In this work, a Deep Reinforcement Learning agent is proposed for controlling and optimizing a school building’s energy consumption. It is designed to search for optimal policies to minimize energy consumption, maintain thermal comfort, and reduce indoor contaminant levels in a challenging 21-zone environment. First, the agent is trained with the baseline in a supervised learning framework. After cloning the baseline strategy, the agent learns with proximal policy optimization in an actor-critic framework. The performance is evaluated on a school model simulated environment considering thermal comfort, CO2 levels, and energy consumption. The proposed methodology can achieve a 21% reduction in energy consumption, a 44% better thermal comfort, and healthier CO2 concentrations over a one-year simulation, with reduced training time thanks to the integration of the behavior cloning learning technique.

2013 ◽  
Vol 368-370 ◽  
pp. 1222-1227 ◽  
Author(s):  
Yuan Su ◽  
Jun Wei Yan

Nowadays, universities are taking responsibility for their environmental impact and are working to ensure environmental sustainability. In this research, we aim to analyze energy system of a model university campus in southern China and grasp the energy consumption of the whole campus from the viewpoint of reducing GHG emission. We investigated and analyzed the present situation of energy system by using measured data and inquiry survey. In order to grasp the data exactly, we introduced building energy management system (BEMS) to some typical buildings with electricity consumption controlling. Then examination of energy consumption intensity according the different typical buildings has been analyzed on the basis of the research at campus. The campus's energy consumption prediction was carried out during the 24-h field measurements period. Furthermore, energy consumption intensity of the whole campus were predicted.


Energies ◽  
2022 ◽  
Vol 15 (2) ◽  
pp. 574
Author(s):  
Muhammad Hilal Khan ◽  
Azzam Ul Asar ◽  
Nasim Ullah ◽  
Fahad R. Albogamy ◽  
Muhammad Kashif Rafique

Energy consumption in buildings is expected to increase by 40% over the next 20 years. Electricity remains the largest source of energy used by buildings, and the demand for it is growing. Building energy improvement strategies is needed to mitigate the impact of growing energy demand. Introducing a smart energy management system in buildings is an ambitious yet increasingly achievable goal that is gaining momentum across geographic regions and corporate markets in the world due to its potential in saving energy costs consumed by the buildings. This paper presents a Smart Building Energy Management system (SBEMS), which is connected to a bidirectional power network. The smart building has both thermal and electrical power loops. Renewable energy from wind and photo-voltaic, battery storage system, auxiliary boiler, a fuel cell-based combined heat and power system, heat sharing from neighboring buildings, and heat storage tank are among the main components of the smart building. A constraint optimization model has been developed for the proposed SBEMS and the state-of-the-art real coded genetic algorithm is used to solve the optimization problem. The main characteristics of the proposed SBEMS are emphasized through eight simulation cases, taking into account the various configurations of the smart building components. In addition, EV charging is also scheduled and the outcomes are compared to the unscheduled mode of charging which shows that scheduling of Electric Vehicle charging further enhances the cost-effectiveness of smart building operation.


Sign in / Sign up

Export Citation Format

Share Document