AI-Based Algorithm for Energy-Efficient Comfort Optimisation
Environmental comfort takes a central role in the well-being and health of people. In modern industrial, commercial, and residential buildings, passive energy sources (such as solar irradiance and heat exchangers) and Heating, Ventilation and Air Conditioning (HVAC) systems are usually employed to achieve the required comfort. While passive strategies can effectively enhance the livability of indoor spaces with limited or no energy cost, active strategies based on HVAC machines are often preferred to have direct control over the environment. Commonly, the working parameters of such machines are manually tuned to a fixed set point during working hours or throughout the whole day, leading to inefficiencies in terms of comfort and energy consumption. Albeit effective, previous works that tackle the comfort-energy tradeoff are tailored to the specific environment under study (in terms of geometry, characteristics of the building, etc.) and thus, cannot be applied on a large, industrial scale. We address the problem from a different angle and propose an adaptive and practical solution for comfort optimisation. It does not require the intervention of expert personnel or any customisations around the environment while it implicitly analyses the influence of different agents (e.g., passive phenomena) on the monitored parameters. A Convolutional Neural Network (CNN) predicts long-term impact on thermal comfort and energy consumption of a range of possible actuation strategies for the HVAC system. The decision on the best HVAC settings is taken by choosing the combination of ON/OFF and Set Point (SP) which optimises thermal comfort and, at the same time, minimises energy consumption. We validate our solution in a real-world scenario and through software simulations, providing a performance comparison against the fixed set point strategy and a greedy approach. Evaluation results show that our solution achieves the target thermal comfort while reducing the energy footprint by up to around 15%.
Datasets and ML models to predict future energy and environmental parameters of retail stores have been published in the AI on Demand portal, while the optimization algorithms are the property of Energenius Srl. For any additional information, please contact the company using the references indicated.
Categories
Governments, regulatory agencies, and public bodies have been promoting policies and measures for healthy and energy-efficient buildings, issuing directives such as the Directive (2018/844) (Parliament, The European. 2018. “Directive (Eu) 2018/844 of the European Parliament and of the Council of 30 May 2018 Amending Directive 2010/31/Eu on the Energy Performance of Buildings and Directive 2012/27/Eu on Energy Efficiency (Text with Eea Relevance).”) developed by the European Parliament. Despite these efforts, a significant amount of energy is too often wasted in industrial, commercial, and residential buildings, yet providing less than ideally comfortable conditions to occupants. Typical examples of such inefficiencies are retail stores, in which energy managers struggle to find a good balance in the trade-off between optimisation of comfort and minimisation of energy consumption by HVAC systems. Indeed, managers need customers to feel comfortable while shopping in any time of the year and under any environmental conditions. Moreover, they seek to gain important IAQ certifications (BREEAM, LEED, …) as means of distinguishing themselves from their competitors.
Currently, HVAC systems are often managed directly on-site in buildings, manually operating on thermostats to regulate thermal comfort with little or no attention to energy efficiency. For instance, in commercial buildings, HVAC systems are often left active at the end of the day, thus continuing to work and consuming unnecessary energy during the night when shops are closed. Another common issue in most buildings is that whatever HVAC configuration in terms of ON/OFF and set point (i.e., desired target temperature) is configured in the early morning, it is usually left unchanged throughout the day. However, according to outdoor weather and its impact on the indoor environments, it might be convenient applying different HVAC settings during the day (e.g., switching the devices off).
Multiple works from literature deal with the topic of comfort maximisation jointly with energy consumption minimisation in buildings. Despite the progress in this field, resulting in innovative solutions e.g., based on advanced passive strategies (Liu, Sheng, Yu Ting Kwok, Kevin Ka-Lun Lau, Wanlu Ouyang, and Edward Ng. 2020. “Effectiveness of Passive Design Strategies in Responding to Future Climate Change for Residential Buildings in Hot and Humid Hong Kong.” Energy and Buildings 228: 110469.), (de Araujo Passos, Luigi Antonio, Peter van den Engel, Simone Baldi, and Bart De Schutter. 2023. “Dynamic Optimization for Minimal Hvac Demand with Latent Heat Storage, Heat Recovery, Natural Ventilation, and Solar Shadings.” Energy Conversion and Management 276: 116573.) or MPC (Wu, Jing, Xiangdong Li, Yang Lin, Yihuan Yan, and Jiyuan Tu. 2020. “A Pmv-Based Hvac Control Strategy for Office Rooms Subjected to Solar Radiation.” Building and Environment 177: 106863.), (Yang, Shiyu, Man Pun Wan, Wanyu Chen, Bing Feng Ng, and Swapnil Dubey. 2020. “Model Predictive Control with Adaptive Machine-Learning-Based Model for Building Energy Efficiency and Comfort Optimization.” Applied Energy 271: 115147.), the major limitation of these solutions is their scalability. Indeed, they often require a detailed physical or mathematical model of individual buildings and the machinery installed therein (e.g., (Ascione, Fabrizio, Nicola Bianco, Claudio De Stasio, Gerardo Maria Mauro, and Giuseppe Peter Vanoli. 2016. “Simulation-Based Model Predictive Control by the Multi-Objective Optimization of Building Energy Performance and Thermal Comfort.” Energy and Buildings 111: 131–44.), (Valladares, William, Marco Galindo, Jorge Gutiérrez, Wu-Chieh Wu, Kuo-Kai Liao, Jen-Chung Liao, Kuang-Chin Lu, and Chi-Chuan Wang. 2019. “Energy Optimization Associated with Thermal Comfort and Indoor Air Control via a Deep Reinforcement Learning Algorithm.” Building and Environment 155: 105–17.), (Gao, Guanyu, Jie Li, and Yonggang Wen. 2020. “DeepComfort: Energy-Efficient Thermal Comfort Control in Buildings via Reinforcement Learning.” IEEE Internet of Things Journal 7 (9): 8472–84.)). Solutions leveraging ai (e.g., based on reinforcement learning) often need for a significant time-bounded amount of data to train these models that might impact their deployment in short time. Furthermore, other solutions use complex information of the building (e.g., (Yang, Shiyu, Man Pun Wan, Wanyu Chen, Bing Feng Ng, and Swapnil Dubey. 2020. “Model Predictive Control with Adaptive Machine-Learning-Based Model for Building Energy Efficiency and Comfort Optimization.” Applied Energy 271: 115147.), (Wu, Jing, Xiangdong Li, Yang Lin, Yihuan Yan, and Jiyuan Tu. 2020. “A Pmv-Based Hvac Control Strategy for Office Rooms Subjected to Solar Radiation.” Building and Environment 177: 106863.), (Martell, M., F. Rodríguez, M. Castilla, and M. Berenguel. 2020. “Multiobjective Control Architecture to Estimate Optimal Set Points for User Comfort and Energy Saving in Buildings.” ISA Transactions 99: 454–64.)), requiring possible customisations within the environment or, in some cases, advanced sensors to be installed. In this regard, despite the benefits in terms of accuracy in thermal comfort modelling, proposed in the literature do not often meet all the operational requirements of companies, which potentially prefer automated-control strategies to optimise their environments.
We have designed a novel solution called EECO, based on dl to regulate HVAC systems in an automated manner. It does not require any intervention of expert personnel or prior information of building (e.g., installed HVAC devices, layout, materials) as it works on real data collected from the environment. In this regard, our aim is to analyse how the different agents, including passive phenomena, impact the parameters within the environment through the collected data. Basically, after an initial configuration of the main parameters (e.g., the comfort interval throughout the day, some parameters of the comfort model), the proposed solution can effectively work just after its deployment and it keeps up to date independently over time, resulting in an automated and practical solution. The objective of HVAC optimisation is to guarantee the comfort requirements, at least during opening hours, and then balance both thermal comfort and energy consumption concerns. Indoor comfort is modelled by means of PMV (Yau, YH, and BT Chew. 2014. “A Review on Predicted Mean Vote and Adaptive Thermal Comfort Models.” Building Services Engineering Research and Technology 35 (1): 23–35.), (Haq Gilani, Syed Ihtsham ul, Muhammad Hammad Khan, and William Pao. 2015. “Thermal Comfort Analysis of Pmv Model Prediction in Air Conditioned and Naturally Ventilated Buildings.” Energy Procedia 75: 1373–9.), a thermal comfort index referenced by different indoor comfort standards all over the world, including European Standard EN 16798. A shallow 1D CNN is used as dl architecture to predict both the short-term evolution of future indoor environmental parameters (i.e., temperature, humidity and CO2) as well as the energy consumption of the HVAC system. The idea behind the DL model is to predict the environmental and energy impact of a set of possible device configurations (ON/OFF, set point) for several upcoming time periods. Basically, a tree of possible actuation strategies which keeps track of the environment evolution in the next future based on past (real or predicted) conditions is generated. Each branch of the resulting tree is then evaluated to select the strategy that maintains the best expected comfort at minimal energy cost.
Our work can contribute to reducing the carbon footprint of buildings caused by HVAC systems, improving the comfort conditions to occupants, and saving on operating costs required to control thermal comfort. The designed approach has been tested both in Summer and Winter periods in a real environment of a small production plant belonging to a large retail company in northern Italy. Furthermore, an additional analysis based on software simulations is proposed.
The main goals of this approach are the following:
-
A practical solution, with no prior information of the local environment (e.g., installed HVAC devices, building features) or need for customisation or intervention of expert personnel, capable of selecting an efficient HVAC configuration in terms of ON/OFF and set point that aims to guarantee the given thermal comfort while minimising energy consumption.
-
An adaptive and continuous update of the actuations through short-term decisions based on long-term predictions of the environment.
-
A comparison analysis in terms of trade-off between thermal comfort and energy consumption with the manual approach, which sets a static set point temperature throughout the day, and a greedy PMV-Based solution, which configures the HVAC devices according to the current environmental conditions.