Privacy-Preserving Regulation Capacity Evaluation for HVAC Systems in Heterogeneous Buildings Based on Federated Learning and Transfer Learning

The importance of the security of building management systems (BMSs) has increased given the advances in the technologies used. Since the Heating, Ventilation, and Air Conditioning (HVAC) system in buildings accounts for about 40% of the total energy consumption, threats targeting the HVAC system can be quite severe and costly. Given the limitations on accessing a real HVAC system for research purposes and the unavailability of public labeled datasets to investigate the cybersecurity of HVAC systems, this paper presents a dataset of a 12-zone HVAC system that was collected from a simulation model using the Transient System Simulation Tool (TRNSYS). It aims to promote and support the research in the field of cybersecurity of HVAC systems in smart buildings [1] by facilitating the validation of attack detection and mitigation strategies, benchmarking the performance of different data-driven algorithms, and studying the impact of attacks on the HVAC system.

<p>Template energy calculation models that have been produced by the Building Energy End-use Study (BEES) team are used to quickly and reliably model commercial buildings and calculate their energy performance. The template models contain standardised equipment, lighting, and occupancy loads; cooling and heating requirements are calculated using an ideal loads air system. Using seven buildings, Cory et al. 2011a have demonstrated that the template models have the potential to closely match the monthly energy performance of detailed (individually purpose built) models and the real buildings. Three of these models were within the ±5% acceptable tolerance to be considered calibrated. The four template models that were not within the acceptable tolerance have been identified to have complex Heating, Ventilation, and Air Conditioning (HVAC) systems that the ideal loads air systems could not replicate. Because HVAC systems consume one of the largest proportions of energy in commercial buildings, this has a significant impact on the reliability of the template models. To address this issue, a set of detailed HVAC systems were needed to replace the ideal loads air systems. Due to HVAC system parameters not being collected by the BEES team and the lack of published modelling input parameters available, it is unknown what values are reasonable to use in the models. This study used a Delphi survey to collect real building information of the commonly installed HVAC systems in New Zealand commercial buildings. The survey formed a consensus between HVAC engineers that determined what the most commonly installed systems are and their associated performance values. The outcome of the survey was a documented set of system types and modelling input parameters that are representative of New Zealand HVAC systems. The responses of the survey were used to produce a set of HVAC system templates that replace the ideal loads air systems. The HVAC template models updated the software default parameter values with values that are representative of commonly installed systems in New Zealand. The importance of the updated input values was illustrated through a comparison of the calculated monthly energy consumption. The resulting difference in energy consumption using the updated parameter values is typically <5% monthly; at worst it is 75% for Variable Air Volume (VAV) system in the Wellington climate during June.</p>

<p>Template energy calculation models that have been produced by the Building Energy End-use Study (BEES) team are used to quickly and reliably model commercial buildings and calculate their energy performance. The template models contain standardised equipment, lighting, and occupancy loads; cooling and heating requirements are calculated using an ideal loads air system. Using seven buildings, Cory et al. 2011a have demonstrated that the template models have the potential to closely match the monthly energy performance of detailed (individually purpose built) models and the real buildings. Three of these models were within the ±5% acceptable tolerance to be considered calibrated. The four template models that were not within the acceptable tolerance have been identified to have complex Heating, Ventilation, and Air Conditioning (HVAC) systems that the ideal loads air systems could not replicate. Because HVAC systems consume one of the largest proportions of energy in commercial buildings, this has a significant impact on the reliability of the template models. To address this issue, a set of detailed HVAC systems were needed to replace the ideal loads air systems. Due to HVAC system parameters not being collected by the BEES team and the lack of published modelling input parameters available, it is unknown what values are reasonable to use in the models. This study used a Delphi survey to collect real building information of the commonly installed HVAC systems in New Zealand commercial buildings. The survey formed a consensus between HVAC engineers that determined what the most commonly installed systems are and their associated performance values. The outcome of the survey was a documented set of system types and modelling input parameters that are representative of New Zealand HVAC systems. The responses of the survey were used to produce a set of HVAC system templates that replace the ideal loads air systems. The HVAC template models updated the software default parameter values with values that are representative of commonly installed systems in New Zealand. The importance of the updated input values was illustrated through a comparison of the calculated monthly energy consumption. The resulting difference in energy consumption using the updated parameter values is typically <5% monthly; at worst it is 75% for Variable Air Volume (VAV) system in the Wellington climate during June.</p>

As people spend up to 87% of their time indoors, intelligent Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings are essential for maintaining occupant comfort and reducing energy consumption. These HVAC systems in smart buildings rely 'on real-time sensor readings, which in practice often suffer from various faults and could also be vulnerable to malicious attacks. Such faulty sensor inputs may lead to the violation of indoor environment requirements (e.g., temperature, humidity, etc.) and the increase of energy consumption. While many model-based approaches have been proposed in the literature for building HVAC control, it is costly to develop accurate physical models for ensuring their performance and even more challenging to address the impact of sensor faults. In this work, we present a novel learning-based framework for sensor fault-tolerant HVAC control, which includes three deep learning based components for 1) generating temperature proposals with the consideration of possible sensor faults, 2) selecting one of the proposals based on the assessment of their accuracy, and 3) applying reinforcement learning with the selected temperature proposal. Moreover, to address the challenge of training data insufficiency in building-related tasks, we propose a model-assisted learning method leveraging an abstract model of building physical dynamics. Through extensive experiments, we demonstrate that the proposed fault-tolerant HVAC control framework can significantly reduce building temperature violations under a variety of sensor fault patterns while maintaining energy efficiency.

Energy efficient HVAC systems

In this paper an abstract model for adaptation of enterprise technologies in heterogeneous networks of small devices is proposed. The model is based on hierarchical multi- tier approach for better manageability and administration. Its structure allows not only separation between business and presentation logic, but also separation of enterprise and automation functions. Thus, changes in business and automation logics do not affect the user. The actual distribution of functions appears on the service and automation tiers. The level of abstraction of the model allows its usage in various environments - home and office automation, industry, medicine, agriculture. In the paper an experimental application of the presented model for an effective management of HVAC (heating, ventilation and air conditioning) systems in buildings is discussed. subsystems. The key goal of the work, presented in the paper, is the analysis of the latest off-the-shelf technologies in business information systems and their possible adaptation in distributed automation, based on controllers with embedded communication facilities. For this purpose, a model of information flow and representation in distributed automation systems is developed, employing the standards of e-business, working on the web. An experimental application of the presented model for an effective management of Heating, Ventilation, and Air-Conditioning (HVAC) systems in residential buildings is proposed. The limited resources of the embedded devices as well as the dynamic nature of building's automation networks are impending factors for the adaptation of web services into the systems. The rest of the paper is organized as follows:

Centrally controlled heating, ventilation, and air conditioning (HVAC) systems in commercial buildings are operated by building management systems (BMS) based on the predefined operational settings and a set of assumptions. Despite the high rate of energy consumption by HVAC systems in commercial buildings, observations showed that a significant portion of the occupants remain dissatisfied with thermal conditions. One of the main reasons is that HVAC systems do not take into account personalized comfort preferences in their operational rules. This study proposes a framework to integrate building occupants in the HVAC control loop, learn their comfort profiles, and control the HVAC system based on occupants’ personalized comfort profiles. The framework fuses occupants’ comfort perception indices (i.e., comfort votes provided by users and mapped to a numerical value), collected through participatory sensing, and ambient temperature data, collected through a sensor network, and computes occupants’ co...

Promoting building energy conservation is a key path to achieving the dual-carbon goal. The heating, ventilation, and air conditioning (HVAC) system in office buildings is a core energy-consuming terminal, and its accurate prediction and optimal scheduling are of great significance for improving energy utilization efficiency and reducing operating costs. Aiming at the limitation that traditional methods are difficult to adapt to dynamic loads and complex nonlinear coupling characteristics, this paper constructs a machine learning-driven integrated framework for HVAC system energy consumption prediction and optimal scheduling. Based on multi-dimensional data from authoritative measured databases and public building energy consumption monitoring platforms, typical machine learning prediction models are systematically constructed and compared to achieve high-precision prediction of short-term cooling and heating loads as well as system energy consumption, providing reliable feedforward support for optimal scheduling. Taking the prediction results as the foundation, an optimal scheduling model based on model predictive control (MPC) integrated with dynamic electricity price mechanism is established, targeting the coordination of operating cost optimization and power grid peak load shifting, with indoor thermal comfort standards as hard constraints. Case verification through professional simulation platforms shows that the proposed integrated method effectively improves the electrical load characteristics and enhances the operational economy and low-carbon performance of the system while ensuring indoor environmental quality, providing a technical path with theoretical value and practical significance for the intelligent and low-carbon upgrading of HVAC systems in office buildings.

Heating, ventilation, and air conditioning (HVAC) systems of commercial and institutional buildings consume a large proportion of the energy used worldwide and, as a result, are a major contributor to greenhouse gas emissions and operational expenses. According to Wang et al. (2021), HVAC systems in commercial buildings account for approximately 40% of total energy consumption, making them a key focus in efforts to reduce energy use and emissions. As climate change and energy resource depletion intensify, increasing the energy efficiency of these buildings is viewed as a sustainable development solution. Improving building energy efficiency is considered one of the most effective strategies to mitigate global energy consumption and carbon footprints (Pérez-Lombard et al., 2008). This critical review re-anchors the current research, strategies, and case studies toward improving energy efficiency in existing commercial and institutional buildings, providing insights on which approaches work best, the challenges of implementation, and ways forward to guide future research and practice. The paper starts by outlining an overall view of the use of energy in commercial and institutional buildings and identifies the key energy-using systems, which include HVAC, lighting, and the building envelope (Mendell et al., 2017). Technological enhancements scientifically proven to reduce energy consumption include efficient HVAC systems, lighting systems, and advancements in insulation and window technologies (Kim et al., 2019). In addition, the utilization of renewable energy within existing building structures—such as solar and wind energy—is explored as a complementary option for reducing reliance on non-renewable energy sources (Hossain et al., 2020). Beyond technological improvements, behavioral change and policy measures play a critical role in improving energy efficiency. Studies have shown that occupant behavior significantly affects energy consumption, and energy management practices, coupled with incentives, can lead to measurable efficiency gains (Delzendeh et al., 2017). Energy performance standards and governmental incentives are essential in fostering greater efficiency in building systems (Ürge-Vorsatz et al., 2012). The review also addresses the challenges of retrofitting, particularly the high initial costs, operational disruptions, and legal constraints involved in upgrading existing buildings. These barriers, particularly in terms of cost and logistics, are critical to overcome if retrofitting is to be widely adopted (Ma et al., 2012). Case studies such as the Empire State Building's retrofitting project, which resulted in a projected 38% energy savings, and Harvard University's energy efficiency initiatives, demonstrate the real-world feasibility of significant energy reductions (Guldmann et al., 2020). It is particularly relevant to stress here that more innovation is required in the sphere of energy-efficient technologies, backed by stronger policy support, education, and collaboration among stakeholders. As noted by Sartori et al. (2012), the collaboration between governments, industry, and academia is essential to address the global challenge of increasing the energy efficiency of buildings and reducing energy consumption in response to climate change.

A hierarchical optimal control strategy for continuous demand response of building HVAC systems to provide frequency regulation service to smart power grids

Increasing demand on heating, ventilation, and air-conditioning (HVAC) systems and their importance, as the respiratory system of buildings, in developing and spreading various microbial contaminations and diseases with their huge global energy consumption share have forced researchers, industries, and policymakers to focus on improving the sustainability of HVAC systems. Understanding and considering various parameters related to the sustainability of new and existing HVAC systems as the respiratory system of buildings are vital to providing healthy, energy-efficient, and economical options for various building types. However, the greatest opportunities for improving the sustainability of HVAC systems exist at the design stage of new facilities and the retrofitting of existing equipment. Considering the high available percentage of existing HVAC systems globally reveals the importance of their retrofitting. The attempt has been made to gather all important parameters that affect decision-making to select the optimum HVAC system development considerations among the various opportunities that are available for sustainability improvement.

This study examines the impact of climate change on the energy consumption and performance of heating, ventilation, and air conditioning (HVAC) systems in buildings. It compares one centralized and one decentralized HVAC configurations under current and future climate scenarios for 2030 and 2050. The research focuses on two building types: a university dormitory and a research building modelled using DesignBuilder. Two HVAC systems were evaluated: packaged terminal air conditioners (PTAC) and central chillers with fan coil units (FCU). Projections for 2050 and 2080 were based on climate data from the CCWorldWeatherGen tool. Results show PTAC systems had the lower energy consumption, while FCU units had the highest, especially in warmer scenarios. Centralized systems may experience a 15.9% increase in energy consumption by 2050, with reduced performance in managing peak loads. The findings highlight the need for adaptive HVAC design strategies to ensure energy efficiency in future climates.

What are the impacts on the HVAC system when it provides frequency regulation? – A comprehensive case study with a Multi-Zone variable air volume (VAV) system

Heating, ventilation, and air conditioning (HVAC) systems in buildings are an emerging application area for model predictive control (MPC) due to the significant cost benefits that can be achieved via load shifting in modern electricity markets. In this paper, we discuss some of the opportunities and challenges associated with applying MPC to commercial HVAC systems. After defining the control problem, a decomposition of the centralized MPC is presented and demonstrated for an example system. Recent work at the Stanford University campus is also highlighted to show these ideas in practice, and an outlook for the field is given.

A dynamic maintenance planning methodology for HVAC systems based on Fuzzy-TOPSIS and failure mode and Effect Analysis