Intelligent Building Control Systems for Thermal Comfort and Energy-Efficiency: A Systematic Review of Artificial Intelligence-Assisted Techniques (2104.02214v1)

Abstract: Building operations represent a significant percentage of the total primary energy consumed in most countries due to the proliferation of Heating, Ventilation and Air-Conditioning (HVAC) installations in response to the growing demand for improved thermal comfort. Reducing the associated energy consumption while maintaining comfortable conditions in buildings are conflicting objectives and represent a typical optimization problem that requires intelligent system design. Over the last decade, different methodologies based on the AI techniques have been deployed to find the sweet spot between energy use in HVAC systems and suitable indoor comfort levels to the occupants. This paper performs a comprehensive and an in-depth systematic review of AI-based techniques used for building control systems by assessing the outputs of these techniques, and their implementations in the reviewed works, as well as investigating their abilities to improve the energy-efficiency, while maintaining thermal comfort conditions. This enables a holistic view of (1) the complexities of delivering thermal comfort to users inside buildings in an energy-efficient way, and (2) the associated bibliographic material to assist researchers and experts in the field in tackling such a challenge. Among the 20 AI tools developed for both energy consumption and comfort control, functions such as identification and recognition patterns, optimization, predictive control. Based on the findings of this work, the application of AI technology in building control is a promising area of research and still an ongoing, i.e., the performance of AI-based control is not yet completely satisfactory. This is mainly due in part to the fact that these algorithms usually need a large amount of high-quality real-world data, which is lacking in the building or, more precisely, the energy sector.

• The paper systematically reviews AI methodologies that optimize HVAC systems to improve thermal comfort and achieve significant energy savings.
• It evaluates around 20 AI approaches, including ANNs, ANFIS, and RL, for real-time control of dynamic building environments.
• The study highlights challenges like data quality and personalized comfort, offering insights for future smart building research.

Intelligent Building Control Systems for Thermal Comfort and Energy Efficiency

The paper under review provides a systematic exploration of AI-assisted methodologies applied in building control systems. These systems focus on optimizing the dual objectives of enhancing thermal comfort and achieving energy efficiency, particularly in HVAC systems. This review is driven by the substantial energy demands faced by the building sector, due to the prevalent use of HVAC installations intended to meet increasing demands for thermal comfort.

Thematic Focus and Methodological Insights

In pursuing this dual objective, the paper outlines the intricacies involved in delivering thermal comfort in an energy-efficient manner, while critically reviewing bibliographic content relevant to AI applications. AI technologies hold particular promise in addressing this optimization challenge, as they offer robust prediction and control mechanisms, essential for maintaining delicate balances between comfort and energy consumption. In particular, the paper places significant emphasis on the quantified impact of these technologies, citing an average energy savings range of 21.81 to 44.36% and a corresponding comfort improvement between 21.67 and 85.77%.

Review of AI Techniques in Building Control

The extensive survey identifies around 20 distinct AI methodologies applied over a broad spectrum of studies. Key techniques include Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), and Reinforcement Learning (RL). Notably, ANNs and fuzzy logic are shown to be particularly prolific in application within building management domains, both for predicting PMV indices and regulating HVAC systems in response to real-time data.

The ANNs, for instance, are applauded for their capacity to manage non-linear functions, providing advanced pattern recognition in multi-layer configurations without necessitating extensive system model knowledge. Similarly, fuzzy logic controllers allow for the incorporation of human-like reasoning into building control systems, thus achieving a more nuanced regulation of internal environments.

Challenges and Opportunities

Despite the promising results highlighted, the review acknowledges existing limitations in the deployment of AI-based controls, particularly due to the demand for high-quality data which remains sparse in the real-world energy sector. Furthermore, the challenges presented by the dynamic and subjective nature of human comfort indicate a compelling need for adaptive models that better individualize comfort parameters.

The discussion also expands on the integration of multi-agent systems (MAS) and distributed artificial intelligence (DAI) to provide decentralized control. These systems are noted for facilitating interaction among various building components, thereby supporting adaptive, real-time control strategies that accommodate occupant preferences and external environmental changes.

Theoretical and Practical Implications

The implications of the reviewed AI techniques extend beyond mere operational efficiency; they underscore a pathway toward smart, interconnected building environments capable of self-optimizing energy usage without compromising thermal comfort. The theoretical contribution is complemented by practical findings that invite future research into more personalized comfort models, enhanced interconnectivity for smart buildings, and more efficient HVAC control strategies.

Future Research and Developments

Looking ahead, future research directions include improving data availability and quality for machine learning applications, exploring IoT-enabled smart building frameworks, and ensuring cybersecurity and privacy in sensor-dense environments. Additionally, there is significant scope for integrating edge computing and stream processing for real-time energy management.

In conclusion, the paper robustly establishes AI as a crucial driver in the evolution of intelligent, energy-efficient building systems. It encourages an ongoing inquiry into how these technologies can harmonize human comfort with the overarching imperative of energy conservation.