Open Access! Despite its high potential, the building's sector lags behind in reducing its energy demand. Tremendous savings can be achieved by deploying building management services during operation, however, the manual deployment of these services needs to be undertaken by experts and it is a tedious, time and cost consuming task. It requires detailed expert knowledge to match the diverse requirements of services with the present constellation of envelope, equipment and automation system in a target building. To enable the widespread deployment of these services, this knowledge-intensive task needs to be automated. Knowledge-based methods solve this task, however, their widespread adoption is hampered and solutions proposed in the past do not stick to basic principles of state of the art knowledge engineering methods. To fill this gap we present a novel methodological approach for the design of knowledge-based systems for the automated deployment of building management services. The approach covers the essential steps and best practices: (1) representation of terminological knowledge of a building and its systems based on well-established knowledge engineering methods; (2) representation and capturing of assertional knowledge on a real building portfolio based on open standards; and (3) use of the acquired knowledge for the automated deployment of building management services to increase the energy efficiency of buildings during operation. We validate the methodological approach by deploying it in a real-world large-scale European pilot on a diverse portfolio of buildings and a novel set of building management services. In addition, a novel ontology, which reuses and extends existing ontologies is presented.
Over the last several years, a great amount of research work has been focused on the development of model predictive control techniques for the indoor climate control of buildings, but, despite the promising results, this technology is still not adopted by the industry. One of the main reasons for this is the increased cost associated with the development and calibration (or identification) of mathematical models of special structure used for predicting future states of the building. We propose a methodology to overcome this obstacle by replacing these hand-engineered mathematical models with a thermal simulation model of the building developed using detailed thermal simulation engines such as EnergyPlus. As designing better controllers requires interacting with the simulation model, a central part of our methodology is the control improvement (or optimisation) module, facilitating two simulation-based control improvement methodologies: one based in multi-criteria decision analysis methods and the other based on state-space identification of dynamical systems using Gaussian process models and reinforcement learning. We evaluate the proposed methodology in a set of simulation-based experiments using the thermal simulation model of a real building located in Portugal. Our results indicate that the proposed methodology could be a viable alternative to model predictive control-based supervisory control in buildings.
Project MOEEBIUS focus is the reduction of the gap between predicted and actual energy performances in buildings. This project will introduce a Holistic Energy Performance Optimization Framework with new tools and methodologies that enhance current building energy performance simulation tools and current modelling approaches. This strategy aims to deeply grasp and describe real-life building operation complexities and introduce continuous optimization of building energy performance in real-time or through retrofitting.
The development of Wireless Sensor Networking technology to deploy in smart home environments for a variety of applications such as Home Area Networking has been the focus of commercial and academic interest for the last decade. Developers of such systems have not adopted a common standard for communications in such schemes. Many Wireless Sensor Network systems use proprietary systems so interoperability between different devices and systems can be at best difficult with various protocols (standards based and non-standards based) used (ZigBee, EnOcean, MODBUS, KNX, DALI, Powerline, etc.). This work describes the development of a novel low power consumption multiradio system incorporating 32-bit ARM-Cortex microcontroller and multiple radio interfaces - ZigBee/6LoWPAN/Bluetooth LE/868MHz platform. The multiradio sensing system lends itself to interoperability and standardization between the different technologies, which typically make up a heterogeneous network of sensors for both standards based and non-standards based systems. The configurability of the system enables energy savings, and increases the range between single points enabling the implementation of adaptive networking architectures of different configurations. The system described provides a future-proof wireless platform for Home Automation Networks with regards to the network heterogeneity in terms of hardware and protocols defined as being critical for use in the built environment. This system is the first to provide the capability to communicate in the 2.4GHz band as well as the 868MHz band as well as the feature of multiboot capability. A description of the system operation and potential for power savings through the use of such a system is provided. Using such a multiradio, multiboot capable, system can not only allow interoperability across multiple radio platforms in a Home Area Network, but can also increase battery lifetime by 20 – 25% in standard sensing applications
With the increasing demand for more energy efficient buildings, the construction and energy services industries are faced with the challenge to ensure that the energy performance and savings predicted during energy efficiency measures definition is actually achieved during operation. There is, however, significant evidence to suggest that buildings underperform illustrating a, so called, "performance gap" which is attributed to a variety of causal factors related to both predicted and in-use performance, implying that predictions tend to be unrealistically low whilst actual energy performance is usually unnecessarily high. In turn the successful penetration and effective application of ESCO business models relies on minimizing the gap between actual and predicted building energy performance. The aforementioned gap, though, prohibit the scaled deployment of energy efficiency projects constituting a significant barrier to the development of the ESCO market. The overall problem (performance gap) could be basically interpreted as an inability of current modelling techniques to represent the realistic use and operation of buildings. MOEEBIUS H2020 project introduces a Holistic Energy Performance Optimization Framework that enhances current (passive and active building elements) modelling approaches with advanced user behaviour modelling and machine learning technologies to create an innovative suite of end-user tools and applications enabling: (i) accurate Building Energy Performance prediction, (ii) precise allocation of detailed performance contributions between critical building components and operations, (iii) real-time building performance optimization, (iv) optimized retrofitting decision-making and, (v) real-time peak-load management optimization at the district level. Through the provision of a robust technological framework MOEEBIUS will enable the creation of attractive business opportunities for ESCOs, Aggregators, Maintenance and Facility Managers in evolving and highly competitive energy services markets.
The deployment of technical building management services is a requirement to further reduce energy demand of future and existing buildings. Automating the process of configuring and deploying technical building management services such as fault detection and diagnosis of technical equipment seems to be a promising path to intensify the adoption of these services. In this work we present a data processing and analytics execution platform which allows the deployment of ontology-based, automated technical building management services on a large-scale. We present the platform architecture and results from a reference implementation performing rule-based fault detection on offline air handling unit data.
The design of retrofitted energy efficient buildings is a promising option towards achieving a cost-effective improvement of the overall building sector's energy performance. With the aim of discovering the best design for a retrofitting project in an automatic manner, a decision making (or optimization) process is usually adopted, utilizing accurate building simulation models towards evaluating the candidate retrofitting scenarios. A major factor which affects the overall computational time of such a process is the simulation execution time. Since high complexity and prohibitive simulation execution time are predominantly due to the full-scale, detailed simulation, in this work, the following simulation-time reduction methodolo-gies are evaluated with respect to accuracy and computational effort in a test building: Hierarchical clustering ; Koopman modes; and Meta-models. The simplified model that would be the outcome of these approaches, can be utilized by any optimization approach to discover the best retrofitting option.