BaaS Papers

BaaS project has been presented in several conferences and congresses with the aim of spreading the project and its results to the scientific community. A summary of the papers submitted is the following. 

  • Second-level space boundary topology generation from CityGML inputs in Building simulation and optimisation

Authors: G. Lilis, I. Prieto, D. Rovas

Conference3rd IBPSA Building Simulation & Optimisation (BSO16)

Date: September 12-14, 2016

Abstract: Under review.

  • Energy model generation process combining IFC and CityGML data inputs

Authors: G. Lilis, G. Giannakis, K. Katsigarakis, G. Costa, S. Sicilia, D. Rovas

Conference11th European Conference on Product and Process Modelling (ECPPM16)

Date: September 9-11, 2016

Abstract: Under review.

  • Context sensitive indoor temperature forecast for energy efficient operation of smart buildings

Authors: M. V. Moreno, A. F. Skarmeta, A. Venturi, M. Schmidt 

Journal: IEEE 2nd World Forum on Internet of Things (WF-IoT), 2015

Date: December, 2015

Abstract: This paper analyzes the potential of knowledge discovery from sensed data, which enables real-time systems monitoring, management, prediction and optimization in smart buildings. State of the art data driven techniques generate predictive short-term indoor temperature models based on real building data collected during daily operation. The most accurate results are achieved by the Bayesian Regularized Neural Network technique. Our results show that we are able to achieve a low relative predictive error for each room temperature in the range of 1.35% - 2.31% with low standard deviation of the residuals.

  • Selective decryption of outsourced IoT data

Authors: J. M. Bohli, R. Kurpatov, M. Schmidt

JournalIEEE 2nd World Forum on Internet of Things (WF-IoT), 2015 

Date: December, 2015

Abstract: Outsourcing of IoT-data is a common concept when using third-party services, e.g. an external building management service is given access to the building's sensor measurements. However, the measurements captured from building systems often need to be protected from unauthorized access, because they are linked to persons, processes or business secrets, and therefore data protection requirements apply. Nevertheless, due to the large data volumes, external storage is desirable from a business perspective. We propose the concept of a Security Broker based on symmetric encryption schemes. It offers a key management scheme to flexibly create short decryption keys for time intervals or specific ranges of measurement values. We further show how the scheme can be generalized or a combination of the schemes can be applied. We implemented a prototype in Java and analyzed its performance. The evaluation proved the mechanism's applicability for mainstream applications running on off-the-shelf computing equipment.

  • Sense-Think-Act framework for intelligent building energy management

Authors: K. Katsigarakis, G.D. Kontes, G.I. Giannakis and D.V. Rovas

Journal: Computer-aided Civil and Infrastructure Engineering Journal, 2015

Date: September, 2015

Abstract: The realization of smart and energetically efficient buildings is contingent upon the successful implementation of two tasks that occur on distinct phases of the building life cycle: in the design and subsequent retrofitting phases, the selection and implementation of an effective energy concept, and, during the operation phase, the actuation of energy systems to ensure parsimonious energy use while retaining acceptable end-user thermal comfort. Operational efficiencies are achieved through the use of Building Energy Management Systems tasked to deliver core Sense, Think, Act (STA) functionalities: Sense, using sensing modalities installed in the building; Think, utilizing, typically a rule-based decision system; and Act, by sending actuation commands to controllable building elements. Providing the intelligence in this STA process can be a formidable task due to the complex interplay of many systems and occurrence of disturbances. In this article, an architectural and algorithmic framework is presented to provide streamlined implementation of this process. Important ingredients in this framework are: (S) a data access component capable of collecting and aggregating information from a number of heterogeneous sources (sensors, weather stations, weather forecasts); (T) a model-based optimization methodology to generate intelligent operational decisions; and (A) an assessment and actuation component. An illustrative application of the proposed methodology in an office building is provided.

  • An IFC4-based middleware for data interoperability in energy building operation

Authors: José Hernández, Susana Martín and César Valmaseda

Congress: ICEIS 2015

Date: April 27-30, 2015

AbstractThis paper addresses the existing gap in data interoperability among heterogeneous resources for energy service systems of building automation. In this sense, the middleware is the core of the communication between heterogeneous data samples and the application services. This kind of solutions integrates the multiple building data resources to gather the information within the context of energy and buildings and couples the data in a single signal. The middleware also manages the data in an harmonized way by means of the representation of the information in a well-established data-model as IFC4 which is widely used in the building topic. This kind of harmonic communication allows the exchange of information among the entities in complex platforms by common formats in order to ease the interpretation of data. Then, interoperability is a key factor for achieving connectivity that is reached in the present middleware though the event-driven communication mechanisms and the well-known interfaces.

  • A novel middleware for smart grid data exchange towards the energy efficiency in buildings

Authors: Susana Martín, José Hernández and César Valmaseda

CongressNetSys 2015

Date: March 9-13, 2015

AbstractThe objective of this paper is to present a generic middleware conceived to operate as the linking element in platforms hosting smart energy management services to reduce energy consumption in buildings. This kind of solution presents specific requirements related to the need of accessing and managing different sources of information, internal and external to the building, and related to its structure, geometry, or energy consumption. This information is then processed by the system to determine how to improve the energy behavior of the building. In this context, different elements, communicating in a different way and speaking different languages, have to inter-operate with each other to reach the common objective of reducing the energy consumption by executing integrated energy management actions. With the aim of making this system interoperable, coherent, easily expandable, and transparent, the proposed middleware provides a homogeneous level of abstraction in this heterogeneous scenario.

  • An ICT platform for building analytics

Authors: Kyriakos Katsigarakis, Giorgos Kontes, Jiri Rojicek, Cesar Valmaseda, Jose Hernandez and Dimitrios Rovas

CongressECPPM 2014

Date: September 17-19, 2014

Abstract: Significant research effort is underway towards designing intelligent BEMS, adapted to the properties of each building at hand and to the microclimatic conditions of the building location, complemented by a collection of assessment services. On the other hand, the adoption of such solutions by the market is still hampered by the necessity of engineering experts to take over system installation on buildings. Thus, optimizing the energetic performance of buildings is not only about defining intelligent services, but also providing an ICT platform able to host and manage a collection of such analytics. In the proposed approach, an ICT platform is developed to facilitate the provision of building analytics. Open source technologies and service-oriented architectures establish the openness, transparency and interoperability characteristics of the platform, while proper selection and development of specific analytics allows applicability to a large portion of the existing buildings stock in Europe and world-wide.

  • Energy simulation for predictive building control

Authors: Juan Rodriguez, Holger Dittmer, Kirsten Hoettges, Miguel Á. García, Luis Á. Bujedo

CongressECPPM 2014

Date: September 17-19, 2014

Abstract: A new building control methodology is being developed under the frame of BaaS project that allows reaching better energy and comfort performances of the managed buildings. Four buildings sited in different locations and with completely different controls and topologies are used as objects of study to evaluate the improvements reached.  

  • Holistic optimization of HVAC systems via distribited data-driven control

Authors: Karel Macek, Dimitrios Rovas, Mischa Schmidt and César Valmaseda

CongressISA 2014

Date: July 15-17, 2014

Abstract: In the present paper, the control design of Heating, Ventilation and Air Conditioning (HVAC) systems is investigated. In large-scale buildings – e.g. hotels or hospitals – the high dimension of the control design problem precludes a solution with reasonable computational effort. In this paper, a distributed control strategy is proposed, where interacting agents are operating sub-systems; interaction between these agents can ensure that an optimum solution can be obtained. A novel method to distributed control tis introduced based on data-driven modeling where the strategy is not based on explicit optimization, but on weighted learning of the control rules; two examples of the addressed system are formulated. A significant advantage of the proposed approach consists in minimal assumptions on the addressed system and the most significant disadvantage is the need of sufficiently rich data-sets.

  • An Event-driven SOA-based Platform for Energy-efficiency Applications in Buildings

AuthorsCesar Valmaseda, Miguel Angel García, Jose-Luis Hernandez, Kyriakos Katsigarakis, Giorgos D. Kontes and Dimitrios V. Rovas

CongressCIB W78 2013

Date: October 9-12, 2013

Abstract: The topic of optimization of building operation is attracting significant interest in the community: monitoring of relevant Key Performance Indicators can help enhance state awareness and understanding; fault detection and identification can help identify irregular and ineffective operational modes; and, advanced control design techniques can yield effective/optimized operation with regards to energy performance and thermal comfort. Despite significant effort on development of algorithmic and methodological approaches to address these problems, the inherent complexity associated with practical demonstrations, has precluded testing and implementation of such approaches in realistic contexts. Within this paper, an event-driven Service-Oriented Architecture platform, is developed to address this gap and help facilitate the provision of advanced energy-efficiency and energy-management services in buildings. The use of the Industry Foundation Classes provides a standardized data-model for describing the building and its components, while the use of Model View definitions is employed to define the exchange requirements for proper software component interoperability. Data collection and homogenization from the building is addressed through an abstraction layer, capable of hiding many of the intricacies and providing a clean interface for the development of building services. An exemplary application of the proposed architecture in a real office building in Greece is presented.

  • Functional and technological definition of BIM-aware services to Assess, Predict and Optimize energy performance of buildings

AuthorsJ. Rojicek, R. Fisera, G. Kontes, G. Giannakis, G.Lilis, D. Rovas

Congress: CESBP 2013

Date: September 9-11, 2013

Abstract: There are a number of important elements in designing of building energy management systems – when data collection, aggregation and management is usually well addressed by existing building management systems, actual analytical components allowing to diagnose a behavior leading to excessive energy consumption and/or compromised occupants’ comfort are far less mature. It is not only about developing algorithms for such tools, but also proper design of a hosting platform and its viability – it should not only enable access to sensor readings, but also provide access to other building data like Building Information Models and allow collaboration and interconnection of such analytics. BaaS project calls such tools Assess, Predict and Optimize services. De-veloping a smart platform supporting these services naturally leads to a concept of the building as a service eco-system (BaaS) where any new tool can be plugged in the system and can benefit from already existing compo-nents. In the present work, the high level architecture of the BaaS platform is presented and the ability of BaaS system to act as a platform enabling the building contextual data as well as dynamic data (sensor readings) to software modules is demonstrated through a use-case example on a simple one zone office building.


  • Capabilities of IFC4 for Advanced Building Performance Management

Authors: K. Menzel, M. Weise, T. Liebich, C. Valmaseda

CongressCESBP 2013

Date: September 9-11, 2013

AbstractThe availability of vendor-neutral, holistic product and process models is a pre-requisite for the efficient management of data exchange between different IT-applications between Architects, Engineers and Construction specialists and Facility Management experts. For many years development efforts focused on ‘core products’ of engineers and architects – the building’s core and shell, structural analysis models and construction management processes. Older versions of building product models had a very limited capability to support the modelling and data exchange of building services components and the specification of related processes in building operation and maintenance. This paper describes what new model components were introduced as part of the IFC 4-standard which became effective in March 2013. It gives an overview about the underpinning modelling principles and the available model components. It concludes with a discussion how queries against model servers can be developedusing relational algebra.


  • A novel approach towards tight integration of existing building automation control systems for improved energy management and resource utilisation

Authors: M. Floeck, A. Schuelke, M. Schmidt, J.L. Hernandez, S. Martín, C. Valmaseda

CongressCESB 2013

Date: June 26-28, 2013

AbstractThis paper presents interim results of the currently ongoing "Building as a Service" (BaaS) EU project. The BaaS project aims at optimising energy performance of non-residential buildings, e.g. schools, universities, hotels, shopping centres, or sports facilities.

An ICT platform is being developed that integrates IT systems that already exist in infrastructure assets with new IT components delivering novel functionalities extending the performance assessment of buildings. The former include building management systems (BMSs), access control systems, or systems providing weather data. The latter are mostly concerned with the assessment, prediction, and optimisation (APO) of energy usage and modelling. The IT infrastructure systems and APO services are linked by an integration middleware. The main features of this middleware are standardised interfaces via which all communication between the components of the system is routed. Functioning and characteristics of the middleware and its interfaces will be explained in the present paper.

  • BaaS project: covering the Design- and Operational-Phase Interoperability Gap

Authors: C. Valmaseda, M.A. García, J.L. Hernández, S. Martín

Congress: ICEBO 2012

Date: October 23-26, 2012

AbstractThere are two important phases in the building life-cycle: the design phase (along with subsequent retrofitting phases) in which design decisions significantly affect subsequent performance; followed by the operation phase where the Building Energy Management System (BEMS) ensures an effective use of the available resources. The development and integration of ICT technologies can help best coordinate the building design and operation phases. Overcoming interoperability gaps between both phases so as providing a way of integration to use existing and future tools and services would help to enhance building operations and controls.

The 7FP EU project titled "Building as a Service" (BaaS) is a research initiative which aims to optimize energy performance in the application domain of “non-residential buildings” in operational stage. Better and more standardized design along with interoperable components working as services at the building level, will lead naturally to the concept of the Building as a Service ecosystem.


  • Thermal Comfort monitoring in comercial buildings

Authors: J. Vaas, J. Rojicek, J. Trojanova

Congress: SEBUA 2012

Date: October 14-20, 2012

AbstractThis paper presents a system for thermal comfort monitoring using the Predicted Mean Vote (PMV). The system is capable of identifying opportunities for energy savings and indicating violation of occupants' thermal comfort. The system consists of multiple modules, including PMV scheduler, PMV thresholding, and PMV visualization (for both online and historical data monitoring). The system has been applied to real data from commercial buildings and interesting PMV-based charts have been obtained. However, since PMV computation requires sensors that are rarely available (e.g. air velocity), alternative approaches for determining PMV are reviewed, including PMV sensors and inferential techniques (soft sensors).


  • From BIM to BEMS, covering the Design- and Operational-Phase Interoperability Gap

Authors: C. Valmaseda, P. Yebra, D.V. Rovas, E. Kosmatopoulos

CongressECPPM 2012

Date: July 25-27, 2012

Abstract: This paper deals with the FP7 EU project "Building as a Service" (BaaS). The BaaS project is a research initiative which aims at providing a generic solution for delivering standardization and interoperabil-ity concepts for building data and open middleware platform covering the Design- and Operational-Phase In-teroperability Gap in the application domain of “non-residential buildings.” There are two important phases in the building life-cycle: the design phase and the operational phase. Development and integration of ICT tech-nologies can help best coordinate the building design and operation phases. Overcoming interoperability gaps between both phases so as providing a way of integration to use existing and future tools and services would help to enhance building operations and controls. Better design, standardization and interoperability can con-tribute themselves to the goals of improving energy efficiency. Interoperable components working as services at the building level, will lead naturally to the concept of the Building as a Service ecosystem. This paper aims at analyzing some of the BaaS project topics: (1) building data management and interoperability: data warehouse to collect, organize, store and aggregate static and dynamic data from various in- and out-of-building sources; an IFC-based BIM will act as a central repository for all static building data, and a data warehouse will be used for dynamic data, both schemes mapped using a unique vocabulary. (2) Integration of building energy management Services using Open Service Middleware Platform technologies. A service mid-dleware platform to abstract the building physical devices, support high level services on the cloud and facili-tate secure two-way communication between the physical and ICT layers (building) with high level services (cloud).