Data Mining - Concepts and Techniques.

Handbook of Data Analysis

The energy consumption of residential and commercial buildings has risen steadily in recent years, an increase largely due to their HVAC systems. Expected energy loads, transportation, and storage as well as user behavior influence the quantity and quality of the energy consumed daily in buildings. However, technology is now available that can accurately monitor, collect, and store the huge amount of data involved in this process. Furthermore, this technology is capable of analyzing and exploiting such data in meaningful ways. Not surprisingly, the use of data science techniques to increase energy efficiency is currently attracting a great deal of attention and interest. This paper reviews how Data Science has been applied to address the most difficult problems faced by practitioners in the field of Energy Management, especially in the building sector. The work also discusses the challenges and opportunities that will arise with the advent of fully connected devices and new computational technologies.

/pdf/data-science-for-building-energy-management-a-review-37zx4z0u63.pdf

Data science for building energy management: a review

https://escholarship.org/content/qt3fb0p5gk/qt3fb0p5gk.pdf?t=pwukh7

Personal thermal comfort models with wearable sensors

Rapid advances in building information modelling (BIM) offer new opportunities to improve efficiency and effectiveness of the construction process and enhance the use of emerging technology throughout project’s lifecycle, not only in buildings, but also in infrastructures. Although some researchers have promoted the use of BIM in infrastructures and several reviews in BIM implementation have been conducted; the comparative study of BIM implementation between building and infrastructure industry in a holistic view has not been identified. Hence, the goal of this study is to explore the extent to which level of BIM implementation has achieved in building and infrastructure industries. This exploration was performed differently from two main sources, namely, academic studies and industrial cases, where conventional reviews in BIM were mainly focused on academic publications only. More than forty case studies in academic journals and conference proceedings and twenty four BIM cases in industrial reports were collected and analysed to determine the current BIM uses and emerging BIM applications in both industries. The results show that (1) BIM case studies in academic journals show the high level of BIM implementation in practice; (2) the initial development of BIM in infrastructure can be referred to the existing BIM experience from the building industry; and (3) the comparative analysis of BIM in infrastructure and building cases highlights the support of new BIM use, enhanced of traditional project management and transformation of project delivery method.

A Comparative Review of Building Information Modelling Implementation in Building and Infrastructure Industries

Multi-dimensional building performance data management for continuous commissioning

Performance monitoring using wireless sensors is now common practice in building operation and maintenance and generates a large amount of building specific data. However, it is difficult for occupants, owners and operators to explore such data and understand underlying patterns. This is especially true in buildings which involve complex interactions, such as ventilation, solar gains, internal gains and thermal mass. Performance monitoring requires collecting data concerning energy consumption and ambient environmental conditions to model and optimise buildings' energy consumption. This paper details the use of data mining techniques in understanding building energy performance of geothermal, solar and gas burning energy systems. The paper is part of an outgoing research into optimisation of building performance under hybrid energy regimes. The objective of the research presented in this paper is to predict comfort levels based on the Heating, Ventilating, and Air Conditioning (HVAC) system performance and external environmental conditions. A C4.5 classification methodology is used to analyse a combination of internal and external ambient conditions. The mining algorithms are used to determine comfort constraints and the influence of external conditions on a building's internal user comfort. To test the performance of classification and its use in prediction, different offices, one to the south and the other to the north of the building are used. Classification rules being developed are analysed for their application to modify control algorithms and to apply results to generalise hybrid system performance. The results of this study can be generalised for an entire building, or a set of buildings, under a single energy network subject to the same constraints.

Using data mining in optimisation of building energy consumption and thermal comfort management

It is a natural business need to have our building stock operating efficiently. A building that operates efficiently is one where most characteristics of the building can be measured, monitored and recorded while responding with relevant actuation. BIM has proved over time to be a valuable asset in contributing to the management of relevant building data. This paper examines how current implemented research in the area of Optimised Building Operation can be used to further the role BIM can play. It also examines experiences using an open source BIM tool and considers the technological approach taken by such a tool as a positive step to achieving a synchronous BIM when integrated with current building performance data gathering techniques. ble Energy, Environmental Engineering, Environmental Chemistry, Environmental Microbial Genomics, Biodiversity to name but a few academic areas. The use of toxic chemicals, the production of waste products or the use of high cost equipment are daily activities at the ERI. BIM functional requirements that emerge in this instance include; (1) BIM shall accommodate occupant roles within a building; (2) BIM shall support a history of hazardous material usage; (3) BIM shall support a history of hazardous waste production and disposal. Finally, some requirements worth mentioning that can assist all stakeholders. (1) The BIM shall support wired, wireless and simulated building performance data; (2) The BIM shall support optimum performance data with regard to renewable energy sources within a building; (3) The BIM shall support a modeling facility to quickly visualise, amend and further develop building models. 1.2 Technology for BIM This research has focused on using an object oriented BIM tool supporting a web browser based client. ITOBO uses BiMserver (BiMserver, 2012), an open source software supporting the following key features:  Industry Foundation Class (IFC), ifcZIP and ifcXML building drawing file formats,  IFC versioning,  Geographic Information System,  Filter and querying,  Web-service Interface,  Web-browser Interface. The BiMserver is certainly not a fileserver and uses the model-driven architecture approach. The uploaded IFC data is brought through a translation process where it is processed into an Eclipse Modeling Framework (EMF) interpretable eCore file. The process of translation involves running the IFC data through a series of parsers compliant with ISO 10303 part 21 where the use of an express dictionary for express to eCore conversion is utilized. The generated eCore file is required to maximize the full benefits of the EMF. Following this translation process, what was once an IFC file is now a series of eCore objects stored in the BiMserver’s underlying Java based Berkley database. The translation process is twofold. The clear advantages of handling IFC data and the packaging of IFC data into objects, is the ease with which object element queries and filtration can be achieved. In addition, object elements can be isolated for further analysis. In the interests of ITOBO, where the production of simulated and real-time sensed building data is abundant, a mechanism to amend object embedded parameters within a BIM is appealing. The philosophy behind BiMserver is to allow users an opportunity to further develop this BIM approach by providing all relevant software as open source. Deployment of the BiMserver is straight forward and what is evident is the hardware demands are quite low. During a testing phase, ITOBO has hosted BiMserver on a regular PC running a Windows7 64-bit operating system. The PC has no special RAM or disk space requirements. BiMserver runs smoothly. One limitation that has been observed is when multiple users (< 10 users) try to login to the BiMserver at the same time, BiMserver complains about a deficiency of memory with the result that a number of users cannot login to the system. The same error occurs during the IFC file upload process. This phenomenon escalates when memory hungry applications are running on the host PC in parallel. A recommendation here would be to run BiMserver on a dedicated server/PC running a server specific operating system. In addition, ITOBO tests have seen that large IFC files, in excess of 30MB failed to fully upload to the BiMserver. This proved to be a limitation with wireless LAN facilities outside the UCC LAN. 1.3 Berkley Database As mentioned the underlying database for the BiMserver is the Berkley Database written in Java and implemented through Berkley DB Java Edition (Oracle, 2012). In short, this allows BiMserver to be supported on many hardware platforms from mobile devices to servers. The Berkley DB offers users a number of database strategies. The strategy adopted and used by BiMserver is the ability to store data using a key value approach. A key value store arranges data in a set of named tables supporting two columns reserved for key and value. The storage size of both key and value nodes can be arbitrary even though the key node has a much more fixed byte size. As is a database norm, all keys are ordered and never duplicated. Each key node is comprised of a Project ID, an Object ID and a Revision ID. In addition, Class ID is optionally supported. 16 bytes (128 bits) can be reserved from the key node. The value node, as mentioned, is more arbitrary with its byte size. All value nodes are written in an EMF defined order and include all super class structural features (BimServer2, 2012). In a nutshell, if a developer is looking for a database with more functionality than what is currently available from a relational database, it is recommended to consider using a Berkley (Oracle, 2012). The Berkley DB Java edition supports the storage of key value data in a b-tree data structure which accommodates efficient data queries, sorts, insertions and deletions. Berkley DB emphasises support for revision control. From a BiMserver perspective, all models are stored as projects. New revisions of a model also adopt their own specific project. All project revisions utilize the Berkley DB b-tree data structure. This facility allows users to retrieve older revisions of models while also supporting a seamless amendment to objects from the same model and revision. Currently, ITOBO uses Oracle 11g data warehouse software to host and process its wired and wireless sensor data. In addition, ITOBO uses a series of Java based applications to examine and retrieve gathered data for building performance graphical representations, sensor device detailing, and data download facilities. What is also of real interest to ITOBO as far as BIM is concerned is the ability to focus in on relevant IFC objects that contain potential to detail and host building performance data. In addition, the ability to enrich these objects with data obtained from simulations and from the ITOBO data warehouse offers an opportunity to embrace the concept of synchronous BIM. Using an object based BIM database complements the object based approach adopted by ITOBO. The Berkley DB based BiMserver offers an efficient fit for an ITOBO BIM solution. 2 IFC OBJECT ANALYSIS

BIM as a centre piece for Optimised Building Operation

For today's building operation business, intelligent building performance analysis solutions with the strength for high replication potential are on urgent demand. While ICT is available throughout ...

A middleware platform for integrated building performance management

After a long period of relative neglect, the mental well-being and the mental health of researchers and employees in academia are increasingly entering the limelight. The growing body of evidence suggests that a high number of doctoral researchers work under elevated levels of stress and frustration, and that this has a significant impact not only on their personal health and research output, but also on their future career development. In this paper, therefore, we first discuss what a dystopian and a utopian learning journey of early career researchers may look like from a well-being perspective. Subsequently, and based on extensive dialogues with more than 250 researchers and professionals active in the researcher mental health domain, we highlight a number of key focal points that both early career researchers, their supervisors, and institutions alike should consider when it comes to planning and delivering mental health oriented educational activities for doctoral researchers. 

Brian Cahill

Papers

Multi-dimensional building performance data management for continuous commissioning

Using data mining in optimisation of building energy consumption and thermal comfort management

BIM as a centre piece for Optimised Building Operation

A middleware platform for integrated building performance management

The well‐being and mental health of doctoral candidates