Hae sivustolta

Mitä etsit?

Futureproofing and scaling machine learning for occupancy prediction

Stjelja, D., Jokisalo, J., & Kosonen, R. (2022). Futureproofing and scaling machine learning for occupancy prediction. teoksessa Proceedings CLIMA2022 : REHVA 14th HVAC Congress, 22-25 May 2022, Rotterdam (Sivut 2332-2338). TU Delft Open.

Abstract

An important instrument for achieving smart and high-performance buildings is Machine Learning (ML). A lot of research was done in exploring the ML learning models for various applications in the built environment such as occupancy prediction. Nevertheless, this research focused mostly on analyzing the feasibility and performance of different supervised ML models but have rarely focused on practical applications and scalability of those models. In this study, we are proposing a transfer learning method as a solution to few typical problems with the practical application of ML in buildings. Such problems are scaling a model to another (different) building, collecting ground truth data necessary for training the supervised model and adapting the model when conditions change. The practical application examined in this work is a deep learning model used for predicting room occupancy using indoor air quality (IAQ) IoT sensors. The importance of occupancy prediction has risen in recent times of remote work and is especially important for futureproofing of the built environment. This work proves that it is possible to reduce significantly the need for ground truth data collection for deep learning based occupancy detection model. Additionally, the robustness of the transferred model was tested, where performance stayed on similar level if suitable normalization technique was used.

Validating the Real-Time Performance of Distributed Energy Resources Participating on Primary Frequency Reserves

Karhula, N., Sierla, S., & Vyatkin, V. (2021). Validating the Real-Time Performance of Distributed Energy Resources Participating on Primary Frequency Reserves. Energies, 14(21), [6914].

Abstract

A significant body of research has emerged for adapting diverse intelligent distributed energy resources to provide primary frequency reserves (PFR). However, such works are usually vague about the technical specifications for PFR. Industrial practitioners designing systems for PFR markets must pre-qualify their PFR resources against the specifications of the market operator, which is usually a transmission system operator (TSO) or independent system operator (ISO). TSO and ISO requirements for PFR have been underspecified with respect to real-time performance, but as fossil-fuel based PFR is being replaced by various distributed energy resources, these requirements are being tightened. The TSOs of Denmark, Finland, Norway, and Sweden have recently released a joint pilot phase specification with novel requirements on the dynamic performance of PFR resources. This paper presents an automated procedure for performing the pre-qualification procedure against this specification. The procedure is generic and has been demonstrated with a testbed of light emitting diode (LED) lights. The implications of low bandwidth Internet of Things communications, as well as the need to avoid abrupt control actions that irritate human users, have been investigated in the automated procedure.

Onsite Renewable Generation Time Shifting for Photovoltaic Systems

Subramanya, R., Aaltonen, H., Sierla, S., & Vyatkin, V. (2023). Onsite Renewable Generation Time Shifting for Photovoltaic Systems. teoksessa 2023 IEEE 32nd International Symposium on Industrial Electronics, ISIE 2023 – Proceedings (IEEE International Symposium on Industrial Electronics; Vuosikerta 2023-June). IEEE.

Abstract:

This paper examines the challenge of bidding a battery system on an electrical power market with varying prices. Optimizing bids for each market interval is a complex challenge since the bid size for one market interval affects the battery availability during several subsequent market intervals. In this paper, a renewable generation unit such as Photovoltaic (PV) and a battery storage are considered, with the battery used to shift electricity sales from low-price market intervals to high-price market intervals. The battery can also be used to smooth momentary fluctuations in generated power, cope with differences between actual and forecasted generation, and help to meet the maximum power limit constraint. This paper evaluates how to best manage the battery for optimal bidding in an electrical power market.

An ontology to support flow system descriptions from design to operation of buildings. Automation in Construction,

Kukkonen, V., Kücükavci, A., Seidenschnur, M., Rasmussen, M. H., Smith, K. M., & Hviid, C. A. (2022). An ontology to support flow system descriptions from design to operation of buildings. Automation in Construction, 134, [104067].

Abstract

The interoperability of information from design to operations is an acknowledged challenge in the fields of architecture, engineering and construction (AEC). As a potential solution to the interoperability issues, there has been increasing interest in how linked data and semantic web technologies can be used to establish an extendable data model. Semantic web ontologies have been developed for the AEC domain, but an ontology for describing the energy and mass flow between systems and components is missing. This study proposes the Flow Systems Ontology (FSO) for describing the composition of flow systems, and their mass and energy flows. Two example models are expressed using FSO vocabulary. SPARQL Protocol and RDF Query Language (SPARQL) queries are performed to further demonstrate and validate the ontology. The main contribution consists of developing FSO as an ontology complementary to the existing ontologies. Finally, the paper introduces a roadmap for future developments building on FSO.

Method for Using Information Models and Queries to Connect HVAC Analytics and Data. Journal of Computing in Civil Engineering

Kukkonen, V. (2023). Method for Using Information Models and Queries to Connect HVAC Analytics and Data. Journal of Computing in Civil Engineering Vol 37. No.6.

Abstract

A significant portion of the energy used in building operations is wasted due to faults and poor operation. Despite volumes of research, the real-world use of analytics applications utilizing the data available from building systems is limited. Mapping the data points from building systems to analytics applications outside the building systems and automation requires expert labor, and is often done in point-to-point integrations. This study proposes a novel method for using queryable information models to connect data points of building systems to a centralized analytics platform without requiring a particular modeling technology. The method is explained in detail through a software architecture and is further demonstrated by walking through an implementation of an example rule from a rule-based fault detection method for air handling units. In the demonstration, an air handling unit is modeled with two different approaches, and the example analytic is connected to both. The method is shown to support reusing analytic implementations between building systems modeled with different approaches, with limited assumptions of the information models.

Smart workplace solutions – can they deliver the offices that employees have been waiting for?

Remes, L., Dooley, K., Ketomäki, J. and Ihasalo, H. (2022), ”Smart workplace solutions – can they deliver the offices that employees have been waiting for?”, Facilities, Vol. 40 No. 15/16, pp. 40-53. 

Abstract

Purpose

User-centred intelligent buildings (IBs) should respond to users’ needs holistically and the demand for end user applications is steadily growing. The purpose of this study is to answer: What are end user applications, what should they be called, and what are their key features?

Design/methodology/approach

This is a mixed-method study. The authors have used different data sources, such as online research and interviews. In data processing, the authors have used word counting and Latent Dirichlet Allocation topic modeling.

Findings

These end user applications can provide the missing user-centered elements of IBs. The authors have found that “smart workplace solution” (SWS) is the best term to describe these applications, and they also describe the key features, which include booking, showing free spaces, occupancy tracking, wayfinding and searching.

Research limitations/implications

As the end user applications are constantly and rapidly evolving, the latest evolving of such applications might not be covered. Furthermore, the authors have relied on companies’ information as given.

Originality/value

IBs have emerged over 20 years ago, and these are the first solutions that can be considered truly user-centered.

Energy Efficiency in the ’Fit for 55’ Framework: Increasingly Ambitious Targets Coupled with Hardening Governance

Penttinen, S-L, Nippala, E., Kallioharju, K. Energy Efficiency in the ’Fit for 55’ Framework: Increasingly

Ambitious Targets Coupled with Hardening Governance. OGEL 1 (2022), in Energy

Abstaract
Energy efficiency has been progressively brought to the forefront to the EU’s decarbonization efforts. The EU’s efforts to develop an energy efficiency framework have traditionally relied on energy end-use reduction, but nowadays it seeks to promote a more integrated approach to energy efficiency in its energy policy framework. A key to this end is, in particular, the ’energy efficiency first’ principle that was first introduced by the EU’s Energy Union framework. The principle is envisaged as the fundamental principle on which the EU’s energy system should be built.

Verification of Energy Efficiency Measures in Three Apartment Buildings Using Gaussian Process

Uusitalo, S. (2022). Verification of Energy Efficiency Measures in Three Apartment Buildings Using Gaussian Process. CLIMA 2022 Conference.

Abstract

The aim of this work was to examine whether the Gaussian process as a machine learning method is suitable for modelling time series data collected from buildings and whether it can be used to verify the effects of energy efficiency measures on three apartment buildings. A Gaussian process regression model was created using outdoor temperature and time information as inputs including information about the day of the week and the hour of the current day. Correspondingly, the output of the model was to estimate the hourly heating power demand corresponding to these inputs. The results provided by the created model were used as a reference point to verify the effects of energy efficiency measures taken on these residential buildings. The model was trained with 2016 hourly data. The 2017 data was used as test data to evaluate the functionality of the model. The impact assessment of the energy efficiency measures was performed with the measured data of 2019, which was compared with the results given by the model. Based on the performed modelling, it can be stated that using the Gaussian process, the need for hourly power of buildings was reasonably well modelled with even small amount of input variables. It can be assumed that the biggest uncertainty factor in the modelling is related to the domestic hot water consumption and the resulting power requirement. By measuring hot water consumption, modelling accuracy could probably be significantly improved. Based on the reviews, it could also be verified that the energy efficiency measures taken have had an impact on the peak power needs of residential buildings as well as on total energy consumption. For all three buildings, peak power needs appear to have decreased and overall energy consumption is lower than it would have been without the actions taken.

Placement and utilization of CO2 measurements in the ventilation and occupancy assessments

Mäkinen, A., Mäkinen, A., Saari, S., Uusitalo, S., Juvela, J.-P., & Kakko, L. (2022). Placement and utilization of CO2 measurements in the ventilation and occupancy assessments. CLIMA 2022 Conference.

Abstract
Continuous carbon dioxide measurements have typically been used to adjust the demand-based ventilation. With the global COVID-19 pandemic, the use of measurements to ensure the functionality of ventilation and to assess the utilization rate of the space has increased in importance due to the significant impact of air exchange on the spread of the disease via aerosols. The work aimed to examine the spread of carbon dioxide in the room and how the location of the sensors and space users affects the measurement result. In our study, six carbon dioxide sensors were placed in the room that serves as a teaching restaurant. Five sensors were placed in the space itself and one sensor in the exhaust valve. Two meals were arranged, each attended by 10 people. The location of the persons in the space was also monitored. Based on the measurements, it was assessed how the air distribution of the space and the location of the users affected the measurement result of carbon dioxide. It was found that the carbon dioxide content measured close to diners differed from the result measured in the exhaust duct. Because the air in the exhaust duct is mixed with more fresh supply air than in the vicinity of the dining table, it can be thought that the concentration measured in the exhaust duct can indicate better the air variability of the whole space. On the other hand, sensors located closer to the seating area are potentially better positioned from the demand-based ventilation point of view. In the future, it will be necessary to study the issue in more detail for different types of premises and to examine the application of ventilation and space utilization assessment to real-time monitoring of the risk of airborne infectious diseases, for example.