Now showing 1 - 10 of 34
  • Publication
    TRUSS Training in Reducing Uncertainty in Structural Safety: D5.2 Final Report: WP5 - Rail and Road Infrastructure
    This deliverable reports on the outputs of eight Early Stage Researchers (ESR7-ESR14) in work package, WP5 (Rail and Road Infrastructure), under the supervision of academic and industrial experts during the three years of their projects within the EU TRUSS (Training in Reducing Uncertainty in Structural Safety, 2015-2018) Innovative Training Network (ITN) programme ( Two types of infrastructure are analysed in WP5: bridges (ESR7-ESR12) and pavements (ESR13-ESR14). The first six projects aim to reduce uncertainty in bridge safety. They address areas of work such as bridge condition assessment (ESR7), probabilistic modelling of bridge damage using damage indicators (ESR8), railway bridge condition monitoring and fault diagnostics (ESR9), condition assessment based on measured vibration level (ESR10), the use of optical fibre distributed sensing for monitoring (ESR11), and the use of displacement and velocity measurements for damage localisation (ESR12). The last two projects are on uncertainty in pavement safety, where ESR13 considers the use of truck sensors for road pavement performance and asset management and ESR14 investigates the possibility of using unmanned aerial vehicles and photogrammetry method for road and bridge inspections. Generally, the areas of work developed in this work package are vehicle-infrastructure interaction, traffic load modelling, road materials, uncertainty modelling, reliability analysis, field measurement and Structural Health Monitoring (SHM) of bridges.
  • Publication
    Quantifying the scalability of reduced-order grey-box energy models for commercial building stock modeling
    Grey-box models are extensively employed in building energy simulations. However, the grey-box approach often leads to application and stakeholder specific models, for instance, the design approach of greybox modeling for commercial buildings differs on a case by case basis. Often, the network order limits the scalability of these networks. Reduced-order grey-box modeling approaches counter these limitations by achieving a trade off between model complexity and desired accuracy. This study, therefore, formulates a generalized methodology to quantify scalability associated with reduced-order grey-box models for heat demand modeling of commercial buildings. The devised methodology assesses model scalability through (1) scalability feature-definition, (2) model identification, (3) multi-level modeling and (4) KPI identification procedures. This study formulates a test-case of 10 buildings (on university campus) with varied operations to implement the devised methodology. Results indicate that model scalability directly associates with the nature of building operation. Furthermore, similar zone variables can effectively represent an entire building provided that the considered zone pre-dominantly occupies majority of the building’s indoor space.
  • Publication
    Evaluation of Machine Learning Algorithms for Demand Response Potential Forecasting
    This paper focuses on the ability of machine learning algorithms to capture the demand response (DR) potential when forecasting the electrical demand of a commercial building. An actual sports-entertainment centre is utilised as a testbed, simulated with EnergyPlus, and the strategy followed during the DR event is the modification of the chiller water temperature of the cooling system. An artificial neural network (ANN) and a support vector machine (SVM) predictive model, are utilised to predict the DR potential of the building, due to the significant amount of execution time of the EnergyPlus model. The data-driven models are trained and tested based on synthetic databases. Results demonstrate that both ANN and SVM models can accurately predict the building electrical power demand for the scenarios without or with daily DR events, whereas both predictive models are not accurate in forecasting the electrical demand during the rebound effect.
  • Publication
    Assessing the effect of network order on epistemic uncertainty quantification for reduced-order grey-box energy models
    Grey-box building energy models are becoming extremely popular for modeling building thermal energy performance and subsequently evaluating base case energy consumption, establishing efficiency scenarios, implementing model predictive control and forecasting building thermal behavior. Energy simulation inputs and model parameters in such models introduce uncertainty and hence, highly affect the accuracy and reliability of energy simulation results. Furthermore, increasing the reduced-order model complexity eventually increases the epistemic uncertainty (lack of knowledge) in energy simulation results due to an associated increase in number of model parameters. Existing studies often provide disintegrated analysis of model complexity, accuracy and uncertainty when implementing reduced-order grey-box models. This study proposes a framework to create reduced-order grey-box energy models and henceforth, quantify and analyze the effect of epistemic uncertainties through variation of network order. The devised framework further enables the identification of a balance between network complexity, accuracy and model uncertainty. A strong relationship exists between network order and model parameter uncertainty. Increasing the model complexity has no significant effect on model accuracy (CVRMSE reduces from 3.65% to 2.55%). The epistemic spread of uncertainties increases by a significant amount (~ 10%).
  • Publication
    Feature Assessment in Data-Driven Models for Unlocking Building Energy Flexibility
    Data-driven approaches are playing an increased role in building automation. This can, in part, be attributed to building operation and energy management system data becoming more readily accessible. A particular application is models to allow predictive control harnessing building energy flexibility, which is of interest to different stakeholders including; energy utilities, aggregators and end-users. Given the possibility of thousands of data features, feature selection becomes a critical part of the model development process. This paper considers various filter, wrapper and embedded methods applied in conjunction with three predictors in addressing the problem of constructing a suitable data-driven model to facilitate predictive control and provision of energy flexibility in a large commercial building. The feature selection algorithms are generally shown to significantly reduce model evaluation time and, in some cases, increase model accuracy. A random forest model with embedded feature selection was found to be the optimal solution in terms of model accuracy.
  • Publication
    Data-Driven Predictive Control for Commercial Buildings with Multiple Energy Flexibility Sources
    Data-Driven Predictive Control, representing the building as a cyber-physical system, shows promising potential in harnessing energy flexibility for demand side management, where the efforts in developing a physics-based model can be significant. Here, predictive control using random forests is applied in a case study closed-loop simulation of a large office building with multiple energy flexibility sources, thereby testing the suitability of the technique for such buildings. Further, consideration is given to the feature selection and feature engineering process. The results show that the data-driven predictive control, under a dynamic grid signal, is capable of minimising energy consumption or energy cost.
  • Publication
    Application Of Intelligent Algorithms For Residential Building Energy Performance Rating Prediction
    Energy Performance Certificates (EPC) provide an indication of buildings’ energy use. The creation of an EPC for individual building requires information surveys. Hence, these ratings are typically non-existent for entire building stock. This paper addresses these information gaps using machine-learning models. Developed models were evaluated with Irish EPC data that included approximately 650,000 residential buildings with 199 inputs variables. Results indicate that the deep learning algorithm produces results with highest accuracy level of 88% when only 82 input variables are available. This identified approach will allow stakeholders such as authorities, policy makers and urban-planners to determine the EPC rating for the rest of the building stock using limited data.
  • Publication
    An Intelligent Knowledge-based Energy Retrofit Recommendation System for Residential Buildings at an Urban Scale
    Buildings play a significant role in driving the urban demand and supply of energy. Research conducted in the urban buildings sector indicates that there is a considerable potential to achieve significant reductions in energy consumption and greenhouse gas emissions. These reductions are possible through retrofitting existing buildings into more efficient and sustainable buildings. Building retrofitting poses a huge challenge for owners and city planners because they usually lack expertise and resources to identify and evaluate cost-effective energy retrofit strategies. This paper proposes a new methodology based on machine learning algorithms to develop an intelligent knowledge-based recommendation system which has the ability to recommend energy retrofit measures. The proposed methodology is based on the following four steps: archetypes development, knowledge-base development, recommendation system development and building retrofitting or performance analysis. A case study of Irish buildings dataset shows that the proposed system can provide effective energy retrofits recommendation and improve building energy performance.
  • Publication
    A Generic Energy Flexibility Evaluation Framework to Characterise the Demand Response Potential of Residential Buildings
    Demand response can enable residential consumers to take advantage of control signals and/or financial incentives to adjust the use of their resources at strategic times. These resources usually refer to energy consumption, locally distributed electricity generation, and energy storage. The building structural mass has an inherent potential either to modify consumption or to be used as a storage medium. In this paper, the energy flexibility potential of a residential building thermal mass for the winter design day is investigated. Various active demand response strategies are assessed using two flexibility indicators: the storage efficiency and storage capacity. Using simulation, it is shown that the available capacity and efficiency associated with active demand response actions depend on thermostat setpoint modulation, demand response event duration, heating system rated power and current consumption.