De Rosa, Mattia

Thumbnail Image
Preferred name
De Rosa, Mattia
Official Name
De Rosa, Mattia

Research Output

Filters

3
Reset filters

Settings

Now showing 1 - 3 of 3
  • Publication
    Towards Robustness of Data-Driven Predictive Control for Building Energy Flexibility Applications
    (2020-09-22)
    Kathirgamanathan, Anjukan 
    ;
    De Rosa, Mattia 
    ;
    Mangina, Eleni 
    ;
    Finn, Donal 
    Identifying physics-based models of complex dynamical systems such as buildings is challenging for applications such as predictive and optimal control for demand side management in the smart grid. Data-driven predictive control using machine learning algorithms show promise as a more scalable solution when considering the greater building stock. The robustness of these algorithms for different climate data, building types, quality and quantity of data, is still not yet well understood. The objective in this study is to investigate model identification and the resultant accuracy for these various contexts using the `separation of variables' technique (DPC-En) and the consequent performance implications of the data-driven controller. The DPC-En controller is tested using a closed-loop simulation testbed of a `large office' archetype building. The results show that the technique is relatively robust to missing data and different climate types and delivers promising results using limited training data without the need for disruptive excitation measures. This work contributes to enabling a greater proportion of the diverse building stock to be utilised for demand side management by harnessing their inherent energy exibility potential.
      135
  • Publication
    Feature Assessment in Data-Driven Models for Unlocking Building Energy Flexibility
    (IBPSA, 2019-09-04)
    Kathirgamanathan, Anjukan 
    ;
    De Rosa, Mattia 
    ;
    Mangina, Eleni 
    ;
    Finn, Donal 
    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.
      323
  • Publication
    Towards Standardising Market-Independent Indicators for Quantifying Energy Flexibility in Buildings
    (Elsevier, 2020-08-01)
    Kathirgamanathan, Anjukan 
    ;
    Péan, Thibault 
    ;
    Zhang, Kun 
    ;
    De Rosa, Mattia 
    ;
    Salom, Jaume 
    ;
    Kummert, Michaël 
    ;
    Finn, Donal 
    Buildings are increasingly being seen as a potential source of energy flexibility to the smart grid as a form of demand side management. Indicators are required to quantify the energy flexibility available from buildings, enabling a basis for a contractual framework between the relevant stakeholders such as end users, aggregators and grid operators. In the literature, there is a lack of consensus and standardisation in terms of approaches and indicators for quantifying energy flexibility. In the present paper, current approaches are reviewed and the most recent and relevant market independent indicators are compared through analysis of four different case studies comprising varying building types, climates and control schemes to assess their robustness and applicability. Of the indicators compared, certain indicators are found to be more suitable for use by the end user when considering energy and carbon dioxide emission reductions. Other indicators are more useful for the grid operator. The recommended indicators are found to be robust to different demand response contexts, such as type of energy flexibility, control scheme, climate and building types. They capture the provided flexibility quantity, its shifting efficiency and rebound effect. A final cost index is also recommended given specific market conditions to capture the cost of a building providing energy flexibility.
      286Scopus© Citations 36