MS thesis and internship
MS thesis proposals
Benchmarking of adaptive control strategies of HVAC systems in a dynamic co-simulation environment |
---|
Topic: Automated System Optimization (ASO) & "Clash" of advanced control strategies in energy and buildings |
Description: In the last few years, many research activities are aimed at exploring strategies for simultaneously optimizing indoor environmental quality and energy demand through multi-objectives and quasi-real time control procedures based on forecasting and online analytics. Adaptive and predictive optimal control provides powerful opportunities for leveraging building properties (e.g. thermal mass, storage, renewable energy sources) to enhance energy flexibility during operation. However, a robust benchmarking of these control strategies against other known techniques remain an open issue to address. |
Tutors: Capozzoli Alfonso, Brandi Silvio Apply here |
Control to respond: Demand response in districts of buildings by means of adaptive controls |
---|
Topic: Automated System Optimization (ASO) & 3DEM: Data Driven Dristrict Energy Management |
Description: Building energy management can enable energy flexibility by enhancing on-site renewable energy exploitation and storage operation, reducing energy costs, and providing services to the grid (i.e., load shifting, peak shaving). However, when the energy management is faced shifting from a single building to a district of buildings, individual demand-side management may have negative effects on the grid reliability, like the peak “rebound” issue. Moreover, uncoordinated management could cause undesirable new peaks or lead to suboptimal solutions to the grid. To overcome these limitations, coordinated energy management takes advantage of the mutual collaboration between single buildings to provide services to the grid (Demand Response). In this context, adaptive and predictive control strategy may provide great benefits with respect to a more common control strategy. In this perspective, the thesis project aims at exploring the opportunity to integrate demand response programs to the coordinated energy management paradigm, demonstrating the feasibility of data-driven control strategies. |
Tutors: Capozzoli Alfonso, Apply here |
Advanced control strategies for improving occupant comfort and energy performance by means of dynamic facades (internship + thesis) |
---|
Topic: ASO (Automated System Optimisation) & ICARE: Intelligent Control for Active and Responsive Envelope |
Description: Dynamic building envelope components, if properly integrated and operated, can significantly contribute towards the achievement of decarbonization targets while maintaining high levels of environmental comfort in the built environment (thermal, daylight, aural comfort and IAQ) . The improvement of everchanging building performance targets, though, is highly dependent on the control strategies adopted. Rule Based Controllers are by far the most adopted control option in the market, due to their easy implementation, nevertheless more advanced control strategies could maximise multiple performance objective considering both energy use and occupant comfort. The aim of this internship and thesis work is to understand: i) issues of implementing control strategies on real building and test facilities; ii) get experience of online measurements, data acquisition systems and single board controllers; iii) investigate advanced and rule based control strategies; iv) test and evaluate (by means of real and virtual experiments and simulations) alternative control strategies for dynamic building envelope components. It is strongly suggested willigness to program in Python, some basic knowledge of Python, Matlab and Energyplus. |
Tutors: Favoino Fabio, Capozzoli Alfonso Apply here |
Exploiting data analytics-based processes for detecting and diagnosing the occurrence of faults in HVAC systems |
---|
Topic: Decision Support systems for building energy management & Fault Detection and Diagnosis (FDD) in building energy systems |
Description: Recent years have seen an increasing interest of the scientific community in exploring solutions to improve energy efficiency in buildings by implementing advanced data-analytics based energy management strategies. According to the literature, around 20% of energy consumption in buildings is attributable to incorrect system configurations and inappropriate operating procedures that can be effectively detected through automatic analytics processes. Due to lack of proper maintenance, failure of components or incorrect installation, building systems are frequently run in faulty conditions where a fault is intended as an unpermitted deviation of at least one characteristic property of the system from the acceptable, usual, standard condition. The objective behind Fault detection and diagnosis (FDD) is twofold. On one hand fault detection consists in the recognition of a fault occurrence, and on the other hand fault diagnosis corresponds to the identification of the causes and the location of the fault. In this perspective the thesis project aims at contributing to the FDD research field demonstrating the high contribution that data analytics methodologies can bring. |
Tutors: Capozzoli Alfonso, Piscitelli Marco Savino Apply here |
Characterization of occupant behaviour in buildings through data analytics techniques |
---|
Topic: Decision Support systems for building energy management |
Description: Occupant behaviour is one of the major factors influencing building energy consumption and introducing sources of uncertainty in building energy use prediction and simulation. Currently the exploitation and characterization of occupant-related data in buildings is insufficient thus limiting opportunities of building design optimizations and energy management improvements. Occupant behaviour is associated with various actions that have a direct or indirect impact upon building energy consumption such as adjustment of thermostat settings, opening and closing of windows, dimming and switching of lights, use of blinds, turning on/off of HVAC systems, presence and movement in building spaces. Quantifying the effect of occupant behaviour on building energy consumption and the potential energy saving achievable through its modification remain primary challenges. In this perspective the thesis project aims at defining a systematic approach for the analysis of occupant-related data that can support the robust identification of typical and infrequent behaviours of occupants in buildings. |
Tutors: Capozzoli Alfonso, Piscitelli Marco Savino Apply here |
Development of a data analytics-based EIS tool for the automatic recognition of anomalous energy consumption patterns in buildings |
---|
Topic: Decision Support systems for building energy management & Detection and diagnosis of anomalous energy consumption patterns in buildings |
Description: Differently from other kinds of energy management DSS tools, EISs read data at meter-level, analyse them and provide informative outputs to a human user (e.g., energy manager, building owner, energy service company).Advanced EISs not only allow new forms of building energy management to be pursued but at the same time significantly reduce the complexity of performance commissioning in existing buildings. According to the Building Commissioning Association (BCA) Existing Building Commissioning (EBCx) is defined as a systematic process aimed at improving the performance of buildings and energy systems by means of low/no cost and capital-intensive measures and ensuring their effect persists over time. Advanced EISs are today capable to enhance such process (i.e., building commissioning) and it is mainly due to the exploitation of data analytics methods. The main objective of this Thesis project is to conceive a methodological framework of analysis that allows the final user to gain insights into energy consumption time series at whole building level and then to enable the identification of incorrect energy management procedures that are responsible of energy wasting during operation. The methodology will exploit time series analytics techniques and automatic pattern recognition methods for developing a framework that can be embedded in a EIS. The case study that will be considered is the campus of Politecnico di Torino. |
Tutors: Capozzoli Alfonso, Piscitelli Marco Savino Apply here |
Current internships and MS students
- Buscemi Giacomo, Development of energy data analytics processes for both control and characterization of HVAC system operation (internship in collaboration with BELIMO Italia s.r.l.)
- Alessandro Carrieri, Development of occupant centric energy information dashboards to enhance energy efficiency in buildings (internship in collaboration with FORWARDINNOVATION s.r.l.)
- Simone Deho', Development of advanced data preprocessing modules for energy data analytics dashboards (internship at DENERG)
- Riccardo Messina, Advanced control strategies in cluster of buildings for enabling demand side management (internship at DENERG)
- Simone Vitale, Anomaly detection in building energy consumption through advanced pattern recognition techniques (internship at DENERG)
- Maria Teresa Zitelli, Census of the monitoring infrastructure installed at PoliTo and development of an open energy information dashboard (internship at DENERG)
- Davide Taddei, A cloud-based Energy Information System (EIS) for innovative energy management in buildings: the case of Politecnico di Torino (MS Thesis)
- Laura Modica, Development of Al-based models for the estimation of building energy demand in energy communities and for the optimization of the energy management (MS Thesis)
Former MS students
The Master students that carried out their thesis project at BAEDA Lab have conducted relevant research in the field of building energy management and AI. Many of them are currently working in universities, research centers and companies leader in the energy sector.
Student |
Thesis title |
Supervisors |
Maria Teresa Zitelli |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2022 |
|
Riccardo Messina |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2022 |
|
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2022 |
||
Simone Vitale |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2022 |
|
Davide Bruno Morciano |
Politecnico di Torino, MSc degree program in Mathematical Engineering, 2021 |
|
Simone Deho' |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2021 |
|
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2021 |
||
Garcia Navarro Alberto Manuel |
Politecnico di Torino, MSc degree program in Petroleum And Mining Engineering, 2021 |
Rocca Vera, Capozzoli Alfonso, Perini Luisa |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2021 |
||
Luca Sandri |
Politecnico di Torino, MSc degree program in in building Engineering, 2021 |
Capozzoli Alfonso, Brandi Silvio, Piscitelli Marco Savino, Favoino Fabio |
Dipierro Noemi |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2021 |
|
Borello Davide |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2020 |
|
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2020 |
||
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2020 |
||
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2020 |
||
Gennaro Giovanni |
Politecnico di Torino, MSc degree program in Management Engineering, 2019 |
|
Nasso Andrea |
Politecnico di Torino, MSc degree program in Management Engineering, 2019 |
Cerquitelli Tania, Capozzoli Alfonso |
|
Politecnico di Torino, MSc degree program in Management Engineering, 2019 |
Savoldi Laura, Capozzoli Alfonso. |
Olivotto Claudia |
Politecnico di Torino, MSc degree program in Architecture for Sustainability Design, 2018 |
|
Chiabrera Edoardo |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2018 |
|
Pinto Mariachiara |
Politecnico di Torino, MSc degree program in building Engineering, 2018 |
Capozzoli Alfonso, Piscitelli Marco Savino, Brandi Silvio,Vincenzo Gentile |
Mazzarelli Daniele Mauro |
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2018 |
|
Fabbro Francesco |
Politecnico di Torino, MSc degree program in Architecture for Sustainability Design, 2018 |
Capozzoli Alfonso, Fabi Valentina, Spigliantini Giorgia |
Novelli Alessandra |
Politecnico di Torino, MSc degree program in building Engineering, 2017 |
|
Politecnico di Torino, MSc degree program in Energy and Nuclear Engineering, 2016 |
||
De Luca Giovanna |
Politecnico di Torino, MSc degree program in Architecture for Sustainability Design, 2016 |
Capozzoli Alfonso, Corrado Vincenzo, Gorrino Alice |
Crosasso Cristina |
Politecnico di Torino, MSc degree program in Architecture for Sustainability Design, 2016 |
|
Roccasalva Giulia, Sabatini Federica |
Politecnico di Torino, MSc degree program in Architecture for Sustainability Design, 2015 |
Capozzoli Alfonso, Pizzuti Stefano, Romano Silvia |
Cuocci Ornella |
Politecnico di Torino, MSc degree program in building Engineering, 2015 |
Capozzoli Alfonso, Serale Gianluca |
Politecnico di Torino, MSc degree program in building Engineering, 2014 |
Capozzoli Alfonso, Serale Gianluca |
|
Grassi Daniele |
Politecnico di Torino, MSc degree program in building Engineering, 2014 |
Capozzoli Alfonso, Mutani Guglielmina |
Tolardo Mariachiara |
Politecnico di Torino, MSc degree program in building Engineering, 2014 |
Capozzoli Alfonso, Corgnati Stefano Paolo |