-
ORGANISATION/COMPANYAramis s.r.l.
-
RESEARCH FIELDEngineering › Industrial engineering
-
RESEARCHER PROFILEFirst Stage Researcher (R1)
-
APPLICATION DEADLINE13/01/2022 22:00 - Europe/Brussels
-
LOCATIONItaly › Milano
-
TYPE OF CONTRACTTemporary
-
JOB STATUSFull-time
-
HOURS PER WEEK40
-
EU RESEARCH FRAMEWORK PROGRAMMEH2020 / Marie Skłodowska-Curie Actions
-
REFERENCE NUMBERGreydient
-
MARIE CURIE GRANT AGREEMENT NUMBER955393
OFFER DESCRIPTION
Within the European Union’s Horizon 2020 research and innovation programme under Marie Sklodowska-Curie project GREYDIENT (https://www.greydient.eu/), we are hiring an of Early Stage Researchers (ESR 7) to develop a methodology to estimate the reliability and availability of energy-grid systems including components equipped with Prognostics and Health Management (PHM) capabilities. First, ESR 7 will model the effect of condition monitoring on the reliability and availability of the single components, assisted by virtual sensors that capture unmeasurable quantities based on measurable quantities and a white-box model of the component. Then, the effect of this change in reliability at the subsystems and network levels is propagated to the grid level, considering mutual dependencies of the components (e.g., via copula theory). Based on these developments, ESR 7 will map hybrid physical-virtual condition monitoring solutions (i.e., results of virtual sensors) to global performance metrics of the network, with corresponding uncertainties making it possible to maximize grid resilience vs. investment cost by optimally selecting portfolios of sensors on the grid elements. Finally, ESR 7 will model and optimize the Operations & Maintenance (O&M) costs of the grid by considering mutual relationships existing between the O&M decisions taken to manage variable energy demand and production, stochastic degradation and failure behaviour of the network elements and, finally, the uncertain information retrievable from PHM. This will be obtained by considering the problem as a sequential decision problem over a long horizon and employing Deep Reinforcement Learning approaches, trained by a white-box model of the network, that encode the stochastic behaviour of renewable energy production and energy demand, and the uncertainty in the sensor signal values.
The ESR will be enrolled at the PhD school of Politecnico di Milano (Italy), and will be supervised by Prof. E. Zio, P. Baraldi, F. Di Maio from Politecnico di Milano, by Prof. M. Beer from LEIBNIZ UNIVERSITAET HANNOVER as external co-supervisor, and by Dr. M. Compare from ARAMIS as Non-university co-supervisor.
More Information
Offer Requirements
-
REQUIRED EDUCATION LEVELEngineering: Master Degree or equivalent
-
REQUIRED LANGUAGESITALIAN: Basic
Skills/Qualifications
The ESR will have a sound mathematical background, which is necessary to formalize and develop the stochastic models at the basis of the optimization algorithms. This must be integrated with knowledge about grid modeling and simulation.
Excellent knowledge of Machine Learning techniques (e.g., Reinforcement Learning, Artificial Neural Networks) completes the ideal ESR profile.
EURAXESS offer ID: 718744
Disclaimer:
The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.
Please contact support@euraxess.org if you wish to download all jobs in XML.