3 dagen geleden - Radboud Universiteit (RU) - Nijmegen
PhD position: Enriching energy system measurements for machine learning applications
Develop methods that enable machine learning for energy system to reach the next level, as part of a European Innovative Training Network.
- Mekelweg, Delft, Zuid-Holland
- Tijdelijk contract / Tijdelijke opdracht
- Uren per week:
- 36 - 40 uur
- € 2434 - € 3111 per maand
InnoCyPES, a European Innovative Training Networks (ITN), funded under H2020 Marie Skłodowska-Curie Actions (MSCA), is recruiting talented, enthusiastic, and ambitious candidates to perform excellent research and achieve breakthroughs in the field of cyber-physical energy systems. InnoCyPES targets the bottlenecks of digital transformation of the current energy system, where the ESRs are expected to study and improve various facets of digitalized and interconnected energy systems. 15 Early-Stage Researchers (ESRs) will enroll in PhD programmes in the InnoCyPES network, consisting of 7 academic and 4 industrial beneficiaries, together with 10 partner organizations. (more info: https://cordis.europa.eu/project/id/956433)
Within the InnoCyPES network, Delft University of Technology is hiring a doctoral candidate on the subject “Enriching energy system measurements for machine learning applications.” This vacancy is only suitable for early-stage researchers that have not lived in the Netherlands for more than 12 months during the previous 3 years (see requirements).
The aim of this project is to develop methods for interpolation, imputation and augmentation of energy system measurements using a combination of machine learning and physical system knowledge. Electrical networks are used as a motivating case, tackling the following challenges:
- Different sampling rates and data dropouts. Whereas PMUs or waveform monitoring systems measure electrical properties at a rate of many kHz, smart meters may report values only once every 30 minutes. Interpolation and imputation are required to generate synchronized pseudo-observations, subject to uncertainty;
- Non-alignment of timestamps. High-end measurement devices have GPS-synchronized clocks, but that is often not the case for low-cost infrastructure;
- Limited availability of training data. Machine learning algorithms usually benefit from large training datasets, but the number of available measurements may be limited or subject to confidentiality. Deep learning approaches such as Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs) will be used to learn salient properties of data and generate virtual measurements with similar statistical properties.
The methods developed will be combined into a flexible, open-source data preprocessing library.
The position includes two scheduled secondments:
- DEPsys, Switzerland (4 months)
- University of Salento, Italy (4 months)
This is a four-year doctoral appointment. You will be jointly supervised by Dr. Simon Tindemans (assistant professor, daily supervisor) and Prof. Peter Palensky (head of group), with industrial co-supervision from Dr. Omid Alizadeh-Mousavi (DEPsys). You will be a member of the section Intelligent Electrical Power Grids in the Faculty of Electrical Engineering, Mathematics and Computer Science. You will join a larger team of researchers and students working on AI/machine learning for energy systems.
All InnoCyPES ESRs will benefit from extensive training in technical and transferrable skills, and from interdisciplinary, international and intersectoral secondment experience. You will be expected to assist in teaching activities (student supervision, labs) related to your subject area. The anticipated start date is between 1 September 2021 and 1 November 2021.
As a condition of the grant, applicants must satisfy the following conditions,
- Early-stage researchers: Applicants must be early-stage researchers, which means at the date of start, be in the first four years (full-time equivalent research experience) of their research careers and have not been awarded a doctoral degree.
- Mobility Rule: researchers must not have resided or carried out their main activity (work, studies, etc.) in the country of the host institute for more than 12 months in the 3 years immediately before the recruitment date. Compulsory national service, short stays such as holidays, and time spent as part of a procedure for obtaining refugee status under the Geneva Convention1 are not taken into account. For international European interest organisations, international organisations, the European Commission's Joint Research Centre (JRC) or an 'entity created under Union law', recruited researchers must not have spent more than 12 months in the 3 years immediately before the recruitment date at the same appointing organisation.
Essential job requirements:
- Demonstrable interest in interdisciplinary and intersectoral research, and specifically the interface between energy systems, computer science and control.
- Completed a Master's degree or equivalent in a highly quantitative and analytical discipline (applied mathematics, physics, computer science, electrical engineering, etc.)
- Excellent academic record (grades of B or higher) and good command of English (minimum C1 or equivalent).
- Good intuition for probability and statistics, and an ability to read and critically analyse computer science/mathematics papers.
- You enjoy performing research. You are independent, self-motivated and eager to learn.
- You enjoy programming and hold your code to a high standard.
- Knowledge of measurement and control of electrical power systems.
- Experience with Python and machine learning libraries.
- Experience with collaborative software development (e.g. open source).
TU Delft offers PhD-candidates a 4-year contract, with an official go/no go progress assessment after one year. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2395 per month in the first year to € 3061 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.
The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.
For more information about this vacancy, please contact Simon Tindemans, assistant professor, email: firstname.lastname@example.org, tel: +31(0)15-2784487.
For information about the selection procedure, please contact Carla Jager, Secretary, IEPG group, email: email@example.com.