General information
Type: Semester/Master project
Period: Start : Feb 2021 or as soon as possible
Project directors: Prof. François Maréchal (IPESE-EPFL)
Assistants: Ermanno Lo Cascio (IPESE-EPFL)
Background
The concept of distributed computing (fog computing) has been recently proposed as an architectural shift in the service provides’ networks in order to support 5G killing applications, such as augmented reality and Industry 4.0, among others [1]
Distributed computing introduces a distributed processing capability close to end users. Energy consumption is a matter of concern in such a system with a large number of computing nodes. Renewable energy sources can be utilized to lessen the burden on the main power grid and reduce the carbon footprint, but due to fluctuations, the effective utilization of renewable energy sources needs proper resource management [2].
For this project, the candidate will be involved in the definition/improvement of a modeling and optimization framework with a specific focus of identifying integration strategies between ICT services and building energy systems.
Project Description
The project will be developed by employing a bottom-up approach. Thus, starting from a case-study, a generalized system integration strategy will be outlined.
To this aim, the candidate will proceed through three main study phases :
- Typification and categorization of ICT (fog) hardware and services: the goal of this phase is to outline a database of the elements of state-of-the-art cloud and fog/edge computing infrastructures. This database will report the current types and characteristics of computing tasks and services, along with basic information about the energy required by the common hardware constituting a data center for different services.
- Identify possible integration strategies that enable synergic cloud services delivery & renewable energy availability and building energy services; i.e. define an optimization problem and run test cases.
- Extrapolate generalized results.
Requirements
- Energy conversion systems knowledge (EPFL courses: Thermo I/II, Energy Conversion, or equivalent) .
- MILP Optimization.
- Programming skills: Matlab, Matlab-Simulink ; Other programming languages.
Other soft skills that are highly appreciated
- Motivation, autonomy and self-organization.
- Ability to communicate results, especially in written form
How to apply
If interested, please take contact with Ermanno Lo Cascio, e-mail: [email protected] attaching your CV and Cover Letter.
Practical information
The IPESE laboratory is located in the Sion EPFL campus. Travels from Lausanne to Sion are compensated by EPFL.
References
[1] Y. Yang, S. Zhao, W. Zhang, Y. Chen, X. Luo and J. Wang, “DEBTS: Delay energy balanced task scheduling in homogeneous fog networks”, IEEE Internet Things J., vol. 5, no. 3, pp. 2094-2106, Jun. 2018.
[2] Karimiafshar, Aref, et al. “Effective utilization of renewable energy sources in fog computing environment via frequency and modulation level scaling.” IEEE Internet of Things Journal 7.11 (2020): 10912-10921.
[3] Li, Wei, et al. “On enabling sustainable edge computing with renewable energy resources.” IEEE Communications Magazine 56.5 (2018): 94-101.
[4] Munir, Md Shirajum, et al. “When edge computing meets microgrid: A deep reinforcement learning approach.” IEEE Internet of Things Journal 6.5 (2019): 7360-7374.