Thesis Work for Prediction of CPU usage in embedded device using ML techniques hos Hitachi ABB Power Grids

Intelligent Electronic Devices (IEDs) are CPU-based embedded devices essential for power grids. These devices collect data from the grid, e.g., current and voltage, to integrate a multitude of fault-detection mechanisms to maximize grid availability. For example, modern IEDs implement functions such as differential current or time overcurrent protection that operators can configure to locate and isolate faulty sections of the grid. Given the vastly varying needs of power grid operators, several IEDs at different price points and CPU capabilities are presented to the customer to help them reduce operating costs. However, an operator might create a heavy configuration that exceeds the CPU capabilities of some less potent IEDs. Currently, such cases are only identified once the IED is in operation and begins to exhibit erratic behaviour. The purpose of this thesis is to find a way to identify if the IED has enough CPU power to execute a given configuration. As the number of possible configurations is too large to categorize, a proposed solution is to predict, before execution, if the operator configuration can be executed or not in its IED. Details: • 30 ECTS credits. • One student. • Thesis work must be done partly in Västerås.

Your responsibilities

  • Identify which are the important factors and variables in a configuration to predict the CPU usage.
  • Predict using a machine learning model if a given configuration can be executed or not in a specific IED.
  • Study and evaluate a continuous learning approach that evolves from the operator new configurations.
  • Research different methods to accelerate predictions.

Your background

  • Currently pursuing a M.S. degree in engineering or similar M.S. degree
  • Strong interpersonal skills good communication skills and quick learner
  • Good oral and written English

Experience in one or several of the fields:

  • Intelligent Systems
  • Machine Learning
  • Python
  • Scripting and Data Manipulation

More about us

Positions are filled continuously. Apply with your CV, academic transcripts and a cover letter in English. Welcome to apply! More information: Recruiting Manager Johan Lundberg, +46 107-38 50 34 and Thesis Supervisor Francisco Pozo, +46 765-61 67 96, will answer your questions. Union representatives - Sveriges Ingenjörer: Stefan Andersson, +46 107-38 08 21, Unionen: Karin Ulvemark, +46 107-38 51 42, Ledarna: Lenny Larsson, +46 21-32 85 47. Any other questions please contact, Talent Acquisition Specialist Angelica From, +46 107-38 00 43. Hitachi ABB Power Grids is a global technology leader with a combined heritage of almost 250 years, employing around 36,000 people in 90 countries. Headquartered in Switzerland, the business serves utility, industry and infrastructure customers across the value chain, and emerging areas like sustainable mobility, smart cities, energy storage and data centres. With a proven track record, global footprint and unparalleled installed base, Hitachi ABB Power Grids balances social, environmental and economic values, and is committed to powering good for a sustainable energy future, with pioneering and digital technologies, as the partner of choice for enabling a stronger, smarter and greener grid. www.hitachiabb-powergrids.com #LI-NEU1

Observera: De examensarbete och projekt som du hittar i Graduateland är inte på förväg godkända av ditt universitet. Du måste själv se till att de eventuella samarbeten som du ingår med organisationer för examensarbete och projekt blir godkända av din handledare eller kursansvarig.