Dela med andra

Prediction of CPU usage in embedded device using Machine Learning techniques

Publicerad 2020-10-09

Om uppdragsgivaren
Hitachi ABB Power Grids is a pioneering technology leader.
Our leading power and digital technologies, advanced automation systems and open digital platforms transform our customers’ businesses and deliver significant operational and business value.
Only through the effective digitalization of all elements of the energy value chain can this be delivered. At Hitachi ABB Power Grids we use leading open digital platforms to bring our grids into the age of the sustainable energy future.

We are contributing pioneering solutions that are making the world’s power grids stronger, smarter and greener. The result is grids that are more reliable, intelligent and focused on a sustainable energy future for all. Through Hitachi ABB Power Grids’ advanced portfolio of sustainable, digital energy solutions, we will create even more value for customers spanning the energy utilities and industry sectors, to mobility, IT and Life Cities sectors.

Beskrivning av examensarbetet
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, some cases of
overload are not detected before testing preparing for commissioning.
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 configurations are too large to categorize, a proposed solution is to predict, before
execution, if the operator configuration can be executed or not in its IED. Your tasks will be to:
• Identify which are the crucial factors and variables in a configuration to predict the CPU usage.
• Analyze the problem to understand characteristics needed for test and validation of data sets.
• Predict using a machine learning model if a given configuration can be executed or not in a specific
• Study and evaluate a continuous learning approach that evolves from collected data from user configurations.
• Research different methods to accelerate predictions.

Francisco Pozo


Hitachi ABB Power Grids


Sista ansökningdag

Thesis Description
Hitachi ABB Power Gr

Bookmark and Share