In order to enable smart manufacturing and smart collaborations in the coming industrial internet-of-things, or Industry 4.0, a key element is to be able to utilize smart services residing in the cloud. The challenge however, is that the applications, such as collaborating industrial robots, autonomous cars, etc. require a very low and predictable end-to-end latency. With the coming 5G technology standard part of this puzzle will be solved since it will allow for a low-latency wireless connection to/from the cloud.

Our research targets the problem of ensuring that we have a sufficiently low and predictable end-to-end latency within the cloud. For instance, if your robot wants to use a network of smart services such as machine learning inference, control loops, analytics, etc. we develop theory that allows these services to automatically scale in order to guarantee you the necessary end-to-end latency.

PhD Student at the Department of Control Theory since September 2014. From September 2018 until March 2019 I have been a visiting researcher at University of California, Berkeley in the USA.

Courses Taken

2017

• WASP Software for Systems Course (6 credits)
• WASP Project Course (6 credits)

2016

• Network Dynamics (7,5 credits)
• Control System Synthesis (10 credits)
• WASP Summer School (2 credits)
• WASP Autonomous Systems Course (6 credits)

2015

• Robust Control (9 credits)
• Introduction to Cloud Computing (10 credits)
• HIPEAC ACACES Summer School (2 credits)
• Programming Big Data (7,5 credits)
• Julia for Scientific Computation (5 credits)
• Introduction to Teaching and Learning in Higher Education (3 credits)

2014

• Introduction Course for new PhD Students (2 credits)
• System Identification (7,5 credits)
• Linear Systems (9 credits)

2018

• Real-Time Systems

2017

• Real-Time Systems
• Applied Robotics

2016

• Real-Time Systems
• Network Dynamics
• Applied Robotics

2015

• Introduction to Cloud Computing (PhD course)

2014

• Automatic Control, Basic Course
• Real-Time Systems