I am currently a PhD candidate at Uppsala University in Sweden. My research interests are broad but are mainly focused around anything that makes use of a network (wireless or wired). I received MSc. in distributed systems at KTH Stockholm, where I also worked as research assistant at NSLab lead by Prof. Dejan Kostic. Furthermore, I also worked as research engineer at Ericsson Research in Stockholm Kista.
At the beginning of my graduate studies I explored how to improve the quality of information delivered by Internet of Things systems with respect to smart factories and large-scale applications. This branch of research, achieved in cooperation with my supervisors Prof. Per Gunningberg and Prof. Christian Rohner, lead to high appreciation and publication in a top-tiered conference like IEEE INFOCOM and workshop co-located with the prestigious conference ACM PODC.
In the second half of my PhD journey I visited and started collaboration with University of Helsinki at CoNe group, lead by Prof. Jussi Kangasharju. I then started investigating the real benefits that edge computing could bring to the end users, and how it differs from the canonical cloud computing paradigm. We are trying to do so by extensive Internet measurements through the whole world by using RIPE Atlas and Speedchecker, that we warmly thank for their support. Our first measurements study will be published at ACM HotNets 2020. I additionally started collaboration with Dr. Ambuj Varshney where we research ultra-low power backscatter system and our battery-free tunnel diode based carrier emitter work is to be published in the flagship conference for mobile computing ACM MobiCom 2020.
Pruning Edge Research with Latency Shears Nitinder Mohan, Lorenzo Corneo, Aleksandr Zavodovski, Suzan Bayhan, Walter Wong and Jussi Kangasharju ACM HotNets, 2020, Chicago, Illinois, USA
Edge computing has gained attention from both academia and industry by pursuing two significant challenges: 1) moving latency critical services closer to the users, 2) saving network bandwidth by aggregating large flows before sending them to the cloud. While the rationale appeared sound at its inception almost a decade ago, several current trends are impacting it. Clouds have spread geographically reducing end-user latency, mobile phones’ computing capabilities are improving, and network bandwidth at the core keeps increasing. In this paper, we scrutinize edge computing, examining its outlook and future in the context of these trends. We perform extensive client-to-cloud measurements using RIPE Atlas, and show that latency reduction as motivation for edge is not as persuasive as once believed; for most applications the cloud is already “close enough” for majority of the world’s population. This implies that edge computing may only be applicable for certain application niches, as opposed to a general-purpose solution.
Tunnel Emitter: Tunnel Diode based Low-Power Carrier Emitters for Backscatter Tags Ambuj Varshney and Lorenzo Corneo ACM MobiCom, 2020, London, UK
Backscatter enables transmissions at orders of magnitude lower energy consumption when compared to conventional radio transmitters. Backscatter tags achieve this by the reflection or absorption of carrier signal generated from emitter devices. However, backscatter systems are limited by these emitter devices, as they are significantly energy-expensive when compared to the tags. While backscatter tags can operate without requiring batteries, relying on the minuscule amounts of energy harvested from the ambient environment. However, the emitter devices, are commonly tethered to an external power supply or operate on large batteries. We present Tunnel Emitter: a tunnel diode oscillator based system that enables the generation of carrier signals at a peak biasing power of tens of uW. Thus, for the first time, it allows battery-free emitter devices. The key enabler to the design is a phenomenon exhibited by tunnel diode oscillators that we call back injection, and we are the first to demonstrate. Back injection enables the emitter devices to amplify (up to 20dB) and relay the backscattered signal. Our results show that Tunnel Emitter when operating together with a tag from long-range backscatter system, facilitates multi-floor communication. Tunnel Emitter, due to the back injection phenomenon, achieves this with a carrier signal that is orders of magnitude weaker than used in state-of-the-art systems. We believe Tunnel Emitter overcomes the key constraint restricting backscatter systems and thus can make backscatter systems ubiquitous.
Age of Information-Aware Scheduling for Timely and Scalable Internet of Things Applications Lorenzo Corneo, Christian Rohner and Per Gunningberg IEEE INFOCOM, 2019, Paris, France
We consider large scale Internet of Things applications requesting data from physical devices. We study the problem of timely dissemination of sensor data towards applications with freshness requirements by means of a cache. We aim to minimize direct access to the possibly battery powered physical devices, yet improving Age of Information as a data freshness metric. We propose an Age of Information-aware scheduling policy for the physical device to push sensor updates to the caches located in cloud data centers. Such policy groups application requests based on freshness thresholds, thereby reduces the number of requests and threshold misses, and accounts for delay variation. The policy is incrementally introduced as we study its behavior over ideal and more realistic communication links with delay variation. We numerically evaluate the proposed policy against a simple yet widely used periodic schedule. We show that our informed schedule outperforms the periodic schedule even under high delay variations.
Scheduling at the Edge for Assisting Cloud Real-Time Applications Lorenzo Corneo and Per Gunningberg ACM TOPIC @ PODC, 2018, Egham, London, UK
We study edge server support for multiple periodic real-time applications located in different clouds. The edge communicates both with sensor devices over wireless sensor networks and with applications over Internet type networks. The edge caches sensor data and can respond to multiple applications with different timing requirements to the data. The purpose of caching is to reduce the number of multiple direct accesses to the sensor since sensor communication is very energy expensive. However, the data will then age in the cache and eventually become stale for some application. A push update method and the concept of age of information is used to schedule data updates to the applications. An aging model for periodic updates is derived. We propose that the scheduling should take into account periodic sensor updates, the differences in the periodic application updates, the aging in the cache and communication variance. By numerical analysis we study the number of deadline misses for two different scheduling policies with respect to different periods.
I served as teaching assistant (TA) in the following courses: