Collaborative, Intelligent, and Adaptive Systems for the Low-Power Internet of Things
Doctoral thesis, 2022

With the emergence of the Internet of Things (IoT), more and more devices are getting equipped with communication capabilities, often via wireless radios. Their deployments pave the way for new and mission-critical applications: cars will communicate with nearby vehicles to coordinate at intersections; industrial wireless closed-loop systems will improve operational safety in factories; while swarms of drones will coordinate to plan collision-free trajectories. To achieve these goals, IoT devices will need to communicate, coordinate, and collaborate over the wireless medium. However, these envisioned applications necessitate new characteristics that current solutions and protocols cannot fulfill: IoT devices require consistency guarantees from their communication and demand for adaptive behavior in complex and dynamic environments.

In this thesis, we design, implement, and evaluate systems and mechanisms to enable safe coordination and adaptivity for the smallest IoT devices. To ensure consistent coordination, we bring fault-tolerant consensus to low-power wireless communication and introduce Wireless Paxos, a flavor of the Paxos algorithm specifically tailored to low-power IoT. We then present STARC, a wireless coordination mechanism for intersection management combining commit semantics with synchronous transmissions. To enable adaptivity in the wireless networking stack, we introduce Dimmer and eAFH. Dimmer combines Reinforcement Learning and Multi-Armed Bandits to adapt its communication parameters and counteract the adverse effects of wireless interference at runtime while optimizing energy consumption in normal conditions. eAFH provides dynamic channel management in Bluetooth Low Energy by excluding and dynamically re-including channels in scenarios with mobility. Finally, we demonstrate with BlueSeer that a device can classify its environment, i.e., recognize whether it is located in a home, office, street, or transport, solely from received Bluetooth Low Energy signals fed into an embedded machine learning model. BlueSeer therefore increases the intelligence of the smallest IoT devices, allowing them to adapt their behaviors to their current surroundings.

Adaptive Networking

Bluetooth Low Energy


Low-Power Wireless Networks



Internet of Things

synchronous transmissions

Lecture Room FB, Fysik Origo, Campus Johanneberg, Fysikgården 4
Opponent: Assoc. Prof. Stephan Sigg, Aalto University, Finland


Valentin Poirot

Network and Systems

Paxos Made Wireless: Consensus in the Air

Proceedings of the 2019 International Conference on Embedded Wireless Systems and Networks,; (2019)p. 1-12

Paper in proceeding

STARC: Low-power Decentralized Coordination Primitive for Vehicular Ad-hoc Networks

Proceedings of IEEE/IFIP Network Operations and Management Symposium 2020: Management in the Age of Softwarization and Artificial Intelligence, NOMS 2020,; (2020)

Paper in proceeding

Dimmer: Self-adaptive network-wide flooding with reinforcement learning

Proceedings - International Conference on Distributed Computing Systems,; Vol. 2021-July(2021)p. 293-303

Paper in proceeding

eAFH: Informed Exploration for Adaptive Frequency Hopping in Bluetooth Low Energy

Proceedings - 18th Annual International Conference on Distributed Computing in Sensor Systems, DCOSS 2022,; (2022)p. 1-8

Paper in proceeding

BlueSeer: AI-Driven Environment Detection via BLE Scans

59th ACM/IEEE Design Automation Conference (DAC ’22),,; (2022)p. 871-876

Paper in proceeding

From smartphones to smartwatches, smart homes to smart cities, many devices around us are getting connected to the Internet. In recent years, we see a trend emerging where our devices have become more collaborative, smarter, and adaptive. We bring our wireless headphones with us everywhere. We can control lightbulbs via our smartphones. Our watches automatically track our physical activities and provide us with personalized health reports. We often refer to those devices as the Internet of Things (IoT), a vision of tomorrow where every Thing can communicate, primarily via wireless communication. In the near future, even cars will communicate to coordinate at intersections and autonomously drive us around, while all our electronics will rely on artificial intelligence to become smarter and make our lives easier.

Yet, many challenges lie ahead of us before we can achieve these goals. When cars coordinate at an intersection, we need to make sure that they all agree on which vehicle will go next, even if communication is spotty and does not work well. As we walk across town, our headphones have to adapt to changing wireless conditions. To correctly recognize our activity, smartwatches need to recognize not only our movements, but also our surroundings.

In this thesis, we provide solutions allowing IoT devices to become more collaborative, intelligent, and adaptive. We specifically target low-power devices, such as wireless headphones, fitness trackers, and small drones, and show that even the smallest device can become more intelligent and benefit from collaboration. We build algorithms and systems and test them on real hardware to showcase their effectiveness in the real world.

AgreeOnIT: Lightweight Consensus and Distributed Computing in the Resource-Constrained Internet of Things

Swedish Research Council (VR) (37200024), 2019-01-01 -- 2022-12-31.

Subject Categories

Communication Systems

Embedded Systems

Computer Systems



Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 5152

Technical report D - Department of Computer Science and Engineering, Chalmers University of Technology and Göteborg University: 223D



Lecture Room FB, Fysik Origo, Campus Johanneberg, Fysikgården 4


Opponent: Assoc. Prof. Stephan Sigg, Aalto University, Finland

More information

Latest update