No results match your search criteria.
Reset filter
2023
Completed
Machine Learning Based Data Rate Optimization for Mobile LoRaWAN Sensors
Supervisor:
Luis Alves
Frank Hessel
Adaptive Data Rate is a feature of LoRaWAN that allows to optimize the network performance by adjusting the data rate of end devices based on their current channel conditions. Current approaches to ADR optimization algorithms focus on static or low-mobile end devices, and the specification recommends to disable ADR for mobile devices, e.g. location trackers. To let these devices also benefit from ADR adjustments, this thesis suggests to implement a predictive ADR algorithm based on deep reinforcement learning. The algorithm is evaluated on a real-world data set captured in the city of Darmstadt.
2023
In progress
Automated Surveillance Recognition in Smart Environments
Supervisor:
Matthias Gazzari
Frank Hessel
This topic is about implementing various models to recognize the presence of as many smart things as possible based on sensor or other time series data. The goal of this topic is to compare and evaluate these models against each other in certain settings like in a smart home environment.
2022
In progress
Power Usage Advisory System for eHUB Inhabitants
Supervisor:
Frank Hessel
Martin Pietsch
Within the research center emergenCITY, we investigate how ICT can be used to strengthen a cities resilience during crises, e.g. blackouts, instead of being another critical infrastructure which can fail. With our freshly renovated living lab eHUB, we want to learn how self-sustaining buildings, which generate a surplus of electrical energy on their own, can support this approach. The eHUB provides a PV system with a battery, ready for starting experiments with off-grid operation. What it still needs is an integrated Smart Home system which can learn from the inhabitants’ behavior and support them in managing their energy budget, and offer the surplus e.g. to neighbors, first responders, or other emergency relief activities.
The house is currently equipped with a KNX-based system for controlling consumers and measuring energy production and consumption. Your task is to extend this system, so that it considers consumption and production, monitors activities within the house with their energy profile, includes external context information (e.g. to relate weather and expected power production), and interacts with the inhabitants. The interaction could happen for example by a (web) app, using wall-mounted displays or through a Smart Home Speaker/Hub developed in the project. We plan to use the interface for further experiments in the eHUB.
Some of the skills that will be helpful for working on this topic are (you do not need to tick all boxes):
UI, App or web design for creating a nice user interface
No fear in working with hardware installations and embedded systems (e.g. Linux on Raspberry Pis, knowledge of KNX, MQTT, … is an advantage)
Machine learning for creating predictive models
Experience with user studies in case you want to use that as method for evaluation.
This thesis will be supervised in cooperation with EINS.
2022
In progress
ePaper Bulletin Boards to Inform Citizens During Crises
Supervisor:
Frank Hessel
Within the research center emergenCITY, we are looking for ways to keep people informed during crises which affect the power gird and/or communication networks. Integrating ePaper displays, which only low power and keep their information during interruption seem to be an interesting appraoch for this use case. This thesis implements a proof of concept for mounting such a display to the facade of a building.
2022
Completed
LoRaWAN in Disaster Scenarios
Supervisor:
Frank Hessel
LoRa comes with characteristics beneficial in crisis situations, like its long range and the low power consumption, which allows to run running devices on batteries significantly longer than, e.g., cellular base stations. However, LoRaWAN does not benefit from these characteristics, as it depends on a centralized, cloud-based network server infrastructure. If gateways can no longer access the backing network, forwarding stops and the network fails in the affected region. This thesis investigates collaboration between gateways to transparently forward frames from LoRaWAN devices in regions suffering from an outage of the backing network.
2022
In progress
Low-Power Network Support for the Recovery of Collapsed 6G Systems
Supervisor:
Leon Würsching
Frank Hessel
A resilient 6G network will be prepared for different failure scenarios and can absorb incidents to a certain level. However, there may be incidents that cannot be absorbed, e.g., a failure of the entire 6G core network due to a large-scale cyber attack. Further possible consequences of such an incident include a large-scale power outage affecting either parts or even the entire mobile network.
In this type of scenario, the 6G network would collapse and split into smaller networks. Such a small network could, e.g., consist of a single isolated base station running on emergency power, and the users connected to it. From here, isolated basestations have to reconnect with other base stations to recover some functionality of the 6G network. However, the need to conserve energy further complicates the recovery process because base stations are running on emergency power.
This thesis evaluates how such a recovery process of the 6G network can be supported with ad-hoc low-power networks.
In this thesis, the student will explore how isolated base stations can coordinate the reconnection of isolated base stations via a low-power network. This includes
discussing and choosing a suitable lower-layer protocol as a basis for the low-power network
implementing a basic consensus protocol to make distributed decisions
testing the developed protocol in simulation.
2022
Completed
Updating Heterogeneous LoRaWAN Nodes Using A Modular LoRaWAN-Stack
Supervisor:
Frank Hessel
The LoRaWAN 1.0 has been shown to suffer from security vulnerabilities which require updating the LoRaWAN implementation on respective sensor nodes. However, updating the firmware of LoRaWAN end devices is a demanding task, as data rate and duty cycle limit the throughput to only a few kilobytes per second. Heterogeneity amongst sensors exacerbates the situation by requiring dedicated images for each sensor type. The thesis addresses both problems by improving the updatability of LoRaWAN end devices by allowing to replace single functions of the LoRaWAN stack with architecture-independent drop-ins based on WebAssembly.
2022
Completed
Practical Evaluation of LoRaWAN in IIoT Environments
Supervisor:
Frank Hessel
2022
Available now
Generalized Network Coded Cooperation in High Density LoRa-Networks
Supervisor:
Luis Alves
Frank Hessel
The wireless channel is a non-linear and time-varying system. Thus, it represents a harsh environment to conduct transfers of information. One of the variables that predict the outage performance of transmissions over the wireless channel is the diversity order, where systems with higher diversity order experience a lower outage probability at a specific signal-to-noise ratio (SNR).
Diversity can be achieved through several means, with the most simple being repetitions (retransmissions) of the same information over different instances of the wireless medium, i.e. over another time period or frequency. One very relevant means is the use of multiple antennas, which adds diversity by also incorporating a spatial element. However, this element can also be obtained when devices with transmissions to a common destination aid each other with retransmitting their partner's information frames. That is the concept behind cooperative communication: achieving a spatial diversity gain without requiring multiple antennas on each device [1].
Network Coded Cooperation (NCC) is a more complex cooperative technique whereby devices perform linear combinations of the data contained in their own and their partner's information frame, creating a parity frame. This allows for an even higher diversity order gain without requiring any additional transmissions beyond the standard information and cooperative phases seen in cooperative communications [2].
This kind of technique can therefore be especially useful in scenarios where multiple devices share a common base station and require energy-efficient communications, such as in LoRa-based networks. LoRa is a prime modulation technique for enabling Low-Power Wide Area Networks (LPWANs), providing adequate interference prevention, relatively low power consumption, and long range. These benefits, however, do not scale well with increases in the network density [3]. Note that, in these high-density scenarios, increasing diversity by simply realizing more transmissions results in an increased collision probability, i.e. even higher interference. For LoRa-networks, this also means the network loses maximum range. Given that the number of connected devices is expected to balloon in this decade, LoRa-based protocols must be adapted to mitigate high levels of interference.
It has been shown that using NCC can produce positive results in the high-density scenario LoRa-based network when associated with a fast inter-device transmission of information frames using high rate frequency shift-keying (FSK). However, previous analyses were purely theoretical and limited to evaluating a two-way cooperation process [3].
This thesis will tackle the empirical and theoretical challenges of implementing generalized network-coded cooperation on LoRa-based networks. Cooperation will be expanded to include multiple devices within the cooperation range, which will generate a higher diversity order for the uplink transmissions. The student is expected to be programing LoRa devices based on either the SX1272 or SX1276 transceivers to validate their results.
If you have any interest in the described topic, please do not hesitate to get in touch.
[1] Cooperative communication in wireless networks
[2] Multiuser Cooperative Diversity Through Network Coding Based on Classical Coding Theory
[3] Network-Coded Cooperative LoRa Network with D2D Communication