Master-Seminar Connected and Mobile Systems

As there exists no clock with absolute accuracy, the time kept by devices, such as sensor nodes, will drift over time. Differences in the time kept by different nodes in a WSN pose challenges with regard to communication, especially if TDMA schemes are used. Therefore, different approaches have been developed to facilitate re-synchronization of clocks in WSNs. Your assignment will be to compare existing approaches using selected metrics, such as energy consumption, achievable accuracy and applicable scenarios.

• Efficient Time Synchronization in a Wireless Sensor Network by Adaptive Value Tracking
• FADS: Fast Scheduling and Accurate Drift Compensation for Time Synchronization of Wireless Sensor Networks

Machine learning is used for a wide variety of different use cases including wireless sensor networks. The traditional challenges of prolonging the battery powered nodes lifetime while being active for a reasonable time as well as routing and data aggregation challenges have been analyzed with different ML techniques. Your task is to provide an overview about the challenges in wireless sensor networks together with their corresponding machine learning solution. Additionally one or two solutions should be discussed in detail with the focus on the ML technique.

• Machine Learning Techniques and Challenges in Wireless Sensor Networks
• Machine Learning in Wireless Sensor Networks for Smart Cities: A Survey

Collective Perception (CP) for vehicular networks will be the key technology for improving traffic safety in the future. With CP, vehicles exchange information about objects perceived with local sensors to improve the situational awareness of other communicating vehicles. Collective Perception Messages (CPMs) will be filled with perceived objects following the object inclusion rules of ETSI TR 103 562 V2.1.1, which defines time and dynamics based triggers. However, when many CP-capable vehicles send CPMs, information for a given object becomes redundant, wasting valuable channel resources. This trade-off between the availability of information and reduction of redundancy led to different techniques, reducing the inclusion of redundant objects in CPMs, which were proposed in standardization and literature. Your task is to give an overview of proposed redundancy mitigation techniques, compare the different approaches and discuss their challenges.

• Intelligent Transport Systems (ITS); Vehicular Communications; Basic Set of Applications; Analysis of the Collective Perception Service (CPS); Release 2