Search for: All records

Thanks to advancements in wireless networks, robotics, and artificial intelligence, future manufacturing and agriculture processes may be capable of producing more output with lower costs through automation. With ultra fast 5G mmWave wireless networks, data can be transferred to and from servers within a few milliseconds for real-time control loops, while robotics and artificial intelligence can allow robots to work alongside humans in factory and agriculture environments. One important consideration for these applications is whether the “intelligence” that processes data from the environment and decides how to react should be located directly on the robotic device that interacts with the environment - a scenario called “edge computing” - or whether it should be located on more powerful centralized servers that communicate with the robotic device over a network - “cloud computing.” For applications that require a fast response time, such as a robot that is moving and reacting to an agricultural environment in real time, there are two important tradeoffs to consider. On the one hand, the processor on the edge device is likely not as powerful as the cloud server, and may take longer to generate the result. On the other hand, cloud computing requires both the input data and the response to traverse a network, which adds some delay that may cancel out the faster processing time of the cloud server. Even with ultra-fast 5G mmWave wireless links, the frequent blockages that are characteristic of this band can still add delay. To explore this issue, we run a series of experiments on the Chameleon testbed emulating both the edge and cloud scenarios under various conditions, including different types of hardware acceleration at the edge and the cloud, and different types of network configurations between the edge device and the cloud. These experiments will inform future use of these technologies and serve as a jumping off point for further research. 

Oblivious routing of network traffic uses predetermined paths that do not change with changing traffic patterns. It has the benefit of using a fixed network configuration while robustly handling a range of varying and unpredictable traffic. Theoretical advances have shown that the benefits of oblivious routing are achievable without compromising much capacity efficiency. For oblivious routing, we only assume knowledge of the ingress/egress capacities of the edge nodes through which traffic enters or leaves the network. All traffic patterns possible subject to the ingress/egress capacity constraints (also known as the hose constraints) are permissible and are to be handled using oblivious routing. We use the widely deployed segment routing method for route control. Furthermore, for ease of deployment and to not deviate too much from conventional shortest path routing, we restrict paths to be 2-segment paths (the composition of two shortest path routed segments). We solve the 2-segment oblivious routing problem for all permissible traffic matrices (which can be infinitely-many).We develop a new adversarial and machine-learning driven approach that uses an iterative gradient descent method to solve the routing problem with worst-case performance guarantees. Additionally, the parallelism involved in descent methods allows this method to scale well with the network size making it amenable for use in practice.