Barun Saha's blog on AI and Networks

Given a network (a set of nodes) and a set of traffic flows, a network flow allocation assigns network paths to these flows, so that data (for example, packets) can be sent from the respective source nodes to the corresponding destination nodes. In case of optimal network flow allocation, certain criteria, such as latency and utilization, need to be optimized. Moreover, in case of integral network flow allocation, all packets from a source node to a given destination node must travel via a single path or none at all. In other words, such a flow cannot be “split” across multiple paths. Optimal network flow allocation is a computationally hard problem, which not only requires a long time to solve, but also high level of skills. The problem becomes further challenging when unique business and industrial requirements are considered. In our recent work, we investigated this problem in the context of power grid networks, where the flows often require delay-symmetric upstream and ...

Conceptual architecture of SeeR Opportunistic Mobile Networks (OMNs) are characterized by intermittent connectivity among nodes. In many scenarios, the nodes attempt at local decision making based on greedy approaches, which can result in getting trapped at local optimum. Moreover, for efficient routing, the nodes often collect and exchange lot of information about others. To alleviate such issues, we present SeeR, a simulated annealing-based routing protocol for OMNs. In SeeR, each message is associated with a cost function, which is evaluated by considering its current hop-count and the average aggregated inter-contact time of the node. A node replicates a message to another node, when the latter offers a lower cost. Otherwise, the message is replicated with decreasing probability. Moreover, SeeR works based solely upon local observations. In particular, a node does not track information about other nodes, and, therefore, reduces the risk of privacy leaks unlike m...