Matching-based cache placement decision for 5G network caching

In this thesis, we present a cache placement scheme to deal with backhaul link constraint in Small Cell Network for 5G wireless network. We formulated the cache placement problem as a graph matching problem and presented an optimal file-helper matching algorithm. We defined stability criterion for the matching and found that our matching solution is stable in the sense that every helper finds at least one file to cache given that no file exceed minimum cache size. We achieved a unique placement of a file within a cluster of helpers to increase the number of files cached within a cluster. Further, our experimental evaluation demonstrates that our algorithm increases local and neighbor hit ratios as compared to a random placement, which in turn significantly decreases the traffic that goes over the backhaul bottleneck link.

Matching-based cache placement decision for 5G network caching

In this thesis, we present a cache placement scheme to deal with backhaul link constraint in Small Cell Network for 5G wireless network. We formulated the cache placement problem as a graph matching problem and presented an optimal file-helper matching algorithm. We defined stability criterion for the matching and found that our matching solution is stable in the sense that every helper finds at least one file to cache given that no file exceed minimum cache size. We achieved a unique placement of a file within a cluster of helpers to increase the number of files cached within a cluster. Further, our experimental evaluation demonstrates that our algorithm increases local and neighbor hit ratios as compared to a random placement, which in turn significantly decreases the traffic that goes over the backhaul bottleneck link.

On the Fidelity of NS-3 Simulations of Wireless Multipath TCP Connections

The multipath transmission control protocol (MPTCP) is considered a promising wireless multihoming solution, and the 3rd generation partnership project (3GPP) includes it as a standard feature in the fifth-generation (5G) networks. Currently, ns-3 (Network Simulator-3) is widely used to evaluate the performance of wireless networks and protocols, including the emerging MPTCP protocol. This paper investigates the fidelity of the Linux kernel implementation of MPTCP in the ns-3 direct code execution module. The fidelity of MPTCP simulation is tested by comparing its performance with a real Linux stack implementation of MPTCP using a hardware testbed for two different setups. One setup emulates the existence of a bottleneck link between the sending and receiving networks, whereas the other setup does not have such a bottleneck. The fidelity of ns-3’s simulation is tested for four congestion control algorithms, namely Cubic, linked-increases algorithm (LIA), opportunistic LIA (OLIA) and wVegas for relatively short and long data flows. It is found that the uplink MPTCP throughput performance exhibited by the ns-3 simulator matches the hardware testbed results only if the flows are long-lived and share no common bottleneck link. Likewise, the MPTCP throughput achieved during a downlink scenario using the ns-3 simulator and the hardware testbed are close to each other across all algorithms except wVegas regardless of the flow size if there is no bottleneck link. Moreover, it is observed that the impact of LTE handover on MPTCP throughput is less significant in the simulator than the real hardware testbed, and it is setup-dependent.

BBR-CWS: Improving the Inter-Protocol Fairness of BBR

TCP congestion control adjusts the sending rate in order to protect Internet from the continuous traffic and ensure fair coexistence among multiple flows. Especially, loss-based congestion control algorithms were mainly used, which worked relatively well for past Internet with low bandwidth and small bottleneck buffer size. However, the modern Internet uses considerably more sophisticated network equipment and advanced transmission technologies, and loss-based congestion control can cause performance degradation due to excessive queueing delay and packet loss. Therefore, Google introduced a new congestion control in 2016, Bottleneck Bandwidth Round-trip propagation time (BBR). In contrast with traditional congestion control, BBR tries to operate at the Kleinrock’s optimal operating point, where delivery rate is maximized and latency is minimized. However, when BBR and loss-based congestion control algorithms coexist on the same bottleneck link, most of bottleneck bandwidth is occupied by flows that use a particular algorithm, and excessive packet retransmission can occur. Therefore, this paper proposes a BBR congestion window scaling (BBR-CWS) scheme to improve BBR’s inter-protocol fairness with a loss-based congestion control algorithm. Through Mininet experiment results, we confirmed that fairness between BBR-CWS and CUBIC improved up to 73% and has the value of 0.9 or higher in most bottleneck buffer environments. Moreover, the number of packet retransmissions was reduced by up to 96%, compared to the original BBR.

Diameter-Aggregation Delay Tradeoff for Data Gathering Trees in Wireless Sensor Networks

We define the aggregation delay as the minimum number of time slots it takes for the data to be aggregated in a Data Gathering tree (DG tree) spanning all the nodes of the sensor network; the diameter of a DG tree is the maximum distance (number of hops) from a leaf node to the root node of the tree. We assume that intermediate nodes at the same level or different levels of a DG tree could simultaneously aggregate data from their respective child nodes using different CDMA (Code Division Multiple Access) codes; but, an intermediate node has to schedule non-overlapping time slots (one for each of its child nodes) to aggregate data from its own child nodes. We employ an algorithm to determine the minimum aggregation delay at every intermediate node of the Bottleneck Node Weight (BNW) and Bottleneck Link Weight (BLW)-based DG trees. We observe the BNW-DG trees to incur a smaller tree diameter, but a significantly larger aggregation delay; on the other hand, the BLW-DG trees incur a larger tree diameter and a relatively lower aggregation delay, especially with increase in node density.

Performance Evaluation of TCP Vegas over TCP Reno and TCP NewReno over TCP Reno

In the Transport layer, there are two types of Internet Protocol are worked, namely- Transmission Control Protocol (TCP) and User datagram protocol (UDP). TCP provides connection oriented service and it can handle congestion control, flow control, and error detection whereas UDP does not provide any of service. TCP has several congestion control mechanisms such as TCP Reno, TCP Vegas, TCP New Reno, TCP Tahoe, etc. In this paper, we have focused on the behavior performance between TCP Reno and TCP Vegas, TCP New Reno over TCP Reno, when they share the same bottleneck link at the router. For instigating this situation, we used drop-tail and RED algorithm at the router and used NS-2 simulator for simulation. From the simulation results, we have observed that the performance of TCP Reno and TCP Vegas is different in two cases. In drop tail algorithm, TCP Reno achieves better Performance and throughput and act more an aggressive than Vegas. In Random Early Detection (RED) algorithm, both of congestion control mechanism provides better fair service when they coexist at the same link. TCP NewReno provides better performance than TCP Reno.