An official website of the United States government
In this paper, we propose a new design framework on Device-to-Device (D2D) coded caching networks with optimal communication load (rate) but significantly less file subpacketizations compared to that of the well-known D2D coded caching scheme proposed by Ji, Caire and Molisch (JCM). The proposed design framework is referred to as the Packet Type-based (PTB) design, where each file is partitioned into packets according to their pre-defined types while the cache placement and user multicast grouping are based on the packet types. This leads to the so-called raw packet saving gain for the subpacketization levels. By a careful selection of transmitters within each multicasting group, a so-called further splitting ratio gain of the subpacketizatios can also be achieved. By the joint effect of the raw packet saving gain and the further splitting ratio gain, an order-wise subpacketization reduction can be achieved compared to the JCM scheme while preserving the optimal rate. In addition, as the first time presented in the literature according to our knowledge, we find that unequal subpacketizaton is a key to achieve subpacketization reductions when the number of users is odd. As a by-product, instead of directly translating shared link caching schemes to D2D caching schemes, at least for the sake of subpackeitzation, a new design framework is indeed needed.
more »
« less
On Reducing Measurement Load on Control-Plane in Locating High Packet-Delay Variance Links for OpenFlow Networks
We previously proposed a method to locate high packetdelay variance links for OpenFlow networks by probing multicast measurement packets along a designed route and by collecting flow-stats of the probe packets from selected OpenFlow switches (OFSs). It is worth AQ1 noting that the packet-delay variance of a link is estimated based on arrival time intervals of probe packets without measuring delay times over the link. However, the previously used route scheme based on the shortest path tree may generate a probing route with many branches in a large network, resulting in many accesses to OFSs to locate all high delay variance links. In this paper, therefore, we apply an Eulerian cycle-based scheme which we previously developed, to control the number of branches in a multicast probing route. Our proposal can reduce the load on the control-plane (i.e., the number of accesses to OFSs) while maintaining an acceptable measurement accuracy with a light load on the data-plane. Additionally, the impacts of packet losses and correlated delays over links on those different types of loads are investigated. By comparing our proposal with the shortest path tree-based and the unicursal route schemes through numerical simulations, we evaluate the advantage of our proposal.
more »
« less
- Award ID(s):
- 1818884
- PAR ID:
- 10289924
- Date Published:
- Journal Name:
- Lecture Notes on Data Engineering and Communications Technologies (LNDECT), Springer
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)The Jellyfish network has recently been proposed as an alternative to the fat-tree network for data centers and high-performance computing clusters. Jellyfish uses a random regular graph as its switch-level topology and has shown to be more cost-effective than fat-trees. Effective routing on Jellyfish is challenging. It is known that shortest path routing and equal cost multi-path routing (ECMP) do not work well on Jellyfish. Existing schemes use variations of k-shortest path routing (KSP). In this work, we study two routing components for Jellyfish: path selection that decides the paths to route traffic, and routing mechanisms that decide which path to be used for each packet. We show that the performance of the existing KSP can be significantly improved by incorporating two heuristics, randomization and edge-disjointness. We evaluate a range of routing mechanisms, including traffic oblivious and traffic adaptive schemes, and identify an adaptive routing scheme with noticeably higher performance than others.more » « less
-
We consider a multicast network in which real-time status updates generated by a source are replicated and sent to multiple interested receiving nodes through independent links. The receiving nodes are divided into two groups: one priority group consists of k nodes that require the reception of every update packet, the other non-priority group consists of all other nodes without the delivery requirement. Using age of information as a freshness metric, we analyze the time-averaged age at both priority and non-priority nodes. For shifted-exponential link delay distributions, the average age at a priority node is lower than that at a non-priority node due to the delivery guarantee. However, this advantage for priority nodes disappears if the link delay is exponential distributed. Both groups of nodes have the same time-averaged age, which implies that the guaranteed delivery of updates has no effect the time-averaged freshness.more » « less
-
We present a novel Packet Type (PT)-based design framework for the finite-length analysis of Device-to-Device (D2D) coded caching. By the exploitation of the asymmetry in the coded delivery phase, two fundamental forms of subpacketization reduction gain for D2D coded caching, i.e., the subfile saving gain and the further splitting saving gain, are identified in the PT framework. The proposed framework features a streamlined design process which uses several key concepts including user grouping, subfile and packet types, multicast group types, transmitter selection, local/global further splitting factor, and PT design as an integer optimization. In particular, based on a predefined user grouping, the subfile and multicast group types can be determined and the cache placement of the users can be correspondingly determined. In this stage, subfiles of certain types can be potentially excluded without being used in the designed caching scheme, which we refer to as subfile saving gain. In the delivery phase, by a careful selection of the transmitters within each type of multicast groups, a smaller number of packets that each subfile needs to be further split into can be achieved, leading to the further splitting saving gain. The joint effect of these two gains results in an overall subpacketization reduction compared to the Ji-Caire-Molisch (JCM) scheme [1]. Using the PT framework, a new class of D2D caching schemes is constructed with order reduction on subpacketization but the same rate when compared to the JCM scheme.more » « less
-
Routing solutions for multi-hop underwater wireless sensor networks suffer significant performance degradation as they fail to adapt to the overwhelming dynamics of underwater environments. To respond to this challenge, we propose a new data forwarding scheme where relay selection swiftly adapts to the varying conditions of the underwater channel. Our protocol, termed CARMA for Channel-aware Reinforcement learning-based Multi-path Adaptive routing, adaptively switches between single-path and multi-path routing guided by a distributed reinforcement learning framework that jointly optimizes route-long energy consumption and packet delivery ratio. We compare the performance of CARMA with that of three other routing solutions, namely, CARP, QELAR and EFlood, through SUNSET-based simulations and experiments at sea. Our results show that CARMA obtains a packet delivery ratio that is up to 40% higher than that of all other protocols. CARMA also delivers packets significantly faster than CARP, QELAR and EFlood, while keeping network energy consumption at bay.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
