Downstream Bandwidth Research Articles

Connection-density-aware satellite-ground federated learning via asynchronous dynamic aggregation

With the development of space technology, the use of satellites for Earth observation is becoming more and more common. Among them, low-earth orbit (LEO) satellites have received a lot of attention because of their short return period and low cost. However, traditional satellite systems are unable to process data in orbit due to technical limitations and can only transmit massive amounts of data with useless information back to ground stations and then perform calculations, putting a tremendous strain on downstream bandwidth. Additionally, there are data walls between satellite affiliates, which makes it difficult to share and use data. To address the lack of data processing capabilities and data barriers in conventional satellite systems, as well as to effectively use satellite resources and enhance worldwide collaboration, we proposed a connection density-aware satellite-ground federated learning (FL) framework. According to this structure, satellites serve as workers in federated learning, analyzing data and transmitting the parameters to ground stations for aggregation. The ground station senses the satellite’s connection density during the aggregation process and implements a dynamic aggregation approach for the downstream parameters. Experiments based on real image datasets and on a simulated satellite network validate the effectiveness of the method in terms of execution efficiency and accuracy.

On formulation of online algorithm and framework of near-optimally tractable eviction for nonuniform caches

Distributed data sharing in Internet, social, and cloud computing paradigms incurs nonuniform costs such as consumed downstream bandwidth, downloading delays, and cloud-data-out monetary charges. To alleviate such costs, caches have been widely deployed and researched to find efficient online-cache-eviction algorithms. However, existing online algorithms have no offline foundation, thus they are far from a global optimum. This paper proposes a framework for developing an online cache eviction algorithm, which is grounded in a near-optimally and tractably offline algorithm namely Shortest Maximum Forward Distance (SMFD). On the formulation of the framework, the near-optimality and tractability properties of existing offline algorithms were evaluated through the formal evaluation of the optimality and computational tractability based upon variable object costs. Subsequently, the lowest-complexity suboptimal schemes were empirically investigated to seek a near-optimal offline one, which appears to be SMFD. Also, the results originally show that SMFD and its variant can practically achieve multiple conventionally upper bounds of limitless cache sizes in a stable and simultaneous manner. SMFD was then transformed into novel online SMFD by quantifying the offline property, maximum forward distance, of SMFD with cache-scope time-to-live approximation. To guarantee the effectiveness of online SMFD over evolving request streams, a safety bound guideline and a cache-scope time-to-live distribution model are also proposed. Finally, experience on the framework was gained via experiments based on deep-neural-network models.

PWC-PON: An Energy-Efficient Low-Latency DBA Scheme for Time Division Multiplexed Passive Optical Networks

Reducing network energy consumption and offering low-latency service quality have been the pursued goals in broadband passive optical networks (PONs). To realize these goals, energy-efficient dynamic bandwidth allocation (DBA) has been extensively studied. Nevertheless, few of these DBA schemes can effectively support low-latency and low-energy requirements, simultaneously. For these existing DBA schemes, the adopted energy-saving methods by sleeping some network elements would not handle the mismatch between the upstream and downstream bandwidth required by an optical network unit (ONU), which brings in a longer active window for each ONU and thus larger packet latencies. In this paper, an energy-efficient low-latency DBA scheme is proposed based on a novel pairwise combination (PWC) method. The essence of the PWC method is to compact the polling cycle length as much as possible by dynamically paring any two ONUs in complementary ways, which in turn also improves latency performance of data packets (i.e., quality of service (QoS)). Moreover, we introduce a multiple-state energy-saving mode into the proposed DBA scheme to reduce the PON energy consumption, with the consideration of both the upstream (US) and downstream (DS) transmissions. We establish an energy saving model for the proposed PWC-PON compared with the PONs with the existing DBA schemes, and also present a comprehensive M/G/1 queuing analysis with modification for the data latency performance. Extensive theoretical analysis and simulation results show that the proposed PWC-PON can reduce US and DS latency by 50% compared with the existing Gate Service (GS)-based DBA scheme. The energy saving efficiency is up to 3.5% higher than the benchmark when the US traffic load is light. It suggests that our PWC-based DBA scheme cannot only reduce the energy consumption, but also reduce the packet latency for PON system.

Dedicated and broadcasting downstream transmission with energy-efficient and latency-aware ONU interconnection in WDM-PON for smart cities

Abstract Currently, Internet of Things (IoT) and use of Information & Communication Technology (ICT) have gained a lot of attraction for developing the smart cities. Wavelength division multiplexed passive optical networks (WDM-PON) are popularly used for supporting the high data rate IoT and ICT services. With the exponential growth of users and traffic demand in access networks, large energy consumption, OPEX, service reliability has become the most challenging bottleneck for smart cities. This paper proposes a flexible, wavelength division multiplexed passive optical network (WDM-PON) architecture which provides a dedicated point to point (P2P), broadcasting downstream transmission and latency-aware direct optical network units (ONUs) interconnection. Broadcasting downstream transmission is achieved by diverting a particular wavelength from the main path towards (N + 1) × (N + 1) star coupler (SC). Direct ONU interconnection is accomplished by separating the inter-ONU signal from the upstream path by using 50 GHz interleaver at the remote node (RN) and redirecting it towards ONUs. Direct ONU intercommunication avoids the complex re-routing, re-scheduling and re-modulation of the inter-ONU signal at optical line terminal (OLT) and thus increases the reliability and energy efficiency of the network. Broadcasting enables the best resource utilization, and direct ONU interconnection reduces the significant transmission latency among different communicating users. Proposed architecture reduces the operational cost and energy consumption of the network by reducing the processing by some components. By reducing the extra burden of the inter-ONU signal on downstream bandwidth, proposed architecture also provides the efficient bandwidth utilization.

Adaptive bandwidth binning for bandwidth management

In this paper, we present a novel bandwidth management scheme that we call adaptive bandwidth binning (ABB). ABB is presented in the context of a DOCSIS cable network, but it has obvious applicability to downstream service on any shared medium access network in which all downstream traffic is scheduled by a single headend device such as a CMTS or wireless base station or access point.ABB is capable of providing approximate weighted max-min fair sharing of downstream bandwidth via a low-overhead scheduler that requires only a small number of permanently allocated queues. A modern delay-based active queue management (AQM) technique is employed to control delays.The performance of ABB is evaluated via ns-2 simulations in which workloads include FTP, HTTP-based adaptive streaming (HAS), and web traffic targeted for different tiered service quality levels. Our results show that ABB is able to provide approximate weighted max-min fair bandwidth allocation among responsive high bandwidth flows while isolating them from low bandwidth and latency sensitive flows. The use of CoDel in each ABB queue is effective in managing latency as required. The use of flow weights in ABB supports service tiering in which subscribers pay more for higher service rates.

Collaborative video caching scheme over OFDM-based long-reach passive optical networks

Abstract Long-reach passive optical networks (LR-PONs) are now considered as a desirable access solution for cost-efficiently delivering broadband services by integrating metro network with access network, among which orthogonal frequency division multiplexing (OFDM)-based LR-PONs gain greater research interests due to their good robustness and high spectrum efficiency. In such attractive OFDM-based LR-PONs, however, it is still challenging to effectively provide video service, which is one of the most popular and profitable broadband services, for end users. Given that more video requesters (i.e., end users) far away from optical line terminal (OLT) are served in OFDM-based LR-PONs, it is efficiency-prohibitive to use traditional video delivery model, which relies on the OLT to transmit videos to requesters, for providing video service, due to the model will incur not only larger video playback delay but also higher downstream bandwidth consumption. In this paper, we propose a novel video caching scheme that to collaboratively cache videos on distributed optical network units (ONUs) which are closer to end users, and thus to timely and cost-efficiently provide videos for requesters by ONUs over OFDM-based LR-PONs. We firstly construct an OFDM-based LR-PON architecture to enable the cooperation among ONUs while caching videos. Given a limited storage capacity of each ONU, we then propose collaborative approaches to cache videos on ONUs with the aim to maximize the local video hit ratio (LVHR), i.e., the proportion of video requests that can be directly satisfied by ONUs, under diverse resources requirements and requests distributions of videos. Simulations are finally conducted to evaluate the efficiency of our proposed scheme.

Flexible 16 $\times$ 10-Gb/s All-Optical Broadcast and Multicast TWDM Passive Optical Network

To achieve flexible packet routing in a time wavelength-division multiplexing passive optical network (PON) architecture, most proposed systems use a tunable transceiver in the optical line terminal (OLT). The tunable transceiver is attractive for use in a PON system because it is able to broadcast and multicast packets within the entire PON system, being limited only to a single PON link. The proposed all-optical packet routing (AOPR) module was designed to incorporate a fixed-type wavelength OLT transmitter with a continuous-wave pump probe signal module. The design of the module is based on the ALL-ON method to support all broadcast signals, which replaces the wavelength tuning feature in the tunable OLT transmitter. The proposed architecture was designed using the multicasting cross-gain modulation (XGM) method. In this proposed design, the XGM function of the OLT system becomes a part of the AOPR OLT transmitter. The arrangement of this design aims to generate single or multiple wavelengths in a downstream direction in each OLT PON port. The measurement results revealed that the proposed system can handle a total of 160-Gb/s broadcast downstream bandwidth to serve 16 PON links using $16\lambda$ with a maximum of 2048 users.

Software defined flexible and efficient passive optical networks for intra-datacenter communications

Facing the huge traffic challenge, optical networking shows great advantages on capacity and energy issues. However, the efficiency and flexibility are not satisfactory to the data center networks, especially for intra-datacenter communications. This article reviews the typical architectures of data center networks, and suggests that TWDM-PON system can be used in the edge layer and aggregation layer in the datacenter networks. It proposes a software defined flexible and efficient passive optical network, combining the software defined technology and network coding, for intra-datacenter communications. Network coding is applied to increase the downstream bandwidth efficiency and overcome network bottleneck, and software defined technology provides the flexibility on wavelength assignment according to traffic statistics dynamically. To increase more efficiency, a seamless DBA (S-DBA) scheme and an ONU grouping algorithm are proposed to fully utilize the upstream idle time and minimize the traffic entering into the core layer of the datacenter networks. They realize flexible scheduling and resource allocation both in time domain and wavelength domain. The experimental simulations indicate that the proposed schemes and algorithms provide low delay, good fairness, increased efficiency and network flexibility.

Fair Bandwidth Sharing Scheme Based on Upload Traffic Control

The current paper presents the evaluation of new fair downstream bandwidth sharing strategy and effective shared link utilization for TCP/IP networks. The proposed method provides download bandwidth fair sharing among multiple data flows based on their upload per-flow rate limitation. We evaluate the current approach by controlling upload rate to obtain fair download bandwidth sharing for each of the flows in the link. The performance of the proposed method is evaluated on physical test network. The experimental results demonstrate that our approach can successfully provide fair bandwidth distribution among multiple data flows and can be promising method for bandwidth management in the real data networks. DOI: http://dx.doi.org/10.5755/j01.eee.20.1.6172

A Hybrid Scalable Peer-to-Peer IP-Based Multimedia Services Architecture in Ethernet Passive Optical Networks

Peer-to-peer (P2P) applications such as P2P video streaming and internet video calling have gained tremendous popularity and are expected to be vastly increasing in the next few years. However, low-cost large-scale video services have remained an intangible goal. The ethernet passive optical network (EPON) is being regarded as one of the promising for next-generation optical access solutions in the access networks attempt to tackle this problem but facing a major challenge to offer scalable large-scale video services. Therefore, in this paper, we propose an architecture which combines the advantages of EPON and P2P architecture to provide scalable Internet Protocol delivery multimedia services and improve quality-of-services. In the proposed architecture, we design new optical network unit (ONU) mechanisms, which support traffic redirection communication among ONUs in combination with caching. Thus, it can reduce the resource consumption and add extra downstream bandwidth at the optical line terminal since the intra-PON traffic is not necessary to be buffered and scheduled in the downstream direction. Finally, we propose a “Redirect” dynamic bandwidth allocation scheme, which can support intra-PON traffic redirection and intertraffic bandwidth allocation. Simulation results have shown that our proposed architecture can improve the overall QoS in terms of end-to-end delay, jitter, system throughput, fairness, and packet dropping rate.

Downstream-based Scheduling for Energy Conservation in Green EPONs

Maximizing the optical network unit's (ONU) sleep time is an effective approach for achieving maxi- mum energy conservation in green Ethernet passive optical networks (EPONs). While overlapping downstream and upstream ONU transmissions can maximize the ONU sleep time, it jeopardizes the quality of service (QoS) performance of the network, especially for downstream traffic in case the overlapping is based on the upstream time slot. In this paper, we study the downstream traffic performance in green EPONs under the limited service discipline and the upstream-based overlapped time window. Specifically, we first derive the expected mean packet delay, and then present a closed-form expression of the ONU sleep time, setting identical upstream/downstream transmission cycle times based on a maximum downstream traffic delay re- quirement. With the proposed system model, we present a novel downstream bandwidth allocation scheme for energy conservation in green EPONs. Simulation results verify the proposed model and highlight the advantages of our scheme over conventional approaches.

Multicast polling for 10G-EPON

A multicast polling scheme is proposed for 10G Ethernet passive optical networks (10G-EPONs). In the multicast polling scheme, the GATE message is broadcast to all ONUs with a new op-code of 0007. Comparing the proposed multicasting with the traditional unicasting scheme, the downstream bandwidth consumption for the control packet of the multicast is 0.011% compared with the unicast of 0.11% at the cycle time of 2ms. As a result of the upstream performance, the channel utilisation improves 3% and the saturation offered load of the end-to-end delay for the multicast and the unicast is 0.8 and 0.7, respectively.

Understanding Characteristics of Available Bandwidth in Wireless Environment

This paper investigates some important characteristics of available Internet bandwidth in commercial wireless environment which have become increasingly available everywhere. Through extensive experiments and performance analysis, the paper identifies three important characteristics. First, the bandwidth bottleneck in a commercial wireless environment lies on the edge of the Internet. Second, the available downstream bandwidth is usually larger than the available upstream bandwidth. Finally, available bandwidth remains relatively persistent and piecewise stationary.

On‐demand data co‐allocation with user‐level cache for grids

AbstractConventional remote data access middlewares usually provide client applications with either a pre‐staging scheme or an on‐demand access scheme to fetch data. The pre‐staging scheme uses parallel downloads to fetch a completed input file from multiple data sources, even when only a tiny file fragment is required. Such a transfer scheme consumes unnecessary data transmission time and storage space. In contrast, the on‐demand scheme downloads only the required data blocks from a single data source and does not fully utilize the downstream bandwidth of the computing nodes. This paper presents a middleware called ‘Spigot’ that facilitates legacy (grid‐unaware) applications to transparently access remote data by using native I/O function calls. Spigot uses the on‐demand concept to avoid unnecessary data transfer and adopts a co‐allocation download algorithm to improve the data transfer performance. Moreover, it uses the pre‐fetching strategy to reduce the data waiting time by overlapping data acquisition and data processing. It also provides the client application with its own user‐level cache, which is advantageous since a larger cache space is available in comparison with the kernel‐level cache. Further, it is easy to maintain data consistency between Spigot nodes. The experimental results indicate that Spigot achieves superior performance in reducing the data waiting time than the pre‐staging and the on‐demand access schemes. Copyright © 2010 John Wiley & Sons, Ltd.

P2P (Peer-to-Peer) 비디오 스트리밍을 위한 다중 비디오 품질 인센티브 기법

인터넷 상에서의 비디오 스트리밍을 위한 대안으로서 P2P(Peer-to-Peer)가 관심을 받고 있다. P2P 시스템은 피어들의 대역폭 기여에 의존하고 있지만, 피어들은 자신의 대역폭을 제공하는 것을 꺼리는 경향이 있다. 본 논문에서 우리는 상향 대역폭 기여를 촉진하는 P2P 스트리밍 시스템을 제안한다. 제안 시스템에서 피어들 간의 공평성을 유지하고, 제어 가능한 방법으로 협력적인 피어와 이기적인 피어에게 다른 품질의 비디오를 제공한다. 제안 시스템은 기여한 상향 대역폭에 기초한 평가 기법으로 피어가 협력적인지 이기적인지를 결정하고, 협력적인 피어들에게는 인센티브로서 고품질의 비디오를 제공한다. 또한 제안시스템이 효과적으로 동작할 수 있도록 트리 재건조 알고리즘을 제안한다. 시뮬레이션을 통해, 트리 재건조 알고리즘이 효과적으로 동작하며, 인센티브 기법이 협력적인 피어에게 더 많은 하향 대역폭을 할당하고 이기적인 피어에게는 저품질 비디오를 제공함을 보인다. Peer-to-Peer (P2P) has attracted attention as an alternative way to enable streaming videos on the Internet. Although P2P systems depend on bandwidth contribution from peers, peers are likely to refuse to contribute their bandwidth. In this paper, we proposed a P2P streaming system that encourages peers to contribute their upstream bandwidth by maintaining fairness among peers and providing different video quality between cooperative peers and selfish peers with a manageable way. Our proposed system determines if peers are cooperative or selfish by a rating mechanism based on their contributed upstream bandwidth, and offers a high quality video to cooperative peers as an incentive. Also we propose a tree reconstruction algorithm to make the system work effectively. Through simulation, we show that the tree reconstruction algorithm works effectively, and our incentive mechanism allocates more downstream bandwidth to cooperative peers and punished selfish peers with low quality video.

A Weighted Scheduling Mechanism to Reduce Multicast Packet Loss in IPTV Service over EPON

This letter proposes a weighted scheduling mechanism for Internet protocol television (IPTV) to improve the loss performance of multicast transmission over an Ethernet passive optical network (EPON). We propose a new weight policy from the number of multicast receivers to proportionally allocate the downstream bandwidth of IPTV traffic. The proposed mechanism is used in an optical line terminal to decrease lost packets of favorite IPTV services because the lost multicast packets are proportional to the number of receivers. The total proportion of lost multicast packets is reduced by up to 73% in an EPON.

波分复用无源光网络中基于周期轮询的动态波长和带宽分配算法

Cyclic polling-based dynamic wavelength and bandwidth allocation algorithm supporting differentiated classes of services in wavelength division multiplexing (WDM) passive optical networks (PONs) is proposed. In this algorithm, the optical line terminal (OLT) polls for optical network unit (ONU) requests to transmit data in a cyclic manner. Services are categorized into three classes: expedited forward (EF) priority, assured forwarding (AF) priority, and best effort (BE) priority. The OLT assigns bandwidth for different priorities with different strategies. Simulation results show that the proposed algorithm saves a lot of downstream bandwidth under low load and does not show the light-load penalty compared with the simultaneous and interleaved polling schemes.

Architecture and Design of IP Broadcasting System Using Passive Optical Network

We propose an IP broadcasting system architecture using passive optical networks (PON) utilizing the optical broadcast links of a PON with a downstream bandwidth allocation algorithm to provide a multi-channel IP broadcasting service to home subscribers on single broadband IP network infrastructures. We introduce the design and adaptation of the optical broadcast links to effectively broadcast video contents to home subscribers. We present a performance analysis that includes the downstream bandwidth utilization efficiency of the broadcast link and the bandwidth control of the IP broadcasting and Internet data. Our analysis and simulation results show that the proposed system can provide 100 HDTV channels to every user over fiber lines. We also propose an IPTV channel selection mechanism in an ONT by selecting a broadcast stream. We developed and evaluated a prototype that can achieve a 15-msec IPTV channel selection speed.

A VME-Based Readout System for the CMS Preshower Sub-Detector

The CMS preshower is a fine grain detector that comprises 4288 silicon sensors, each containing 32 strips. The raw data are transferred from the detector to the counting room via 1208 optical fibres. Each fibre carries a 600-byte data packet per event. The maximum average level-1 trigger rate of 100 kHz results in a total data flow of ~72 GB/s from the preshower. For the readout of the preshower, 56 links to the CMS DAQ have been reserved, each having a bandwidth of 200 MB/s (2 kB/event). The total available downstream bandwidth of GB/s necessitates a reduction in the data volume by a factor of at least 7. A modular VME-based system is currently under development. The main objective of each VME board in this system is to acquire on-detector data from at least 22 optical links, perform on-line data reduction and pass the concentrated data to the CMS DAQ. The principle modules that the system is based on are being developed in collaboration with the TOTEM experiment.

Full-sharing: efficient bandwidth scheduling for video streaming over broadband cable networks (BCNs)

Broadband Cable Networks (BCNs) bring high-speed Internet access to home and make emerging multimedia streaming applications feasible. However, bandwidth contention is still a challenging problem in providing efficient IP-based Video-On-Demand (VOD) service on BCNs, due to the lack of effective approaches to exploit the unique characteristics of BCNs. To address the bandwidth contention issue, we propose an efficient video scheduling technique, called full-sharing scheduling in this paper. This technique fully exploits the unique characteristics of BCNs to reduce the bandwidth consumption of video sessions sharing a cable channel of fixed capacity, thereby maximizing the number of simultaneous video sessions on the single channel. Furthermore, we analyze the expected bandwidth and the session blocking probability of a video under the full-sharing scheduling. Based on this analysis, we design an efficient video assignment mechanism for maximizing the profit of a VOD system in scheduling videos on BCNs. Through both analysis and simulation, we show that our approach minimizes the bandwidth consumption of video sessions compared with the previous approaches and has significant advantages on BCNs. The proposed approach is also directly applicable on other broadcast/multicast networks in which clients have sufficient buffer and downstream bandwidth, e.g., satellite broadband networks.