Publications

DiffPerf: Towards Performance Differentiation and Optimization with SDN Implementation

Published in IEEE TNSM (under review), 2021

Continuing the current trend, Internet traffic is expected to grow significantly over the coming years, with video traffic consuming the biggest share. On the one hand, this growth poses challenges to access providers, who have to upgrade their infrastructure to meet the growing traffic demands as well as find new ways to monetize their network resources. On the other hand, despite numerous optimizations of the transport congestion control, and the switch buffer sizing and management algorithms; however, the complex interaction among all of them still leads to uncertain user performance and thus degrades user-perceived quality, under various network and traffic conditions. The culprit is the difficulty to dynamically control the amount of bandwidth allocated to each of the competing flows under bottleneck due to the algorithms lack of visibility of buffer content where the flows reside. We address both concerns by proposing DiffPerf, an in-network bandwidth allocation system. At a macroscopic level, DiffPerf elastically allocates bandwidth to performance-centric service classes pre-defined by access provider, and at a microscopic level it relies on a lightweight learning algorithm to statistically differentiate and isolate traffic flows in each class to help them achieve better performance in an online and dynamic manner. We built two SDN-based prototypes of DiffPerf; one on OpenDaylight with OpenFlow Brocade hardware switches and the other with data plane Intel Tofino hardware switches. We evaluate it from an application perspective for ABR video streaming as it accounts for a majority of the Internet traffic. Our evaluations demonstrate the practicality and flexibility that DiffPerf provides access providers with capabilities through which a spectrum of qualities are provisioned at multiple classes and assists users within the same class in achieving better fairness and improving overall user-perceived quality.

Recommended citation: Walid Aljoby, Xin Wang, Dinil Divakaran, Tom Fu, Richard Ma. "DiffPerf:Towards Performance Differentiation and Optimization with SDN Implementation". IEEE Transactions on Network and Service Management (IEEE TNSM), "under review"

DiffPerf: An In-Network Performance Optimization for Improving User-Perceived QoE

Published in IEEE NetSoft, 2021

Continuing the current trend, Internet traffic is expected to grow significantly over the coming years, with video traffic consuming the biggest share. Despite numerous optimizations of the transport congestion control, and the switch butter sizing and management algorithms; however, the complex interaction among all of them still leads to uncertain user performance and thus degrades user-perceived quality, under various network and traffic conditions. The culprit is the difficulty to dynamically control the amount of bandwidth allocated to each of the competing flows under bottleneck due to the algorithms lack of visibility of butter content where the flows reside. We address this bandwidth allocation problem by proposing DiffPerf, an in-network system that relies on a lightweight learning algorithm to statistically differentiate and isolate user flows to help them achieve better performance in an online and dynamic manner. We built two SDN-based prototypes of DiffPerf; one on OpenDaylight with OpenFlow Brocade switch and the other with programmable data plane Barefoot Tofino switch. We evaluate it from an application perspective for ABR video streaming as it accounts for a majority of the Internet traffic. Our evaluations demonstrate the practicality and flexibility that DiffPerf assists users in achieving better fairness and improving overall user-perceived quality. On average DiffPerf yields a quality improvement of about 4.6× and 1.2× higher than TCP BBR and TCP CUBIC, respectively.

Recommended citation: Walid Aljoby, Xin Wang, Dinil Divakaran, Tom Fu, Richard Ma. "DiffPerf: An In-Network Performance Optimization for Improving User-Perceived QoE". In the 7th International Conference on Network Softwarization (NetSoft), Tokyo, Japan.

On SDN-Enabled Online and Dynamic Bandwidth Allocation for Stream Analytics (Extended Version)

Published in IEEE JSAC, 2019

Data communication in cloud-based distributed stream data analytics often involves a collection of parallel and pipelined TCP flows. As the standard TCP congestion control mechanism is designed for achieving “fairness” among competing flows and is agnostic to the application layer contexts, the bandwidth allocation among a set of TCP flows traversing bottleneck links often leads to sub-optimal application-layer performance measures, e.g., stream processing throughput or average tuple complete latency. Motivated by this and enabled by the rapid development of the Software-Defined Networking (SDN) techniques, in this paper, we re-investigate the design space of the bandwidth allocation problem and propose a cross-layer framework which utilizes the additional information obtained from the application layer and provides on-the-fly and dynamic bandwidth adjustment algorithms for helping the stream analytics applications achieving better performance during the runtime. We implement a prototype cross-layer bandwidth allocation framework based on a popular open-source distributed stream processing platform, Apache Storm, together with the OpenDaylight controller, and carry out extensive experiments with real-world analytical workloads on top of a local cluster consisting of 10 workstations interconnected by a SDN-enabled fat-tree like testbed. The experiment results clearly validate the effectiveness and efficiency of our proposed framework and algorithms. Finally, we leverage the proposed cross-layer SDN framework and introduce an exemplary mechanism for bandwidth sharing and performance reasoning among multiple active applications and show a case of a point solution on how to approximate application-level fairness.

Recommended citation: Walid Aljoby, Xin Wang, Tom Fu, Richard Ma. "On SDN-Enabled Online and Dynamic Bandwidth Allocation for Stream Analytics". IEEE Journal on Selected Areas in Communications (JSAC), 2019.

On SDN-Enabled Online and Dynamic Bandwidth Allocation for Stream Analytics

Published in IEEE ICNP, 2018

Data communication in cloud-based distributed stream data analytics often involves a collection of parallel and pipelined TCP flows. As the standard TCP congestion control mechanism is designed for achieving “fairness” among competing flows and is agnostic to the application layer contexts, the bandwidth allocation among a set of TCP flows traversing bottleneck links often leads to sub-optimal application-layer performance measures, e.g., stream processing throughput or average tuple complete latency. Motivated by this and enabled by the rapid development of the Software-Defined Networking (SDN) techniques, in this paper, we re-investigate the design space of the bandwidth allocation problem and propose a cross-layer framework which utilizes the additional information obtained from the application layer and provides on-the-fly and dynamic bandwidth adjustment algorithms for helping the stream analytics applications achieving better performance during the runtime. We implement a prototype cross-layer bandwidth allocation framework based on a popular open-source distributed stream processing platform, Apache Storm, together with the OpenDaylight controller, and carry out extensive experiments with real-world analytical workloads on top of a local cluster consisting of 10 workstations interconnected by a SDN-enabled switch. The experiment results clearly validate the effectiveness and efficiency of our proposed framework and algorithms.

Recommended citation: Walid Aljoby, Xin Wang, Tom Fu, Richard Ma. "On SDN-Enabled Online and Dynamic Bandwidth Allocation for Stream Analytics". IEEE 26th International Conference on Network Protocols (ICNP), Cambridge, UK.

Impacts of task placement and bandwidth allocation on stream analytics

Published in IEEE ICNP, 2017

We consider data intensive cloud-based stream analytics where data transmission through the underlying communication network is the cause of the performance bottleneck. Two key inter-related problems are investigated: task placement and bandwidth allocation. We seek to answer the following questions. How does task placement make impact on the application-level throughput? Does a careful bandwidth allocation among data flows traversing a bottleneck link results in better performance? In this paper, we address these questions by conducting measurement-driven analysis in a SDN-enabled computer cluster running stream processing applications on top of Apache Storm. The results reveal (i) how tasks are assigned to computing nodes make large difference in application level performance; (ii) under certain task placement, a proper bandwidth allocation helps further improve the performance as compared to the default TCP mechanism; and (iii) task placement and bandwidth allocation are collaboratively making effects in overall performance.

Recommended citation: Walid Aljoby, Tom Fu, Richard Ma. "Impacts of task placement and bandwidth allocation on stream analytics". IEEE 25th International Conference on Network Protocols (ICNP), Toronto, Canada.

A novel approach for extracting spatial correlation of visual information in heterogeneous wireless multimedia sensor networks

Published in Computer Networks, 2017

In applied wireless multimedia sensor networks, heterogeneous camera nodes with different sensing capabilities are usually deployed due to their role in enhancing the overall network performance and lifetime. Exploiting the correlation characteristics of the overlapping fields of view of different camera nodes would enable very efficient collaborative in-network processing algorithms. This paper introduces a novel geometrical model to extract the spatial correlation characteristics of heterogeneous camera nodes in wireless multimedia sensor networks, taking into consideration the different sensing radii and the angles of view of the camera nodes. The novelty in the proposed model is in using virtual cameras at the two far ends of the camera’s field-of-view. In order to provide better coverage of the field-of-view and hence better estimation of the correlation characteristics, key points in the observed scene are projected at the virtual cameras; in addition to the physical camera. This is shown to significantly improve the estimation of the spatial correlation characteristics to be almost identical to that extracted by well-known image processing techniques. An analytical closed-form solution of the proposed model is derived and validated and its performance is evaluated and compared against the state-of-the-art models; in terms of correlation characteristics estimating accuracy, visual information gain, and distortion ratio. The experimental and simulation results demonstrate that, compared to similar existing models, the proposed model achieves very accurate estimation of the correlation characteristics and significant improvement on the overall network resource utilization for a negligible increase in the camera node’s computational cost.

Recommended citation: Moad Mowafi, Fahed Awad, Walid Aljoby. "A novel approach for extracting spatial correlation of visual information in heterogeneous wireless multimedia sensor networks". Computer Networks, 2014.