ISKIP: a fair and efficient scheduling algorithm for input-queued crossbar switches

The delay and throughput characteristics of a packet switch depend mainly on the queueing scheme and the scheduling algorithm deployed at the switch. Early research on scheduling algorithms has mainly focused on maximum weight matching scheduling algorithms. It is known that maximum weight matching algorithms guarantee the stability of input-queued switches, but are impractical due to their high computational complexity. Later research showed that the less complex maximal matching algorithms can stabilize input-queued switches when they are deployed with a speed-up of two. For practical purposes, neither a high computational complexity nor a speed-up of two is desirable.In this paper, we investigate the application of matching algorithms that approximate maximum weight matching algorithms to scheduling problems. We show that while having a low computational complexity, they guarantee the stability of input queued switches when they are deployed with a moderate speed-up.In particular, we show that the improve_matching algorithm stabilizes input-queued switches when it is deployed with a speed-up of 3<over>2+ε.In a second step, we further improve on these results by proposing a class of maximal weight matching algorithms that stabilize an input-queued switch without any speed-up.Whereas initial research has only focused on scheduling algorithms that guarantee the stability of a single switch, recent work has shown how scheduling algorithms for single switches can be modified in order to design distributed scheduling algorithms that stabilize networks of input-queued switches. Using those results, we show that the switching algorithms proposed in this paper do not only stabilize a single switch, but also networks of input-queued switches.

Currently the research on input-queued ATM switches is one of the most active research fields. Many achievements have been made in the research on scheduling algorithms for unicast input-queued ATM switches and also applied in commerce. But the goal of the research on scheduling algorithms for multicast input-queued ATM switches only focuses on providing high throughput and inadvertently ignoring its undesired effects on QoS of the multicast traffic. In this paper we present a design scheme of input-queued ATM switches supporting multicast and corresponding scheduling algorithm, referred to as multicast longest normalized queue first (MLNQF). The MLNQF algorithm has the characteristics of improving throughput, satisfying QoS requirements and providing service fairly.

Scheduling algorithms for input-queued packet switches have been widely researched. It has been shown that various classes of scheduling algorithms provide guarantees on stability and on average delay for single switches. However, recent research has demonstrated that most of these scheduling algorithms do not guarantee stability for networks of switches. Most of the research that treats networks of switches proposes switching policies that require coordination among the single switches. The problem to find <i>distributed</i> scheduling policies that guarantee the stability of a network of switches has so far only been investigated for a policy based on a computationally very complex maximum weight matching algorithm. In this paper, we investigate <i>distributed</i> scheduling algorithms of <i>low complexity</i> that belong to the classes of maximal weight matching algorithms, <i>p</i>-maximal weight matching algorithms for switch architectures based on a space-division multiplexing extension, and MNCM algorithms. For these scheduling algorithms, we prove the stability of networks of input-queued switches where all switches deploy the same scheduling policy. We also show that networks of input-queued switches in which specific classes of different switching policies are deployed simultaneously at different switches are stable.

An efficient iterative scheduling algorithm for input-queued switches, called round robin with longest queue first (RR/LQF), is proposed in this paper. RR/LQF consists of three phases: report, grant, and accept. In each phase, only a single-bit message per port is sent for reporting a packet arrival, granting an input for packet sending, or accepting a grant. In both the grant and accept phases, scheduling priority is given to the preferred input–output pairs first and the longest virtual output queuing (VOQ) next. The notion of the preferred input–output pair is to keep a global RR schedule among all the inputs and the outputs. By serving the preferred input–output pairs first, the match size tends to be maximized. By serving the longest VOQ next, the match weight is also boosted. When RR/LQF is executed for a single iteration (i.e., RR/LQF-1), we show by simulations that RR/LQF-1 outperforms all the existing single-bit-single-iteration scheduling algorithms. When RR/LQF is executed up to $N$ iterations (i.e., RR/LQF- $N$ ), we prove that under any admissible traffic pattern, RR/LQF- $N$ is stable with a speedup of $2-1/N$ , where $N$ is the switch size. To the best of our knowledge, this is the first work showing that an iterative scheduling algorithm is stable with a speedup less than 2. We then generalize RR/LQF to become a class of algorithms that have the same speedup bound of $2-1/N$ . Efforts are then made to further reduce the implementation complexity of RR/LQF. To this end, the pipelined RR/LQF and RR/RR, a simpler variant of RR/LQF, are proposed.

Fair scheduling or Fair Queueing (FQ) algorithms have received much attention in recent years because of their ability to provide a wide range of Quality-ofService (QoS) guarantees to end users. In this paper, we present a new analysis method that can statistically model such fair scheduling algorithms under Poisson arrivals and a general packet length distribution. We coin the new term M/G/FQ to describe this analysis method, which fits a broad range of scheduling policies including WFQ, SCFQ, SFQ and SPFQ.

Static round-robin scheduling algorithms for scalable switches by Pun Kong Hong thesis 2002 vii, 48 leaves : ill. ; 30 cm The Clos-network is widely recognized as a scalable architecture for high-performance switches and routers. One of the key challenges…Read more ›

Input-Queued switching fabrics are widely used in high speed network switches for their scalability. However, a scheduling algorithm must be elaborative designed for input-queued switches to get high throughput. The randomized algorithms are attractive in kinds of scheduling algorithms for their low complexity and well performance. In this paper, a fluid model is introduced to analyze the rate stability of switching systems with randomized schedulers. By this method, we proved that the randomized scheduling algorithm can achieve 100% throughput under any admissible traffics which satisfy the strong law of large numbers (SLLN).

In 5G networks, wide-band mmWave can be used to provide extreme data rates to user equipments (UEs). However, since mmWave is coverage limited, it necessitates dense placement of base stations, which in turn can significantly increase the fiber deployment cost. One solution being considered is to replace fibers with Integrated Access and Backhaul (IAB) network, where a part of the wireless spectrum is used for connecting base stations. In an asymmetric IAB network, standard proportional fair scheduling algorithm (PF) fails to distribute resources among UEs fairly. We propose a new weighted proportional fair (WPF) scheduling algorithm to improve the fairness of UE’s achieved throughput in an IAB network. Also to mitigate congestion in IAB nodes and improve system throughput, we propose an IABaware end-to-end flow control (I-EEFC) algorithm. Through detailed analyses for both symmetric and asymmetric network topologies, we show that our proposed combined scheduling and flow control algorithm (WPF+I-EEFC) improves both fairness and system throughput.

GENIUS – A genetic scheduling algorithm for high-performance switches

Packet switching remains one of the bottlenecks in building fast Internet routers. Load balancing and switch scheduling are two important algorithms in the effort to maximize the throughput and minimize the latency of these packet switches. A load balancing algorithm regulates the traffic to conform to the service rates while a switch scheduling algorithm allocates the service rates adaptive to the arrival patterns. Many existing load balancing and switch scheduling algorithms are very similar. We show that load balancing and switch scheduling systems are dual systems based on the linear queue dynamics approximation. This allows us to cast a load balancing problem as a scheduling problem, and vice versa. We further show an example of designing a new algorithm for load balancing using an existing scheduling algorithm based on the duality. The duality perspective also allows us to solve unknown problems. We find the entropy rate of the randomized bandwidth allocation system with linear queue dynamics based on the knowledge of the entropy rate of the randomized load balancing system. For the general case, we find both an upper and a lower bound on the entropy rate. The joint use of dual load balancing and switch scheduling algorithms leads to performance gains as we show using mean field analysis.

Analysis of temporal and throughput fair scheduling in multirate WLANs

Artificial intelligence (AI) algorithms are prone to bias at multiple stages of model development, with potential for exacerbating health disparities. However, bias in imaging AI is a complex topic that encompasses multiple coexisting definitions. Bias may refer to unequal preference to a person or group owing to preexisting attitudes or beliefs, either intentional or unintentional. However, cognitive bias refers to systematic deviation from objective judgment due to reliance on heuristics, and statistical bias refers to differences between true and expected values, commonly manifesting as systematic error in model prediction (ie, a model with output unrepresentative of real-world conditions). Clinical decisions informed by biased models may lead to patient harm due to action on inaccurate AI results or exacerbate health inequities due to differing performance among patient populations. However, while inequitable bias can harm patients in this context, a mindful approach leveraging equitable bias can address underrepresentation of minority groups or rare diseases. Radiologists should also be aware of bias after AI deployment such as automation bias, or a tendency to agree with automated decisions despite contrary evidence. Understanding common sources of imaging AI bias and the consequences of using biased models can guide preventive measures to mitigate its impact. Accordingly, the authors focus on sources of bias at stages along the imaging machine learning life cycle, attempting to simplify potentially intimidating technical terminology for general radiologists using AI tools in practice or collaborating with data scientists and engineers for AI tool development. The authors review definitions of bias in AI, describe common sources of bias, and present recommendations to guide quality control measures to mitigate the impact of bias in imaging AI. Understanding the terms featured in this article will enable a proactive approach to identifying and mitigating bias in imaging AI. Published under a CC BY 4.0 license. Test Your Knowledge questions for this article are available in the supplemental material. See the invited commentary by Rouzrokh and Erickson in this issue.

The Internet is facing two problems simultaneously: there is a need for a faster switching/routing infrastructure and a need to introduce guaranteed qualities-of-service (QoS). Each problem can be solved independently: high performance routers can be made faster by using input-queued crossbars instead of shared memory systems; QoS can be provided using packet fair queueing (PFQ) algorithms. Until now, however, the two solutions have been mutually exclusive-all of the work on PFQ algorithms has required that routers use output-queueing or centralized shared memory. In this paper, we design and implement a packet scheduling algorithm, DF/sup 2/Q (distributed feedback fair queueing), on the basis of CIOQ (combined input output queueing) architecture. The most important feature of this scheduling algorithm is the introduction of a feedback mechanism. We analyze and discuss the performance of DF/sup 2/Q, and the experimental results show that it can avoid internal congestion effectively and improve the efficiency of resource utilization.

Due to its simplicity and scalability, the differentiated services (DiffServ) model is expected to be widely deployed across the Internet. For each DiffServ compliant router, the scheduling algorithm is critical in implementing per hop behaviors (PHBs), according to which packets are forwarded. We propose a hierarchical DiffServ scheduling (HDS) algorithm to support DiffServ classes on input-queued switches. The proposed HDS algorithm features in a hierarchical scheduling scheme that consists of two levels of schedulers. One level is the central scheduler which is designed to maximize the switch throughput by computing a maximal size matching between input ports and output ports. The other level is formed by input port schedulers which provide differentiated services by serving cells belonging to different classes dynamically. Using such a hierarchical scheme, the implementation complexity and the amount of information needed to be transmitted between input ports and the central scheduler are dramatically reduced compared with existing maximal weight matching based DiffServ scheduling algorithms. The tradeoff of its slightly worse delay performance is acceptable.

All-optical shared-buffer packet switches have been studied intensively in literature and many scheduling algorithms have been proposed. However, these algorithms either suffer from not being able to make resource reservation, or require high time-complexity to compute scheduling assignment for packets. In this paper, we propose a fast scheduling algorithm for all-optical shared-buffer packet switches. In our algorithm, packet scheduling is first formulated as a tree-searching problem. By breaking down the search tree into multiple smaller subsets and assigning each subset to a secondary processor, solutions can be obtained in a much shorter duration since the secondary processors are working in parallel. For instance, a scheduling assignment can be calculated for a packet in 55 ns with 8 processors, and in 25 ns with 64 processors, assuming a processor clock rate of 200 MHz. We show that our algorithm can achieve a loss rate of ~10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-7</sup> even at load 0.9 for a 32times32 switch.