Limited Buffer Size Research Articles

Investigation of Tandem Queuing Systems Using Machine Learning Methods

This paper considers tandem queuing systems with limited buffer sizes in each phase. The system handles an incoming correlated MAP flow and the service time obeys a PH-distribution. Models of such systems and methods for their investigation are briefly reviewed from the historical perspective. According to the review, the problem statement presented below, the methods proposed for solving this problem, and the corresponding results are novel. An accurate algorithm for calculating the performance characteristics of low-dimensional tandem queuing systems is described, including an estimate of the algorithm’s complexity. An approach using both machine learning and simulation modeling is suggested for the investigation of high-dimensional tandem queuing systems. Numerical analysis results are provided to show the effectiveness of machine learning methods for estimating the performance of tandem queuing systems.

Automatic Design of Efficient Heuristics for Two-Stage Hybrid Flow Shop Scheduling

This paper addresses the two-stage hybrid flow shop scheduling problem with a batch processor in the first stage and a discrete processor in the second stage. Incompatible job families and limited buffer size are considered. This hybrid flow shop configuration commonly appears in manufacturing operations and the batch processor is always the bottleneck which breaks the symmetry of processing time. Since making a real-time high-quality schedule is challenging, we focus on the automatic design of efficient heuristics for this two-stage problem based on the genetic programming method. We develop a hyper-heuristic approach to automate the tedious trial-and-error design process of heuristics. The goal is to generate efficient dispatching rules for identifying complete schedules to minimize the total completion time. A genetic programming with cooperative co-evolution approach is proposed to evolve the schedule policy automatically. Numerical results demonstrate that the proposed approach outperforms both the constructive heuristic and meta-heuristic algorithms, and is capable of producing high-quality schedules within seconds.

Modeling and analysis of the security system information in service networks

The optimal setting of the information security system (ISS) is determined as a system of increasing service with loss, with an unlimited amount of buffer memory, expanding the use of computing network security by transferring all unauthorized access flows (UAF) from the protection mechanism (PM). Computational procedures and algorithms have been developed to study the optimal characteristics of the ISS as single-phase multichannel queuing systems (QS) with losses, with a limited and unlimited buffer size. Computational experiments have been carried out and numerical results have been obtained, which allow them to be used in the construction of ISS in the service network of oil and gas facilities.

Congestion control in Internet of Things: Classification, challenges, and future directions

Internet of Things (IoT) is a collection of billions of smart objects connected via different types of communication media. Although IoT devices generate enormous data, they are still constrained by low processing, power, and limited buffer size. Constraints within smart devices are a prime cause of congestion among IoT networks, causing performance degradation and data loss. Hence, this survey focuses on congestion and related issues as the primary source causing significant performance issues in IoT networks. IoT communication is categorized into reliable and unreliable, identical to the Internet-based systems. This survey presents a detailed study of various congestion control schemes for reliable and unreliable communication, as well as evaluate “divergence” among IoT devices. Congestion control within and among IoT networks is either (i) end-to-end, or (ii) hop-by-hop. We summarize and compare the techniques prevalent among existing IoT networks. We further present a detailed study of communication technologies for IoT devices. Moreover, we focus on the various granularities of congestion for the IoT network stack. We also present essential artifacts in the congestion taxonomy, depicting critical aspects of IoT congestion control. Moreover, we give a detailed study of various congestion control algorithms based on rate adaption and traffic engineering schemes.

Weighted Online Fountain Codes With Limited Buffer Size and Feedback Transmissions

Online fountain codes (OFC) have attracted much attention for their good intermediate performance, which is important for receivers with low-complexity requirement. However, low-complexity receivers generally have limited buffer size to store coded symbols that have not been fully decoded yet, as well as limited power budget for feedback transmissions. In this paper, we propose improved transmission schemes for online fountain codes to reduce the buffer occupancy and feedback transmissions. Firstly, we analyze the relationship between buffer occupancy and overhead as well as the relationship between recovery rate and overhead for online fountain codes. Motivated by the analysis, we propose the weighted online fountain codes (WOFC) which can adapt to various buffer sizes by adjusting the weight to control the probability that a coded symbol can be fully processed immediately, and analyze its performance. Then we further propose weighted online fountain codes with low feedback (WOFC-LF), which utilize the proposed analysis to estimate the recovery rate, and reduce feedback transmissions. Simulation results verify the effectiveness of the analysis for both OFC and WOFC, and demonstrate the superior performance of WOFC-LF with limited buffer size and feedback transmissions.

Performance analysis and optimisation of stochastic flow lines with limited material supply

We consider stochastic flow lines with limited buffer sizes and limited material supply. In these systems, the configuration of the flow line parameters and the configuration of the material supply determine the system output. Shortages of material supply can limit the performance of the production system. We use flexible (mixed-integer) linear programming approaches to evaluate and optimise the performance of long stochastic flow lines with limited material supply in discrete and continuous time. The approaches are used to quantify the impact of material shortages on the system output. Further, they are applied to determine the minimum material levels that are required to prevent material shortages of a given flow line configuration. The results of the numerical study reveal insights on the approximation accuracy of the linear programs as well as on the dependence of optimal material levels on flow line characteristics such as the presence of bottleneck machines and the system variability. The contribution of this paper consists of both, integrated models for stochastic flow lines with limited material supply and new insights on the optimal material supply of stochastic flow lines.

Energy-Efficient Optimal Admission Control for Body Area Networks

This paper proposes an optimal Admission Control (AC) scheme for Body Area Networks (BANs). The scheme captures BAN characteristics, such as limited buffer size and power consumption of sensor nodes, and QoS-sensitive heterogeneous traffic types. Unable to admit a new flow, the Hub initially considers a novel mechanism of adjusting some of the already admitted (or new) flows' connection parameters to free up enough bandwidth. Adjustment does not violate a flow's QoS requirements but comes at the cost of extra energy consumption. An efficient scheme is proposed that traverses viable adjustment options until the least costly is found. When adjustment does not suffice, a combination of adjusting a set of flows and terminating some existing ones is considered. For the flow termination scheme, a bandwidth-efficient algorithm is proposed that terminates the least number of flows that have lower priory than the one requesting to join. The optimality of the proposed AC scheme for BANs is also studied. Compared to conventional schemes, our results show on average an increase of up to 33% in the number -and considerable improvement in terms of the priority- of admitted flows, at a diminutive cost of less than 1.5% on the nodes' energy consumption.

Cooperative Network Model for Joint Mobile Sink Scheduling and Dynamic Buffer Management Using Q-Learning

Development of energy-efficient wireless sensor networks is crucial in the deployment of IoT and IIoT for modern day applications like smart home, smart vehicles, and smart industries. Several methods like network clustering, mobile sink deployment and dynamic sensing rate have been used in improving the energy-efficiency of wireless sensor networks in IoT framework. However, these methods have been developed independently which can lead to certain network issues like reduced lifetime, network breakdown among others. In this work, an energy-efficient method that optimizes mobile sink scheduling while concurrently providing dynamic buffer management is proposed. A cooperative network model that incorporates node clustering and mobile sink deployment in variable node sensing rate scenario is first developed. However, in such cooperative network models, mobile sink scheduling and buffer overflow management which causes information loss become challenging. This is primarily due to limited buffer size, variable sensing rate of the nodes, and the unavailability of mobile sink at all times near a cluster. Therefore, a reinforcement Q-learning framework is developed for scheduling the mobile sink while minimizing the information loss caused by buffer overflow in each cluster of a clustered WSN. More specifically, the network behaviour is learnt in the context of buffer overflow using Q-learning approach. The proposed method computes the adaptive halt-times for the mobile sink based on information loss and buffer overflow in each cluster. Performance of the proposed joint mobile sink scheduling and dynamic buffer management method is evaluated on a medium scale WSN. A clustered wireless sensor network with a total of 600 sensor nodes is considered for performance evaluation. The proposed method is shown to learn the variable node sensing rate in a reasonable amount of time using convergence analysis. Numeric evaluations indicate that the proposed method minimizes the information loss in a medium scale wireless sensor network while improving the network lifetime simultaneously. The proposed cooperative network model also outperforms in terms of energy-efficiency when compared to conventional WSN. The results are motivating enough for the use of cooperative network model in practical WSNs for IoT applications.

Workload Control order release in general and pure flow shops with limited buffer size induced blocking: an assessment by simulation

Most manufacturing shops in practice have limited physical space in front of each workstation, due, for example, to physical, economical or operational constraints. As a result, a job may cause blocking because it has to remain at a given station after an operation has been completed until space in front of the next station in its routing becomes available. Despite this practical reality, the Workload Control literature typically assumes infinite buffer limits and therefore neglects the impact of blocking. Using simulation, we highlight the direct, detrimental impact of blocking in both the pure and general flow shop. Workload Control order release dampens the effect of blocking and improves overall performance. This makes Workload Control order release even more important in the context of shops with blocking or physical space constraints. Further analysis reveals that the impact of blocking is less pronounced in the pure flow shop given its directed routing. Finally, most of the blocking that occurs is because jobs cannot enter the shop, i.e. there is no space in front of the gateway station. This re-emphasises the close relationship between blocking and release methods that limit the workload, and it highlights the importance of workload balancing.

Multiple traffic states and Braess' paradox in dynamical networks with limited buffer size

Traffic dynamics has always been a research hotspot of complex networks. In this letter, dynamical networks in which the nodes are moving with limited buffer size are studied. We propose an adaptive routing strategy where Euclidean distance and node load are combined by a tunable parameter. The packet loss and traffic congestion can be observed in our model due to limited buffer size. Traffic congestion will occur unless the tunable parameter is in a critical interval. We mainly focus on the impact of the buffer size on traffic congestion and obtain four different traffic states: partial-, short-, no- and long-congestion state. Moreover, a phenomenon similar to the Braess' paradox can be observed in our model. We also find that the higher the node speed, the worse the traffic capacity.

Buffer-Aided Adaptive Wireless Powered Communication Network With Finite Energy Storage and Data Buffer

In this paper, the access point (AP) in a wireless network is assumed to provide energy supply via wireless energy transfer to multiple terminals in the downlink, and all the terminals use the harvested energy to transmit their collected data to the AP in the uplink in a time division multiple access (TDMA) manner. Each terminal is provisioned with a finite energy storage and a finite data buffer to store the harvested energy and to buffer the arrived data traffic, respectively. Due to the limited data buffer and energy storage size, there might be data loss due to either data buffer overflow or energy storage depletion. Firstly, we aim at maximizing the long-term weighted sum-rate through energy beamforming vector design, power allocations, rate control, time allocations, and transmission mode selection subject to average transmit power, peak transmit power, data loss ratio requirements, practical data buffer as well as energy storage constraints. Secondly, the weighted max-min scheduling scheme is proposed to guarantee the fair access requirement by multiple terminals. Numerical analyses are presented to show that, the proposed adaptive design can substantially improve the average achievable rate region, while the proposed weighted max-min fair scheduling can effectively ensure the fair access requirements.

Major impact of queue-rule choice on the performance of dynamic networks with limited buffer size**Project supported by the National Natural Science Foundation of China (Grant Nos. 71801066 and 71431003) and the Fundamental Research Funds for the Central Universities of China (Grant Nos. PA2019GDQT0020 and JZ2017HGTB0186).

We investigate the similarities and differences among three queue rules, the first-in-first-out (FIFO) rule, last-in-first-out (LIFO) rule and random-in-random-out (RIRO) rule, on dynamical networks with limited buffer size. In our network model, nodes move at each time step. Packets are transmitted by an adaptive routing strategy, combining Euclidean distance and node load by a tunable parameter. Because of this routing strategy, at the initial stage of increasing buffer size, the network density will increase, and the packet loss rate will decrease. Packet loss and traffic congestion occur by these three rules, but nodes keep unblocked and lose no packet in a larger buffer size range on the RIRO rule networks. If packets are lost and traffic congestion occurs, different dynamic characteristics are shown by these three queue rules. Moreover, a phenomenon similar to Braess’ paradox is also found by the LIFO rule and the RIRO rule.

Maximizing D2D-Based Offloading Efficiency With Throughput Guarantee and Buffer Constraint

Device-to-device (D2D) based offloading stands out as a promising approach to mitigate the pressure over cellular networks. From the perspectives of both operators and users, an ideal solution is expected to maximize the offloading efficiency (ratio) while guaranteeing the quality-of-service (QoS) of users. However, existing approaches seldom jointly take into consideration offloading efficiency optimization and QoS guarantee. In this paper, we study how to maximize the percentage of total offloaded traffic of mobile content downloading via D2D, while guaranteeing the user minimum throughput under limited buffer size. The major challenge is how to incorporate all potential D2D opportunities to maximize the offloading performance. We propose a spatial–temporal dynamic graph (STDG) to capture all possible D2D opportunities in D2D-based traffic offloading. Based on STDG, we mathematically formulate an optimization problem of maximizing the offloading efficiency, subject to throughput requirement and buffer size constraint. The formulated problem is a linear-fractional problem and can be transformed into an equivalent linear program, whose solution reveals the maximum offloading ability that D2D achieves under QoS satisfaction. Trace-based simulations validate the superiority of our approach over three benchmark approaches.

A probabilistic epidemic forwarding method for resource-constrained heterogeneous delay tolerant internet of things

Internet of things (IoT) is defined by networks of physical objects called smart things able to sense the environment, compute the results and communicate among themselves. IoT development needs to overcome many challenges regarding its constraints. Using IoT devices in delay tolerant networks (DTNs) scheme seems to be a solution to overcome its resource constraints and intermittent connectivity. Limited available battery and buffer size in small objects motivates the researchers to find optimised DTN routing schemes. DTNs are wireless networks that do not often have an end to end path between the source and destination objects. Epidemic routing (ER) protocol is a simple way to perform routing in such networks which is not effective from the energy point of view. To solve this problem the probabilistic epidemic (p-epidemic) routing protocol for the heterogeneous sets of smart objects is suggested. The accuracy of this forwarding method is supported by simulation results.

A probabilistic epidemic forwarding method for resource-constrained heterogeneous delay tolerant internet of things

Internet of things (IoT) is defined by networks of physical objects called smart things able to sense the environment, compute the results and communicate among themselves. IoT development needs to overcome many challenges regarding its constraints. Using IoT devices in delay tolerant networks (DTNs) scheme seems to be a solution to overcome its resource constraints and intermittent connectivity. Limited available battery and buffer size in small objects motivates the researchers to find optimised DTN routing schemes. DTNs are wireless networks that do not often have an end to end path between the source and destination objects. Epidemic routing (ER) protocol is a simple way to perform routing in such networks which is not effective from the energy point of view. To solve this problem the probabilistic epidemic (p-epidemic) routing protocol for the heterogeneous sets of smart objects is suggested. The accuracy of this forwarding method is supported by simulation results.

A Real-time LAN/WAN and Web Attack Prediction Framework Using Hybrid Machine Learning Model

Real-time network attacks have become an increasingly serious issue to LAN/WAN security in recent years. As the size of the network flow increases, it becomes difficult to pre-process and analyze the network packets using the traditional network intrusion detection tools and techniques. Traditional NID tools and techniques require high computational memory and time to process large number of packets in incremental manner due to limited buffer size. Web intrusion detection is also one of the major threat to real-time web applications due to unauthorized user’s request to web server and online databases. In this paper, a hybrid real-time LAN/WAN and Web IDS model is designed and implemented using the machine learning classifier. In this model, different types of attacks are detected and labelled prior to train the machine learning model. Future network packets are predicted using the trained machine learning classifier for attack prediction. Experimental results are simulated on real-time LAN/WAN network and client-server web application for performance analysis. Simulated results show that the proposed machine learning based attack detection model is better than the traditional statistical and rule based learning models in terms of time, detection rate are concerned.

An Optimal Randomized Online Algorithm for QoS Buffer Management

The QoS buffer management problem, with significant and diverse computer applications, e.g., in online cloud resource allocation problems, is a classic online admission control problem in the presence of resource constraints. In its basic setting, packets with different values, arrive in online fashion to a switching node with limited buffer size. Then, the switch needs to make an immediate decision to either admit or reject the incoming packet based on the value of the packet and its buffer availability. The objective is to maximize the cumulative profit of the admitted packets, while respecting the buffer constraint. Even though the QoS buffer management problem was proposed more than a decade ago, no optimal online solution has been proposed in the literature. This paper proposes an optimal randomized online algorithm for this problem.

A Modification of the Fuzzy Logic Based DASH Adaptation Scheme for Performance Improvement

We propose a modification of the fuzzy logic based DASH adaptation scheme (FDASH) for seamless media service in time‐varying network conditions. The proposed scheme (mFDASH) selects a more appropriate bit‐rate for the next segment by modification of the Fuzzy Logic Controller (FLC) and estimates more accurate available bandwidth than FDASH scheme by using History‐Based TCP Throughput Estimation. Moreover, mFDASH reduces the number of video bit‐rate changes by applying Segment Bit‐Rate Filtering Module (SBFM) and employs Start Mechanism for clients to provide high‐quality videos in the very beginning stage of the streaming service. Lastly, Sleeping Mechanism is applied to avoid any expected buffer overflow. We then use NS‐3 Network Simulator to verify the performance of mFDASH. Upon the experimental results, mFDASH shows no buffer overflow within the limited buffer size, which is not guaranteed in FDASH. Also, we confirm that mFDASH provides the highest QoE to DASH clients among the three schemes (mFDASH, FDASH, and SVAA) in Point‐to‐Point networks, Wi‐Fi networks, and LTE networks, respectively.

An Optimal Randomized Online Algorithm for QoS Buffer Management

The QoS (Quality of Service) buffer management problem, with significant and diverse computer applications, e.g., in online cloud resource allocation problems, is a classic online admission control problem in the presence of resource constraints. In its basic setting, packets with different values according to their QoS requirements, arrive in online fashion to a switching node with limited buffer size. Then, the switch needs to make an immediate decision to either admit or reject the incoming packet based on the value of the packet and its buffer availability. The objective is to maximize the cumulative profit of the admitted packets, while respecting the buffer constraint. Even though the QoS buffer management problem was proposed more than a decade ago, no optimal online solution has been proposed in the literature. This paper contributes to this problem by proposing: 1) A fixed threshold-based online algorithm with smaller competitive ratio than the existing results; 2) an optimal deterministic online algorithm under fractional admission model in which a packet could be admitted partially; and 3) an optimal randomized online algorithm for the general problem. We consider the last result being the main contribution of this paper.

Retrial Queueing Systems in Series of Space Experiments “Kontur”

This article describes queueing systems model of data transmission system for remote control of robot from board of ISS using public networks. Model has two incoming flows, one service channel, limited buffer size and randomized push-out mechanism. Also model of a retrial queueing system and lost packets with specified probability are able to get back on service. Two parameters: retrial and pushing-out probabilities of randomized mechanism have extremely high influence on model parameters like loss probability and average queue length and allow changing them on tens of percents. Also shown that retrial queueing models are having areas of linear behavior and blocking too, as model without retrial.