Abstract: This paper presents a subjective job scheduler based
on a 3-layer Backpropagation Neural Network (BPNN) and a greedy
alignment procedure in order formulates a real-life situation. The
BPNN estimates critical values of jobs based on the given subjective
criteria. The scheduler is formulated in such a way that, at each time
period, the most critical job is selected from the job queue and is
transferred into a single machine before the next periodic job arrives.
If the selected job is one of the oldest jobs in the queue and its
deadline is less than that of the arrival time of the current job, then
there is an update of the deadline of the job is assigned in order to
prevent the critical job from its elimination. The proposed
satisfiability criteria indicates that the satisfaction of the scheduler
with respect to performance of the BPNN, validity of the jobs and the
feasibility of the scheduler.
Abstract: The Internet telephony employs a new type of Internet communication on which a mutual communication is realized by establishing sessions. Session Initiation Protocol (SIP) is used to establish sessions between end-users. For unreliable transmission (UDP), SIP message should be retransmitted when it is lost. The retransmissions increase a load of the SIP signaling network, and sometimes lead to performance degradation when a network is overloaded. The paper proposes an overload control for a SIP signaling network to protect from a performance degradation. Introducing two thresholds in a queue of a SIP proxy server, the SIP proxy server detects a congestion. Once congestion is detected, a SIP signaling network restricts to make new calls. The proposed overload control is evaluated using the network simulator (ns-2). With simulation results, the paper shows the proposed overload control works well.
Abstract: Traffic congestion has become a major problem in
many countries. One of the main causes of traffic congestion is due
to road merges. Vehicles tend to move slower when they reach the
merging point. In this paper, an enhanced algorithm for traffic
simulation based on the fluid-dynamic algorithm and kinematic wave
theory is proposed. The enhanced algorithm is used to study traffic
congestion at a road merge. This paper also describes the
development of a dynamic traffic simulation tool which is used as a
scenario planning and to forecast traffic congestion level in a certain
time based on defined parameter values. The tool incorporates the
enhanced algorithm as well as the two original algorithms. Output
from the three above mentioned algorithms are measured in terms of
traffic queue length, travel time and the total number of vehicles
passing through the merging point. This paper also suggests an
efficient way of reducing traffic congestion at a road merge by
analyzing the traffic queue length and travel time.
Abstract: How to efficiently assign system resource to route the
Client demand by Gateway servers is a tricky predicament. In this
paper, we tender an enhanced proposal for autonomous recital of
Gateway servers under highly vibrant traffic loads. We devise a
methodology to calculate Queue Length and Waiting Time utilizing
Gateway Server information to reduce response time variance in
presence of bursty traffic.
The most widespread contemplation is performance, because
Gateway Servers must offer cost-effective and high-availability
services in the elongated period, thus they have to be scaled to meet
the expected load. Performance measurements can be the base for
performance modeling and prediction. With the help of performance
models, the performance metrics (like buffer estimation, waiting
time) can be determined at the development process.
This paper describes the possible queue models those can be
applied in the estimation of queue length to estimate the final value
of the memory size. Both simulation and experimental studies using
synthesized workloads and analysis of real-world Gateway Servers
demonstrate the effectiveness of the proposed system.
Abstract: This paper is aimed at describing a delay-based endto-
end (e2e) congestion control algorithm, called Very FAST TCP
(VFAST), which is an enhanced version of FAST TCP. The main
idea behind this enhancement is to smoothly estimate the Round-Trip
Time (RTT) based on a nonlinear filter, which eliminates throughput
and queue oscillation when RTT fluctuates. In this context, an evaluation
of the suggested scheme through simulation is introduced, by
comparing our VFAST prototype with FAST in terms of throughput,
queue behavior, fairness, stability, RTT and adaptivity to changes in
network. The achieved simulation results indicate that the suggested
protocol offer better performance than FAST TCP in terms of RTT
estimation and throughput.
Abstract: In this work, we study the impact of dynamically
changing link slowdowns on the stability properties of packetswitched
networks under the Adversarial Queueing Theory
framework. Especially, we consider the Adversarial, Quasi-Static
Slowdown Queueing Theory model, where each link slowdown may
take on values in the two-valued set of integers {1, D} with D > 1
which remain fixed for a long time, under a (w, ¤ü)-adversary. In this
framework, we present an innovative systematic construction for the
estimation of adversarial injection rate lower bounds, which, if
exceeded, cause instability in networks that use the LIS (Longest-in-
System) protocol for contention-resolution. In addition, we show that
a network that uses the LIS protocol for contention-resolution may
result in dropping its instability bound at injection rates ¤ü > 0 when
the network size and the high slowdown D take large values. This is
the best ever known instability lower bound for LIS networks.
Abstract: The modern queueing theory is one of the powerful
tools for a quantitative and qualitative analysis of communication systems, computer networks, transportation systems, and many other technical systems. The paper is designated to the analysis of queueing
systems, arising in the networks theory and communications theory
(called open queueing network). The authors of this research in the
sphere of queueing theory present the theorem about the law of the iterated logarithm (LIL) for the queue length of a customers in open
queueing network and its application to the mathematical model of
the open message switching system.
Abstract: In the queueing theory, it is assumed that customer
arrivals correspond to a Poisson process and service time has the
exponential distribution. Using these assumptions, the behaviour of
the queueing system can be described by means of Markov chains
and it is possible to derive the characteristics of the system. In the
paper, these theoretical approaches are presented on several types of
systems and it is also shown how to compute the characteristics in a
situation when these assumptions are not satisfied
Abstract: The use of buffer thresholds, blocking and adequate
service strategies are well-known techniques for computer networks
traffic congestion control. This motivates the study of series queues
with blocking, feedback (service under Head of Line (HoL) priority
discipline) and finite capacity buffers with thresholds. In this paper,
the external traffic is modelled using the Poisson process and the
service times have been modelled using the exponential distribution.
We consider a three-station network with two finite buffers, for
which a set of thresholds (tm1 and tm2) is defined. This computer
network behaves as follows. A task, which finishes its service at
station B, gets sent back to station A for re-processing with
probability o. When the number of tasks in the second buffer exceeds
a threshold tm2 and the number of task in the first buffer is less than
tm1, the fed back task is served under HoL priority discipline. In
opposite case, for fed backed tasks, “no two priority services in
succession" procedure (preventing a possible overflow in the first
buffer) is applied. Using an open Markovian queuing schema with
blocking, priority feedback service and thresholds, a closed form
cost-effective analytical solution is obtained. The model of servers
linked in series is very accurate. It is derived directly from a twodimensional
state graph and a set of steady-state equations, followed
by calculations of main measures of effectiveness. Consequently,
efficient expressions of the low computational cost are determined.
Based on numerical experiments and collected results we conclude
that the proposed model with blocking, feedback and thresholds can
provide accurate performance estimates of linked in series networks.
Abstract: Network management techniques have long been of
interest to the networking research community. The queue size plays
a critical role for the network performance. The adequate size of the
queue maintains Quality of Service (QoS) requirements within
limited network capacity for as many users as possible. The
appropriate estimation of the queuing model parameters is crucial for
both initial size estimation and during the process of resource
allocation. The accurate resource allocation model for the
management system increases the network utilization. The present
paper demonstrates the results of empirical observation of memory
allocation for packet-based services.
Abstract: We consider a network of two M/M/1 parallel queues having the same poisonnian arrival stream with rate λ. Upon his arrival to the system a customer heads to the shortest queue and stays until being served. If the two queues have the same length, an arriving customer chooses one of the two queues with the same probability. Each duration of service in the two queues is an exponential random variable with rate μ and no jockeying is permitted between the two queues. A new numerical method, based on linear programming and convex optimization, is performed for the computation of the steady state solution of the system.
Abstract: IEEE 802.11e is the enhanced version of the IEEE
802.11 MAC dedicated to provide Quality of Service of wireless
network. It supports QoS by the service differentiation and
prioritization mechanism. Data traffic receives different priority
based on QoS requirements. Fundamentally, applications are divided
into four Access Categories (AC). Each AC has its own buffer queue
and behaves as an independent backoff entity. Every frame with a
specific priority of data traffic is assigned to one of these access
categories. IEEE 802.11e EDCA (Enhanced Distributed Channel
Access) is designed to enhance the IEEE 802.11 DCF (Distributed
Coordination Function) mechanisms by providing a distributed
access method that can support service differentiation among
different classes of traffic. Performance of IEEE 802.11e MAC layer
with different ACs is evaluated to understand the actual benefits
deriving from the MAC enhancements.
Abstract: Economic dispatch (ED) is considered to be one of the
key functions in electric power system operation. This paper presents
a new hybrid approach based genetic algorithm (GA) to economic
dispatch problems. GA is most commonly used optimizing algorithm
predicated on principal of natural evolution. Utilization of chaotic
queue with GA generates several neighborhoods of near optimal
solutions to keep solution variation. It could avoid the search process
from becoming pre-mature. For the objective of chaotic queue
generation, utilization of tent equation as opposed to logistic equation
results in improvement of iterative speed. The results of the proposed
approach were compared in terms of fuel cost, with existing
differential evolution and other methods in literature.
Abstract: Continuously growing needs for Internet applications
that transmit massive amount of data have led to the emergence of
high speed network. Data transfer must take place without any
congestion and hence feedback parameters must be transferred from
the receiver end to the sender end so as to restrict the sending rate in
order to avoid congestion. Even though TCP tries to avoid
congestion by restricting the sending rate and window size, it never
announces the sender about the capacity of the data to be sent and
also it reduces the window size by half at the time of congestion
therefore resulting in the decrease of throughput, low utilization of
the bandwidth and maximum delay. In this paper, XCP protocol is
used and feedback parameters are calculated based on arrival rate,
service rate, traffic rate and queue size and hence the receiver
informs the sender about the throughput, capacity of the data to be
sent and window size adjustment, resulting in no drastic decrease in
window size, better increase in sending rate because of which there is
a continuous flow of data without congestion. Therefore as a result of
this, there is a maximum increase in throughput, high utilization of
the bandwidth and minimum delay. The result of the proposed work
is presented as a graph based on throughput, delay and window size.
Thus in this paper, XCP protocol is well illustrated and the various
parameters are thoroughly analyzed and adequately presented.
Abstract: The group mutual exclusion (GME) problem is an
interesting generalization of the mutual exclusion problem. Several
solutions of the GME problem have been proposed for message
passing distributed systems. However, none of these solutions is
suitable for real time distributed systems. In this paper, we propose a
token-based distributed algorithms for the GME problem in soft real
time distributed systems. The algorithm uses the concepts of priority
queue, dynamic request set and the process state. The algorithm uses
first come first serve approach in selecting the next session type
between the same priority levels and satisfies the concurrent
occupancy property. The algorithm allows all n processors to be
inside their CS provided they request for the same session. The
performance analysis and correctness proof of the algorithm has also
been included in the paper.
Abstract: The transient analysis of a queuing system with fixed-size batch Poisson arrivals and a single server with exponential service times is presented. The focus of the paper is on the use of the functions that arise in the analysis of the transient behaviour of the queuing system. These functions are shown to be a generalization of the modified Bessel functions of the first kind, with the batch size B as the generalizing parameter. Results for the case of single-packet arrivals are obtained first. The similarities between the two families of functions are then used to obtain results for the general case of batch arrival queue with a batch size larger than one.
Abstract: Scheduling algorithms are used in operating systems
to optimize the usage of processors. One of the most efficient
algorithms for scheduling is Multi-Layer Feedback Queue (MLFQ)
algorithm which uses several queues with different quanta. The most
important weakness of this method is the inability to define the
optimized the number of the queues and quantum of each queue. This
weakness has been improved in IMLFQ scheduling algorithm.
Number of the queues and quantum of each queue affect the response
time directly. In this paper, we review the IMLFQ algorithm for
solving these problems and minimizing the response time. In this
algorithm Recurrent Neural Network has been utilized to find both
the number of queues and the optimized quantum of each queue.
Also in order to prevent any probable faults in processes' response
time computation, a new fault tolerant approach has been presented.
In this approach we use combinational software redundancy to
prevent the any probable faults. The experimental results show that
using the IMLFQ algorithm results in better response time in
comparison with other scheduling algorithms also by using fault
tolerant mechanism we improve IMLFQ performance.
Abstract: This paper introduces a technique for simulating a
single-server exponential queuing system. The technique called the
Q-Simulator is a computer program which can simulate the effect of
traffic intensity on all system average quantities given the arrival
and/or service rates. The Q-Simulator has three phases namely: the
formula based method, the uncontrolled simulation, and the
controlled simulation. The Q-Simulator generates graphs (crystal
solutions) for all results of the simulation or calculation and can be
used to estimate desirable average quantities such as waiting times,
queue lengths, etc.
Abstract: The paper considers a single-server queue with fixedsize
batch Poisson arrivals and exponential service times, a model
that is useful for a buffer that accepts messages arriving as fixed size
batches of packets and releases them one packet at time. Transient
performance measures for queues have long been recognized as
being complementary to the steady-state analysis. The focus of the
paper is on the use of the functions that arise in the analysis of the
transient behaviour of the queuing system. The paper exploits
practical modelling to obtain a solution to the integral equation
encountered in the analysis. Results obtained indicate that under
heavy load conditions, there is significant disparity in the statistics
between the transient and steady state values.
Abstract: High speed networks provide realtime variable bit rate
service with diversified traffic flow characteristics and quality
requirements. The variable bit rate traffic has stringent delay and
packet loss requirements. The burstiness of the correlated traffic
makes dynamic buffer management highly desirable to satisfy the
Quality of Service (QoS) requirements. This paper presents an
algorithm for optimization of adaptive buffer allocation scheme for
traffic based on loss of consecutive packets in data-stream and buffer
occupancy level. Buffer is designed to allow the input traffic to be
partitioned into different priority classes and based on the input
traffic behavior it controls the threshold dynamically. This algorithm
allows input packets to enter into buffer if its occupancy level is less
than the threshold value for priority of that packet. The threshold is
dynamically varied in runtime based on packet loss behavior. The
simulation is run for two priority classes of the input traffic –
realtime and non-realtime classes. The simulation results show that
Adaptive Partial Buffer Sharing (ADPBS) has better performance
than Static Partial Buffer Sharing (SPBS) and First In First Out
(FIFO) queue under the same traffic conditions.