Using a Machine Learning Approach for Analysis of Polling Systems with Correlated Arrivals

Vishnevsky, Vladimir; Bui, Duy T.

doi:10.1007/978-3-030-92507-9_27

Cited by 5 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same authors in [13] developed their research on polling systems to systems with correlated arrival flows such as MAP, BMAP, and the group Poisson arrivals. In Vishnevskiy et al [14], it was shown that the results obtained by a neural network are close enough to the results of analytical or simulation calculations for the M/M/1 and MAP/M/1-type polling systems with cyclic polling. Markovian versions of a single-server model with parallel queues have been investigated by a number of authors.…”

Section: Introductionmentioning

confidence: 62%

Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques

Efrosinin

Vishnevsky

Stepanova³

2023

Sensors

View full text Add to dashboard Cite

The problem of optimal scheduling in a system with parallel queues and a single server has been extensively studied in queueing theory. However, such systems have mostly been analysed by assuming homogeneous attributes of arrival and service processes, or Markov queueing models were usually assumed in heterogeneous cases. The calculation of the optimal scheduling policy in such a queueing system with switching costs and arbitrary inter-arrival and service time distributions is not a trivial task. In this paper, we propose to combine simulation and neural network techniques to solve this problem. The scheduling in this system is performed by means of a neural network informing the controller at a service completion epoch on a queue index which has to be serviced next. We adapt the simulated annealing algorithm to optimize the weights and the biases of the multi-layer neural network initially trained on some arbitrary heuristic control policy with the aim to minimize the average cost function which in turn can be calculated only via simulation. To verify the quality of the obtained optimal solutions, the optimal scheduling policy was calculated by solving a Markov decision problem formulated for the corresponding Markovian counterpart. The results of numerical analysis show the effectiveness of this approach to find the optimal deterministic control policy for the routing, scheduling or resource allocation in general queueing systems. Moreover, a comparison of the results obtained for different distributions illustrates statistical insensitivity of the optimal scheduling policy to the shape of inter-arrival and service time distributions for the same first moments.

show abstract

Section: Introductionmentioning

confidence: 62%

Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques

Efrosinin

Vishnevsky

Stepanova³

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This method can be effectively used to study many problems in the theory of queues, for which finding a rigorous analytical solution and numerical results is either difficult or even impossible using traditional approaches. In particular, this method was applied to study a Fork-join type QS, and in [14] to estimate performance characteristics of complex adaptive polling systems.…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of the Priority Multi-Server System MMAP/PH/M/N Using Machine Learning Methods

et al. 2021

View full text Add to dashboard Cite

In this paper, we present the results of a study of a priority multi-server queuing system with heterogeneous customers arriving according to a marked Markovian arrival process (MMAP), phase-type service times (PH), and a queue with finite capacity. Priority traffic classes differ in PH distributions of the service time and the probability of joining the queue, which depends on the current length of the queue. If the queue is full, the customer does not enter the system. An analytical model has been developed and studied for a particular case of a queueing system with two priority classes. We present an algorithm for calculating stationary probabilities of the system state, loss probabilities, the average number of customers in the queue, and other performance characteristics for this particular case. For the general case with K priority classes, a new method for assessing the performance characteristics of complex priority systems has been developed, based on a combination of machine learning and simulation methods. We demonstrate the high efficiency of the new method by providing numerical examples.

show abstract

Application of Machine Learning Methods to Solving Problems of Queuing Theory

Vishnevsky

Gorbunova

2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Using a Machine Learning Approach for Analysis of Polling Systems with Correlated Arrivals

Cited by 5 publications

References 8 publications

Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques

Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques

Performance Evaluation of the Priority Multi-Server System MMAP/PH/M/N Using Machine Learning Methods

Application of Machine Learning Methods to Solving Problems of Queuing Theory

Contact Info

Product

Resources

About