An efficient resource allocation scheme for mobile multimedia networks

Abstract

Abstracl-In mobile multimedia networks the traffic Bucluation is unpredictable and also due to limited resource availability, lhe resource allocation to multimedia applications of varying Quality of Service (QoS) requirement becomes B complex issue. This paper proposes an efficient resource allmation scheme based on resource reduction of running applications without hampering their QOS guarantee, in a single mobile cellular environment We propose a Linear Programming (LP) based resource reductiun far efficient Resource Allocation (RA). Artificial Neural Network model is used to solve lhe linear programming problem, which facilitates in real time control decision in the practical systems. The model is computationally less expensive and faster for resource allocation.The suggested scheme along with the LP-based resource reduction has shown that it is appropriate for the reduction of assigned resources for running applications during over load conditions and allocation of resources to requesting applicatioos. The simulation results for lhe proposed scheme yielded an improved resource utilization and lower percentage of rejection lo hand-off and new applications due to elfcient resource allocation.

Estimating plastic waste generation using supervised time-series learning techniques in Johannesburg, South Africa

“…The neural network technique comprises three layers including input, hidden, and output layers. The input layer receives the input parameters from the training data set and the output is envisaged to specify any of these; success, fail, or abort [ 40 , 41 ]. ANN time series models include the nonlinear autoregressive model (NAR), the NAR with external input model (NARX), and the nonlinear input-output model (NIO).…”

Application of artificial intelligence to improve quality of service in computer networks

“…Chou and Wu [8] proposed a neural network-based model that adaptively adjusts network parameters like threshold, push-out probability, and incremental bandwidth size of virtual path to maintain guaranteed QoS in ATM networks. Kumar et al [9] demonstrated that reduction in assigned resources needed to maintain guaranteed QoS under network overload conditions could be successfully done in real time with the assistance of neural networks. Rovithakis et al [10] proposed a method that uses neural networks as a controller to map QoS parameters at the application level for multimedia services into appropriate values for the media characteristics in order to achieve the required user satisfaction without violating the available bandwidth constraints.…”

An Intelligent Model to Control Preemption Rate of Instantaneous Request Calls in Networks with Book-Ahead Reservation

“…Chou and Wu proposed a neural network based model [6] which adaptively adjusts network parameters like threshold, push-out probability and incremental bandwidth size of virtual path to maintain guaranteed QoS in ATM networks. Kumar et al demonstrated that reduction of assigned resources needed to maintain guaranteed QoS under network overload conditions could be successfully done in real time with the assistance of neural networks [7]. Rovithakis et al [8] proposed a method which uses neural networks as a controller to map QoS parameters at the application level for multimedia services into appropriate values for the media characteristics in order to achieve the required user satisfaction without violating the available bandwidth constraints.…”