Sudhansu Sekhar Singh

A functional Link Artificial Neural Network for location management in cellular network

Mobility management is one of the major issues in mobile networks to provide an efficient and low-cost service. In this paper, we intend a prediction-based location management scheme for locating a mobile host (MH) or mobile station, which depends on its history of movement pattern of a mobile subscriber. A multilayer neural network (MNN) model for mobile movement prediction is designed to predict the future movement of a mobile host. For predicting the location of a mobile host the MNN is trained with respect to the data obtained from the movement pattern. The difficulties associated with the location management can be solved by nonlinear neural network that is computationally efficient. The major issue in feed forward neural network such as Multilayer perceptron (MLP) trained with back Propagation (BP) is that it requires a large amount of computation time for learning the network. Functional Link Neural Network (FLNN) is proposed here and that is simpler than MLP-BP. This is basically a single layer structure in which nonlinearity is introduced where the input pattern is enhanced with nonlinear functional expansion. The novelty of the proposed work is it requires less computation than that of MLP-BP. With proper choice of functional expansion in case of FLANN, this network performs better than multilayer perceptron with back propagation. It is observed from the simulation result that FLANN outperforms MLP-BP in terms of performance error. It is also shown that proposed network is computationally cheap and gives better classification accuracy than that of MLP classifier.

Cost Reduction in Location Management Using Reporting Cell Planning and Particle Swarm Optimization

This paper introduces a critical and intricate location management issue that combines both location inquiry or location update and location search or paging in cellular computational environment. It is required to develop the algorithm that could entangle the issue which yet simple to implement and solve a wide range of complex problems incorporated in the cellular network. It is essential to optimize the network to locate a mobile terminal in a cellular computing environment with an optimal location area is an NP-complete problem. In recent years to solve this location management issue many metaheuristic algorithms have been developed which are capable of searching in larger search space efficiently and effectively. This paper proposes binary particle swarm optimization (BPSO) using optimal reporting cell planning technique with the objective of reducing location management cost that incurred during the tracking procedure in locating the user in a cellular network. To evaluate the system performance of the BPSO, the simulation results depict as the technique is simple, computationally effective among other evolutionary algorithms and prove to be better when compared to the existing conventional binary genetic algorithm. The extensive simulations are performed in different existing data networks of various network sizes and also to prove the efficacy as well as robustness of the algorithm the proposed BPSO algorithm is validated in real data network and demonstrate the performance in terms of cost parameters like cost per call arrival, paging cost and total cost etc.

Cost Reduction in Reporting Cell Planning Configuration Using Soft Computing Algorithm

This paper presents Binary Genetic Algorithm (BGA) is a heuristic, adaptive population based method and which has shown to be a very powerful global search method used for optimization process. Using BGA the objective of this work is used to minimize the location management cost thereby achieve trade-off between location update and paging cost based on reporting cell planning configuration. This BGA algorithm is used to solve location management cost using reporting cell planning problem. With the use of reporting cell location management some cells are designated as reporting cells where mobile station (MS) updates its location upon entering the same coverage. The effectiveness of the technique is tested for collected real data for validation and presented in the paper. The simulation results obtained from this work with reasonable degree of accuracy are very encouraging.

Evolutionary algorithm for cost reduction in cellular network

Mobility management is a prime issue in a wireless computing environment. There is a need to develop various algorithms that could capture this complexity and used to solve the mobility management scenarios. When a mobile user moves from one cell to another cell some amount of cost is acquired for the same. These cells are assigned as either “reporting cell” or “non-reporting cell”, also known as reporting cell planning problem (RCP). In this paper, to reduce the total cost, two optimization techniques are adopted and compared to solve the problem. Total cost in location management signifies location update cost and paging cost. Two optimization algorithms needed to capture the issue are Genetic Algorithm (GA) and Binary Particle Swarm Optimization Algorithm (BPSO) which is also compared to measure the performance in terms of cost. For the same problem BPSO is shown to outperform GA in terms of quality of solution and also proved to be efficient in a competitive approach for the several benchmark issues. The simulation results also indicate BPSO is robust, gives higher solution quality and offers faster global convergence. These proposed techniques are also validated on service data and compared with the synthetic data of the different subscribers present in different reporting cells. A number of optimization problems are solved using this evolutionary algorithm and results obtained are quite satisfactory.

Soft computing technique for cost reduction in cellular network.

In cellular network location management is a fundamental and complex problem which deals how to track the subscriber on move. Some amount of cost is incurred for the subscriber during the movement in a particular service area. This cost basically involved location update cost and paging cost. The main objective of this work is to reduce this total cost which includes this location update cost and paging cost by using different evolutionary techniques. This paper presents binary genetic algorithm to solve the location management problem by partitioning the given cellular network into location areas so as to minimize the location management cost. Binary Genetic Algorithm (BGA) is a meta-heuristic method which has presented to be a very powerful widely used, prominent and a population-based optimization approach. Among the entire evolutionary techniques Genetic algorithm is a biological, simple inspired optimization with reduced complexity. With the help of this algorithm optimal location areas are obtained corresponding to the minimized cost. Simulation results and optimal location area planning for different networks are demonstrated and discussed. The effectiveness of GA result is shown to be effective using less number of iteration.

Bio-Inspired Algorithms for Mobile Location Management—A New Paradigm

Mobile location management (MLM) has gained a new aspect in today’s cellular wireless communication scenario. It has two perspectives: location registration and location search and a trade-off between the two give optimal cost for location management. An outline of the prominent solutions for the cost optimization in location management using various bio-inspired computations is surveyed. For solving complex optimization problems in various engineering applications more and more such bio-inspired algorithms are recently being explored along with incremental improvement in the existing algorithms. This paper surveys and discusses potential approaches for cost optimization using fifteen bio-inspired algorithms such as Artificial Neural Network, Genetic Algorithm to newly developed Flower Pollination Algorithm and Artificial Plant Optimization. Finally, we survey the potential application of these bio-inspired algorithms for cost optimization in mobile location management issue available in the recent literature and point out the motivation for the use of bio-inspired algorithms in cost optimization and design of optimal cellular network.

Parallel Multi-Criterion Genetic Algorithms: Review and Comprehensive Study

The objective of this paper is to study the existing and current research on parallel multi-objective genetic algorithms PMOGAs through an intensive experiment. Many early efforts on parallelizing multi-objective genetic algorithms were introduced to reduce the processing time needed to reach an acceptable solution of them with various examples. Further, the authors tried to identify some of the issues that have not yet been studied systematically under the umbrella of parallel multi-objective genetic algorithms. Finally, some of the potential application of parallel multi objective genetic algorithm is discussed.

Dynamic profile based paging in mobile communication

In cellular network finding a mobile terminal effectively is a vital component and it has a strong impact on signaling load. Location management has a set of techniques such as location update and paging implemented to reduce this mobility based signaling traffic. Paging and location update techniques work together with to decide in searching of the user on the arrival of a call. Here a profile based paging algorithm is proposed in terms of paging success rate and bandwidth conservation comparing with various other paging algorithms. This work is validated by taking a novel data to profile the users and simulated the algorithm with actual user data. In this work the proposed algorithm gives improved better paging success rate of 3% to 9% and saves bandwidth of 60% to 20% compared to conventional paging and sequential paging respectively.

Robust nonlinear congestion controller for cognitive radio based wireless network

Under the constraints of limited bandwidth and exponentially rising user demand, there is a dire need to maximize throughput. Maintaining Quality of Service (QoS) in a communication network demands congestion control with high accuracy. This paper focuses on this challenging task that incorporates design of effective congestion controller to reduce packet loss in cognitive radio networks. Limited buffer capacity and bandwidth impose restriction on the performance when number of requests increase. The controller is designed on the notions of sliding mode which is a variable structure control technique known for its robustness and disturbance rejection capabilities. An optimal design strategy is used in development of the controller. The efficiency of the controller is confirmed by numerical simulations.

Novel intelligent soft computing techniques for location prediction in mobility management

Voice and data services are provided by cellular networks to the users with mobility. To bring services to the mobile users, the cellular network is capable of tracking the locations of the users, and allowing user movement during the conversations. With the growing number of mobile users, global connectivity, and the small size of cells, location management is one of the most critical issues regarding these networks. The objective of a dynamic location management system is to maintain a low paging cost in the communication system. As the data associated with the communication system is a purely non-stationary, therefore soft-computing approach this time playing major roles for achieving the real objective of the location management system. In this research article, an attempt has been made to apply PPN (Polynomial Perceptron Network) for development of an intelligent location management system. In this work a comparison of several locations management techniques are performed under identical terminal mobility model and network characteristics. From the simulation result it is seen that MLP (Multilayer Perceptron) has better performance than PPN network, however PPN network takes very less CPU time comparing with MLP system.