• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

A Markov Decision Process (MDP) based Load Balancing Algorithm for Multi-cell Networks with Multi-carriers

Vol. 8, No.10, October 31, 2014
10.3837/tiis.2014.10.006, Download Paper (Free):

Abstract

Conventional mobile state (MS) and base station (BS) association based on average signal strength often results in imbalance of cell load which may require more powerful processor at BSs and degrades the perceived transmission rate of MSs. To deal with this problem, a Markov decision process (MDP) for load balancing in a multi-cell system with multi-carriers is formulated. To solve the problem, exploiting Sarsa algorithm of on-line learning type [12], _ -controllable load balancing algorithm is proposed. It is designed to control tradeoff between the cell load deviation of BSs and the perceived transmission rates of MSs. We also propose an _ -differential soft greedy policy for on-line learning which is proven to be asymptotically convergent to the optimal greedy policy under some condition. Simulation results verify that the _ -controllable load balancing algorithm controls the behavior of the algorithm depending on the choice of _ . It is shown to be very efficient in balancing cell loads of BSs with low _ .


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
Janghoon Yang, "A Markov Decision Process (MDP) based Load Balancing Algorithm for Multi-cell Networks with Multi-carriers," KSII Transactions on Internet and Information Systems, vol. 8, no. 10, pp. 3394-3408, 2014. DOI: 10.3837/tiis.2014.10.006

[ACM Style]
Yang, J. 2014. A Markov Decision Process (MDP) based Load Balancing Algorithm for Multi-cell Networks with Multi-carriers. KSII Transactions on Internet and Information Systems, 8, 10, (2014), 3394-3408. DOI: 10.3837/tiis.2014.10.006