ABSTRACT
Reducing power consumption in LTE networks has become an important issue for mobile network operators. The 3GPP organization has included such operation as one of SON (Self-Organizing Networks) functions [1][2]. Using the approach presented in this paper the decision about turning Radio Access Network (RAN) nodes off and on, according to the network load (which is typically low at night), is taken into account. The process is controlled using a combination of Fuzzy Logic and Q-Learning techniques (FQL). The effectiveness of the proposed approach has been evaluated using the LTE-Sim simulator with some extensions. The simulations are very close to real network implementation: we used the RAN node parameters that are defined by 3GPP and simulations take into account the network behaviour in the micro time scale.
- 3GPP, "LTE; Evolved Universal Terrestrial Radio Access (E-UTRA); Potential solutions for energy saving for E-UTRAN (Release 11)", TR 36.927, 2012.Google Scholar
- 3GPP, "Technical Specification Group Services and System Aspects; Telecommunication management; Study on Energy Savings Management (ESM) (Release 10)", TR32.826, 2010.Google Scholar
- 3GPP, "Technical Specification Group Services and System Aspects; Telecommunication Management; Self-Organizing Networks (SON); Concepts and requirements (Release 10)", TS 32.500, 2010.Google Scholar
- 3GPP, "Evolved Universal Terrestrial Radio Access (E-UTRA); Layer 2 - Measurements (Release 11)", TS 36.314, 2012.Google Scholar
- 3GPP, "E-UTRA Radio Resource Control (RRC); Protocol specification (Release 11)", TS 36.331, 06.2012.Google Scholar
- 3GPP, "Evolved Universal Terrestrial Radio Access (E-UTRA); Radio Resource Control (RRC); Protocol specification (Release 12) ", TS 36.331, 03.2014.Google Scholar
- R. Sutton "Reinforcement learning: An introduction" MIT Press 1998. Google ScholarDigital Library
- T. J. Ross, Fuzzy logic With Engineering Applications, 2010.Google ScholarCross Ref
- Mataric, M. J.: Reward functions for accelerated learning. In: Proc. of the 11th ICML. (1994) 181--189.Google Scholar
- L. Matignon et all. Reward Function and Initial Values: Better Choices for Accelerated Goal-Directed Reinforcement Learning. Artificial Neural Networks - ICANN 2006. Lecture Notes in Computer Science Volume 4131, 2006, pp 840--849. Google ScholarDigital Library
- G. Piro, L. A. Grieco, G. Boggia, F. Capozzi and P. Camarda, "Simulating LTE Cellular Systems: an Open Source Framework", online, http://telematics.poliba.it/publications/2010/TVT/PiroTVT2010.pdfGoogle Scholar
- W. Keating, "Reducing Energy Consumption in Access Networks", August 2011. School of Electronic Engineering, Dublin City University.Google Scholar
- http://www.celtic-initiative.org/Projects/Celtic-projects/Call8/COMMUNE/commune-default.asp.Google Scholar
Index Terms
- Reinforcement learning based energy efficient LTE RAN
Recommendations
Self organizing method for handover performance optimization in LTE-advanced network
Classical wireless cellular networks configure semi-static values of handover decision parameters, which are usually been modified manually by the operator at a certain time interval post analyzing the network performance report. To reduce the operator'...
A Seamless Handover Based MIH-Assisted PMIPV6 in Heterogeneous Network(LTE-WIFI)
BDCA'17: Proceedings of the 2nd international Conference on Big Data, Cloud and ApplicationsWe consider the user equipment (UE) velocity as a vital trend in association problem in heterogeneous networks (HetNets), since there is a considerable relation between the velocity and the handover failure (HOF) as well as the probability of ...
SON Handover Algorithm for Green LTE-A/5G HetNets
Fourth generation networks and beyond (5G) have recently emerged to satisfy the increasing demand for high data bit rates. Cost-effective means such as small cells have been designed in 3GPP LTE-Advanced standard since the Release 10 to significantly ...
Comments