Random Case Analysis of Inductive Learning Algorithms
DS '98 Proceedings of the First International Conference on Discovery Science
Challenges in mobile network operation: Towards self-optimizing networks
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Average-case analysis of a nearest neighbor algorthim
IJCAI'93 Proceedings of the 13th international joint conference on Artifical intelligence - Volume 2
System level analysis of vertical sectorization for 3GPP LTE
ISWCS'09 Proceedings of the 6th international conference on Symposium on Wireless Communication Systems
Introduction to Machine Learning
Introduction to Machine Learning
Energy savings in mobile networks based on adaptation to traffic statistics
Bell Labs Technical Journal - Green Information and Communications Technology (ICT) for Eco-Sustainability
A fuzzy reinforcement learning approach for self‐optimization of coverage in LTE networks
Bell Labs Technical Journal
Automated optimization of service coverage and base station antenna configuration in UMTS networks
IEEE Wireless Communications
Self-optimization of random access channel in 3rd Generation Partnership Project Long Term Evolution
Wireless Communications & Mobile Computing
| Hi-index | 0.00 |
In wireless communications the demand for wide range of services is leading to a rapid increase in network performance requirements. Hence, today's cellular radio technologies are designed to operate closer to Shannon capacity bound which sets the ultimate upper limit for the wireless channel capacity. Yet, good link level performance does not necessarily mean that network resources are used efficiently as the cellular capacity and coverage performance may not be optimal resulting from dynamic conditions in radio network environment such as urbanization, insertion or deletion of base stations, and malfunctioning nodes. Due to the fact that reacting on those inherent problems manually is very expensive and time consuming, automated optimization of cellular coverage and capacity by means of self-optimization of adaptive antenna system parameters could be an attractive solution from the network operator's point of view. Furthermore, suboptimal antenna parameter selection in long term evolution (LTE) network planning or the reuse of the sites and antenna parameters of a preceding access technology requires optimization of adaptive antenna system parameters. In this article we propose a novel centralized self-optimization approach that can be used for adapting antenna system parameters in order to automatically control network capacity and coverage in a macro-cellular deployment. In the proposed approach we present case-based reasoning (CBR) based self-optimization aided by an exemplary rule-based scheme which is required during the training phase of CBR. Dynamic system level downlink simulator is developed to validate the performance of the proposed approach in a realistic macro-cellular scenario. In performance evaluations the 3rd generation partnership project LTE system framework is assumed and propagation is modeled in three dimensions.