On the Performance of Static Inter-cell Interference Coordination in Realistic Cellular Layouts

González, David; García-Lozano, Mario; Ruíz, Silvia; Bonafé, Juan José Olmos

doi:10.1007/978-3-642-21444-8_15

Cited by 11 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the testing stage, we have generated an additional instance for each of 180 configurations, and explored again 30 random actions per cell, thus obtaining an additional 50000 samples to evaluate the accuracy of the trained neural network 3 .…”

Section: B Training and Testing The Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-Agent Neural Network for Dynamic Frequency Reuse in LTE Networks

Marinescu

Macaluso

DaSilva

2018

2018 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

Fractional Frequency Reuse techniques can be employed to address interference in mobile networks, improving throughput for edge users. There is a tradeoff between the coverage and overall throughput achievable, as interference avoidance techniques lead to a loss in a cell's overall throughput, with spectrum efficiency decreasing with the fencing off of orthogonal resources. In this paper we propose MANN, a dynamic multiagent frequency reuse scheme, where individual agents in charge of cells control their configurations based on input from neural networks. The agents' decisions are partially influenced by a coordinator agent, which attempts to maximise a global metric of the network (e.g., cell-edge performance). Each agent uses a neural network to estimate the best action (i.e., cell configuration) for its current environment setup, and attempts to maximise in turn a local metric, subject to the constraint imposed by the coordinator agent. Results show that our solution provides improved performance for edge users, increasing the throughput of the bottom 5% of users by 22%, while retaining 95% of a network's overall throughput from the full frequency reuse case. Furthermore, we show how our method improves on static fractional frequency reuse schemes.

show abstract

Section: B Training and Testing The Neural Networkmentioning

confidence: 99%

“…However, schemes such as PFR typically come at the cost of overall cell capacity [1], and in some cases, a static FFR scheme can even be detrimental to cell-edge users. Dynamic FFR schemes that can adapt to environment conditions (e.g., traffic load and UE distributions) are more suitable in such instances [2], [3].…”

Section: Introductionmentioning

confidence: 99%

A Multi-Agent Neural Network for Dynamic Frequency Reuse in LTE Networks

Marinescu

Macaluso

DaSilva

2018

2018 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

show abstract

“…Thus, designing a flexible scheme able to tradeoff among these conflicting criteria is an important design target [15]. For this reason, the performance assessment is based on the following criteria that need to be simultaneously satisfied:…”

Section: Proposed Multiobjective Frameworkmentioning

confidence: 99%

“…Figure 8 shows the required classification threshold for different values of β . Implementation was done according to the guidelines originally suggested in [15], but considering the cellular deployment (test case) used herein. 3.…”

Section: Bandwidth Proportionalitymentioning

confidence: 99%

“…In particular, FFR is well-known for its ability to provide high levels of Signal to Interference plus Noise Ratio (SINR) to cell edge users due to the higher frequency reuse applied to them. However, the performance of FFR in realistic deployments featuring irregular cellular layouts is poor according to results reported in [15]. This issue has been also pointed out in [6], where the authors remarked the need for additional research efforts in this direction since no simple reuse pattern can be easily derived for such scenarios.…”

mentioning

confidence: 91%

See 1 more Smart Citation

Multiobjective optimization of fractional frequency reuse for irregular OFDMA macrocellular deployments

et al. 2015

Self Cite

View full text Add to dashboard Cite

Interference mitigation has been identified as a key challenge for emerging cellular technologies based on Orthogonal Frequency Division Multiple Access (OFDMA), such as LTE. In this context, static Intercell Interference Coordination including Fractional Frequency Reuse (FFR) have been adopted by mobile operators as a good alternative to improve the Quality of Service (QoS) at cell edges. Nevertheless, recent results made evident the need for additional research efforts as default FFR configurations only offer tradeoffs in which spectral efficiency is severely penalized. Moreover, the performance of such baseline designs has been showed to be poor in realistic cellular deployments featuring irregular cell patterns. This paper solves this problematic by introducing a novel multiobjective optimization framework based on evolutionary algorithms that jointly takes into account system capacity, cell edge performance, and energy consumption. With respect to important reference schemes, the proposed algorithm succeeds in finding FFR configurations achieving gains between 10% and 40% in terms of system capacity while simultaneously improving cell edge performance up to 70%.

show abstract

On the need for dynamic downlink intercell interference coordination for realistic Long Term Evolution deployments

González

García-Lozano

Ruíz

et al. 2012

Wirel. Commun. Mob. Comput.

Self Cite

View full text Add to dashboard Cite

Intercell interference is the main issue limiting the capacity of modern orthogonal frequency‐division multiple access based cellular networks. Recently, extensive research work has been carried out in this field, and intercell interference coordination techniques have been recognized as key enablers of current (and future) cellular technologies. In this article, (i) a comprehensive survey of the most representative contributions is provided together with (ii) a generic methodology to measure their actual merit. The performance of several interference avoidance strategies has been evaluated both from system and user point of view in the context of a Long Term Evolution (LTE)‐based network considering not only synthetic cellular scenarios but also realistic deployments. Our literature review indicates that there is a need for adaptive/operator‐customizable low‐complex intercell interference coordination (ICIC) schemes suitable for realistic LTE deployments. Results obtained by means of a comprehensive set of simulations corroborate and support this premise. In this article, it is shown that simultaneous gains in terms of spectral/energy efficiency and fairness can be achieved through dynamic mechanisms with respect to both classic hard reuse schemes and static ICIC techniques. Besides numerical results, a novel merit assessment methodology based on several weighted performance metrics is proposed. Our findings show that dynamic schemes outperform static techniques by around 20–35% in realistic deployments. Copyright © 2012 John Wiley & Sons, Ltd.

show abstract

On the Performance of Static Inter-cell Interference Coordination in Realistic Cellular Layouts

Cited by 11 publications

References 11 publications

A Multi-Agent Neural Network for Dynamic Frequency Reuse in LTE Networks

A Multi-Agent Neural Network for Dynamic Frequency Reuse in LTE Networks

Multiobjective optimization of fractional frequency reuse for irregular OFDMA macrocellular deployments

On the need for dynamic downlink intercell interference coordination for realistic Long Term Evolution deployments

Contact Info

Product

Resources

About