Mobility Load Balancing Method for Self-Organizing Wireless Networks Inspired by Synchronization and Matching With Preferences

Park, Jaesung; Kim, Young-Jae; Lee, Jung-Ryun

doi:10.1109/tvt.2017.2769704

Cited by 19 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, we denote the set of multiple behavior policies to follow as M = {β 1 , β 2 , · · · , β M }, where M is the total number of behavior policies. Based on the objective under a single behavior policy given in (12), the objective under multiple behavior policies could be written as…”

Section: B Opdpg With Multiple Behavior Policiesmentioning

confidence: 99%

“…Game-theoretic methods, on the other hand, model the MLB process as an ongoing game among cells. For example, Sheng et al [9] modeled the MLB problem as a Cournot game; Park et al [12] optimized the user assignment and the target cell selection based on the Kuramoto synchronization and matching theory, respectively. However, the equilibrium and optimality of game-theoretic models are usually built upon specific assumptions over the wireless gaming environment.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, it is promising to incorporate self-organizing functionalities into 5G UDNs to enable adaptive and scalable load balancing. The traditional load balancing technique with self-organizing characteristics is referred to as mobility load balancing (MLB) [9][10][11][12], which usually optimizes the load distribution via tuning a parameter named cell individual offset (CIO) to control the user handovers. Current literature has proposed various MLB methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Load Balancing for Ultradense Networks: A Deep Reinforcement Learning-Based Approach

Wang

et al. 2019

IEEE Internet Things J.

View full text Add to dashboard Cite

In this paper, we propose a deep reinforcement learning (DRL) based mobility load balancing (MLB) algorithm along with a two-layer architecture to solve the large-scale load balancing problem for ultra-dense networks (UDNs). Our contribution is three-fold. First, this work proposes a two-layer architecture to solve the large-scale load balancing problem in a self-organized manner. The proposed architecture can alleviate the global traffic variations by dynamically grouping small cells into self-organized clusters according to their historical loads, and further adapt to local traffic variations through intra-cluster load balancing afterwards. Second, for the intra-cluster load balancing, this paper proposes an off-policy DRL-based MLB algorithm to autonomously learn the optimal MLB policy under an asynchronous parallel learning framework, without any prior knowledge assumed over the underlying UDN environments. Moreover, the algorithm enables joint exploration with multiple behavior policies, such that the traditional MLB methods can be used to guide the learning process thereby improving the learning efficiency and stability. Third, this work proposes an offlineevaluation based safeguard mechanism to ensure that the online system can always operate with the optimal and well-trained MLB policy, which not only stabilizes the online performance but also enables the exploration beyond current policies to make full use of machine learning in a safe way. Empirical results verify that the proposed framework outperforms the existing MLB methods in general UDN environments featured with irregular network topologies, coupled interferences, and random user movements, in terms of the load balancing performance.

show abstract

Section: B Opdpg With Multiple Behavior Policiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Load Balancing for Ultradense Networks: A Deep Reinforcement Learning-Based Approach

Wang

et al. 2019

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…In [9], the authors proposed a game-theoretic solution to overcome potential ping-pong load transfer problem and slow-convergence issue of load balancing. The authors in [10] adopted a synchronization process and a matching technique to solved the load balancing problem. An MLB algorithm in [11] considered an adaptive threshold to decide overloaded cells in a smallcell network; therefore, the algorithm can adapt to loadvarying environments.…”

Section: Introductionmentioning

confidence: 99%

Cluster-Based Load Balancing Algorithm for Ultra-Dense Heterogeneous Networks

Hasan

Kwon

2020

IEEE Access

View full text Add to dashboard Cite

In a highly dense heterogeneous cellular network, the loads across cells are uneven due to random deployment of cells and the mobility of user equipments (UEs). Such unbalanced loads result in performance degradation such as throughput and handover success. In order to solve the uneven load problem for better network performance, we propose a cluster-based mobility load-balancing algorithm for heterogeneous cellular networks. Traditional mobility load balancing (MLB) schemes that consider only the adjacent neighbors cannot provide enough improvement in network performance. On the other hand, the previous MLB schemes consider neighbors in the entire network suffer from unnecessary MLB actions. However, in the load balancing process, the proposed algorithm considers overloaded cells and their neighbors within the n-tiers. First, the algorithm models the network as a directed multi-graph and constructs clusters taking the overloaded cells and their n-tier neighbors. Therefore, by adjusting cell individual offset parameters of the cells in the clusters the algorithm achieves load balancing locally. Since load balancing is performed inside the clusters, the network can be optimized more efficiently by avoiding unnecessary MLB actions. Simulations show that the proposed algorithm distributes the load across the network more evenly than other MLB algorithms, and in a low UE velocity scenario, it increases the overall network throughput by 6.42% compared to a non-optimized network without an MLB algorithm.INDEX TERMS Ultra-dense network, small cell, macro cell, user equipment, self-organizing network, mobility load balancing, directed multi-graph, cluster, cell individual offset, handover, throughput.

show abstract

“…Several research works have studied the problem of mobility load balancing in a cellular network. In [14], the authors resolved the mismatch between the distribution of network resources and traffic demand by handing over UEs of an overloaded cell to a neighboring cell. A utility-based mobility load balancing algorithm in [13] considered operator utility and user utility for the handover process in 5G networks.…”

Section: Introductionmentioning

confidence: 99%

Load Balancing for 5G Integrated Satellite-Terrestrial Networks

et al. 2020

View full text Add to dashboard Cite

We propose a load balancing algorithm for a multi-RAT (radio access technology) network including a non-terrestrial network (NTN) and a terrestrial network (TN). Fifth generation (5G) and beyond-5G networks consider NTNs to provide connectivity and data delivery to large numbers of user equipments (UEs). However, previous load balancing algorithms do not consider the coexistence of NTNs and TNs and ignore the different resource allocation units in a multi-RAT network. Hence, we define a radio resource utilization ratio (RRUR) as a common load metric to measure the cell load of each RAT and employ an adaptive threshold to determine overloaded cells. The proposed algorithm consists of two steps to overcome the uneven load distribution across 5G cells: intra-RAT load balancing and inter-RAT load balancing. Based on the RRUR of a cell, the algorithm first performs intra-RAT load balancing by offloading the appropriate edge UEs of an overloaded cell to underutilized neighboring cells. If the RRUR of the cell is still higher than a predefined threshold, then inter-RAT load balancing is performed by offloading the delay-tolerant data flows of UEs to a satellite link. Furthermore, the algorithm estimates the impact of moving loads to the target cell load to avoid unnecessary load balancing actions. Simulation results show that the proposed algorithm not only distributes the load across terrestrial cells more evenly but also increases network throughput and the number of quality of service satisfied UEs more than previous load balancing algorithms.INDEX TERMS 5G, cellular network, satellite, NTN, radio access network, multi-RAT, QoS, load balancing, data flows, load measurement.

show abstract

Mobility Load Balancing Method for Self-Organizing Wireless Networks Inspired by Synchronization and Matching With Preferences

Cited by 19 publications

References 31 publications

Load Balancing for Ultradense Networks: A Deep Reinforcement Learning-Based Approach

Load Balancing for Ultradense Networks: A Deep Reinforcement Learning-Based Approach

Cluster-Based Load Balancing Algorithm for Ultra-Dense Heterogeneous Networks

Load Balancing for 5G Integrated Satellite-Terrestrial Networks

Contact Info

Product

Resources

About