• Corpus ID: 67855738

Decentralized AP selection using Multi-Armed Bandits: Opportunistic {\epsilon}-Greedy with Stickiness

  title={Decentralized AP selection using Multi-Armed Bandits: Opportunistic \{\epsilon\}-Greedy with Stickiness},
  author={Marc Carrascosa and Boris Bellalta},
  journal={arXiv: Networking and Internet Architecture},
WiFi densification leads to the existence of multiple overlapping coverage areas, which allows user stations (STAs) to choose between different Access Points (APs). The standard WiFi association method makes the STAs select the AP with the strongest signal, which in many cases leads to underutilization of some APs while overcrowding others. To mitigate this situation, Reinforcement Learning techniques such as Multi-Armed Bandits can be used to dynamically learn the optimal mapping between APs… 


Collaborative Spatial Reuse in Wireless Networks via Selfish Multi-Armed Bandits
This work studies the exploration-exploitation trade-off by means of the $\varepsilon$-greedy, EXP3, UCB and Thompson sampling action-selection strategies and shows that optimal proportional fairness can be achieved, even if no information about neighboring networks is available to the learners and WNs operate selfishly.
Decentralized AP selection in large-scale wireless LANs considering multi-AP interference
  • P. Oni, S. Blostein
  • Computer Science
    2017 International Conference on Computing, Networking and Communications (ICNC)
  • 2017
A decentralized AP selection scheme that takes interference at the candidate APs into account and selects AP that offers best signal-interference-plus noise ratio (SINR) is proposed, which achieves 99% and 43% gains in aggregate throughput over SSF and MPD, respectively.
Channel Selection for Network-Assisted D2D Communication via No-Regret Bandit Learning With Calibrated Forecasting
A network-assisted distributed channel selection approach in which D2D users are only allowed to use vacant cellular channels is proposed, and the proposed approach not only yields vanishing regret in comparison to the global optimal solution but also guarantees that the empirical joint frequencies of the game converge to the set of correlated equilibria.
WLC19-4: Effective AP Selection and Load Balancing in IEEE 802.11 Wireless LANs
This paper proposes two effective new AP selection algorithms that can significantly increase overall system throughput and reduce average frame delay and shows that better performance can be achieved when the APs provide assistance in delay measurements.
Cell Breathing Techniques for Load Balancing in Wireless LANs
This paper presents a new load balancing technique by controlling the size of WLAN cells (i.e., AP's coverage range), which is conceptually similar to cell breathing in cellular networks, and develops a set of polynomial time algorithms that find the optimal beacon power settings which minimize the load of the most congested AP.
A Neural Network based cognitive engine for IEEE 802.11 WLAN Access Point selection
A Cognitive AP selection scheme that allows the mobile station to learn from its past experience how to select the best AP, and a cognitive engine based on a Neural Network trained on this data drives the AP selection process.
An empirical analysis of the IEEE 802.11 MAC layer handoff process
This paper presents an empirical study of this handoff process at the link layer, with a detailed breakup of the latency into various components, showing that a MAC layer function - probe is the primary contributor to the overall handoff latency.
The TMB path loss model for 5 GHz indoor WiFi scenarios: On the empirical relationship between RSSI, MCS, and spatial streams
This paper assesses empirically the suitability of the available IEEE 802.11ax path loss models at 5 GHz on some real testbeds and proposes a new model with higher abstraction level, able to obtain an estimation of RSSI, selected modulation and coding scheme (MCS), and number of spatial streams in function of the AP configuration and the AP-STA distance.
A performance study of roaming in wireless local area networks based on IEEE 802.11r
Simulation results demonstrate the flexibility of the IEEE 802.11r and the effectiveness of its roaming procedure, and a noticeable reduction in roaming time and delays at APs is shown to be achievable, which guarantees the required quality of service level of Voice over IP over WLAN (VoWLAN) applications.
Machine Learning Paradigms for Next-Generation Wireless Networks
The goal is to assist the readers in refining the motivation, problem formulation, and methodology of powerful machine learning algorithms in the context of future networks in order to tap into hitherto unexplored applications and services.