Understanding WiFi Cross-Technology Interference Detection in the Real World

Näytä kaikki kuvailutiedot



Pysyväisosoite

http://hdl.handle.net/10138/335911

Lähdeviite

Pulkkinen , T , Nurminen , J K & Nurmi , P 2021 , Understanding WiFi Cross-Technology Interference Detection in the Real World . in 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS) . IEEE International Conference on Distributed Computing Systems , IEEE Computer Society Conference Publishing Services , pp. 954-964 , International Conference on Distributed Computing Systems , Singapore , 29/11/2020 . https://doi.org/10.1109/ICDCS47774.2020.00061

Julkaisun nimi: Understanding WiFi Cross-Technology Interference Detection in the Real World
Tekijä: Pulkkinen, Teemu; Nurminen, Jukka K; Nurmi, Petteri
Tekijän organisaatio: Department of Computer Science
Julkaisija: IEEE Computer Society Conference Publishing Services
Päiväys: 2021-02-23
Kieli: eng
Sivumäärä: 11
Kuuluu julkaisusarjaan: 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)
Kuuluu julkaisusarjaan: IEEE International Conference on Distributed Computing Systems
ISBN: 978-1-7281-7002-2
ISSN: 1063-6927
DOI-tunniste: https://doi.org/10.1109/ICDCS47774.2020.00061
URI: http://hdl.handle.net/10138/335911
Tiivistelmä: WiFi networks are increasingly subjected to cross-technology interference with emerging IoT and even mobile communication solutions all crowding the 2.4 GHz ISM band where WiFi networks conventionally operate. Due to the diversity of interference sources, maintaining high level of network performance is becoming increasing difficult. Recently, deep learning based interference detection has been proposed as a potentially powerful way to identify sources of interference and to provide feedback on how to mitigate their effects. The performance of such approaches has been shown to be impressive in controlled evaluations; however, little information exists on how they generalize to the complexity of everyday environments. In this paper, we contribute by conducting a comprehensive performance evaluation of deep learning based interference detection. In our evaluation, we consider five orthogonal but complementary metrics: correctness, overfitting, robustness, efficiency, and interpretability. Our results show that, while deep learning indeed has excellent correctness (i.e., detection accuracy), it can be prone to noise in measurements (e.g., struggle when transmission power is dynamically adjusted) and suffers from poor interpretability. To compensate for weaknesses of deep learning, as our second contribution we propose a novel signal modeling approach for interference detection and compare it against the deep learning. Our results demonstrate that, in terms of errors, there are some differences across the two approaches, with signal modeling being better at identifying technologies that rely on frequency hopping or that have dynamic spectrum signatures but suffering in other cases. Based on our results, we draw guidelines for improving interference detection performance.
Avainsanat: 113 Computer and information sciences
NETWORKS
Vertaisarvioitu: Kyllä
Tekijänoikeustiedot: unspecified
Pääsyrajoitteet: openAccess
Rinnakkaistallennettu versio: acceptedVersion


Tiedostot

Latausmäärä yhteensä: Ladataan...

Tiedosto(t) Koko Formaatti Näytä
Comparing_AI_Systems_2.pdf 1.785MB PDF Avaa tiedosto

Viite kuuluu kokoelmiin:

Näytä kaikki kuvailutiedot