6533b7d6fe1ef96bd1265ccb
RESEARCH PRODUCT
Learning From Errors: Detecting Cross-Technology Interference in WiFi Networks
Nicola InzerilloIlenia TinnirelloFabrizio GiulianoDomenico GarlisiDaniele Crocesubject
MonitoringComputer Networks and CommunicationsComputer scienceReal-time computingheterogeneous network050801 communication & media studies02 engineering and technologySpectrum managementZigBee0508 media and communicationsArtificial IntelligencePHY0202 electrical engineering electronic engineering information engineeringLong Term EvolutionDemodulationWireless fidelityHidden Markov modelsHidden Markov modelCross technology interferenceArtificial neural networkSettore ING-INF/03 - Telecomunicazioni05 social sciencesComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKScoexistenceunlicensed bands020206 networking & telecommunicationsThroughputLearning from errorsHardware and ArchitectureInterferenceCoding (social sciences)description
In this paper, we show that inter-technology interference can be recognized using commodity WiFi devices by monitoring the statistics of receiver errors. Indeed, while for WiFi standard frames the error probability varies during the frame reception in different frame fields (PHY, MAC headers, and payloads) protected with heterogeneous coding, errors may appear randomly at any point during the time the demodulator is trying to receive an exogenous interfering signal. We thus detect and identify cross-technology interference on off-the-shelf WiFi cards by monitoring the sequence of receiver errors (bad PLCP, bad FCS, invalid headers, etc.) and propose two methods to recognize the source of interference based on artificial neural networks and hidden Markov chains. The result is quite impressive, reaching an average accuracy of over 95% in recognizing ZigBee, microwave, and LTE (in unlicensed spectrum) interference.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2018-01-01 |