NB-IoT Random Access: Data-driven Analysis and ML-based Enhancements

The content in this webpage complements the paper “NB-IoT Random Access: Data-driven Analysis and ML-based Enhancements”. The paper has been accepted for publication in IEEE Internet of Things Journal, and an early access version can be found here.

The complete dataset is available below. Please consider to cite the paper if you use the dataset: G. Caso et. al. “NB-IoT Random Access: Data-driven Analysis and ML-based Enhancements,” IEEE Internet Things J., to appear, 2021.

Tool Description

Measurement System

For the NB-IoT measurements in Oslo and Rome, we used the Rohde&Schwarz (R&S) TSMA6 toolkit, along with an Exelonix Narrowband (NB) USB device and a global position-ing system (GPS) antenna.

Dataset Description

A description of the dataset attributes collected by the TSMA6 toolkit is available here.

A description of the dataset attributes related to Random Access (RA) and jointly collected by TSMA6 and Exelonix device is available below:

  • Timestamp [hh:mm:ss]: Timestamp
  • NPCI: Narrowband Physical Cell Identifier
  • NRSRP: Narrowband Reference Signal Received Power [dBm]
  • NRSSI: Narrowband Reference Signal Strength Indicator [dBm]
  • NSINR: Narrowband Signal-to-Interference-plus-Noise Ratio [dB]
  • NRSRQ: Narrowband Reference Signal Received Quality [dB]
  • Coverage Level: Numerical indication between 0 and 2
  • Tx Power: Power transmitted on NPUSCH channel [dBm]
  • NPRACH Single MSG1 Tx Power: Power used to transmit a specific preamble (MSG1) during a RA procedure [dBm]
  • NPRACH Final Tx Power: Power used to transmit the successful preamble (MSG1) during a RA procedure [dBm]
  • NPRACH Final Trigger Pathloss: Path loss triggering a RA procedure [dB]
  • NPRACH Single Failed Attempt: Cause of failure of a preamble (MSG1) transmission attempt (e.g., “Failed@MSG2”, “Failed@MSG4”)
  • NPRACH Final MSG1 Tx Count: Number of preamble (MSG1) attempts needed to conclude a RA procedure
  • NPRACH Final Result: Indication of RA Result (e.g., “Success”, “Fail”, “Abort”)
  • NPRACH Final Duration: Duration of a RA entire procedure [ms]
  • NPRACH SIB2 Max Tx Count: Number of detected SIB2 messages
  • Dataset

    The dataset contains the above RA-related data collected in 21, 69, and 24 sub-campaigns in Deep Indoor (DI), Indoor (I), and Outdoor (O) scenarios, respectively. O is divided in Outdoor Walking (OW) and Outdoor Driving (OD) sub-campaigns. Overall, two NB-IoT operators (Op1 and Op2) have been detected.

    A sample of the dataset related to RA, consisting of one complete OD sub-campaign for Op2 is available below:

    sample data

    Test Cases Configurations

    We configured the Exelonix module via ATtention (AT) Commands, and created the following three test cases. For each operator, we run the test cases in parallel with the scanner measurements.

    Test Case 1: The device performs repeated RA executions spaced out by short waiting times

    Test Case 2: The device performs, after a successful RA, a connectivity test via Internet Control Message Protocol (ICMP) ping composed by 4 pings, toward the Google Domain Name System (DNS) server located at

    Test Case 3: The device performs, after a successful RA, a 1 KB data upload via File Transfer Protocol (FTP), toward a proprietary server located in Oslo.

    Supplementary Material

    Statistical validation of coverage results.

    Sub-campaign average RSRP across scenarios for Op1 and Op2
    Sub-campaign average SINR across scenarios for Op1 and Op2

    We perform additional statistical significance tests to pinpoint differences between the means of the distributions.  In particular, we examine the following cases:

    1. Operator Comparison: For a given scenario, we show if there is a significant difference between the two operators in terms of RSRP and SINR.
    2. Scenario ComparisonFor a given operator, we show if there is significant difference between any combination of the three scenarios.

    We perform the Kruskal-Wallis non-parametric analysis of variance test to assess whether the data come from the same distribution. For the scenario comparison, since we have more than two groups, we also leverage the Dunn’s test to identify significant difference between the means of two or more distributions for a given confidence interval.

    • Null Hypothesis: There is no significant difference between the two distributions
    • Alternative Hypothesis: There is significant difference between the two distributions.

    We report the p-values below: (Significant codes: ‘*’ 0.05 , ‘**’ 0.01, ‘***’ 0.001)

    RSRP0.15940.00033 ***0.0403 *
    SINR0.38240.00054 ***0.2224
    Operator comparison
    Op1/RSRP1.47e-07 ***1.2e-07 ***0.2948
    Op2/RSRP2.3e-06 ***9.2e-10 ***0.006 **
    Op1/SINR0.00178 **0.940660.00034 ***
    Op2/SINR0.0282 *0.0282 *0.6942
    Scenario comparison

    Out-of-bag accuracy for the Random Forest classifier, as a function of the number of trained trees.

    The results show that after about 10/20 trees the Out-of-bag accuracy converges in DI and I scenarios. For O, it slightly increases after 20 trees, in particular when more features are used for the classification task. Hence, 50 trees represents a good rather conservative choice for the classifier in all scenarios.

    DI Scenario
    I Scenario
    O Scenario

    Confusion matrix for each Operator/Scenario combination. The Random Forest classifier uses 50 trees and {RSRP, RSRQ, SINR} feature set to predict the RA outcomes.

    Op1 / DI
    Op1 / I
    Op1 / O
    Op2 / DI
    Op2 / I
    Op2 / O
    %d bloggers like this: