Abstract
Supporting a massive amount of Internet of Things applications requires a large pool of spectrum. DSM is a promising ecosystem to improve the spectrum efficiency. In the era of LoRaWAN, the physical hardware constraints, along with the bandwidth-hungry applications pose new challenges. In this article, we investigate a novel deep-reinforcement-learning-based spectrum-sharing paradigm, termed Intelligent Overlapping, that explores partially overlapping channels for concurrent spectrum access in LoRaWAN. Our key insight is to leverage the coding redundancy to expand the available spectrum without complicated data processing algorithms. In particular, we learn the extra coding redundancy from the data on the non-overlapping spectrum via a deep-Q-learning network, and we apply such redundancy to recover the data on the overlapping spectrum. In the Media Access Control layer, we predict the channel condition and strategically learn and assign the appropriate overlapping portion to the concurrent access end devices. In the Physical layer, we harness interleaving to randomize the mutual interference to ensure that all the data remains decodable. Simulation results demonstrate that Intelligent Overlapping greatly improves the spectrum efficiency with a fast convergence rate compared to the conventional DSM mechanisms.
- [1] . 2017. Mobile edge computing: A survey. IEEE Internet Things J. 5, 1 (2017), 450–465.Google ScholarCross Ref
- [2] . 2019. FREE—Fine-grained scheduling for reliable and energy-efficient data collection in LoRaWAN. IEEE Internet Things J. 7, 1 (2019), 669–683.Google ScholarCross Ref
- [3] . 2007. Self-management in chaotic wireless deployments. Wireless Netw. 13, 6 (2007), 737–755.Google ScholarDigital Library
- [4] . 2015. Analysis of spectrum occupancy using machine learning algorithms. IEEE Trans. Vehic. Technol. 65, 9 (2015), 6853–6860.Google ScholarCross Ref
- [5] . 2009. White space networking with wi-fi like connectivity. ACM SIGCOMM Comput. Commun. Rev. 39, 4 (2009), 27–38.Google ScholarDigital Library
- [6] . 2004. Interleaver technology: Comparisons and applications requirements. J. Lightwave Technol. 22, 1 (2004), 281.Google ScholarCross Ref
- [7] . 1978. Broadcast channels with confidential messages. IEEE Trans. Info. Theory 24, 3 (1978), 339–348.Google ScholarDigital Library
- [8] . 2019. 5G waveforms for IoT applications. IEEE Commun. Surveys Tutor. 21, 3 (2019), 2554–2567. Google ScholarCross Ref
- [9] . 2017. Empowering low-power wide area networks in urban settings. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication. 309–321.Google ScholarDigital Library
- [10] . 2020. LMAC: Efficient carrier-sense multiple access for LoRa. In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking. 1–13.Google ScholarDigital Library
- [11] . 2008. Zigzag Decoding: Combating Hidden Terminals in Wireless Networks. Vol. 38. ACM.Google ScholarDigital Library
- [12] . 2011. MPAP: Virtualization architecture for heterogenous wireless APs. ACM SIGCOMM Computer Commun. Rev. 41, 4 (2011), 475–476.Google ScholarDigital Library
- [13] . 2011. Practical, real-time, full duplex wireless. In Proceedings of the ACM MobiCom. 301–312.Google ScholarDigital Library
- [14] . 2007. Embracing wireless interference: Analog network coding. In ACM SIGCOMM Computer Communication Review, Vol. 37. ACM, 397–408.Google Scholar
- [15] . 2021. NELoRa: Towards ultra-low SNR LoRa communication with neural-enhanced demodulation. In Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems. 56–68.Google ScholarDigital Library
- [16] . 2010. Retransmission\(\ne\) repeat: Simple retransmission permutation can resolve overlapping channel collisions. In Proceedings of the ACM Mobicom.Google Scholar
- [17] . 2010. Wireless communication method and system for bit interleaved coded modulation and iterative decoding.
U.S. Patent 7,802,171. Google Scholar - [18] . 2019. Spectrum sharing in vehicular networks based on multi-agent reinforcement learning. IEEE J. Select. Areas Commun. 37, 10 (2019), 2282–2292.Google ScholarCross Ref
- [19] . 2018. Anti-jamming communications using spectrum waterfall: A deep reinforcement learning approach. IEEE Commun. Lett. 22, 5 (2018), 998–1001.Google ScholarCross Ref
- [20] . 2020. Covert wireless communication in IoT network: From AWGN channel to THz band. IEEE Internet Things J. 7, 4 (2020), 3378–3388.Google ScholarCross Ref
- [21] . 2008. Dynamic spectrum management: Complexity and duality. IEEE J. Select. Topics Signal Process. 2, 1 (2008), 57–73.Google ScholarCross Ref
- [22] . 2006. Partially overlapped channels not considered harmful. In Proceedings of the Joint International Conference on Measurement and Modeling of Computer Systems. 63–74.Google ScholarDigital Library
- [23] . 2015. Human-level control through deep reinforcement learning. Nature 518, 7540 (2015), 529–533.Google ScholarCross Ref
- [24] . 2017. Deep multi-user reinforcement learning for dynamic spectrum access in multichannel wireless networks. In Proceedings of the IEEE Global Communications Conference (GC’17). IEEE, 1–7.Google ScholarDigital Library
- [25] . 2014. Power allocation in OFDM based NOMA systems: A DC programming approach. In Proceedings of the IEEE Globecom Workshops (GC’14). IEEE, 1026–1031.Google ScholarCross Ref
- [26] . 2021. Concurrent interference cancellation: Decoding multi-packet collisions in LoRa. In Proceedings of the ACM SIGCOMM Conference. 503–515.Google ScholarDigital Library
- [27] . 2019. Efficient spectrum slicing in 5G networks: An overlapping coalition formation approach. IEEE Trans. Mobile Comput. 19, 6 (2019), 1299–1316.Google ScholarCross Ref
- [28] . 2013. Machine learning techniques for cooperative spectrum sensing in cognitive radio networks. IEEE J. Select. Areas Commun. 31, 11 (2013), 2209–2221.Google ScholarCross Ref
- [29] . 2020. Combating packet collisions using non-stationary signal scaling in LPWANs. In Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services. 234–246.Google ScholarDigital Library
- [30] . 2020. Colora: Enabling multi-packet reception in lora. In Proceedings of the IEEE Conference on Computer Communications (INFOCOM’20). IEEE, 2303–2311.Google ScholarDigital Library
- [31] . 2010. Opportunistic bandwidth sharing through reinforcement learning. IEEE Trans. Vehic. Technol. 59, 6 (2010), 3148–3153.Google ScholarCross Ref
- [32] . 2012. Combating hidden and exposed terminal problems in wireless networks. IEEE Trans. Wireless Commun. 11, 11 (2012), 4204–4213.Google ScholarCross Ref
- [33] . 2019. MLoRa: A multi-packet reception protocol in LoRa networks. In Proceedings of the IEEE 27th International Conference on Network Protocols (ICNP’19). IEEE, 1–11.Google ScholarCross Ref
- [34] . 2012. hJam: Attachment transmission in WLANs. IEEE Trans. Mobile Comput. 12, 12 (2012), 2334–2345.Google ScholarDigital Library
- [35] . 2021. PCube: Scaling LoRa concurrent transmissions with reception diversities. In Proceedings of the 27th Annual International Conference on Mobile Computing and Networking. 670–683.Google ScholarDigital Library
- [36] . 2020. FTrack: Parallel decoding for LoRa transmissions. IEEE/ACM Trans. Netw. 28, 6 (2020), 2573–2586.Google ScholarDigital Library
- [37] . 2010. Design of non-orthogonal multi-channel sensor networks. In Proceedings of the IEEE 30th International Conference on Distributed Computing Systems (ICDCS’10). IEEE, 358–367.Google ScholarDigital Library
- [38] . 2019. Wireless networks design in the era of deep learning: Model-based, AI-based, or both?IEEE Trans. Commun. 67, 10 (2019), 7331–7376.Google ScholarCross Ref
- [39] . 2011. Adaptive subcarrier nulling: Enabling partial spectrum sharing in wireless LANs. In Proceedings of the 19th IEEE International Conference on Network Protocols (ICNP’11). IEEE, 311–320.Google ScholarDigital Library
- [40] . 2019. Dynamic spectrum management via machine learning: state of the art, taxonomy, challenges, and open research issues. IEEE Netw. 33, 4 (2019), 54–62.Google ScholarCross Ref
Index Terms
- Exploring Partially Overlapping Channels for Low-power Wide Area Networks
Recommendations
Dynamic spectrum management for cognitive radio: an overview
Cognitive Radio and Advanced Spectrum ManagementThe currently in use spectrum management policies are responsible for the poor utilization of the electromagnetic radio spectrum. By performing dynamic spectrum management (DSM), cognitive radio (CR) has the potential to increase the radio spectrum ...
Cooperative bargaining solution for efficient and fair spectrum management in cognitive wireless networks
This paper studies the fairness among the primary users PUs and the secondary users SUs for resource allocation in cognitive radio systems. We propose a novel co-opetition strategy based on the Kalai-Smorodinsky bargaining solution to balance the system ...
Channel assignment based on bee algorithms in multi‐hop cognitive radio networks
Spectrum management policies are responsible for poor utilisation of the radio spectrum. By carrying out dynamic spectrum management (DSM), cognitive radio (CR) can increase the radio spectrum in wireless systems efficiently. CR technology accounts for ...
Comments