資料載入中.....
|
請使用永久網址來引用或連結此文件:
https://nccur.lib.nccu.edu.tw/handle/140.119/158478
|
| 題名: | 考量負載條件的物聯網裝置自我調適型錯誤偵測機制
Load-Aware Self-Adaptive Fault Detection for IoT Devices |
| 作者: | 陳繹帆
Chen, Yi-Fan |
| 貢獻者: | 廖峻鋒
Liao, Chun-Feng
陳繹帆
Chen, Yi-Fan |
| 關鍵詞: | 物聯網
自適應心跳
故障偵測
可靠性模型
Internet of Things
adaptive heartbeat
fault detection
reliability model |
| 日期: | 2025 |
| 上傳時間: | 2025-08-04 13:58:19 (UTC+8) |
| 摘要: | 隨著物聯網技術的快速發展，設備之間的即時通訊與狀態監控成為確保系統穩定運作的關鍵。但是在長時間運行下，裝置可能因高負載、通訊延遲或硬體老化而導致故障，影響整體系統之效能與可靠性。傳統以固定頻率傳送心跳訊號的監控方式雖然實作簡便，但在如 LoRaWAN、WirelessHART 等資源受限場域中，頻繁傳輸將導致不必要的能耗與頻寬浪費，且缺乏針對設備狀態進行動態調整的能力。
為解決上述問題，本研究提出一套基於主動式心跳的自適應監控機制，由控制點（Control Point, CP）主動向設備發送狀態請求，並依據其回傳之即時負載與延遲資訊，動態調整心跳間隔頻率。本機制以可靠性理論為基礎，建構指數分佈模型並引入負載調節故障率推導公式，進一步結合非線性風險因子與平滑處理邏輯，實現具備即時反應能力的心跳調節策略。
在系統實作上，研究採用 Raspberry Pi 作為模擬裝置，建立完整監控架構並模擬高變動負載與隨機故障情境。實驗結果顯示，相較於固定頻率心跳策略，本機制可有效降低通訊次數與總能耗，同時維持甚至優於傳統策略的異常偵測延遲表現，證明其在資源受限場景中具備高度實用潛力。
With the rapid advancement of Internet of Things (IoT) technologies, real-time communication and state monitoring between devices have become crucial for maintaining system stability. However, over prolonged operation, devices may encounter failures due to high workload, communication delays, or hardware degradation, thereby compromising system performance and reliability. Traditional heartbeat monitoring strategies, which transmit signals at fixed frequencies, are simple to implement but incur unnecessary energy and bandwidth overhead—especially in resource-constrained environments such as LoRaWAN and WirelessHART—and lack the ability to adapt to the dynamic status of devices.
To address these limitations, this study proposes an adaptive monitoring mechanism based on a monitor-initiated heartbeat model. A central Control Point (CP) actively sends status requests to devices and dynamically adjusts the heartbeat interval based on real-time workload and latency feedback. The proposed mechanism is grounded in reliability theory, utilizing an exponential failure distribution model combined with a workload-adjusted failure rate function. Furthermore, a nonlinear risk factor and smoothing logic are introduced to enhance responsiveness and ensure stable interval updates.
In the system implementation, Raspberry Pi devices are used to simulate IoT endpoints, forming a complete monitoring framework capable of handling highly variable workloads and randomly induced failures. Experimental results demonstrate that compared to fixed-frequency heartbeats, the proposed approach significantly reduces communication overhead and energy consumption while achieving equal or better fault detection latency. This confirms its high practical potential for deployment in resource-constrained IoT scenarios. |
| 參考文獻: | [1] M. S. Hossain and G. Muhammad, “Cloud-assisted industrial internet of things (iiot)–enabled framework for health monitoring”, Computer Networks, vol. 101, pp. 192–202, 2016, Industrial Technologies and Applications for the Internet of Things, ISSN: 1389-1286. DOI: 10.1016/j.comnet.2016.01.009.
[2] M. Banerjee, C. Borges, K.-K. R. Choo, J. Lee, and C. Nicopoulos, “A hardwareassisted heartbeat mechanism for fault identification in large-scale iot systems”, IEEE Transactions on Dependable and Secure Computing, vol. 19, no. 2, pp. 1254– 1265, 2022. DOI: 10.1109/TDSC.2020.3009212.
[3] O. D. Nekui, W. Wang, C. Liu, Z. Wang, and B. Ding, “Iot-based heartbeat ratemonitoring device powered by harvested kinetic energy”, Sensors, vol. 24, no. 13, 2024, ISSN: 1424-8220. DOI: 10.3390/s24134249.
[4] N. Murphy and M. Barr, “Watchdog timers”, Embedded Systems Programming, vol. 14, no. 11, pp. 79–80, 2001.
[5] J. W. Cutler and J. Beningo, “Watchdog-based fault recovery on nanosatellites”, Journal of Aerospace Information Systems, vol. 19, no. 8, pp. 522–529, 2022.
[6] H. Zhu and H. Chen, “Adaptive failure detection via heartbeat under hadoop”, in 2011 IEEE Asia-Pacific Services Computing Conference, IEEE, 2011, pp. 231–238.
[7] G. Moloudian, M. Hosseinifard, S. Kumar, et al., “Rf energy harvesting techniques for battery-less wireless sensing, industry 4.0, and internet of things: A review”, IEEE Sensors Journal, vol. 24, no. 5, pp. 5732–5745, 2024. DOI: 10.1109/JSEN. 2024.3352402.
[8] A. V. Papadopoulos, S. A. Asadollah, M. Ashjaei, S. Mubeen, H. Pei-Breivold, and M. Behnam, “Slas for industrial iot: Mind the gap”, in 2017 5th International 43 Conference on Future Internet of Things and Cloud Workshops (FiCloudW), 2017, pp. 75–78. DOI: 10.1109/FiCloudW.2017.70.
[9] S. Noureddine and B. Meriem, “Ml-sla-iot: An sla specification and monitoring framework for iot applications”, in 2021 International Conference on Information Systems and Advanced Technologies (ICISAT), 2021, pp. 1–12. DOI: 10 . 1109 / ICISAT54145.2021.9678460.
[10] Cisco, Cisco annual internet report (2018–2023) white paper, https://www.cisco. com/c/en/us/solutions/collateral/executive-perspectives/annual-internetreport/white-paper-c11-741490.html, 2020.
[11] T. D. Chandra and S. Toueg, “Unreliable failure detectors for reliable distributed systems”, J. ACM, vol. 43, no. 2, pp. 225–267, Mar. 1996, ISSN: 0004-5411. DOI: 10.1145/226643.226647.
[12] Y. Chahid, M. Benabdellah, and A. Azizi, “Internet of things protocols comparison, architecture, vulnerabilities and security: State of the art”, in Proceedings of the 2nd International Conference on Computing and Wireless Communication Systems, ser. ICCWCS’17, Larache, Morocco: Association for Computing Machinery, 2017, ISBN: 9781450353069. DOI: 10.1145/3167486.3167554.
[13] K. Ponnusamy and N. Rajagopalan, “Internet of things: A survey on iot protocol standards”, in Progress in Advanced Computing and Intelligent Engineering, Singapore: Springer Singapore, 2018, pp. 651–663, ISBN: 978-981-10-6875-1.
[14] L. Iiyambo, G. Hancke, and A. M. Abu-Mahfouz, “A survey on nb-iot random access: Approaches for uplink radio access network congestion management”, IEEE Access, vol. 12, pp. 95 487–95 506, 2024. DOI: 10.1109/ACCESS.2024.3419216.
[15] M. Jouhari, N. Saeed, M.-S. Alouini, and E. M. Amhoud, “A survey on scalable lorawan for massive iot: Recent advances, potentials, and challenges”, IEEE Communications Surveys & Tutorials, vol. 25, no. 3, pp. 1841–1876, 2023. DOI: 10. 1109/COMST.2023.3274934.
[16] D. Todoli-Ferrandis, J. Silvestre-Blanes, V. Sempere-Payá, and S. Santonja-Climent, “Polling mechanisms for industrial iot applications in long-range wide-area net44 works”, Future Internet, vol. 16, no. 4, 2024, ISSN: 1999-5903. DOI: 10.3390/ fi16040130.
[17] M. Barletta, M. Cinque, and C. Di Martino, “Sla-driven software orchestration in industry 4.0”, IEEE Internet of Things Magazine, vol. 5, no. 4, pp. 136–141, 2022. DOI: 10.1109/IOTM.001.2200216.
[18] A. Asanjarani, B. Liquet, and Y. Nazarathy, “Estimation of semi-markov multistate models: A comparison of the sojourn times and transition intensities approaches”, The International Journal of Biostatistics, vol. 18, no. 1, pp. 243–262, 2022. DOI: doi:10.1515/ijb-2020-0083.
[19] Z. Hou, Y. Huang, S. Zheng, X. Dong, and B. Wang, “Design and implementation of heartbeat in multi-machine environment”, in 17th International Conference on Advanced Information Networking and Applications, 2003. AINA 2003., 2003, pp. 583–586. DOI: 10.1109/AINA.2003.1192949.
[20] M. A. P. Putra, A. Zainudin, R. N. Alief, G. A. Sampedro, D.-S. Kim, and J.-M. Lee, “Blockchain-based federated learning for bearing fault detection in the industrial internet of things”, in 2023 14th International Conference on Information and Communication Technology Convergence (ICTC), 2023, pp. 1069–1074. DOI: 10.1109/ICTC58733.2023.10392487.
[21] X. Lu and K. Phang, “An enhanced hadoop heartbeat mechanism for mapreduce task scheduler using dynamic calibration”, China Communications, vol. 15, no. 11, pp. 93–110, 2018.
[22] S. Mayya, R. K. Ramachandran, L. Zhou, et al., “Adaptive and risk-aware target tracking for robot teams with heterogeneous sensors”, IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 5615–5622, 2022. DOI: 10.1109/LRA.2022.3155805.
[23] O. Kiss, Performance evaluation of event-driven network resource monitoring in radio software lab, 2024.
[24] Y. Wang, L. Zheng, and Y. Wang, “Event-driven tool condition monitoring methodology considering tool life prediction based on industrial internet”, Journal of Manufacturing Systems, vol. 58, pp. 205–222, 2021, ISSN: 0278-6125. DOI: 10.1016/ j.jmsy.2020.11.019. 45
[25] Y. Igarashi, R. Nakano, and N. Wakamiya, “A polling-based transmission scheme using a network traffic uniformity metric for industrial iot applications”, Sensors, vol. 19, no. 1, p. 187, 2019.
[26] X. Zhang, K. P. Rane, I. Kakaravada, and M. Shabaz, Nonlinear Engineering, vol. 10, no. 1, pp. 245–254, 2021. DOI: doi:10.1515/nleng-2021-0019. [Online]. Available: https://doi.org/10.1515/nleng-2021-0019.
[27] W. Sun, J. Liu, and Y. Yue, “Ai-enhanced offloading in edge computing: When machine learning meets industrial iot”, IEEE Network, vol. 33, no. 5, pp. 68–74, 2019. DOI: 10.1109/MNET.001.1800510.
[28] F. Liang, W. Yu, X. Liu, D. Griffith, and N. Golmie, “Toward edge-based deep learning in industrial internet of things”, IEEE Internet of Things Journal, vol. 7, no. 5, pp. 4329–4341, 2020. DOI: 10.1109/JIOT.2019.2963635.
[29] J. Dong, Z. Li, Y. Zheng, J. Luo, M. Zhang, and X. Yang, “Real-time fault detection for iiot facilities using ga-att-lstm based on edge-cloud collaboration”, Frontiers in Neurorobotics, vol. 18, L. Li, Ed., p. 1 499 703, 2024, Received: 21 September 2024; Accepted: 28 October 2024; Published: 11 November 2024. DOI: 10.3389/ fnbot.2024.1499703.
[30] W. Zhang, W. Guo, X. Liu, et al., “Lstm-based analysis of industrial iot equipment”, IEEE Access, vol. 6, pp. 23 551–23 560, 2018. DOI: 10.1109/ACCESS.2018. 2825538.
[31] G.-Q. Zeng, Y.-W. Yang, K.-D. Lu, G.-G. Geng, and J. Weng, “Evolutionary adversarial autoencoder for unsupervised anomaly detection of industrial internet of things”, IEEE Transactions on Reliability, pp. 1–15, 2025. DOI: 10.1109/TR. 2025.3528256.
[32] Y. Feng, J. Chen, Z. Liu, H. Lv, and J. Wang, “Full graph autoencoder for one-class group anomaly detection of iiot system”, IEEE Internet of Things Journal, vol. 9, no. 21, pp. 21 886–21 898, 2022. DOI: 10.1109/JIOT.2022.3181737.
[33] R. Xuan, F. Wang, and S. Chen, “Network topology detection method based on bgp protocol and simulation verification”, in 2024 10th International Conference 46 on Big Data and Information Analytics (BigDIA), 2024, pp. 541–545. DOI: 10. 1109/BigDIA63733.2024.10808882.
[34] F. Tommasi, V. De Luca, and C. Melle, “Qos monitoring in real-time streaming overlays based on lock-free data structures”, Multimedia Tools and Applications, vol. 80, no. 14, pp. 20 929–20 970, 2021.
[35] F. Neumeister, M. Göckel, and M. Zitterbart, “Trust: Transparent redundancy for udp streams”, in 2023 IEEE 21st International Conference on Industrial Informatics (INDIN), 2023, pp. 1–7. DOI: 10.1109/INDIN51400.2023.10218145.
[36] R. K. Unni, P. Vijayanand, and Y. Dilip, “Fpga implementation of an improved watchdog timer for safety-critical applications”, in 2018 31st International Conference on VLSI Design and 2018 17th International Conference on Embedded Systems (VLSID), 2018, pp. 55–60. DOI: 10.1109/VLSID.2018.37.
[37] B. Asch, E. Jellum, M. Lohstroh, and E. A. Lee, “Software-defined watchdog timers for cyber-physical systems”,IEEE Embedded Systems Letters, vol. 17, no. 2, pp. 115– 118, 2025. DOI: 10.1109/LES.2024.3467332.
[38] P. Matoušek, O. Ryšavý, and L. Polčák, “Unified snmp interface for iot monitoring”, in 2021 IFIP/IEEE International Symposium on Integrated Network Management (IM), 2021, pp. 938–943.
[39] K. Cereceda, J. But, and P. Branch, “Experimental observations and analysis of bgp route flapping dynamics”, in 2025 International Conference on Information Networking (ICOIN), 2025, pp. 105–110. DOI: 10 . 1109 / ICOIN63865 . 2025 . 10993166.
[40] K. Sankaranarayanan, R. B. Roy, and D. Tiwari, “Pulse: Using mixed-quality models for reducing serverless keep-alive cost”, in SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2024, pp. 99–109. DOI: 10.1109/SCW63240.2024.00021.
[41] B. A. Johnsson, M. Nordahl, and B. Magnusson, “Evaluating a dynamic keepalive messaging strategy for mobile pervasive systems”, Procedia Computer Science, vol. 109, pp. 319–326, 2017, 8th International Conference on Ambient Systems, Networks and Technologies, ANT-2017 and the 7th International Confer47 ence on Sustainable Energy Information Technology, SEIT 2017, 16-19 May 2017, Madeira, Portugal, ISSN: 1877-0509. DOI: https://doi.org/10.1016/j.procs. 2017.05.358.
[42] T. Peng, “Edge computing service framework for it/ot converged networks for cyberresiliency: Machine learning-assisted sdn”, in 2023 IEEE 3rd International Conference on Electronic Communications, Internet of Things and Big Data (ICEIB), 2023, pp. 230–234. DOI: 10.1109/ICEIB57887.2023.10170421.
[43] J. Arshad, M. Aziz, A. A. Al-Huqail, et al., “Implementation of a lorawan based smart agriculture decision support system for optimum crop yield”, Sustainability, vol. 14, no. 2, 2022, ISSN: 2071-1050. DOI: 10.3390/su14020827.
[44] A. Pötsch and F. Haslhofer, “Practical limitations for deployment of lora gateways”, in 2017 IEEE International Workshop on Measurement and Networking (MN), 2017, pp. 1–6. DOI: 10.1109/IWMN.2017.8078360.
[45] S. Trendov, M. Gering, and E. Siemens, “Impact of lorawan transceiver on end device battery lifetime”, in 2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP), 2023, pp. 1–5. DOI: 10.1109/IWSSIP58668. 2023.10180293.
[46] C. Garrido-Hidalgo, J. Haxhibeqiri, B. Moons, et al., “Lorawan scheduling: From concept to implementation”,IEEE Internet of Things Journal, vol. 8, no. 16, pp. 12 919– 12 933, 2021. DOI: 10.1109/JIOT.2021.3064430.
[47] Z. Yang, L. Mao, B. Yan, J. Wang, and W. Gao, “Performance analysis and prediction of asymmetric two-level priority polling system based on bp neural network”, Applied Soft Computing, vol. 99, p. 106 880, 2021, ISSN: 1568-4946. DOI: https: //doi.org/10.1016/j.asoc.2020.106880.
[48] W. Minqi, H. Qiurun, W. Chenhao, et al., “A two-way asymmetric heartbeat packet sending algorithm for improving the stability of narrow-band-internet-of-things tcp long connection with least resource consumption”, in 2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), 2021, pp. 317–320. DOI: 10.1109/MLISE54096.2021.00066. 48
[49] A. Alzubaidi, K. Mitra, and E. Solaiman, “A blockchain-based sla monitoring and compliance assessment for iot ecosystems”, Journal of Cloud Computing, vol. 12, no. 1, p. 50, 2023.
[50] A. Alzubaidi, K. Mitra, P. Patel, and E. Solaiman, “A blockchain-based approach for assessing compliance with sla-guaranteed iot services”, in 2020 IEEE International Conference on Smart Internet of Things (SmartIoT), 2020, pp. 213–220. DOI: 10.1109/SmartIoT49966.2020.00039.
[51] S. Gupta and V. Khaitan, “Reliability and survivability analysis of long-term evolution vehicular ad-hoc networks: An analytical approach”, Journal of Network and Systems Management, vol. 29, pp. 1–34, 2021.
[52] D. Li, Q. Zhang, E. Zio, S. Havlin, and R. Kang, “Network reliability analysis based on percolation theory”, Reliability Engineering System Safety, vol. 142, pp. 556– 562, 2015, ISSN: 0951-8320.
[53] D. Jiang, B. Zhu, X. Liu, and S. Mumtaz, “Alcod: An adaptive load-aware approach to load balancing for containers in iot edge computing”, IEEE Internet of Things Journal, vol. 11, no. 23, pp. 37 480–37 492, 2024. DOI: 10.1109/JIOT.2024. 3427642.
[54] D. Sahu, Nidhi, R. Chaturvedi, et al., “Revolutionizing load harmony in edge computing networks with probabilistic cellular automata and markov decision processes”, Scientific Reports, vol. 15, no. 1, p. 3730, 2025.
[55] J. Wan, B. Chen, S. Wang, M. Xia, D. Li, and C. Liu, “Fog computing for energyaware load balancing and scheduling in smart factory”, IEEE Transactions on Industrial Informatics, vol. 14, no. 10, pp. 4548–4556, 2018. DOI: 10.1109/TII. 2018.2818932.
[56] N. Cameron, “Esp32 microcontroller”, in ESP32 Formats and Communication: Application of Communication Protocols with ESP32 Microcontroller. Berkeley, CA: Apress, 2023, pp. 1–54, ISBN: 978-1-4842-9376-8. DOI: 10.1007/978-1-4842- 9376-8_1. |
| 描述: | 碩士
國立政治大學
資訊科學系
112753116 |
| 資料來源: | http://thesis.lib.nccu.edu.tw/record/#G0112753116 |
| 資料類型: | thesis |
| 顯示於類別: | [資訊科學系] 學位論文
|
文件中的檔案:
| 檔案 |
描述 |
大小 | 格式 | 瀏覽次數 |
|---|
| 311601.pdf | | 1325Kb | Adobe PDF | 0 | 檢視/開啟 |
|
在政大典藏中所有的資料項目都受到原著作權保護.
|
