提供系統永續性的無電池物聯網（IoT）裝置逐漸引起關注。然而，在這些裝置上執行具高能量需求及高計算需求的深度神經網路（DNNs）時，面臨反應延遲與能源不足的挑戰。為了提升無電池裝置的計算能力和能量資源，本論文提出實現卸載推論的排程框架。該框架有效地在無電池裝置之間卸載工作負載，其包含動態能源感知的工作負載分割用以提高能源效率、傳輸處理程序用以最小化傳輸成本、以及卸載管理器通過異步傳輸資料流來減少延遲。實驗結果發現將所提出的排程框架實現在實際平台上，並且與本地推論相比，在反應時間滿足率和進度率方面都取得了顯著的改善。

Inference on battery-less IoT devices is getting attention to provide sustainable development. However, executing deep neural networks (DNNs) with high energy and computational demands on these devices suffers timing response and insufficient energy challenges. To enhance computing power and energy resources, we propose a framework, extit{EONNI}. This framework efficiently offloads workloads between battery-less devices by providing dynamic energy-aware workload partitioning for maximizing energy efficiency, a connection handler for minimizing connection overhead, and an offloading manager for reducing latency through enabling asynchronous data flow. The proposed framework has been implemented on a real platform and demonstrates significant improvements in both the meet ratio and progress ratio compared to local inference.

[1] M. Ebrahimi, M. Khoshtaghaza, S. Minaei, and B. Jamshidi, “Vision-based pest detection based on svm classification method,” Computers and Electronics in Agriculture, vol. 137, pp. 52–58, 2017.
[2] M. Rasheduzzaman, P. B. Pillai, A. N. C. Mendoza, and M. M. De Souza, “A study of the performance of solar cells for indoor autonomous wireless sensors,” in 2016 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP), pp. 1–6, 2016.
[3] Y. Tan, Y. Shiiki, and H. Ishikuro, “Optimization of gate voltage in capacitive dc–dc converters for thermoelectric energy harvesting,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 30, no. 4, pp. 463–473, 2022.
[4] T. Wan, Y. Karimi, M. Stanaevi, and E. Salman, “Ac computing methodology for rf powered iot devices,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 27, no. 5, pp. 1017–1028, 2019.
[5] Y. Zhao, S. S. Afzal, W. Akbar, O. Rodriguez, F. Mo, D. Boyle, F. Adib, and H. Haddadi, “Towards battery-free machine learning and inference in underwater environments,” in Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications, HotMobile ’22, (New York, NY, USA), p. 29–34, Association for Computing Machinery, 2022.
[6] G. Gobieski, B. Lucia, and N. Beckmann, “Intelligence beyond the edge: Inference on intermittent embedded systems,” in Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS ’19, (New York, NY, USA), p. 199–213, Association for Computing Machinery, 2019.
[7] C.-K. Kang, H. R. Mendis, C.-H. Lin, M.-S. Chen, and P.-C. Hsiu, “Everything leaves footprints: Hardware accelerated intermittent deep inference,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 39, no. 11, pp. 34793491, 2020.
[8] C.-K. Kang, H. R. Mendis, C.-H. Lin, M.-S. Chen, and P.-C. Hsiu, “More is less: Model augmentation for intermittent deep inference,” ACM Trans. Embed. Comput. Syst., vol. 21, oct 2022.
[9] C.-H. Yen, H. R. Mendis, T.-W. Kuo, and P.-C. Hsiu, “Keep in balance: Runtime reconfigurable intermittent deep inference,” ACM Trans. Embed. Comput. Syst., vol. 22, sep 2023.
[10] C.-C. Lin, C.-Y. Liu, C.-H. Yen, T.-W. Kuo, and P.-C. Hsiu, “Intermittent-aware neural network pruning,” in 2023 60th ACM/IEEE Design Automation Conference (DAC), pp. 1–6, 2023.
[11] B. Islam and S. Nirjon, “Zygarde: Time-sensitive on-device deep inference and adaptation on intermittently-powered systems,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 4, Sept. 2020.
[12] C.-C. Lin, T.-C. Yen, and Y.-S. Chen, “Multiple time-sensitive inferences scheduling on energy-harvesting iot devices,” in Proceedings of the 2023 International Conference on Research in Adaptive and Convergent Systems, RACS ’23, (New York, NY, USA), Association for Computing Machinery, 2023.
[13] N. Kumari, A. Yadav, and P. K. Jana, “Task offloading in fog computing: A survey of algorithms and optimization techniques,” Computer Networks, vol. 214, p. 109137, 2022.
[14] Y.-T. Lin, Y.-C. Hsiao, and C.-Y. Wang, “Enabling mobile edge computing for batteryless intermittent iot devices,” in 2021 IEEE Global Communications Conference (GLOBECOM), pp. 1–6, 2021.
[15] Q. Ju, G. Sun, H. Li, and Y. Zhang, “Collaborative in-network processing for internet of battery-less things,” IEEE Internet of Things Journal, vol. 6, no. 3, pp. 5184–5195, 2019.
[16] K. Geissdoerfer and M. Zimmerling, “Bootstrapping battery-free wireless networks: Efficient neighbor discovery and synchronization in the face of intermittency,” in 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21), pp. 439–455, USENIX Association, Apr. 2021.
[17] C.Pan, W.Zhang, Y.Wang,andM.Xie,“Elixir: Anexpedientconnection paradigm for self-powered iot devices,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 42, no. 11, pp. 3743–3756, 2023.
[18] V. Deep, M. L. Wymore, A. A. Aurandt, V. Narayanan, S. Fu, H. Duwe, and D. Qiao, “Experimental study of lifecycle management protocols for batteryless intermittent communication,” in 2021 IEEE 18th International Conference on Mobile Ad Hoc and Smart Systems (MASS), pp. 355–363, 2021.
[19] K. Geissdoerfer and M. Zimmerling, “Learning to communicate effectively between battery-free devices,” in 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22), (Renton, WA), pp. 419–435, USENIX Association, Apr. 2022.
[20] A. Branco, L. Mottola, M. H. Alizai, and J. H. Siddiqui, “Intermittent asynchronous peripheral operations,” in Proceedings of the 17th Conference on Embedded Networked Sensor Systems, SenSys ’19, (New York, NY, USA), p. 55–67, Association for Computing Machinery, 2019.
[21] K. Maeng and B. Lucia, “Supporting peripherals in intermittent systems with justin-time checkpoints,” in Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2019, (New York, NY, USA), p. 1101–1116, Association for Computing Machinery, 2019.
[22] M. Surbatovich, L. Jia, and B. Lucia, “Automatically enforcing fresh and consistent inputs in intermittent systems,” in Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, PLDI 2021, (New York, NY, USA), p. 851–866, Association for Computing Machinery, 2021.
[23] E.Yildiz, S. Ahmed, B. Islam, J. Hester, and K. S. Yildirim, “Efficient and safe i/o operations for intermittent systems,” in Proceedings of the Eighteenth European Conference on Computer Systems, EuroSys ’23, (New York, NY, USA), p. 63–78, Association for Computing Machinery, 2023.
[24] K. Maeng and B. Lucia, “Adaptive low-overhead scheduling for periodic and reactive intermittent execution,” in Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2020, (New York, NY, USA), p. 1005–1021, Association for Computing Machinery, 2020.
[25] L. K. Xuan, C.-C. Lin, T.-C. Yen, Y.-S. Chen, and C.-P. Hsu, “Fase: Energy isolation framework for latency-sensitive applications in intermittent systems with multiple peripherals,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, pp. 1–1, 2023.
[26] H. R. Mendis, C.-K. Kang, and P.-c. Hsiu, “Intermittent-aware neural architecture search,” ACM Trans. Embed. Comput. Syst., vol. 20, sep 2021.
[27] A. Gomez, A. Tretter, P. A. Hager, P. Sanmugarajah, L. Benini, and L. Thiele, “Dataflow driven partitioning of machine learning applications for optimal energy use in batteryless systems,” ACM Trans. Embed. Comput. Syst., vol. 21, dec 2022.
[28] A. Montanari, M. Sharma, D. Jenkus, M. Alloulah, L. Qendro, and F. Kawsar, “Eperceptive: Energy reactive embedded intelligence for batteryless sensors,” in Proceedings of the 18th Conference on Embedded Networked Sensor Systems, SenSys ’20, (New York, NY, USA), p. 382–394, Association for Computing Machinery, 2020.
[29] C.-H. Yen, H. R. Mendis, T.-W. Kuo, and P.-C. Hsiu, “Stateful neural networks for intermittent systems,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 41, no. 11, pp. 4229–4240, 2022. [30] Q. Ju, G. Sun, H. Li, and Y. Zhang, “Latency-aware in-network computing for internet of battery-less things,” in 2018 IEEE 88th Vehicular Technology Conference (VTCFall), pp. 1–5, 2018.
[31] K. S. Yıldırım, A. Y. Majid, D. Patoukas, K. Schaper, P. Pawelczak, and J. Hester, “Ink: Reactive kernel for tiny batteryless sensors,” in Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems, SenSys ’18, (New York, NY, USA), p. 41–53, Association for Computing Machinery, 2018.
[32] J. Hester, N. Tobias, A. Rahmati, L. Sitanayah, D. Holcomb, K. Fu, W. P. Burleson, and J. Sorber, “Persistent clocks for batteryless sensing devices,” ACM Trans. Embed. Comput. Syst., vol. 15, aug 2016.
[33] J. de Winkel, C. Delle Donne, K. S. Yildirim, P. Pawełczak, and J. Hester, “Reliable timekeeping for intermittent computing,” in Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS ’20, (New York, NY, USA), p. 53–67, Association for Computing Machinery, 2020.
[34] D. Balsamo, A. S. Weddell, G. V. Merrett, B. M. Al-Hashimi, D. Brunelli, and L. Benini, “Hibernus: Sustaining computation during intermittent supply for energy harvesting systems,” IEEE Embedded Systems Letters, vol. 7, no. 1, pp. 15–18, 2015.
[35] Y.-C. Lin, P.-C. Hsiu, and T.-W. Kuo, “Autonomous i/o for intermittent iot systems,” in 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), pp. 1–6, 2019.
[36] J. Wu, C. Leng, Y. Wang, Q. Hu, and J. Cheng, “Quantized convolutional neural networks for mobile devices,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
[37] Y.-Z. Liu, “Airby: A distributed scheduling on multiple intermittent devices for boosting timely progress,” Master's thesis, National Taiwan University of Science and Technology, 2023.
[38] P. Warden, “Speech commands: A dataset for limited-vocabulary speech recognition,” 2018.