物聯網(IoT)數據量的爆炸性成長，使得有效的數據管理解決方案成為海量數據存取的關鍵。傳統的B+樹索引管理方案雖然適用於一般物聯網系統，但其對於具有預先分佈感測器的場景中存在一些局限性。這些索引管理方案未能充分利用這些感測器數據固有的分佈模式，導致系統產生過多的寫入操作和隨之而來的能源消耗。此外，隨著非揮發性記憶體（NVM）技術逐漸運用於物聯網系統中，其固有的讀寫不對稱性在執行數據寫入密集型應用時，可能會對於系統可靠度產生負面影響。本研究提出了一種自適應預建樹(APB-Tree)索引管理方案，旨在基於非揮發性記憶體的物聯網系統中降低數據寫入開銷。APB-Tree透過剖析已知鍵範圍內的高頻存取區域預先建構索引結構，從而減少線上索引結構的管理成本並提升系統執行效能。同時，APB-Tree保留了傳統樹型索引結構的可擴展性，以適應物聯網系統新增節點時帶來的大量新數據。藉由考量數據寫入開銷與系統環境中鍵範圍分佈假設的樹型索引設計，我們的解決方案有效克服了運用B+樹方案時產生的資料存取問題。綜合性的實驗結果顯示出APB-Tree對於數據寫入作業取得了顯著的效能提升，同時有效改善了基於非揮發性記憶體的物聯網系統中數據存取的能耗。

The exponential growth of IoT data requires efficient data management solutions for the vast access to information. Traditional B+-tree indexing methods, while effective for general-purpose IoT systems, exhibit limitations in scenarios involving pre-distributed sensors. These indexes fail to capitalize on the inherent data distribution patterns, resulting in excessive writes and consequent energy expenditure. Moreover, the advent of non-volatile memory (NVM) technology introduces the issue of read/write latency asymmetry, which can negatively impact the reliability of IoT applications that frequently write data. To address the write overhead in NVM-based IoT systems, this research introduces the adaptive pre-built tree (APB-Tree) indexing method. APB-Tree identifies commonly accessed key regions within the known key range and pre-builds index structures for these areas, reducing the need for online index management and improving runtime performance. At the same time, APB-Tree retains the scalability of traditional tree-based structures, allowing for seamless data integration from new IoT nodes. By reconsidering tree-based indexing design in light of write overheads and key-range distribution assumptions, our solution addresses the challenges of B+-tree schemes in IoT contexts. Comprehensive experimental analysis indicates that the APB-Tree significantly enhances performance in write operations and concurrently improves energy consumption within NVM-based IoT environments.

[1] Amad Alanhdi and L´aszl´o Toka. A survey on integrating edge computing with ai and blockchain in maritime domain, aerial systems, iot, and industry 4.0. IEEE Access, 12:28684–28709, 2024.
[2] Ahmed Izzat Alsalibi, Mohd Khaled Yousef Shambour, Muhannad A Abu- Hashem, Mohammad Shehab, Qusai Shambour, and Riham Muqat. Nonvolatile memory-based internet of things: a survey. Artificial intelligence-based internet of things systems, pages 285–304, 2022.
[3] Joy Arulraj and Andrew Pavlo. How to build a non-volatile memory database management system. In Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD ’17, page 1753–1758, New York, NY, USA, 2017. Association for Computing Machinery.
[4] Hyokyung Bahn and Kyungwoon Cho. Implications of nvm based storage on memory subsystem management. Applied Sciences, 10(3):999, 2020.
[5] Beneyaz Ara Begum and Satyanarayana V Nandury. Data aggregation protocols for wsn and iot applications–a comprehensive survey. Journal of King Saud University-Computer and Information Sciences, 35(2):651–681, 2023.
[6] Jalil Boukhobza, St´ephane Rubini, Renhai Chen, and Zili Shao. Emerging nvm: A survey on architectural integration and research challenges. ACM Transactions on Design Automation of Electronic Systems (TODAES), 23(2):1–32, 2017.
[7] Paolo Cappelletti, Roberto Annunziata, Franck Arnaud, Fabio Disegni, Alfonso Maurelli, and Paola Zuliani. Phase change memory for automotive grade embedded nvm applications. Journal of Physics D: Applied Physics, 53(19):193002, 2020.
[8] Yu-Wei Chan, Halim Fathoni, Hao-Yi Yen, and Chao-Tung Yang. Implementation of a cluster-based heterogeneous edge computing system for resource monitoring and performance evaluation. Ieee Access, 10:38458–38471, 2022.
[9] Ajay Chaudhary and Sateesh K Peddoju. Ada2- iot: An adaptive data aggregation algorithm for iot infrastructure. Internet of Things, 27:101299, 2024.
[10] An Chen. A review of emerging non-volatile memory (nvm) technologies and applications. Solid-State Electronics, 125:25–38, 2016.
[11] Jie Chen, Ron C Chiang, H Howie Huang, and Guru Venkataramani. Energy-aware writes to non-volatile main memory. ACM SIGOPS Operating Systems Review, 45(3):48–52, 2012.
[12] Junqi Chen, Yong Wang, Miao Ye, and Qiuxiang Jiang. A secure cloud-edge collaborative fault-tolerant storage scheme and its data writing optimization. IEEE Access, 2023.
[13] Shimin Chen, Phillip B Gibbons, Suman Nath, et al. Rethinking database algorithms for phase change memory. In Cidr, volume 11, page 5th, 2011.
[14] Shimin Chen and Qin Jin. Persistent b+-trees in non-volatile main memory. Proceedings of the VLDB Endowment, 8(7):786–797, 2015.
[15] Tseng-Yi Chen, Yuan-Hao Chang, Chun-Feng Wu, Chi-Heng Lee, Wei- Kuan Shih, et al. Beyond write-reduction consideration: A wear-leveling-enabled b+-tree indexing scheme over an nvram-based architecture. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 40(12):2455–2466, 2021.
[16] Yi-Shen Chen, Chun-Feng Wu, Yuan-Hao Chang, and Tei-Wei Kuo. A write-friendly arithmetic coding scheme for achieving energy-efficient non-volatile memory systems. In Proceedings of the 26th Asia and South Pacific Design Automation Conference, pages 633–638, 2021.
[17] Ping Chi, Wang-Chien Lee, and Yuan Xie. Making b+-tree efficient in pcm-based main memory. In Proceedings of the 2014 International Symposium on Low Power Electronics and Design, ISLPED ’14, page 69–74, New York, NY, USA, 2014. Association for Computing Machinery.
[18] Ping Chi, Wang-Chien Lee, and Yuan Xie. Adapting b+-tree for emerging nonvolatile memory-based main memory. IEEE Transactions on Computer- Aided Design of Integrated Circuits and Systems, 35(9):1461–1474, 2015.
[19] Ping Chi, Shuangchen Li, Yuanqing Cheng, Yu Lu, Seung H Kang, and Yuan Xie. Architecture design with stt-ram: Opportunities and challenges. In 2016 21st Asia and South Pacific design automation conference (ASP-DAC), pages 109–114. IEEE, 2016.
[20] Gyu Sang Choi, Byung-Won On, and Ingyu Lee. Pb+-tree: Pcm-aware b+- tree. IEEE Transactions on Knowledge and Data Engineering, 27(9):2466– 2479, 2015.
[21] Kihan Choi, Hyuck Han, Hyungsoo Jung, and Sooyong Kang. Workload-optimized sensor data store for industrial iot gateways. Future Generation Computer Systems, 135:394–408, 2022.
[22] Yongheng Deng, Feng Lyu, Tengxi Xia, Yuezhi Zhou, Yaoxue Zhang, Ju Ren, and Yuanyuan Yang. A communication-efficient hierarchical federated learning framework via shaping data distribution at edge. IEEE/ACM Transactions on Networking, 2024.
[23] Jialin Ding, Umar Farooq Minhas, Jia Yu, Chi Wang, Jaeyoung Do, Yinan Li, Hantian Zhang, Badrish Chandramouli, Johannes Gehrke, Donald Kossmann, et al. Alex: an updatable adaptive learned index. In Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, pages 969– 984, 2020.
[24] Abel E Edje, MS Abd Latiff, and Weng Howe Chan. Iot data analytic algorithms on edge-cloud infrastructure: A review. Digital Communications and Networks, 9(6):1486–1515, 2023.
[25] Tetsuo Endoh, Hiroki Koike, Shoji Ikeda, Takahiro Hanyu, and Hideo Ohno. An overview of nonvolatile emerging memories— spintronics for working memories. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 6(2):109–119, 2016.
[26] Yasmin Fathy, Payam Barnaghi, and Rahim Tafazolli. Large-scale indexing, discovery, and ranking for the internet of things (iot). ACM Computing Surveys (CSUR), 51(2):1–53, 2018.
[27] Elham Fazel, Hamid Esmaeili Najafabadi, Mohammad Rezaei, and Henry Leung. Unlocking the power of mist computing through clustering techniques in iot networks. Internet of Things, 22:100710, 2023.
[28] Lu´ıs Meruje Ferreira, F´abio Coelho, and Jos´e Orlando Pereira. Towards mram byte-addressable persistent memory in edge database systems. In VLDB Workshops, 2023.
[29] Asier Garcia-Perez, Ra´ul Mi˜n´on, Ana I Torre-Bastida, and Ekaitz Zulueta- Guerrero. Analysing edge computing devices for the deployment of embedded ai. Sensors, 23(23):9495, 2023.
[30] Xuran Ge, Yang Liu, Lizhou Wu, Yang Ou, Zhiguang Chen, and Nong Xiao. Pm-based persistent key value stores: a survey. In 2022 5th International Conference on Data Science and Information Technology (DSIT), pages 1–7. IEEE, 2022.
[31] Panagiotis Gkonis, Anastasios Giannopoulos, Panagiotis Trakadas, Xavi Masip-Bruin, and Francesco D’Andria. A survey on iot-edge-cloud continuum systems: status, challenges, use cases, and open issues. Future Internet, 15(12):383, 2023.
[32] Brij B Gupta and Megha Quamara. An overview of internet of things (iot): Architectural aspects, challenges, and protocols. Concurrency and Computation: Practice and Experience, 32(21):e4946, 2020.
[33] Alexander Hankin, Tomer Shapira, Karthik Sangaiah, Michael Lui, and Mark Hempstead. Evaluation of non-volatile memory based last level cache given modern use case behavior. In 2019 IEEE International Symposium on Workload Characterization (IISWC), pages 143–154. IEEE, 2019.
[34] Jo¨el Hartmann, Paolo Cappelletti, Nitin Chawla, Franck Arnaud, and Andreia Cathelin. Artificial intelligence: Why moving it to the edge? In ESSDERC 2021-IEEE 51st European Solid-State Device Research Conference (ESSDERC), pages 1–6. IEEE, 2021.
[35] Qiang He, Siyu Tan, Feifei Chen, Xiaolong Xu, Lianyong Qi, Xinhong Hei, Hai Jin, and Yun Yang. Edindex: Enabling fast data queries in edge storage systems. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 675–685, 2023.
[36] Jorg Henkel, Lokesh Siddhu, Lars Bauer, Jurgen Teich, Stefan Wildermann, Mehdi Tahoori, Mahta Mayahinia, Jeronimo Castrillon, Asif Ali Khan, Hamid Farzaneh, et al. Special session-non-volatile memories: Challenges and opportunities for embedded system architectures with focus on machine learning applications. In Proceedings of the International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, pages 11–20, 2023.
[37] Aleksandar Jevremovic, Zona Kostic, and Dragan Perakovic. Energy-efficient edge intelligence: A comparative analysis of aiot technologies. Mobile Networks and Applications, pages 1–9, 2023.
[38] Thomas Jew. Mram in microcontroller and microprocessor product applications. In 2020 IEEE International Electron Devices Meeting (IEDM), pages 11–1. IEEE, 2020.
[39] Rize Jin, Hyung-Ju Cho, Sang-Won Lee, and Tae-Sun Chung. Lazy-split b+- tree: a novel b+-tree index scheme for flash-based database systems. Design Automation for Embedded Systems, 17:167–191, 2013.
[40] Saeed Kargar and Faisal Nawab. Challenges and future directions for energy, latency, and lifetime improvements in nvms. Distributed and Parallel Databases, pages 1–27, 2022.
[41] Asif Khan, Khurram S Khattak, Zawar H Khan, Thomas Aaron Gulliver, and Abdullah. Edge computing for effective and efficient traffic characterization. Sensors, 23(23):9385, 2023.
[42] Muhammad Nafees Ulfat Khan, Zhiling Tang, Weiping Cao, Yawar Abbas Abid, Wanghua Pan, and Ata Ullah. Fuzzy-based efficient healthcare data collection and analysis mechanism using edge nodes in the iomt. Sensors, 23(18):7799, 2023.
[43] Quy Vu Khanh, Van-Hau Nguyen, Quy Nguyen Minh, Anh Dang Van, Ngoc Le Anh, and Abdellah Chehri. An efficient edge computing management mechanism for sustainable smart cities. Sustainable Computing: Informatics and Systems, 38:100867, 2023.
[44] Youngjin Kim, Chiwon Song, Hyuck Han, Hyungsoo Jung, and Sooyong Kang. Collaborative task scheduling for iot-assisted edge computing. IEEE Access, 8:216593–216606, 2020.
[45] Aya M Kishk, Mahmoud Badawy, Hesham A Ali, and Ahmed I Saleh. A new traffic congestion prediction strategy (tcps) based on edge computing. Cluster Computing, 25(1):49–75, 2022.
[46] Raed Kontar, Naichen Shi, Xubo Yue, Seokhyun Chung, Eunshin Byon, Mosharaf Chowdhury, Jionghua Jin, Wissam Kontar, Neda Masoud, Maher Nouiehed, et al. The internet of federated things (ioft). IEEE Access, 9:156071–156113, 2021.
[47] Tim Kraska, Alex Beutel, Ed H Chi, Jeffrey Dean, and Neoklis Polyzotis. The case for learned index structures. In Proceedings of the 2018 international conference on management of data, pages 489–504, 2018.
[48] Manuel Le Gallo and Abu Sebastian. An overview of phase-change memory device physics. Journal of Physics D: Applied Physics, 53(21):213002, 2020.
[49] Lu Li, Peiquan Jin, Chengcheng Yang, Shouhong Wan, and Lihua Yue. Xb+- tree: A novel index for pcm/dram-based hybrid memory. In Databases Theory and Applications: 27th Australasian Database Conference, ADC 2016, Sydney, NSW, September 28-29, 2016, Proceedings 27, pages 357–368. Springer, 2016.
[50] Yu-Pei Liang, Tseng-Yi Chen, Yuan-Hao Chang, Shuo-Han Chen, Kam-Yiu Lam, Wei-Hsin Li, and Wei-Kuan Shih. Enabling sequential-write-constrained b+-tree index scheme to upgrade shingled magnetic recording storage performance. ACM Transactions on Embedded Computing Systems (TECS), 18(5s):1–20, 2019.
[51] Mingliu Liu, Deshi Li, Qimei Chen, Jixuan Zhou, Kaitao Meng, and Song Zhang. Sensor information retrieval from internet of things: Representation and indexing. IEEE Access, 6:36509–36521, 2018.
[52] Baotong Lu, Jialin Ding, Eric Lo, Umar Farooq Minhas, and Tianzheng Wang. Apex: a high-performance learned index on persistent memory. Proc. VLDB Endow., 15(3):597–610, nov 2021.
[53] Supriya Mishra, Bhavesh N Gohil, and Suprio Ray. A survey on persistent memory indexes: Recent advances, challenges and opportunities. Journal of Systems Architecture, page 103140, 2024.
[54] Sparsh Mittal and Jeffrey S Vetter. A survey of software techniques for using non-volatile memories for storage and main memory systems. IEEE Transactions on Parallel and Distributed Systems, 27(5):1537–1550, 2015.
[55] Mani Dheeraj Mudaliar and N Sivakumar. Iot based real time energy monitoring system using raspberry pi. Internet of Things, 12:100292, 2020.
[56] S Muruganandam, Anas A Salameh, Mohd Affendi Ahmad Pozin, SV Manikanthan, and T Padmapriya. Sensors and machine learning and ai operation-constrained process control method for sensor-aided industrial internet of things and smart factories. Measurement: Sensors, 25:100668, 2023.
[57] Fabian Oboril, Rajendra Bishnoi, Mojtaba Ebrahimi, and Mehdi B Tahoori. Evaluation of hybrid memory technologies using sot-mram for on-chip cache hierarchy. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 34(3):367–380, 2015.
[58] Ismail Oukid, Johan Lasperas, Anisoara Nica, Thomas Willhalm, and Wolfgang Lehner. Fptree: A hybrid scm-dram persistent and concurrent b-tree for storage class memory. In Proceedings of the 2016 International Conference on Management of Data, pages 371–386, 2016.
[59] Kouki Ozawa, Takahiro Hirofuchi, Ryousei Takano, and Midori Sugaya. fogcached: Dram-nvm hybrid memory-based kvs server for edge computing. In Edge Computing–EDGE 2020: 4th International Conference, Held as Part of the Services Conference Federation, SCF 2020, Honolulu, HI, USA, September 18-20, 2020, Proceedings 4, pages 50–62. Springer, 2020.
[60] Said Quqa, Alessio Antolini, Eleonora Franchi Scarselli, Antonio Gnudi, Andrea Lico, Marcella Carissimi, Marco Pasotti, Roberto Canegallo, Luca Landi, and Pier Paolo Diotallevi. Phase change memories in smart sensing solutions for structural health monitoring. Journal of Computing in Civil Engineering, 36(4):04022013, 2022.
[61] Abida Sharif, Jian Ping Li, and Muhammad Asim Saleem. Internet of things enabled vehicular and ad hoc networks for smart city traffic monitoring and controlling: a review. International Journal of Advanced Networking and Applications, 10(3):3833–3842, 2018.
[62] Jiwu Shu. Data storage architectures and technologies, 2024.
[63] Pierre-Louis Sixdenier, Stefan Wildermann, Martin Ottens, and J¨urgen Teich. Seque: Lean and energy-aware data management for iot gateways. In 2023 IEEE International Conference on Edge Computing and Communications (EDGE), pages 133–139. IEEE, 2023.
[64] Karim Sonbol, ¨Oznur ¨Ozkasap, Ibrahim Al Oqily, and Moayad Aloqaily. Edgekv: Distributed key-value store for the network edge. In 2020 IEEE Symposium on Computers and Communications (ISCC), pages 1–6. IEEE, 2020.
[65] Hao Sun, Lan Chen, Xiaoran Hao, Chenji Liu, and Mao Ni. An energy-efficient and fast scheme for hybrid storage class memory in an aiot terminal system. Electronics, 9(6):1013, 2020.
[66] Songtao Tang, Xin Du, Zhihui Lu, Keke Gai, Jie Wu, Patrick CK Hung, and Kim-Kwang Raymond Choo. Coordinate-based efficient indexing mechanism for intelligent iot systems in heterogeneous edge computing. Journal of Parallel and Distributed Computing, 166:45–56, 2022.
[67] Jeffrey S Vetter and Sparsh Mittal. Opportunities for nonvolatile memory systems in extreme-scale high-performance computing. Computing in Science & Engineering, 17(2):73–82, 2015.
[68] Jiantao Wang, Kam-Yiu Lam, Yuan-Hao Chang, Jen-Wei Hsieh, and Po- Chun Huang. Block-based multi-version b+ -tree for flash-based embedded database systems. IEEE Transactions on Computers, 64(4):925–940, 2015.
[69] Shawn Wang, Susamma Barua, Kunal Desai, and Swaroop Deshmukh. Geotnavi–smart navigation using geo-temporal traffic information. International Journal of Data Mining, Modelling and Management, 5(1):20–36, 2013.
[70] Zihui Wang, Xiaojie Hao, Pengfa Xu, Longqian Hu, Dongha Jung, Woojin Kim, Kimihiro Satoh, Bing Yen, Zhiqiang Wei, Lienchang Wang, et al. Stt-mram for embedded memory applications. In 2020 IEEE International Memory Workshop (IMW), pages 1–3. IEEE, 2020.
[71] Fei Xia, Dejun Jiang, Jin Xiong, and Ninghui Sun. Hikv: a hybrid index key-value store for dram-nvm memory systems. In 2017 USENIX Annual Technical Conference (USENIX ATC 17), pages 349–362, 2017.
[72] Jun Yang, Qingsong Wei, Cheng Chen, Chundong Wang, Khai Leong Yong, and Bingsheng He. Nv-tree: Reducing consistency cost for nvm-based single level systems. In FAST, volume 15, pages 167–181, 2015.
[73] Chongnan Ye and Chundong Wang. Boosting the search performance of b+- tree with sentinels for non-volatile memory. 2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC), pages 244–249, 2021.
[74] Furqan Zahoor, Tun Zainal Azni Zulkifli, and Farooq Ahmad Khanday. Resistive random access memory (rram): an overview of materials, switching mechanism, performance, multilevel cell (mlc) storage, modeling, and applications. Nanoscale research letters, 15:1–26, 2020.
[75] Xinjing Zhou, Lidan Shou, Ke Chen, Wei Hu, and Gang Chen. Dptree: differential indexing for persistent memory. Proceedings of the VLDB Endowment, 13(4):421–434, 2019.