Workload Characterization in Embedded Systems Utilizing Hybrid Intelligent Gated Recurrent Unit and Extreme Learning Machines
Keywords:
Embedded System, Gated Recurrent Unit, Extreme Learning Machines, Workload CharacterizationAbstract
As the demand for embedded systems continues to rise exponentially, accurately estimating and predicting the necessary resources for these systems remains a significant challenge due to their dynamic workloads. Numerous intelligent algorithms have been developed using machine learning and deep learning techniques, leveraging their computational power and ability to capture workload patterns. However, these algorithms still require further refinement to effectively handle the increasingly diverse and rapidly evolving workloads. This framework aims to design Gated Extreme learning machines for Embedded Workload Characterization (GEEWC) to address the challenges of accurately characterizing and predicting resource requirements in embedded systems, which often operate under dynamic and unpredictable workloads. By combining the Gated Recurrent Unit (GRU) and Extreme Learning Machines (ELM), GEEWC leverages the strengths of both models to improve the accuracy and efficiency of workload characterization and resource prediction. The results of the experimentation show that the suggested framework performs consistently well across all three workload benchmarks such as the Internet of Medical Things (IoMT), EEMBC, and SPARK workloads. The F1-Score, recall, specificity, accuracy, and recall metrics consistently reflect high levels of performance, indicating that the framework is able to effectively handle dynamic workloads. This robustness makes it a reliable solution for real-world scenarios where workloads can vary significantly. Further analysis of the results reveals that the framework is particularly effective in handling the complex IoMT workload, suggesting its suitability for healthcare applications. Moreover, the framework exhibits robustness and scalability, allowing it to handle large datasets and accommodate future growth in the healthcare industry. The results also highlight the framework's ability to accurately predict and diagnose medical conditions, making it a valuable tool for healthcare professionals. Overall, these findings solidify the framework's potential for revolutionizing healthcare applications and improving patient outcomes.
Downloads
References
J. Lee and H. Bahn, "Analyzing Memory Access Traces of Deep Learning Workloads for Efficient Memory Management," 12th International Conference on Information Technology in Medicine and Education (ITME), Xiamen, China, 2022, pp. 389-393, 2022 doi: 10.1109/ITME56794.2022.00090.
S. Hsia, U. Gupta, M. Wilkening, C. -J. Wu, G. -Y. Wei and D. Brooks, "Cross-Stack Workload Characterization of Deep Recommendation Systems," 2020 IEEE International Symposium on Workload Characterization (IISWC), Beijing, China, 2020, pp. 157-168, doi: 10.1109/IISWC50251.2020.00024.
X. Li et al., "LongTail-Bench: A Benchmark Suite for Domain-Specific Operators in Deep Learning," 2022 IEEE International Symposium on Workload Characterization (IISWC), Austin, TX, USA, 2022, pp. 282-295, doi: 10.1109/IISWC55918.2022.00032.
Z. Quan, X. Chen and Y. Han, "AIC-Bench: Workload Selection Methodology for Benchmarking AI Chips," 2022 IEEE 24th IntConf on High Performance Computing & Communications; 8th IntConf on Data Science & Systems; 20th IntConf on Smart City; 8th IntConf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys), Hainan, China, 2022, pp. 687-694, doi: 10.1109/HPCC-DSS-SmartCity-DependSys57074.2022.00117.
A. A. Awan, A. Jain, C. -H. Chu, H. Subramoni and D. K. Panda, "Communication Profiling and Characterization of Deep Learning Workloads on Clusters with High-Performance Interconnects," 2019 IEEE Symposium on High-Performance Interconnects (HOTI), Santa Clara, CA, USA, 2019, pp. 49-53, doi: 10.1109/HOTI.2019.00025.
A. A. Awan, A. Jain, C. -H. Chu, H. Subramoni and D. K. Panda, "Communication Profiling and Characterization of Deep-Learning Workloads on Clusters With High-Performance Interconnects," in IEEE Micro, vol. 40, no. 1, pp. 35-43, 1 Jan.-Feb. 2020, doi: 10.1109/MM.2019.2949986.
M. Barve, S. Sinha, R. P. Hardikar, A. Gunturu and W. Mallik, "Workload Characterization in HPC Environment for Auto-scaling of Resources – Preliminary Study," 2022 IEEE 19th India Council International Conference (INDICON), Kochi, India, 2022, pp. 1-6, doi: 10.1109/INDICON56171.2022.10040124.
J. Liu, J. Liu, W. Du and D. Li, "Performance Analysis and Characterization of Training Deep Learning Models on Mobile Device," 2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS), Tianjin, China, 2019, pp. 506-515, doi: 10.1109/ICPADS47876.2019.00077.
Q. Hu, P. Sun, S. Yan, Y. Wen and T. Zhang, "Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters," SC21: International Conference for High Performance Computing, Networking, Storage and Analysis, St. Louis, MO, USA, 2021, pp. 1-15.
A. F. Inci, M. MericIsgenc and D. Marculescu, "DeepNVM: A Framework for Modeling and Analysis of Non-Volatile Memory Technologies for Deep Learning Applications," 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 2020, pp. 1295-1298, doi: 10.23919/DATE48585.2020.9116263.
Jiwoo Bang, Chunyong Kim, Kesheng Wu, Alex Sim, Suren Byna, Sunggon Kim, and HyeonsangEom. 2020. HPC Workload Characterization Using Feature Selection and Clustering. In 3rd International Workshop on Systems and Network Telemetry and Analytics (SNTA ’20), June 23, 2020, Stockholm, Sweden. ACM, New York, NY, USA, 8 pages. https://doi.org/10.1145/3391812. 3396270.
Y. Ren, S. Yoo and A. Hoisie, "Performance Analysis of Deep Learning Workloads on Leading-edge Systems," 2019 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), Denver, CO, USA, 2019, pp. 103-113, doi: 10.1109/PMBS49563.2019.00017.
J. E and V. R, "Application Workload Characterization using BAT_LSTM Learning algorithm for Asymmetric Architectures," 2021 Emerging Trends in Industry 4.0 (ETI 4.0), Raigarh, India, 2021, pp. 1-5, doi: 10.1109/ETI4.051663.2021.9619290.
A. Khan, X. Yan, S. Tao and N. Anerousis, "Workload characterization and prediction in the cloud: A multiple time series approach," 2012 IEEE Network Operations and Management Symposium, Maui, HI, USA, 2012, pp. 1287-1294, doi: 10.1109/NOMS.2012.6212065.
Sebastian Ştefan and Virginia Niculescu, "Microservice-Oriented Workload Prediction Using Deep Learning", In e-Informatica Software Engineering Journal, vol. 16, no. 1, pp. 220107, 2022. DOI: 10.37190/e-Inf220107.
Krishan Kumar, K. Gangadhara Rao, Suneetha Bulla, D Venkateswarulu, “Forecasting of Cloud Computing Services Workload using Machine Learning,” Turkish Journal of Computer and Mathematics Education, Vol.12, No.11, pp. 4841-4846, 2021.
R.Sivaramakrishnan, and Dr.G.Senthilkumar. “LICHA –WORKLOAD CHARACTERIZATION USING LSTM BASED INTELLIGENT CLASSIFICATION FOR HETEROGENEOUS ARCHITECTURES.” Turkish Journal of Physiotherapy and Rehabilitation Vol.32,No.3,pp. 250-261(2021).
Ahamed, Zaakki, Maher Khemakhem, FathyEassa, FawazAlsolami, and Abdullah S. Al-Malaise Al-Ghamdi. 2023. "Technical Study of Deep Learning in Cloud Computing for Accurate Workload Prediction" Electronics 12, no. 3: 650. https://doi.org/10.3390/electronics12030650.
KumarK. Dinesh and UmamaheswariE.. "HPCWMF: A Hybrid Predictive Cloud Workload Management Framework Using Improved LSTM Neural Network" Cybernetics and Information Technologies 20, no.4 (2020): 55-73. https://doi.org/10.2478/cait-2020-0047
Om, Khandu, Spyros Boukoros, AnupiyaNugaliyadde, Tanya McGill, Michael Dixon, PolychronisKoutsakis, and KokWai Wong. "Modelling email traffic workloads with RNN and LSTM models." Human-centric Computing and Information Sciences 10, no. 1 (2020). Gale Academic OneFile (accessed March 19, 2023). https://link.gale.com/apps/doc/A634355033/AONE?u=tel_oweb&sid=googleScholar&xid=ebf8a9c2.
C. I. Lee, M. Y. Lin, C. L. Yang and Y. K. Chen: Iotbench: A benchmark suite for intelligent internet of things edge devices. IEEE International Conference on Image Processing. 170-174 (2019).
M. R. Guthaus, J. S. Ringenberg, D. Ernst, T. M. Austin, T. Mudge and R. B. Brown: MiBench: a free, commercially representative embedded benchmark suite. Proceedings of the Fourth Annual IEEE International Workshop on Workload Characterization. 3-14 (2001).
A. J. Awan, M. Brorsson, V. Vlassov and E. Ayguade: Micro-architectural characterization of apache spark on batch and stream processing workloads. IEEE International Conferences on Big Data and Cloud Computing (BDCloud), Social Computing and Networking (SocialCom), Sustainable Computing and Communications (SustainCom) (BDCloud-SocialCom-SustainCom). 59-66 (2016).
J. C. Heck and F. M. Salem, "Simplified minimal gated unit variations for recurrent neural networks," 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), Boston, MA, USA, 2017, pp. 1593-1596, doi: 10.1109/MWSCAS.2017.8053242.
M. Zhou and W. Ai, "Distributed Reduced Kernel Extreme Learning Machine," 2021 China Automation Congress (CAC), Beijing, China, 2021, pp. 3384-3387, doi: 10.1109/CAC53003.2021.9728238.
D. Singh, R. Salgotra and U. Singh, "A novel modified bat algorithm for global optimization," 2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), Coimbatore, India, 2017, pp. 1-5, doi: 10.1109/ICIIECS.2017.8275904.
A. H. Ahmadi and S. K. Y. Nikravesh, "A novel instantaneous exploitation based bat algorithm," 2016 24th Iranian Conference on Electrical Engineering (ICEE), Shiraz, Iran, 2016, pp. 1751-1756, doi: 10.1109/IranianCEE.2016.7585804.
J. Bi, S. Li, H. Yuan, Z. Zhao, and H. Liu: Deep neural networks for predicting task time series in cloud computing systems. IEEE International Conference on Networking, Sensing and Control. 86–91 (2019).
U. U. Hafeez and A. Gandhi, "Empirical Analysis and Modeling of Compute Times of CNN Operations on AWS Cloud," 2020 IEEE International Symposium on Workload Characterization (IISWC), Beijing, China, 2020, pp. 181-192, doi: 10.1109/IISWC50251.2020.00026.
Qinghao Hu, Peng Sun, Shengen Yan, Yonggang Wen, and Tianwei Zhang. Characterization and prediction of deep learning workloads in large-scale GPU datacenters. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC '21). Association for Computing Machinery, New York, NY, USA, Article 104, 1–15. 2021 https://doi.org/10.1145/3458817.3476223
Milan Jain, Sayan Ghosh, and Sai PushpakNandanoori. Workload characterization of a time-series prediction system for spatio-temporal data. In Proceedings of the 19th ACM International Conference on Computing Frontiers (CF '22). Association for Computing Machinery, New York, NY, USA, 159–168 2022. https://doi.org/10.1145/3528416.3530242.
Chinthamu, N. ., Gooda, S. K. ., Shenbagavalli, P. ., Krishnamoorthy, N. ., & Selvan, S. T. . (2023). Detecting the Anti-Social Activity on Twitter using EGBDT with BCM. International Journal on Recent and Innovation Trends in Computing and Communication, 11(4s), 109–115. https://doi.org/10.17762/ijritcc.v11i4s.6313
Chaudhary, D. S. . (2021). ECG Signal Analysis for Myocardial Disease Prediction by Classification with Feature Extraction Machine Learning Architectures. Research Journal of Computer Systems and Engineering, 2(1), 06:10. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/12
Keerthi, R. S., Dhabliya, D., Elangovan, P., Borodin, K., Parmar, J., & Patel, S. K. (2021). Tunable high-gain and multiband microstrip antenna based on liquid/copper split-ring resonator superstrates for C/X band communication. Physica B: Condensed Matter, 618 doi:10.1016/j.physb.2021.413203
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
