Ultra-Efficient RISC-V Processor with Brain-Inspired Computing for Resource-Constrained IoT Devices

Authors

  • M.Shanthi, Karpagam Kanadasan, K.E. Purushothaman, K. Nagendran, T. Rengaraj, D. Harika

Keywords:

Power management integrated circuits (PMICs), Maximum Power Point Tracking (MPPT), Neuromorphic Hardware Accelerators, Sparse Coding Algorithm.

Abstract

In this era of ubiquitous computing, where interconnected devices permeate nearly every aspect of daily life, the demand for energy-efficient solutions for resource-constrained IoT devices continues to escalate. Often deployed in remote or off-grid locations, these devices face significant power consumption and computational efficiency challenges. This research presents a groundbreaking approach to address this pressing challenge by introducing an ultra-low power, high-performance RISC-V processor integrated with brain-inspired computing principles. Several key technologies meticulously woven into the processor's architecture are at the heart of this innovation. Neuromorphic hardware accelerators, drawing inspiration from the brain's neural networks, enable energy-efficient, parallel processing, facilitating complex tasks such as pattern recognition and sensor data processing while consuming minimal power. The integration of maximum power point tracking (MPPT) algorithms ensures optimal energy harvesting from renewable sources, such as solar panels, by dynamically adjusting the operating point to maximize power extraction under varying environmental conditions. This adaptive approach enhances the device's energy autonomy, which is crucial for prolonged operation in remote environments. Power management integrated circuits (PMICs) play a pivotal role in regulating and optimizing power distribution within the device. Through intelligent power gating, voltage scaling, and energy harvesting techniques, PMICs enhance overall energy efficiency, extending device runtime and reliability. The processor design leverages system-on-chip (SoC) platforms, providing a highly integrated solution that combines processing, memory, and I/O functionalities on a single chip. This integration reduces system complexity, footprint, and power consumption, making it ideal for resource-constrained IoT deployments. Sparse coding algorithms efficiently represent and process sensory data, minimizing computational complexity and energy consumption while preserving information content. By exploiting the inherent sparsity in many IoT data streams, sparse coding enables efficient data compression and analysis, further enhancing overall system performance. Integrating neuromorphic hardware accelerators resulted in a 20% improvement in computational performance, while MPPT optimization techniques led to a 15% reduction in energy consumption. Additionally, implementing PMICs enabled efficient power distribution and regulation, contributing to a 25% increase in overall system efficiency.Top of Form

Downloads

Download data is not yet available.

References

Ahmed, S., & Khan, M. (2023). Securing the Internet of Things (IoT): A comprehensive study on the intersection of cybersecurity, privacy, and connectivity in the IoT ecosystem. AI, IoT and the Fourth Industrial Revolution Review, 13(9), 1-17.

Almusaed, A., Yitmen, I., & Almssad, A. (2023). Enhancing smart home design with AI models: A case study of living spaces implementation review. Energies, 16(6), 2636.

López, O. L., Rosabal, O. M., Ruiz-Guirola, D. E., Raghuwanshi, P., Mikhaylov, K., Lovén, L., & Iyer, S. (2023). Energy-sustainable IoT connectivity: Vision, technological enablers, challenges, and future directions. IEEE Open Journal of the Communications Society.

Qaim, W. B., Ometov, A., Molinaro, A., Lener, I., Campolo, C., Lohan, E. S., & Nurmi, J. (2020). Towards energy efficiency in the internet of wearable things: A systematic review. IEEE Access, 8, 175412-175435.

Kornaros, G. (2022). Hardware-assisted machine learning in resource-constrained IoT environments for security: review and future prospective. IEEE Access, 10, 58603-58622.

Azghadi, M. R., Lammie, C., Eshraghian, J. K., Payvand, M., Donati, E., Linares-Barranco, B., & Indiveri, G. (2020). Hardware implementation of deep network accelerators for healthcare and biomedical applications. IEEE Transactions on Biomedical Circuits and Systems, 14(6), 1138-1159.

Ahmad, F. F., Ghenai, C., & Bettayeb, M. (2021). Maximum power point tracking and photovoltaic energy harvesting for Internet of Things: A comprehensive review. Sustainable Energy Technologies and Assessments, 47, 101430.

Kumar, S., & Yadav, P. (2022). Energy Harvesting–Based Architecture in IoT: Basics of Energy Harvesting, Key Technology for Enhancing the Life of IoT Devices, Challenges of IoT in Terms of Energy and Power Consumption. In Energy Harvesting (pp. 1-18). Chapman and Hall/CRC.

Henry, G., Palangpour, P., Thomson, M., Gardner, J. S., Arden, B., Donahue, J., ... & Walker, T. (2020, May). High-performance deep-learning coprocessor integrated into x86 soc with server-class cpus industrial product. In 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA) (pp. 15-26). IEEE.

Du, X., Zhou, Z., Zhang, Y., & Rahman, T. (2020). Energy-efficient sensory data gathering based on compressed sensing in IoT networks. Journal of Cloud Computing, 9, 1-16.

Nassra, I., & Capella, J. V. (2023). Data compression techniques in IoT-enabled wireless body sensor networks: A systematic literature review and research trends for QoS improvement. Internet of Things, 100806.

Mezger, B. W., Santos, D. A., Dilillo, L., Zeferino, C. A., & Melo, D. R. (2022). A survey of the RISC-V architecture software support. IEEE Access, 10, 51394-51411.

Garofalo, A., Tagliavini, G., Conti, F., Rossi, D., & Benini, L. (2020, March). XpulpNN: Accelerating quantized neural networks on RISC-V processors through ISA extensions. In 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE) (pp. 186-191). IEEE.

Liang, Y., Tan, J., Xie, Z., Chen, Z., Lin, D., & Yang, Z. (2023). Research on Convolutional Neural Network Inference Acceleration and Performance Optimization for Edge Intelligence. Sensors, 24(1), 240.

Wang, S., Chen, X., Huang, X., Wei Zhang, D., & Zhou, P. (2020). Neuromorphic engineering for hardware computational acceleration and biomimetic perception motion integration. Advanced Intelligent Systems, 2(11), 2000124.

Satyanarayana, P., Diwakar, G., Subbayamma, B. V., Kumar, N. P. S., Arun, M., & Gopalakrishnan, S. (2023). Comparative analysis of new meta-heuristic-variants for privacy preservation in wireless mobile ad-hoc networks for IoT applications. Computer Communications, 198, 262-281.

Anitha, R., Sundaramoorthy, K., Selvi, S., Gopalakrishnan, S., & Sheela, M. S. Detection and Segmentation of Meningioma Brain Tumors in MRI brain Images using Curvelet Transform and ANFIS. International Journal of Electrical and Electronics Research, 11(2), 412-417.

Downloads

Published

06.08.2024

How to Cite

M.Shanthi. (2024). Ultra-Efficient RISC-V Processor with Brain-Inspired Computing for Resource-Constrained IoT Devices. International Journal of Intelligent Systems and Applications in Engineering, 12(23s), 98–110. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/6436

Issue

Section

Research Article

Similar Articles

You may also start an advanced similarity search for this article.