Abstract
Artificial intelligence (AI) and machine learning (ML)-based decision-making is proliferating to application spaces with dynamic and evolving inputs such as Internet of things (IoTs). The need for real-time decision-making in such applications requires the edge devices in IoT networks to possess in situ intelligence processing capability. Edge intelligence in the networks is critical to avert unpredictable latency of an otherwise cloud-based intelligence processing. Edge intelligence in IoTs also minimizes their energy demand by avoiding raw data transmission and better preserving data privacy by only transmitting actionable information. Meanwhile, due to form factor and cost constraints and battery-powered operation, the energy budget and computing/storage resources for edge intelligence are very limited in a typical IoT node. Addressing such computational challenges in IoTs, in this chapter, an architectural framework for self-powered edge intelligence is reviewed. First, architectural techniques are reviewed to exploit sensors in IoTs to harvest energy from their environment to sustain local intelligence processing. Next, architectures that can identify and focus on regions of interest (ROI) are discussed to exploit sparsity in input and to minimize edge intelligence workload. Finally, learning-based architectures are discussed to reduce power wastage, such as due to leakage power. With a synergistic integration of the above architectural techniques, many IoTs can leverage self-powered edge intelligence to heighten awareness of their application domains.
Similar content being viewed by others
References
Agarwal K, Deogun H, Sylvester D, Nowka K (2006) Power gating with multiple sleep modes. In: 7th international symposium on quality electronic design (ISQED’06). IEEE, p 5
Akl CJ, Ayoubi RA, Bayoumi MA (2009) An effective staggered-phase dam** technique for suppressing power-gating resonance noise during mode transition. In: 2009 10th international symposium on quality electronic design. IEEE, pp 116–119
Amazon Blink. https://www.amazon.com/stores/page/C5DECBBE-4F56-4C36-B933-E6214457 8691
Anandkumar A, Ge R, Hsu D, Kakade SM, Telgarsky M (2014) Tensor decompositions for learning latent variable models. J Mach Learn Res 15(80):2773–2832. [Online]. Available: http://jmlr.org/papers/v15/anandkumar14b.html
Arora S, Leighton T, Maggs B (1990) On-line algorithms for path selection in a nonblocking network. In: Proceedings of ACM symposium on theory of computing (STOC), pp 149–158
Bank RE, Douglas CC (1993) Sparse matrix multiplication package (SMMP). Adv Comput Math 1:127–137
Benezeth Y, Jodoin P-M, Emile B, Laurent H, Rosenberger C (2010) Comparative study of background subtraction algorithms. J Electron Imag 19(3):033003
Bennett J, Lanning S (2007) The Netflix prize. In: KDD cup and workshop in conjunction with KDD
Boyapati R, Huang J, Wang N, Kim KH, Yum KH, Kim EJ (2017) Fly-over: a light-weight distributed power-gating mechanism for energy-efficient networks-on-chip. In: 2017 IEEE international parallel and distributed processing symposium (IPDPS). IEEE, pp 708–717
Brutzer S, Höferlin B, Heidemann G (2011) Evaluation of background subtraction techniques for video surveillance. In: IEEE CVPR, pp 1937–1944. [Online]. Available: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5995508
Cevik I, Huang X, Yu H, Yan M, Ay S (2015) An ultra-low power CMOS image sensor with on-chip energy harvesting and power management capability. Sensors 15(3):5531–5554. [Online]. Available: http://www.mdpi.com/1424-8220/15/3/5531/
Charania T, Opal A, Sachdev M (2012) Analysis and design of on-chip decoupling capacitors. IEEE Trans Very Large Scale Integr (VLSI) syst 21(4):648–658
Chefi A, Soudani A, Sicard G (2013) A CMOS image sensor with low-complexity video compression for wireless sensor networks. In: IEEE NEWCAS, pp 1–4. [Online]. Available: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6573591 http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6573591
Chiou AY-C, Hsieh C-C (2015) A 0.4 V self-powered CMOS imager with 140 dB dynamic range and energy harvesting C86 C87, pp 86–87
Dong L, ** C, Closson AB, Trase I, Richards HR, Chen Z, Zhang JX (2020a) Cardiac energy harvesting and sensing based on piezoelectric and triboelectric designs. Nano Energy 76:105076
Dong L, Closson AB, ** C, Nie Y, Cabe A, Escobedo D, Huang S, Trase I, Xu Z, Chen Z et al (2020b) Multifunctional pacemaker lead for cardiac energy harvesting and pressure sensing. Adv Healthcare Mater 9(11):2000053
Dunne MC, Potts RB (1964) Algorithm for traffic control. Oper Res 12(6):870–881
Eisenstat SC, Elman HC, Schultz MH, Sherman AH (1984) The (new) Yale sparse matrix package. In: Elliptic Problem Solvers, vol 2, pp 45–52
Elgammal A, Harwood D, Davis L (2000) Non-parametric model for background subtraction. In: ECCV, vol 1843, pp 751–767
Fallah YP, Mansour H, Khan S (2008) A link adaptation scheme for efficient transmission. Circuits Syst Video Technol IEEE 18(7):875–887
Gao W, Hsu D, Lee WS, Shen S, Subramanian K (2017) Intention-Net: integrating planning and deep learning for goal-directed autonomous navigation, CoRR, vol. abs/1710.05627. [Online]. Available: http://arxiv.org/abs/1710.05627
Google Home. https://store.google.com/us/magazine/compare_nest_speakers_displays
Grasedyck L, Kressner D, Tobler C (2013) A literature survey of low-rank tensor approximation techniques
Grois D, Hadar O (2014) Complexity-aware adaptive preprocessing scheme for region-of-interest spatial scalable video coding. IEEE Trans Circuits Syst Video Technol 24(6):1025–1039. [Online]. Available: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6727577
Grois D, Member S, Hadar O (2011) Efficient adaptive bit-rate control for scalable video coding by using computational complexity-rate-distortion analysis. In: The IEEE international symposium on broadband multimedia systems and broadcasting (BMSB)
Gulcehre C, Denil M, Malinowski M, Razavi A, Pascanu R, Hermann KM, Battaglia P, Bapst V, Raposo D, Santoro A et al (2018) Hyperbolic attention networks, ar**v preprint ar**v:1805.09786
Hampapur A, Brown L, Connell J, Pankanti S, Senior A, Tian Y (2003) Smart surveillance applications, technologies and implications.pdf. In: ICICS-FCM
Han S, Mao H, Dally WJ (2016a) Deep compression: compressing deep neural network with pruning, trained quantization and Huffman coding. In: International conference on learning representations (ICLR). [Online]. Available: http://arxiv.org/abs/1510.00149
Han S, Liu X, Mao H, Pu J, Pedram A, Horowitz MA, Dally WJ (2016b) EIE: efficient inference engine on compressed deep neural network. In: Proceedings of international symposium on computer architecture (ISCA), pp 243–254
Han S, Liu X, Mao H, Pu J, Pedram A, Horowitz MA, Dally WJ (2016c) Eie: efficient inference engine on compressed deep neural network. ACM SIGARCH Comput Archit News 44(3):243–254
Hapla V, Horak D, Merta M (2013) Use of direct solvers in TFETI massively parallel implementation. Springer, Berlin/Heidelberg, pp 192–205
Haratcherev L, Taal J (2005) Fast 802.11 link adaptation for real-time video streaming by cross-layer signaling. In: IEEE international symposium on circuits and systems. [Online]. Available: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1465389
Hegde K, Asghari-Moghaddam H, Pellauer M, Crago N, Jaleel A, Solomonik E, Emer J, Fletcher CW (2019) ExTensor: an accelerator for sparse tensor algebra. In: Proceedings of IEEE/ACM international symposium on microarchitecture (MICRO), pp 319–333
Horowitz M. Energy table for 45 nm process, Stanford VLSI Wiki. [Online]. Available: https://sites.google.com/site/seecproject
Hu Z, Buyuktosunoglu A, Srinivasan V, Zyuban V, Jacobson H, Bose P (2004) Microarchitectural techniques for power gating of execution units. In: Proceedings of the 2004 international symposium on low power electronics and design, pp 32–37
Hu Y, Meng F, Wang Y (2012) Improved JPEG compression algorithm based on saliency maps. In: CISP
Hu K-Y, Tsai C-H, Tsai C-W (2020) Digital v2 constant on-time control buck converter with adaptive voltage positioning and automatic calibration mechanism. IEEE Trans Power Electron 36: 7178–7188
Huang C, Lin C (2009) Multiple-priority region-of-interest H.264 video compression using constraint variable bitrate control for video surveillance. Opt Eng 48(4):047004. [Online]. Available: https://doi.org/10.1117/1.3120485
Imran M, Ahmad N, Khursheed K, Waheed MA, Lawal N, O’Nils M (2013) Implementation of wireless vision sensor node with a lightweight bi-level video coding. IEEE JETCAS 3(2):198–209
Jiang H, Marek-Sadowska M, Nassif SR (2005) Benefits and costs of power-gating technique. In: 2005 international conference on computer design. IEEE, pp 559–566
Jouppi NP, Young C, Patil N, Patterson D, Agrawal G, Bajwa R, Bates S, Bhatia S, Boden N, Borchers A, Boyle R, Cantin P, Chao C, Clark C, Coriell J, Daley M, Dau M, Dean J, Gelb B, Ghaemmaghami TV, Gottipati R, Gulland W, Hagmann R, Ho CR, Hogberg D, Hu J, Hundt R, Hurt D, Ibarz J, Jaffey A, Jaworski A, Kaplan A, Khaitan H, Killebrew D, Koch A, Kumar N, Lacy S, Laudon J, Law J, Le D, Leary C, Liu Z, Lucke K, Lundin A, MacKean G, Maggiore A, Mahony M, Miller K, Nagarajan R, Narayanaswami R, Ni R, Nix K, Norrie T, Omernick M, Penukonda N, Phelps A, Ross J, Ross M, Salek A, Samadiani E, Severn C, Sizikov G, Snelham M, Souter J, Steinberg D, Swing A, Tan M, Thorson G, Tian B, Toma H, Tuttle E, Vasudevan V, Walter R, Wang W, Wilcox E, Yoon DH (2017) In-datacenter performance analysis of a tensor processing unit. In: ACM/IEEE international symposium on computer architecture (ISCA), pp 1–12
Kahng AB, Kang S, Rosing TS, Strong R (2013) Many-core token-based adaptive power gating. IEEE Trans Comput-Aided Des Integr Circuits Syst 32(8):1288–1292
Kim C, Hwang J-N (2002) Fast and automatic video object segmentation and tracking for content-based applications. IEEE TCSVT 12(2):122–129. [Online]. Available: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=988659
Kim S, Kosonocky SV, Knebel DR (2003) Understanding and minimizing ground bounce during mode transition of power gating structures. In: Proceedings of the 2003 international symposium on low power electronics and design, pp 22–25
Kim K, Chalidabhongse TH, Harwood D, Davis L (2005) Real-time foreground-background segmentation using codebook model. Real-Time Imag 11(3):172–185. [Online]. Available: http://linkinghub.elsevier.com/retrieve/pii/S1077201405000057
Kim G, Lee Y, Foo Z, Pannuto P, Kuo YS, Kempke B, Ghaed MH, Bang S, Lee I, Kim Y, Jeong S, Dutta P, Sylvester D, Blaauw D (2014) A millimeter-scale wireless imaging system with continuous motion detection and energy harvesting. In: IEEE symposium on VLSI circuits, digest of technical papers, no. Dec 2011, pp 31–32
Ko JH, Mukhopadhyay S (2016) An energy-aware approach to noise-robust moving object detection for low-power wireless image sensor platforms. In: International symposium on low power electronics and design (ISLPED)
Ko JH, Ahmed KZ, Amir MF, Na T, Mukhopadhyay S (2017) A single-chip image sensor node with energy harvesting from CMOS pixel array. IEEE Trans Circuits Syst I, Reg Papers64(9):2295–2307
Ko JH, Mudassar BA, Mukhopadhyay S (2015) An energy-efficient wireless video sensor node for moving object surveillance. IEEE TMSCS 1(1):7–18
Ko JH, Na T, Mukhopadhyay S (2016) An energy-efficient wireless video sensor node with a region-of-interest based multi-parameter rate controller for moving object surveillance. In: IEEE advanced video and signal-based surveillance (AVSS), pp 138–144
Kung J, Park J, Park S, Kim J-J (2019) Peregrine: a flexible hardware accelerator for LSTM with limited synaptic connection patterns. In: Proceedings of the 56th annual design automation conference (DAC)
Lai W, Gu X-D, Wang R-H, Dai L-R, Zhang H-J (2004) A region based multiple frame-rate tradeoff of video streaming. In: 2004 international conference on image processing, 2004. ICIP’04, vol 3, pp 2067–2070. [Online]. Available: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1421491
Law MK, Bermak A, Shi C (2011) A low-power energy-harvesting logarithmic CMOS image sensor with reconfigurable resolution using two-level quantization scheme. IEEE Trans Circuits Syst II: Express Briefs 58(2):80–84
Lin X, Zhao C, Pan W (2017) Towards accurate binary convolutional neural network, ar**v preprint ar**v:1711.11294
Liu T, Qi Y, Shi L, Yan J (2019) Locate-then-detect: real-time web attack detection via attention-based deep neural networks. In: IJCAI, pp 4725–4731
Mattson T, Bader D, Berry J, Buluc A, Dongarra J, Faloutsos C, Feo J, Gilbert J, Gonzalez J, Hendrickson B, Kepner J, Leiserson C, Lumsdaine A, Padua D, Poole S, Reinhardt S, Stonebraker M, Wallach S, Yoo A (2013) Standards for graph algorithm primitives. In: IEEE high performance extreme computing conference (HPEC), pp 1–2
McKenna SJ, Raja Y, Gong S (1999) Tracking colour objects using adaptive mixture models. Image Vis Comput 17(3–4):225–231. [Online]. Available: http://linkinghub.elsevier.com/retrieve/pii/S0262885698001048
Meddeb M, Cagnazzo M, Pesquet-Popesc B (2014) Region-of-interest based rate control scheme for high efficiency video coding. In: APSIPA transactions on signal and information processing, pp 1–9
Narasimman N, Salahuddin R, Singh RP (2020) An 86% efficiency multi-phase buck converter using time-domain compensator and adaptive dead-time control for DVS application. In: IECON 2020 the 46th annual conference of the IEEE industrial electronics society. IEEE, pp 2255–2260
Nasrin S, Drobitch JL, Bandyopadhyay S, Trivedi AR (2019) Low power restricted boltzmann machine using mixed-mode magneto-tunneling junctions. IEEE Electron Device Lett 40(2):345–348
Nasrin S, Ramakrishna S, Tulabandhula T, Trivedi AR (2020) Supported-binarynet: bitcell array-based weight supports for dynamic accuracy-energy trade-offs in sram-based binarized neural network. In: 2020 IEEE international symposium on circuits and systems (ISCAS). IEEE, pp 1–5
Nasrin S, Badawi D, Cetin A, Gomes W, Trivedi AR (2021a) MF-Net: compute-in-memory sram for multibit precision inference using memory-immersed data conversion and multiplication-free operators. IEEE Trans Circuits Syst-I 68:1966–1978
Nasrin S, Shukla P, Jaisimha S, Trivedi AR (2021b) Compute-in-memory upside down: a learning operator co-design perspective for scalability. In: IEEE design automation and test in Europe (DATE)
Naumov M, Mudigere D, Shi HM, Huang J, Sundaraman N, Park J, Wang X, Gupta U, Wu C, Azzolini AG, Dzhulgakov D, Mallevich A, Cherniavskii I, Lu Y, Krishnamoorthi R, Yu A, Kondratenko V, Pereira S, Chen X, Chen W, Rao V, Jia B, **ong L, Smelyanskiy M (2019) Deep learning recommendation model for personalization and recommendation systems, CoRR, vol. abs/1906.00091. [Online]. Available: http://arxiv.org/abs/1906.00091
Nayar SK, Sims DC, Fridberg M (2015) Towards self-powered cameras. In: 2015 IEEE international conference on computational photography (ICCP), pp 1–10
Oliver NM, Rosario B, Pentland AP (2000) A bayesian computer vision system for modeling human interactions. IEEE Trans Pattern Anal Mach Intell 22(8):831–843
Ordejon P (1998) Order-N tight-binding methods for electronic-structure and molecular dynamics. Comput Mater Sci 12(3):157–191
Pal S, Beaumont J, Park D, Amarnath A, Feng S, Chakrabarti C, Kim H, Blaauw D, Mudge T, Dreslinski R (2018) OuterSPACE: an outer product based sparse matrix multiplication accelerator. In: IEEE international symposium on high performance computer architecture (HPCA), pp 724–736
Parashar A, Rhu M, Mukkara A, Puglielli A, Venkatesan R, Khailany B, Emer J, Keckler SW, Dally WJ (2017) SCNN: an accelerator for compressed-sparse convolutional neural networks. ACM SIGARCH Comput Archit News 45(2):27–40
Qin E, Samajdar A, Kwon H, Nadella V, Srinivasan S, Das D, Kaul B, Krishna T (2020) SIGMA: a sparse and irregular GEMM accelerator with flexible interconnects for DNN training. In: IEEE international symposium on high performance computer architecture (HPCA), pp 58–70
Robinson HA, Cherry C (1967) Results of a prototype television bandwidth compression scheme. Proc IEEE 55(3):356–364
Shehata N, Hassanin AH, Elnabawy E, Nair R, Bhat SA, Kandas I (2020) Acoustic energy harvesting and sensing via electrospun pvdf nanofiber membrane. Sensors 20(11):3111
Shukla P, Muralidhar A, Iliev N, Tulabandhula T, Fuller SB, Trivedi AR (2021) Ultralow-power localization of insect-scale drones: interplay of probabilistic filtering and compute-in-memory. IEEE Trans Very Large Scale Integr (VLSI) Syst 30:68–80
Shylendra A, Shukla P, Mukhopadhyay S, Bhunia S, Trivedi AR (2020a) Low power unsupervised anomaly detection by nonparametric modeling of sensor statistics. IEEE Trans Very Large Scale Integr (VLSI) Syst 28(8):1833–1843
Shylendra A, Alizad SH, Shukla P, Trivedi AR (2020b) Non-parametric statistical density function synthesizer and monte carlo sampler in CMOS. In: 2020 33rd international conference on VLSI design and 2020 19th international conference on embedded systems (VLSID). IEEE, pp 19–24
Singh M, Fayed AA (2020) A 1-a 6-mhz digitally assisted buck–boost converter with seamless mode transitions and fast dynamic performance for mobile devices. IEEE Trans Power Electron 36(4):4338–4351
Trivedi AR, Mukhopadhyay S (2012) Self-adaptive power gating with test circuit for on-line characterization of energy inflection activity. In: 2012 IEEE 30th VLSI test symposium (VTS). IEEE, pp 38–43
Trivedi AR, Mukhopadhyay S (2014) Potential of ultralow-power cellular neural image processing with Si/Ge tunnel FET. IEEE Trans Nanotechnol 13(4):627–629
Trivedi AR, Amir MF, Mukhopadhyay S (2014a) Ultra-low power electronics with si/ge tunnel FET. In: 2014 design, automation & test in Europe conference & exhibition (DATE). IEEE, pp 1–6
Trivedi AR, Yueh W, Mukhopadhyay S (2014b) In situ power gating efficiency learner for fine-grained self-adaptive power gating. IEEE Trans Circuits Syst II: Express Briefs 61(5):344–348
Trivedi A, Pandey R, Liu H, Datta S, Mukhopadhyay S (2015) Gate/source overlapped heterojunction tunnel FET for non-boolean associative processing with plasticity. In: 2015 IEEE international electron devices meeting (IEDM). IEEE, pp 17–8
Tsapatsoulis N, Loizou C, Pattichis C (2007) Region of interest video coding for low bit-rate transmission of carotid ultrasound videos over 3G wireless networks. In: Annual international conference of the IEEE engineering in medicine and biology, pp 3717–3720
Tuan M-C, Chen S-L (2015) Fully pipelined VLSI architecture of a real-time block-based object detector for intelligent video surveillance systems. In: 2015 IEEE/ACIS 14th international conference on computer and information science (ICIS), pp 149–154. [Online]. Available: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7166585
Uzun OA, Köse S (2014) Converter-gating: a power efficient and secure on-chip power delivery system. IEEE J Emerg Sel Top Circuits Syst 4(2):169–179
Vasudevan A, Anderson A, Gregg D (2017) Parallel multi channel convolution using general matrix multiplication. In: IEEE international conference on application-specific systems, architectures and processors (ASAP), pp 19–24
Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks, ar**v preprint ar**v:1710.10903
Wang H-T, Leon-Salas WD (2015) An image sensor with joint sensing and energy harvesting functions. IEEE Sens J 15(2):902–916. [Online]. Available: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6894563
Zhang S, Du Z, Zhang L, Lan H, Liu S, Li L, Guo Q, Chen T, Chen Y (2016) Cambricon-x: an accelerator for sparse neural networks. In: 2016 49th annual IEEE/ACM international symposium on microarchitecture (MICRO). IEEE, pp 1–12
Zhang Z, Wang H, Han S, Dally WJ (2020) SpArch: efficient architecture for sparse matrix multiplication. In: IEEE international symposium on high performance computer architecture (HPCA), pp 261–274
Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J (2019) Edge intelligence: paving the last mile of artificial intelligence with edge computing. Proc IEEE 107(8):1738–1762
Zohair M, Moyer K, Eaves-Rathert J, Meng C, Waugh J, Pint CL (2020) Continuous energy harvesting and motion sensing from flexible electrochemical nanogenerators: toward smart and multifunctional textiles. ACS Nano 14(2):2308–2315
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Section Editor information
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this entry
Cite this entry
Trivedi, A.R., Kung, J., Ko, J.H. (2022). Architectures for Self-Powered Edge Intelligence. In: Chattopadhyay, A. (eds) Handbook of Computer Architecture. Springer, Singapore. https://doi.org/10.1007/978-981-15-6401-7_9-1
Download citation
DOI: https://doi.org/10.1007/978-981-15-6401-7_9-1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-6401-7
Online ISBN: 978-981-15-6401-7
eBook Packages: Springer Reference EngineeringReference Module Computer Science and Engineering