Fundamentals and Literature Review

  • Hantao HuangEmail author
  • Hao Yu
Part of the Computer Architecture and Design Methodologies book series (CADM)


In this chapter, edge computing on IoT devices is firstly discussed to achieve low-latency, energy efficient, private and scalable computation. Then we use IoT based smart buildings as one example to illustrate the edge computing in IoT system for applications such as indoor positioning, energy management and network intrusion detection. Furthermore, we will discuss the basics of the machine learning algorithms, distributed machine learning, machine learning accelerators and machine learning model optimizations. A comprehensive literature review on distributed and compact machine learning algorithms is also provided.


Edge computing Machine learning Distributed machine learning Neural network compression 


  1. 1.
    (2017) Apache spark hardware provisioning. Accessed 03 May 2017
  2. 2.
    Abid S, Fnaiech F, Najim M (2002) A new neural network pruning method based on the singular value decomposition and the weight initialization. In: European signal processing conference, Toulouse, France, pp 1–4Google Scholar
  3. 3.
    Altini M, Brunelli D, Farella E, Benini L (2010) Bluetooth indoor localization with multiple neural networks. In: International symposium on wireless pervasive computing, Modena, Italy, pp 295–300Google Scholar
  4. 4.
    Amodei D, Ananthanarayanan S, Anubhai R, Bai J, Battenberg E, Case C, Casper J, Catanzaro B, Cheng Q, Chen G et al (2016) Deep speech 2: End-to-end speech recognition in English and Mandarin. In: International conference on machine learning, New York City, pp 173–182Google Scholar
  5. 5.
    Bengio Y et al (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1–127MathSciNetCrossRefGoogle Scholar
  6. 6.
    Buciluǎ C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: International conference on knowledge discovery and data mining, Philadelphia, Pennsylvania, pp 535–541Google Scholar
  7. 7.
    Cai Y, Rai SK, Yu H (2015) Indoor positioning by distributed machine-learning based data analytics on smart gateway network. In: International conference on indoor positioning and indoor navigation, Alberta, Canada, pp 1–8Google Scholar
  8. 8.
    Chen S, Liu T, Zhou Y, Shen C, Gao F, Che Y, Xu Z (2015) SHE: Smart home energy management system based on social and motion behavior cognition. In: International conference on smart grid communications, Miamimiami, Floridia, pp 859–864Google Scholar
  9. 9.
    Chen W, Wilson JT, Tyree S, Weinberger KQ, Chen Y (2015) Compressing neural networks with the hashing trick. In: International conference on machine learning, Lille, France, pp 2285–2294Google Scholar
  10. 10.
    Chen W, Wilson J, Tyree S, Weinberger KQ, Chen Y (2016) Compressing convolutional neural networks in the frequency domain. In: International conference on knowledge discovery and data mining, San Francisco, California, pp 1475–1484Google Scholar
  11. 11.
    Chen YH, Krishna T, Emer JS, Sze V (2017) Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J Solid-State Circuits 52(1):127–138CrossRefGoogle Scholar
  12. 12.
    Cheng Q, Yao J, Wu H, Chen S, Liu C, Yao P (2013) Short-term load forecasting with weather component based on improved extreme learning machine. In: Chinese automation congress, Hunan, China, pp 316–321Google Scholar
  13. 13.
    Chua L (1971) Memristor-the missing circuit element. IEEE Trans Circuit Theory 18(5):507–519CrossRefGoogle Scholar
  14. 14.
    Cong J, Xiao B (2014) Minimizing computation in convolutional neural networks. In: International conference on artificial neural networks, Hamburg, Germany, pp 281–290Google Scholar
  15. 15.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297zbMATHGoogle Scholar
  16. 16.
    Dean J, Corrado G, Monga R, Chen K, Devin M, Mao M, Senior A, Tucker P, Yang K, Le QV et al (2012) Large scale distributed deep networks. In: Advances in neural information processing systems, Lake Tahoe, Nevada, pp 1223–1231Google Scholar
  17. 17.
    Denil M, Shakibi B, Dinh L, de Freitas N et al (2013) Predicting parameters in deep learning. In: Advances in neural information processing systems, Lake Tahoe, Nevada, pp 2148–2156Google Scholar
  18. 18.
    Google (2016) Apache Haddop. Accessed 02 Nov 2016
  19. 19.
    Gropp W, Lusk E, Doss N, Skjellum A (1996) A high-performance, portable implementation of the MPI message passing interface standard. Parallel Comput 22(6):789–828CrossRefGoogle Scholar
  20. 20.
    Guinde NB, Ziavras SG (2010) Efficient hardware support for pattern matching in network intrusion detection. Comput Secur 29(7):756–769CrossRefGoogle Scholar
  21. 21.
    Han S, Mao H, Dally WJ (2015) Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv:151000149
  22. 22.
    Harvey LD (2010) Energy and the new reality 1: Energy efficiency and the demand for energy services. RoutledgeGoogle Scholar
  23. 23.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, Caesars Palace, Nevada, pp 770–778Google Scholar
  24. 24.
    He S, Chan SHG (2016) Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons. IEEE Commun Surv Tutor 18(1):466–490CrossRefGoogle Scholar
  25. 25.
    Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv:150302531
  26. 26.
    Hippert HS, Pedreira CE, Souza RC (2001) Neural networks for short-term load forecasting: A review and evaluation. IEEE Trans Power Syst 16(1):44–55CrossRefGoogle Scholar
  27. 27.
    Holtz S, Rohwedder T, Schneider R (2012) The alternating linear scheme for tensor optimization in the tensor train format. SIAM J Sci Comput 34(2):A683–A713MathSciNetCrossRefGoogle Scholar
  28. 28.
    Hossain AM, Soh WS (2015) A survey of calibration-free indoor positioning systems. Comput Commun 66:1–13CrossRefGoogle Scholar
  29. 29.
    Hoverstad BA, Tidemann A, Langseth H, Ozturk P (2015) Short-term load forecasting with seasonal decomposition using evolution for parameter tuning. IEEE Trans Smart Grid 6(4):1904–1913CrossRefGoogle Scholar
  30. 30.
    Huang H, Cai Y, Xu H, Yu H (2017) A multi-agent minority-game based demand-response management of smart buildings towards peak load reduction. IEEE Trans Comput-Aided Des Integr Circuits Syst 36(4):573–585. Scholar
  31. 31.
    Huang H, Xu H, Cai Y, Khalid RS, Yu H (2018) Distributed machine learning on smart-gateway network toward real-time smart-grid energy management with behavior cognition. ACM Trans Des Autom Electron Syst (TODAES) 23(5):56. Scholar
  32. 32.
    Hubara I, Courbariaux M, Soudry D, El-Yaniv R, Bengio Y (2016) Quantized neural networks: Training neural networks with low precision weights and activations. arXiv:160907061
  33. 33.
    Hubara I, Soudry D, Yaniv RE (2016) Binarized neural networks. arXiv:160202505
  34. 34.
    Hung M (2017) Leading the IoT. Accessed 09 Feb 2018
  35. 35.
    Hwang K, Cai M, Chen Y, Qin M (2007) Hybrid intrusion detection with weighted signature generation over anomalous internet episodes. IEEE Trans Dependable Secur Comput 4(1)Google Scholar
  36. 36.
    Janicka J, Rapinski J (2016) Application of RSSI based navigation in indoor positioning. In: Geodetic congress (geomatics), Baltic, Gdansk, Poland, pp 45–50Google Scholar
  37. 37.
    Johnson BJ, Starke MR, Abdelaziz OA, Jackson RK, Tolbert LM (2014) A method for modeling household occupant behavior to simulate residential energy consumption. In: Innovative smart grid technologies conference, Washington, DC, USA, pp 1–5Google Scholar
  38. 38.
    Kleissl J, Agarwal Y (2010) Cyber-physical energy systems: Focus on smart buildings. In: Proceeding of design automation conference, San Francisco, California, pp 749–754Google Scholar
  39. 39.
    Lacey G, Taylor GW, Areibi S (2016) Deep learning on FPGAs: Past, present, and future. arXiv:160204283
  40. 40.
    Li D, Lee DL (2008) A topology-based semantic location model for indoor applications. In: International workshop on security and privacy in GIS and LBS, Irvine, California, pp 6:1–6:10Google Scholar
  41. 41.
    Lin D, Talathi S, Annapureddy S (2016) Fixed point quantization of deep convolutional networks. In: International conference on machine learning, New York City, pp 2849–2858Google Scholar
  42. 42.
    Liu H, Darabi H, Banerjee P, Liu J (2007) Survey of wireless indoor positioning techniques and systems. IEEE Trans Syst Man Cybern Part C: Appl Rev 37(6):1067–1080CrossRefGoogle Scholar
  43. 43.
    Lu N, Taylor T, Jiang W, Correia J, Leung LR, Wong PC (2009) The temperature sensitivity of the residential load and commercial building load. In: Power and energy society general meeting. IEEE, Alberta, Canada, pp 1–7Google Scholar
  44. 44.
    Nakkiran P, Alvarez R, Prabhavalkar R, Parada C (2015) Compressing deep neural networks using a rank-constrained topology. In: Sixteenth annual conference of the international speech communication association, Dresden, GermanyGoogle Scholar
  45. 45.
    Ni L, Huang H, Yu H (2016) On-line machine learning accelerator on digital RRAM-crossbar. In: International symposium on circuits and systems, pp 113–116.
  46. 46.
    Ni L, Wang Y, Yu H, Yang W, Weng C, Zhao J (2016) An energy-efficient matrix multiplication accelerator by distributed in-memory computing on binary RRAM crossbar. In: Design automation conference (ASP-DAC). IEEE, Macao, China, pp 280–285Google Scholar
  47. 47.
    Novikov A, Podoprikhin D, Osokin A, Vetrov DP (2015) Tensorizing neural networks. In: Advances in neural information processing systems, Montreal Canada, pp 442–450Google Scholar
  48. 48.
    PD SM, Yu H, Huang H, Xu D (2016) A Q-learning based self-adaptive I/O communication for 2.5 D integrated many-core microprocessor and memory. IEEE Trans Comput 65(4):1185–1196.
  49. 49.
    Polinder H et al (2013) International energy agency program on buildings and community. Annex 43-occupants behavior and modeling. International Energy AgencyGoogle Scholar
  50. 50.
    Quinlan JR (2014) C4. 5: Programs for machine learning. Elsevier, AmsterdamGoogle Scholar
  51. 51.
    Richardson DB, Harvey L (2015) Strategies for correlating solar PV array production with electricity demand. Renew Energy 76:432–440CrossRefGoogle Scholar
  52. 52.
    Roesch M et al (1999) Snort: Lightweight intrusion detection for networks. In: USENIX systems administration conference, Seattle, Washington, pp 229–238Google Scholar
  53. 53.
    Sandels C, Widén J, Nordström L (2014) Forecasting household consumer electricity load profiles with a combined physical and behavioral approach. Appl Energy 131:267–278CrossRefGoogle Scholar
  54. 54.
    Scarfone K, Mell P (2007) Guide to intrusion detection and prevention systems (IDPS). NIST Special Publication 800:94–96Google Scholar
  55. 55.
    Sim J, Park JS, Kim M, Bae D, Choi Y, Kim LS (2016) 14.6 A 1.42 TOPS/W deep convolutional neural network recognition processor for intelligent IoT systems. In: International solid-state circuits conference, San Francisco, California, pp 264–265Google Scholar
  56. 56.
    Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:14091556
  57. 57.
    Sutton RS, Barto AG (1998) Introduction to reinforcement learning, vol 135. MIT Press, CambridgeGoogle Scholar
  58. 58.
    Theodoridis S, Pikrakis A, Koutroumbas K, Cavouras D (2010) Introduction to pattern recognition: A Matlab approach. Academic, New YorkGoogle Scholar
  59. 59.
    Torres-Solis J, Falk TH, Chau T (2010) A review of indoor localization technologies: Towards navigational assistance for topographical disorientation. INTECH PublisherGoogle Scholar
  60. 60.
    Viegas E, Santin AO, França A, Jasinski R, Pedroni VA, Oliveira LS (2017) Towards an energy-efficient anomaly-based intrusion detection engine for embedded systems. IEEE Trans Comput 66(1):163–177MathSciNetCrossRefGoogle Scholar
  61. 61.
    Wang Y, Huang H, Ni L, Yu H, Yan M, Weng C, Yang W, Zhao J (2015) An energy-efficient non-volatile in-memory accelerator for sparse-representation based face recognition. In: Design, automation and test in Europe conference and exhibition (DATE), 2015. IEEE, pp 932–935Google Scholar
  62. 62.
    Xia L, Gu P, Li B, Tang T, Yin X, Huangfu W, Yu S, Cao Y, Wang Y, Yang H (2016) Technological exploration of RRAM crossbar array for matrix-vector multiplication. J Comput Sci Technol 31(1):3–19MathSciNetCrossRefGoogle Scholar
  63. 63.
    Xu D, Yu N, Huang H, Manoj PS, Yu H (2018) Q-learning-based voltage-swing tuning and compensation for 2.5-D memory-logic integration. IEEE Des Test 35(2):91–99.
  64. 64.
    Xu J, Liu W, Lang F, Zhang Y, Wang C (2010) Distance measurement model based on RSSI in WSN. Wirel Sens Netw 2(08):606CrossRefGoogle Scholar
  65. 65.
    Yang C, Shao HR (2015) Wi-Fi-based indoor positioning. IEEE Commun Mag 53(3):150–157CrossRefGoogle Scholar
  66. 66.
    Zaharia M, Chowdhury M, Das T, Dave A, Ma J, McCauley M, Franklin MJ, Shenker S, Stoica I (2012) Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX conference on networked systems design and implementation, USENIX Association, pp 2–2Google Scholar
  67. 67.
    Zhang C, Li P, Sun G, Guan Y, Xiao B, Cong J (2015) Optimizing FPGA-based accelerator design for deep convolutional neural networks. In: International symposium on field-programmable gate arrays, Monterey, California, pp 161–170Google Scholar
  68. 68.
    Zhang F, Deng H, Margolis R, Su J (2015) Analysis of distributed-generation photo voltaic deployment, installation time and cost, market barriers, and policies in China. Energy Policy 81:43–55Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Electrical and Electronic EngineeringNanyang Technological UniversitySingaporeSingapore
  2. 2.Department of Electrical and Electronic EngineeringSouthern University of Science and TechnologyShenzhenChina

Personalised recommendations