Reconciling Cloud and Mobile Computing Using Activity-Based Predictive Caching

  • Dawud Gordon
  • Sven Frauen
  • Michael Beigl
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 130)


Cloud computing has greatly increased the utility of mobile devices by allowing processing and data to be offloaded, leaving an interface with higher utility and lower resource consumption on the device. However, mobility leads to loss of connectivity, making these remote resources inaccessible, breaking that utility completely during offline periods. We present a concept for reconciling the fragile connectivity of mobile devices with the distributed nature of cloud computing. We predict periods without connectivity on the mobile devices before they occur and cache process states for applications running on distributed cloud back-ends. The goal is to maintain partial or full utility during offline periods, and thereby to enable an improved user experience. We demonstrate prediction must include real-time behavioral information in addition to location and temporal models. The approach is implemented for mobile phones which learn to quantify human behavior using activity recognition, and then learn patterns in that behavior which lead to disconnectivity. We evaluate it for a streaming music scenario, where data is cached before the user goes offline, allowing seamless playback. The results show that theoretically we can successfully predict 100% of disconnection events on average 8 minutes in advance (std. dev. 46 secs.) with minimal false-positive caching in this scenario, although in the wild these events could prove more difficult to predict.


predictive caching activity recognition mobile cloud computing connectivity prediction mobile apps 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bao, L., Intille, S.S.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  2. 2.
    de Araño, G.M., Pinto, A., Kaiser, J., Becker, L.B.: An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks. Procedia Computer Science 10, 1100–1105 (2012), ANT 2012 and MobiWIS 2012CrossRefGoogle Scholar
  3. 3.
    Forman, G., Zahorjan, J.: The challenges of mobile computing. Computer 27(4), 38–47 (April)Google Scholar
  4. 4.
    Gordon, D., Czerny, J., Miyaki, T., Beigl, M.: Energy-efficient activity recognition using prediction. In: 2012 16th International Symposium on Wearable Computers (ISWC), pp. 29–36 (June 2012)Google Scholar
  5. 5.
    Kobayashi, K., Matsunaga, Y.: Radio quality prediction based on user mobility and radio propagation analysis. In: International Symposium on Personal, Indoor and Mobile Radio Communications, pp. 2137–2141. IEEE Computer Society Press, Los Alamitos (2009)Google Scholar
  6. 6.
    Kumar, K., Lu, Y.-H.: Cloud computing for mobile users: Can offloading computation save energy? Computer 43(4), 51–56 (2010)CrossRefGoogle Scholar
  7. 7.
    Lungaro, P., Segall, Z., Zander, J.: Contextshift: A model for efficient delivery of content in mobile networks. In: 2010 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1–6 (April 2010)Google Scholar
  8. 8.
    Mayrhofer, R., Radi, H., Ferscha, A.: Recognizing and predicting context by learning from user behavior. Radiomatics: Journal of Communication Engineering, Special Issue on Advances in Mobile Multimedia 1(1), 30–42 (2004)Google Scholar
  9. 9.
    Mell, P., Grance, T.: The NIST Definition of Cloud Computing. Technical report (July 2009)Google Scholar
  10. 10.
    Motahari, S., Zang, H., Reuther, P.: The impact of temporal factors on mobility patterns. In: 2012 45th Hawaii International Conference on System Science (HICSS), pp. 5659–5668 (January 2012)Google Scholar
  11. 11.
    Mummert, L.B., Ebling, M.R., Satyanarayanan, M.: Exploiting weak connectivity for mobile file access. SIGOPS Oper. Syst. Rev. 29(5), 143–155 (1995)CrossRefGoogle Scholar
  12. 12.
    Murphy, K.P.: Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning series). The MIT Press (August 2012)Google Scholar
  13. 13.
    Nicholson, A.J., Noble, B.D.: Breadcrumbs: forecasting mobile connectivity. In: Proceedings of the 14th ACM International Conference on Mobile Computing and Networking, MobiCom 2008, pp. 46–57. ACM, New York (2008)Google Scholar
  14. 14.
    Rahmati, A., Zhong, L.: Context-based network estimation for energy-efficient ubiquitous wireless connectivity. Mobile Computing 10, 54–66 (2011)CrossRefGoogle Scholar
  15. 15.
    Seneviratne, A., Pedrasa, J., Rathnayake, U.: Network availability prediction: Can it be done? In: Global Information Infrastructure Symposium (2011)Google Scholar
  16. 16.
    Shin, C., Hong, J.-H., Dey, A.K.: Understanding and prediction of mobile application usage for smart phones. In: Proceedings of the Conference on Ubiquitous Computing, pp. 173–182. ACM, New York (2012)Google Scholar
  17. 17.
    Sigg, S., Gordon, D., von Zengen, G., Beigl, M., Haseloff, S., David, K.: Investigation of context prediction accuracy for different context abstraction levels. IEEE Transactions on Mobile Computing 11(6), 1047–1059 (June)Google Scholar
  18. 18.
    Ward, J.A., Lukowicz, P., Gellersen, H.W.: Performance metrics for activity recognition. ACM Trans. Intell. Syst. Technol. 2(1), 6:1–6:23 (2011)CrossRefGoogle Scholar
  19. 19.
    Yang, Q., Zhang, H.H.: Web-log mining for predictive web caching. IEEE Trans. on Knowl. and Data Eng. 15(4), 1050–1053 (2003)CrossRefGoogle Scholar

Copyright information

© ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering 2014

Authors and Affiliations

  • Dawud Gordon
    • 1
  • Sven Frauen
    • 1
  • Michael Beigl
    • 1
  1. 1.Karlsruhe Institute of Technology (KIT)KarlsruheGermany

Personalised recommendations