SafeTECKS: Protect Data Safety in Things-Edge-Cloud Architecture with Knowledge Sharing
With the rapid development of Internet of Things (IoT) technology, massive data are generated by IoT terminals. Cloud computing is the current mainstream method to process these massive data effectively. However, the centralized cloud computing has the risk of data leakage during data transmission. To address the issue of data safety, we propose a novel edge computing architecture, called SafeTECKS. It consists of three-layer functional structure: IoT Devices, Edge Nodes, Cloud Center. Each edge node converts private data to knowledge by Agent component, and keeps them in Knowledge Store. Edge node shares knowledge with each other, instead of raw data, which can prevent data leakage caused by data transmission. An algorithm named MKF (Multi-Knowledge Fusion) is presented to integrate all knowledge learned from edge nodes. We use taxi demand prediction as a case to verify the effectiveness of our SafeTECKS on a real-world large scale data generated by taxis in Beijing. Results show that our method not only outperforms the baselines, but also can ensure data security.
KeywordsMassive data Data safety Cloud computing Edge computing Share knowledge
This paper is supported by science and technology project of Beijing Municipal Commission of Transport and project of Beijing Municipal Science & Technology Commission (No. Z171100005117001).
- 3.Mao, Y., You, C., Zhang, J., et al.: Mobile edge computing: survey and research outlook. arXiv preprint arXiv:1701.01090 (2017)
- 5.Chang, H., Hari, A., Mukherjee, S., et al.: Bringing the cloud to the edge. In: 2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pp. 346–351. IEEE (2014)Google Scholar
- 8.Louk, M., Lim, H.: Homomorphic encryption in mobile multi cloud computing. In: 2015 International Conference on Information Networking (ICOIN), pp. 493–497. IEEE (2015)Google Scholar
- 13.Bahrami, M., Singhal, M.: A light-weight permutation based method for data privacy in mobile cloud computing. In: 2015 3rd IEEE International Conference on Mobile Cloud Computing, Services, and Engineering (MobileCloud), pp. 189–198. IEEE (2015)Google Scholar
- 17.Tzeng, E., Hoffman, J., Zhang, N., et al.: Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:1412.3474 (2014)
- 18.Long, M., Cao, Y., Wang, J., et al.: Learning transferable features with deep adaptation networks. arXiv preprint arXiv:1502.02791 (2015)
- 19.Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
- 20.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing systems, pp. 1097–1105 (2012)Google Scholar
- 21.Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM (1999)Google Scholar