Abstract
The mandate of citizens for more socially responsible information systems that respect privacy and autonomy calls for a computational and storage decentralization. Crowd-sourced sensor networks monitor energy consumption and traffic jams. Distributed ledgers systems provide unprecedented opportunities to perform secure peer-to-peer transactions using blockchain. However, decentralized systems often show performance bottlenecks that undermine their broader adoption: propagating information in a network is costly and time-consuming. Optimization of cost-effectiveness with supervised machine learning is challenging. Training usually requires privacy-sensitive local data, for instance, adjusting the communication rate based on citizens’ mobility. This paper studies the following research question: How feasible is to train with privacy-preserving aggregate data and test on local data to improve cost-effectiveness of a decentralized system? Centralized machine learning optimization strategies are applied to DIAS, the Dynamic Intelligent Aggregation Service and they are compared to decentralized self-adaptive strategies that use local data instead. Experimental evaluation with a testing set of 2184 decentralized networks of 3000 nodes aggregating real-world Smart Grid data confirms the feasibility of a linear regression strategy to improve both estimation accuracy and communication cost, while the other optimization strategies show trade-offs.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Available af http://dias-net.org (last access: May 2018).
- 2.
\(B_{U}=c\) assumes that gossiping updates the view at least once per epoch.
- 3.
https://github.com/epournaras/DIAS and https://github.com/epournaras/PeerSamplingService (last access: May 2018).
- 4.
https://www.cscs.ch (last access: May 2018).
- 5.
https://scicomp.ethz.ch/wiki/Euler (last access: May 2018).
- 6.
http://www.ucd.ie/issda/data/commissionforenergyregulationcer/ (last accessed: May 2018).
- 7.
https://www.cs.waikato.ac.nz/ml/weka/ (last access: May 2018).
- 8.
http://scikit-learn.org/stable/ (last access: May 2018).
- 9.
Linear regression has an average precision, recall, f1-score of 0.8 and 0.96 for neural network. 273662 occurrences appear for save and 123557 for consume in linear regression. The respective occurences are 274108 and 123111 for neural network. Validation metrics documentation: http://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html (last access: May 2018).
References
Azimi, R., Sajedi, H.: A decentralized gossip based approach for data clustering in peer-to-peer networks. J. Parallel Distrib. Comput. 119, 64–80 (2018)
Barjini, H., Othman, M., Ibrahim, H., Udzir, N.I.: Shortcoming, problems and analytical comparison for flooding-based search techniques in unstructured P2P networks. Peer-to-Peer Netw. Appl. 5(1), 1–13 (2012)
Bhattarai, B., de Cerio Mendaza, I.D., Myers, K.S., Bak-Jensen, B., Paudyal, S.: Optimum aggregation and control of spatially distributed flexible resources in smart grid. IEEE Trans. Smart Grid (2017). https://ieeexplore.ieee.org/document/7886280/
Broder, A., Mitzenmacher, M.: Network applications of bloom filters: a survey. Int. Math. 1(4), 485–509 (2004)
Dagar, M., Mahajan, S.: Data aggregation in wireless sensor network: a survey. Int. J. Inf. Comput. Technol. 3(3), 167–174 (2013)
Dietzel, S., Petit, J., Kargl, F., Scheuermann, B.: In-network aggregation for vehicular ad hoc networks. IEEE Commun. Surv. Tutorials 16(4), 1909–1932 (2014)
Dwork, C., Roth, A., et al.: The algorithmic foundations of differential privacy. Found. Trends® Theor. Comput. Sci. 9(3–4), 211–407 (2014)
Galuba, W., Aberer, K., Despotovic, Z., Kellerer, W.: ProtoPeer: a P2P toolkit bridging the gap between simulation and live deployement. In: Proceedings of the 2nd International Conference on Simulation Tools and Techniques, p. 60. ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering) (2009)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)
Hameed, A., Khoshkbarforoushha, A., Ranjan, R., Jayaraman, P.P., Kolodziej, J., Balaji, P., Zeadally, S., Malluhi, Q.M., Tziritas, N., Vishnu, A.: A survey and taxonomy on energy efficient resource allocation techniques for cloud computing systems. Computing 98(7), 751–774 (2016)
Jelasity, M., Voulgaris, S., Guerraoui, R., Kermarrec, A.M., Van Steen, M.: Gossip-based peer sampling. ACM Trans. Comput. Syst. (TOCS) 25(3), 8 (2007)
Lee, A., Silvapulle, M.: Ridge estimation in logistic regression. Commun. Stat.-Simul. Comput. 17(4), 1231–1257 (1988)
Luo, L., Liu, M., Nelson, J., Ceze, L., Phanishayee, A., Krishnamurthy, A.: Motivating in-network aggregation for distributed deep neural network training. In: Workshop on Approximate Computing Across the Stack (2017)
Parmar, P.V., Padhar, S.B., Patel, S.N., Bhatt, N.I., Jhaveri, R.H.: Survey of various homomorphic encryption algorithms and schemes. Int. J. Comput. Appl. 91(8), 26–32 (2014)
Pilgerstorfer, P., Pournaras, E.: Self-adaptive learning in decentralized combinatorial optimization: a design paradigm for sharing economies. In: Proceedings of the 12th International Symposium on Software Engineering for Adaptive and Self-Managing Systems, pp. 54–64. IEEE Press (2017)
Pournaras, E., Nikolić, J.: On-demand self-adaptive data analytics in large-scale decentralized networks. In: 2017 IEEE 16th International Symposium on Network Computing and Applications (NCA), pp. 1–10. IEEE (2017)
Pournaras, E., Nikolic, J.: Self-corrective dynamic networks via decentralized reverse computations. In: Proceedings of the 14th International Conference on Autonomic Computing (ICAC 2017) (2017)
Pournaras, E., Nikolic, J., Omerzel, A., Helbing, D.: Engineering democratization in internet of things data analytics. In: Proceedings of the 31st IEEE International Conference on Advanced Information Networking and Applications-AINA-2017. IEEE (2017)
Pournaras, E., Vasirani, M., Kooij, R.E., Aberer, K.: Measuring and controlling unfairness in decentralized planning of energy demand. In: 2014 IEEE International Energy Conference (ENERGYCON), pp. 1255–1262. IEEE (2014)
Ramassamy, C., Fouchal, H.: A decision-support tool for wireless sensor networks. In: 2014 IEEE International Conference on Communications (ICC), pp. 7–11. IEEE (2014)
Wu, J., Jia, Q.S., Johansson, K.H., Shi, L.: Event-based sensor data scheduling: trade-off between communication rate and estimation quality. IEEE Trans. Autom. Control 58(4), 1041–1046 (2013)
Xiao, Z., Song, W., Chen, Q.: Dynamic resource allocation using virtual machines for cloud computing environment. IEEE Trans. Parallel Distrib. Syst. 24(6), 1107–1117 (2013)
Acknowledgements
This work is supported by the European Community’s H2020 Program under the scheme ‘ICT-10-2015 RIA’, grant agreement #688364 ‘ASSET: Instant Gratification for Collective Awareness & Sustainable Consumerism’ (http://www.asset-consumerism.eu).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Nikolić, J., Schöengens, M., Pournaras, E. (2019). Train Global, Test Local: Privacy-Preserving Learning of Cost-Effectiveness in Decentralized Systems. In: Xhafa, F., Barolli, L., Greguš, M. (eds) Advances in Intelligent Networking and Collaborative Systems. INCoS 2018. Lecture Notes on Data Engineering and Communications Technologies, vol 23. Springer, Cham. https://doi.org/10.1007/978-3-319-98557-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-98557-2_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98556-5
Online ISBN: 978-3-319-98557-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)