Survey of data aggregation techniques using soft computing in wireless sensor networks

In wireless sensor networks (WSN), data aggregation using soft computing methods is a challenging issue because of the security factors. When a node is compromised, it is easy for an adversary to inject false data and mislead the aggregator to accept false readings. Therefore there is a need for secure data aggregation. Although sufficient works on the survey of data aggregation in WSNs are done, it seems less satisfactory in terms of maintaining a secured data aggregation, and measuring accurate values. This study presents an up to date survey of major contributions to the security solutions in data aggregation which mainly use soft computing techniques. Here, classification of protocols is done according to the soft computing technique as: fuzzy logic, swarm intelligence, genetic algorithm and neural networks. Accuracy, energy consumption, cost reduction and security measures are the metrics used for the classification. Finally, the authors provide a comparative study of all aggregation techniques.

[1]  Emiliano De Cristofaro,et al.  FAIR: fuzzy-based aggregation providing in-network resilience for real-time wireless sensor networks , 2009, WiSec '09.

[2]  B. Aoued,et al.  Artificial neural network-based face recognition , 2004, First International Symposium on Control, Communications and Signal Processing, 2004..

[3]  Mohamed K. Watfa,et al.  A Sensor Network Data Aggregation Technique , 2009 .

[4]  Pranav B. Lapsiwala,et al.  Data Aggregation in Wireless Sensor Network , 2012 .

[5]  Jamal N. Al-Karaki,et al.  Data aggregation and routing in Wireless Sensor Networks: Optimal and heuristic algorithms , 2009, Comput. Networks.

[6]  Weilian Su,et al.  Data fusion algorithms in cluster-based wireless sensor networks using fuzzy logic theory , 2007 .

[7]  Subir Kumar Sarkar,et al.  Issues in Wireless Sensor Networks , 2008 .

[8]  Luo Juan,et al.  Ant System Based Anycast Routing in Wireless Sensor Networks , 2007, 2007 International Conference on Wireless Communications, Networking and Mobile Computing.

[9]  Tughrul Arslan,et al.  A novel application specific network protocol for wireless sensor networks , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[10]  Wei Zhao,et al.  A Multipath Routing Protocol Based on Clustering and Ant Colony Optimization for Wireless Sensor Networks , 2009 .

[11]  Yuan Feng,et al.  EDA: Event-oriented data aggregation in sensor networks , 2009, 2009 IEEE 28th International Performance Computing and Communications Conference.

[12]  Francesco Marcelloni,et al.  Reducing Power Consumption in Wireless Sensor Networks Using a Novel Approach to Data Aggregation , 2008, Comput. J..

[13]  R. B. Patel,et al.  Coverage and Connectivity Aware Neural Network Based Energy Efficient Routing in Wireless Sensor Networks , 2010, ArXiv.

[14]  Josep Domingo-Ferrer,et al.  Aggregation Methods to Evaluate Multiple Protected Versions of the Same Confidential Data Set , 2002 .

[15]  Sajid Hussain,et al.  Genetic algorithm for data aggregation trees in wireless sensor networks , 2007 .

[16]  Pramod K. Varshney,et al.  Data-aggregation techniques in sensor networks: a survey , 2006, IEEE Communications Surveys & Tutorials.

[17]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[18]  S. J. Huang,et al.  Enhancement of Hydroelectric Generation Scheduling Using Ant Colony System-Based Optimization Approaches , 2001, IEEE Power Engineering Review.

[19]  Khalil Shihab,et al.  A Backpropagation Neural Network for Computer Network Security , 2006 .