Professional Documents
Culture Documents
Neural Network Based Energy Efficient Clustering and Routing in Wireless Sensor
Networks
1
Neeraj Kumar, 2 Manoj Kumar, 3R.B. Patel
1,2
School of computer Science and Engineering, SMVD University, Katra (J&K), India
3
Department of Computer Science and Engineering, MM University, Mullana (Ambala), Haryana
E-mail: nehra04@yahoo.co.in,vermamk@gmail.com, patel_r_b@yahoo.com
*
, R.B. Patel
Shri Mata Vaishno Devi University, Katra(J&K), India
Abstract
power radio transmission is employed, wireless
Energy is a valuable resource in Wireless Sensor communication is far from being perfect [4,5,6].
Networks (WSNs). The status of energy consumption In this paper, we address the issue of energy-efficient
should be continuously monitored after network clustering and routing in WSNs using neural networks
deployment. The information about energy status can be with the objective of maximizing the network lifetime.
used to early notify both sensor nodes and Network First, we propose an efficient neural network based
Deployers about resource depletion in some parts of the clustering algorithm for WSNs. Secondly, we propose
network. It can also be used to perform energy-efficient routing and data transmission algorithm for WSNs. We
routing in WSNs. In this paper, we propose a neural define an efficient metric to be used in taking the
network based clustering and energy efficient routing in selection of next hop in routing. The problem is
WSN with the objective of maximizing the network lifetime. formulated as LP with specified constraints and routing
In the proposed scheme, the problem is formulated as metric
linear programming (LP) with specified constraints. Rest of the paper is organized as follows: Section 2
Cluster head selection is done using adaptive learning in discusses related work, section 3 defines the energy
neural networks followed by routing and data model used along with the defined routing metric and
transmission. The simulation results show that the problem formulation, Section 4 describe the proposed
proposed scheme can be used in wide area of solution, Section 5 provides the simulation and results
applications in WSNs. obtained, and finally Section 6 concludes the article.
Keywords: Sensor networks; Energy Efficient Routing,
Linear Programming, Neural Networks. 2. Related Work
There are number of clustering protocols have been
1. Introduction proposed in literature e.g. LEACH [7], PEGASIS [8],
Wireless Sensor Networks (WSNs) is a class of wireless HEED [9], EEUC [10], and FLOC [11]. The cluster
ad hoc networks in which sensor nodes collect, process, formation overhead of the clustering protocols includes
and communicate data acquired from the physical packet transmission cost of the advertisement, node
environment to an external Base-Station (BS). But these joining and leaving, and scheduling messages from
networks have several challenges such as sensor nodes in sensor nodes. All these protocols do not support adaptive
WSNs are normally battery-powered, and hence energy multi-level clustering, in which the clustering level
has to be carefully used in order to avoid early cannot be changed until the new configuration is not
termination of sensors’ lifetimes [1]. As such, the made. Therefore, the existing protocols are not adaptable
concept of continuous monitoring of network resources to the various node distributions or the various sensing
becomes a very important topic in WSNs. This same area. If the sensing area is changed by dynamic
concept has been already investigated in many other circumstances of the networks, the fixed-level clustering
environments, e.g., power plants [2], and in many protocols may operate inefficiently in terms of energy
distributed systems [3]. consumption.
Many recent experimental studies have shown that, Bandyopadhyay and Coyle [12] proposed the
especially in the field of sensor networks where low randomized clustering algorithm to organize sensors into
35
LP is to select a number of nodes with higher levels of
residual energy to form an optimal route, while Output Layer
Elected
minimizing the total routing cost. Let us label the base- CH
station as node 0 and label the CH nodes as nodes 1 to n,
where n is the total number of CH sensor nodes. So the
Competition
problem reduces to Layer
Minimize ∑ R_C
1≤i ≤ n
Subject to following constraints
δ ( s, w 2 ) δ ( s, wm )
∑ Dij −
1≤ j ≤ n
∑ D ji = bi ………….(4)
1≤ j ≤ n
δ ( s, w1 )
Dij ≥ 0 , 1 ≤ j ≤ n ………….….(5)
E ≤ Pmax imum ……………………(6)
Input Layer
Constraint (4) specifies the amount of data transmitted bi
between two nodes S i and S j , Constraint (5) specifies
amount of data to be transmitted from two nodes
S i and S j , Constraints (6) guarantees a minimum node Input Sensor node for election to be CH
36
routes, the sink node first generates a Route Discovery
1. Initialize the Vector S = {S1 , S 2 ,...., S m } of message that is broadcasted throughout the network.
sensor nodes competing for Cluster head. Upon receiving the broadcast message, each sensor node
//Processing at Input Layer introduces a delay proportional to its cost before it
2. Choose a winner k from sensor nodes as CH forwards the Route Discovery message to nodes in
range R . In this way a message arrives at each node
whose E i D is minimum as follows
along the desired minimum cost path. The cumulative
k = arg min{E i D } // Competition Layer cost of the routing path from the sink to the node
obtained in this phase is called the energy aware routing
3. Also E i D smallest Euclidean distance to BS i.e. cost of the node described in (3).
Ei D = k ∑| S
i =1, 2 ,...m
i − BS | , where k is proponality 1. Sort the paths p1 , p 2 ,....... p m according to
consumed by node S i in transmitting to the next node on 10. Calculate the value of R _ C from equation (3)
route l . For the sake of simplicity, we assume that this and R _ C updated = R _ C // Update value of routing
parameter depends only on the distance between the cost
transmitting and the receiving node. Then, we associate
11. Until | R − C updated − R − C |< δ 1 (predefined
with each route l an energy cost routing metric defined
in equation (3) above. The proposed algorithm scan all threshold)
routes in R and determine the least expensive route to 12. Update the values of energy for each data
reach the BS. A source will select the route that has the transmission as E C ,m Updated = E C , m
least energy consumption or the one that maximizes the
network lifetime. Until | E C ,m Updated − E C ,m |< δ 2
13. j = j + 1 // Update the counter of the paths
14. Until m > Destination _ node
Source Destination
15. Compare all paths using R _ C metric and select
the smallest one.
16. Send the data across the multiple paths defined.
Fig. 4: Multipath Routing Fig. 5: Algorithm for Routing and Data Transmission
Route Update
The cluster head nodes send their data over multi-hop Given m available paths, the overall energy consumption
paths to the sink as shown in Figure 4. To obtain these per packet, E, can be written as
37
E= ∑ E L , where E
i =1, 2...m
i i is the energy consumption for
one bit along path i and L is the packet length in bits. 100
Proposed
80 PEACH
5. Simulation and Results
have simulated the proposed scheme on ns-2[17]. Fig. 7: Number of alive nodes in PEACH and Proposed
Figure 6 presents the energy consumption of the Scheme
proposed scheme with well known PEACH clustering
protocol [16] when the maximum transmission range is 100
Proposed
60 m. The results demonstrate that the energy PEACH
consumption of proposed neural network based 90
0.10
70
Proposed
PEACH
0.08 60
Mean Residual Energy
50
0.06
40
0.04 50 100 150 200 250 300
Number of Nodes
Fig.6: Mean residual Energy in PEACH and Proposed presented in Figures 8 and 9. Proposed scheme has
Scheme highest percentage of residual energy compared with
PEACH protocol. Also, the variation in the mean of
Figure 7 presents the number of nodes alive when residual energy of proposed scheme is smaller than
using clustering in proposed scheme and PEACH. This PEACH
result directly reflects the network lifetime of the
wireless sensor networks. In the case of networks using
PEACH with the maximum transmission range r = 60 m,
where a node runs out of energy occurs nearly after 4000
rounds, while in propped scheme there is a slight
improvement and node runs out of energy in nearly
4200 rounds.
.
38
[6]. J. Zhao, R. Govindan, Understanding packet
0.10
delivery performance in dense wireless sensor
Proposed networks, in: Proceedings of the 1st ACM
PEACH
International Conference on Embedded Networked
0.08
Sensor Systems, SENSYS, ACM Press, Los
Angeles, CA, USA, 2003.
Mean Residual Energy
0.06
[7]. W.R. Heinzelman, A. Chandrakasan, H.
Balakrishnan, Energyefficient communication
0.04 protocol for wireless microsensor networks, in:
Hawaii International Conferenceon System
0.02
Sciences (HICSS), 2000.
[8]. S. Lindsey, C. Raghavendra, K.M. Sivalingam,
Data gathering algorithms in sensor networks
0.00
50 100 150 200 250 300 using energy metrics, IEEE Transactions on
Number of Nodes Parallel and Distributed Systems, 13: 9, 924–935,
Fig. 9: Mean residual Energy in PEACH and Proposed Scheme 2002.
after 1500 rounds [9]. O. Younis, S. Fahmy, Heed: A hybrid, energy-
efficient, distributed clustering approach for ad
6. Conclusions hoc sensor networks, IEEE Transactions on
This paper has proposed a neural network based energy Mobile Computing, 3: 4, 366–379, 2004.
efficient routing and clustering protocol for WSNs. The [10]. C. Li, M. Ye, G. Chen, J. Wu, An energy-efficient
selection of CH is done using adaptive learning unequal clustering mechanism for wireless sensor
mechanism. Simulations results show that it performs networks, in: Proceedings of the 2nd IEEE
better than existing routing protocol PEACH in terms of International Conference on Mobile Ad-hoc and
residual energy and .number of alive nodes. So the Sensor Systems (MASS’05), 2005.
proposed scheme can be used in wide areas of sensor [11]. M. Demirbas, A. Arora, V. Mittal, Floc: A fast
networks where energy efficiency is a critical issue. local clustering service for wireless sensor
networks, in: Orkshop on Dependability Issues in
References Wireless Ad Hoc Networks and Sensor Networks (
[1]. J.N. Al-Karaki, A.E. Kamal, Routing techniques DIWANS/DSN), 2004.
in wireless sensor networks: a survey, IEEE [12]. S. Bandyopadhyay, E.J. Coyle, An energy-
Wireless Communications, 11:6, 6–28, 2004. efficient hierarchical clustering algorithm for
[2]. P. Bates, Debugging heterogeneous distributed wireless sensor networks, in: IEEE INFOCOM,
systems using eventbased models of behavior, 3,1713–1723, 2003.
ACM Transactions on Computer Systems, 13: 1 [13]. T. Moscibroda, R. Wattenhofer, Maximizing the
1995. lifetime of dominating sets, in proc. of 19th
[3]. C. Frei, Abstraction techniques for resource International Parallel and Distributed Processing
allocation in communication networks, Ph.D. Symposium, 2005.
dissertation, Swiss Federal Inst. Technol. (EPFL), [14]. S.V. Pemmaraju, I.A. Pirwani, Energy
Lausanne, Switzerland, 2000. conservation in wireless sensor networks via
[4]. Cerpa, N. Busek, D. Estrin, Scale: A tool for dominating partitions, in: MOBIHOC, 2006.
simple connectivity assessment in lossy [15]. H.O. Tan, I. Korpeoglu, Power efficient data
environments, Tech. Rep. 21, Center for gathering and aggregation in wireless sensor
Embedded Networked Sensing, University of networks, Issue on Sensor Network Technology,
California, Los Angeles, CA, USA, September SIGMOD Record.
2003. [16]. Sangho Yi , Junyoung Heo , Yookun Cho , Jiman
[5]. M. Yarvis, W. Conner, L. Krishnamurthy, J. Hong, PEACH: Power-efficient and adaptive
Chhabra, B. Elliott, A. Mainwaring, Real-world clustering hierarchy protocol for wireless sensor
experiences with an interactive ad hoc sensor networks, Computer Communications, 30, 2842–
network, in: Proceedings of the 31st IEEE 2852, 2007.
International Conference on Parallel Processing [17]. K. Fall and K. Varadhan (editors), NS notes and
Workshops, ICPPW, IEEE Computer Society, documentation, The VINT project, LBL, Feb
Vancouver, BC, Canada, 2002. 2000, http://www.isi.edu/nsnam/ns/ .
39