Ameliorate the performance using soft computing approaches in wireless networks

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 13, No. 1, February 2023, pp. 502~510
ISSN: 2088-8708, DOI: 10.11591/ijece.v13i1.pp502-510  502
Journal homepage: http://ijece.iaescore.com
Ameliorate the performance using soft computing approaches
in wireless networks
Chandrika Dadhirao, Ravi Sankar Sangam
School of Computer Science and Engineering, VIT-AP University, Andhra Pradesh, India
Article Info ABSTRACT
Article history:
Received Jan 13, 2022
Revised Jul 28, 2022
Accepted Aug 25, 2022
Wireless sensor networks are an innovative and rapidly advanced network
occupying the broad spectrum of wireless networks. It works on the
principle of “use with less expense, effort and with more comfort.” In these
networks, routing provides efficient and effective data transmission between
different sources to access points using the clustering technique. This work
addresses the low-energy adaptive clustering hierarchy (LEACH) protocol’s
main backdrop of choosing head nodes based on a random value. In this, the
soft computing methods are used, namely the fuzzy approach, to overcome
this barrier in LEACH. Our approach’s primary goal is to extend the
network lifetime with efficient energy consumption and by choosing the
appropriate head node in each cluster based on the fuzzy parameters. The
proposed clustering algorithm focused on two fuzzy inference structures,
namely Mamdani and Sugeno fuzzy logic models in two scenarios,
respectively. We compared our approach with four existing works, the
conventional LEACH, LEACH using the fuzzy method, multicriteria cluster
head delegation, and fuzzy-based energy efficient clustering approach
(FEECA) in wireless sensor network. The proposed scenario based fuzzy
LEACH protocol approaches are better than the four existing methods
regarding stability, network survivability, and energy consumption.
Keywords:
Energy efficiency
Head node
Mamdani
Network lifetime
Sugeno
Wireless sensor networks
routing protocol
This is an open access article under the CC BY-SA license.
Corresponding Author:
Chandrika Dadhirao
School of Computer Science and Engineering, VIT-AP University
near Vijayawada, 522237, Andhra Pradesh, India
Email: chandrikad10@gmail.com
1. INTRODUCTION
Microcontrollers, networking technology, microelectromechanical systems, and nanotechnology
have developed novel sensing and communication systems, referred to as wireless sensor networks. These
new technologies have also contributed to the advancement of nanotechnology (WSNs). Figure 1 presents a
schematic representation of a wireless sensor network.
They are skilled with opportunity providing technology which pings its role in a wide range of
applications that bare minimum human intervention and play a critical function in making the future smarter.
It uses spatially distributed self-governing nodes that use sensors to track any circumstance, either physical or
environmental. WSN are continuing to be the most effective aid to sensing and monitoring tasks. The ability
to work in uncertain environments, easy implementation, and high performances are among the many reasons
for the popularity. Their primary benefit is the ability to be carried out to any discipline and in any
surroundings. Unlike popular networks that, for their application, require extensively stringent conditions. In
this mechanism, node energy, in conjunction with balancing glide, is the primary trouble in which sources are
scarcely to claim approximately a way to reduce strength intake and prolong the network lifetime for the
structure of WSNs using existing routing protocols.

Int J Elec & Comp Eng ISSN: 2088-8708 
Ameliorate the performance using soft computing approaches in wireless networks (Chandrika Dadhirao)
503
In terms of productivity in WSNs, routing protocols [1], [2] play a vital role. Routing is one of the
most challenging techniques on WSN. It is necessary to find the best path between the source node and the
target node. This method is the mathematical portrayal of human concepts. The main motto of any network is
the efficient and effective transmission of information between the source and the final destination. This
routing is one of the best solutions to provide an efficient and best path for wireless sensor networks. In
routing, in this work the clustering approach is chosen [3]–[9] for selecting the best way for intra-clustering
and inter-clustering. The classification of routing protocols [10]–[12] relies upon two critical elements, i.e.,
first off, primarily based on network structure and secondly based on the protocol operation. The chore of
discovering and retaining routes in WSNs is not minor, as energy restrictions and sudden changes in a node.
WSN has attracted tremendous attention from academics and industry worldwide in the past, present, and
future. The wide range of applications [13] of WSNs is flora and fauna, military, industrial, urban,
environmental, health, education, entertainment [14]–[20]. WSN involve millions of nodes that operate
together, detecting and transmitting ambient knowledge to the base station [21]. Apart from those have
worked on multiple sink nodes in a WSN to increase the scalability and lifetime of the network [22]. Many
cluster heads choose a specific sink node and try to send their data to the sink simultaneously. Sujith et al.
[23] suggested an energy-efficient zone-based clustering algorithm for WSN. In their approach, they
considered zones as clusters and zone monitor as cluster head. Bagga et al. [24] has initiated an fuzzy logic-
based clustering routing (FLBCR) protocol as a routing scheme that applies fluctuating logic to determine the
likelihood of selecting a node as a cluster head (CH) with a variable setting existence a network. For instance,
an improved low-energy adaptive clustering hierarchy–mobile fuzzy (LEACH MF) protocol has been
addressed to prolong lifetime of wireless sensor networks and they show in their results that the proposed
modified parameter LEACH MF is better in performance and energy consumption [25]. This compared type1
and type2 fuzzy logic approach in choosing cluster head selection to increase the wireless sensor networks.
Figure 1. Layout of the wireless sensor network
2. METHOD
The main steps of our proposed fuzzy based LEACH approach are discussed in this section. In
proposed algorithm, optimum number of head nodes are chosen using Kopt from (1).
𝐾𝑜𝑝𝑡 =
√𝑏
√2∗𝑇ℎ
∗ 𝜃0 ∗
𝑀
𝑑𝐵𝑆2 (1)
where b is the number of nodes, Th is the user defined threshold value, θ0 is the computed ratio of energy
dissipated in the free space (µ) by the energy dissipated in multi path (ϑ), M is the product of area of the
network and sink coordinates, and dBS2
is the first form of Euclidean distance of respective node to the sink
node. The current heads of nodes calculate their W i (output fuzzy parameter) value using the fuzzy method
and broadcast the current head node (HN) message to all nodes coming under the communication range. The
member nodes choose the nearest HN and join it to form clusters, respectively using dBS (2):
𝐷𝑖𝑠𝑡𝑎𝑛𝑐𝑒 = min⁡
(√(𝑆𝑝 − 𝑆𝑞)
2
, (𝑆𝑞 − 𝑆𝑏𝑗)2) (2)

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 13, No. 1, February 2023: 502-510
504
where 𝑆𝑝 and 𝑆𝑞 are the length and width of the area of the network, respectively, and 𝑆𝑏𝑖 and 𝑆𝑏𝑗 are the sink
coordinates. The residual energy γRe is calculated based on node coordinates Bbij and user defined threshold
value ψ:
ϒ𝑅𝑒⁡ = ⁡𝛹 ∗ (∑ 𝐻𝑖
𝑏
𝑖=1 ) − (∑ 𝐶𝑗
𝑏
𝑗=1 ) (3)
where i,j are the coordinating positions of the node deployed in the network, b is the total number of nodes in
the area, H is x coordinate of the node, and C is the y coordinate of the node. The calculations of Dist and d
are shown in (4).
𝐷𝑖𝑠𝑡𝑚𝑖𝑛 = √∑ ((𝐻𝑖 − 𝑗)2 + (𝐶𝑖 − 𝐶𝑗)2)
𝑏
𝑞𝑖,𝑗=1
(4)
Initially, the cluster range will be considered as a value. Based on the calculated distance of the
nodes with respect to the mote is checked. Whether the distance is less than the range of the cluster
℧
Clusterrange in the network is calculated as (5):
ʊ𝐶𝑙𝑢𝑠𝑡𝑒𝑟𝑅𝑎𝑛𝑔𝑒 = 𝐷𝑖𝑠𝑡⁡ ≤⁡ʊ𝐶𝑙𝑢𝑠𝑡𝑒𝑟𝑅𝑎𝑛𝑔𝑒 (5)
𝑑 = √∑ ((𝑆𝑝𝑖 − (𝐻𝑖)2)⁡ + (𝑆𝑞𝑗 − (𝐶𝑗)2)⁡)
𝑏
𝑞𝑖,𝑗=1
(6)
where 𝑆𝑝 and 𝑆𝑞 are the length and width of the area of the network, respectively, and 𝑆𝑏𝑖 and 𝑆𝑏𝑗 are the sink
coordinates.
𝐶𝑜𝑠𝑡 =
𝐷𝑖𝑠𝑡(𝑇ℎ𝑛)
((𝑇ℎ𝑛)−1)+𝑑
(7)
where Thn is the tentative head node, d is the minimum distance. The CH generates a time division multiple
access (TDMA) schedule and sends it to its members until the CH and its members are fixed. The method of
choosing a head node by the use of fuzzy procedure is done in 4 steps for Scenario 1.
a. Input and fuzzification: We fetch the three input values to the fuzzy inference system using (3), (2) and
(7). Those input fuzzy parameters determine the cost of each enter based on the respective membership
feature µ.
b. Fuzzy inferences: We offer the membership values acquired to our if then rules to acquire to our new
fuzzy set output. Our fuzzy if then rules have more than one input and the bushy and operator which
selects the minimal of our 3 membership values.
c. Aggregation: The aggregation is a unity of all the results from the implementation of all rules received.
We use an OR fuzzy logic operator when we aggregate all our rules in our FIS as shown in Table 1. To
produce a new aggregate fuzzy set which will be used in the defuzzification stage, this operator chooses
the limit of the rule evaluation values.
d. Defuzzification: With a purpose to calculate the chance of each node, we mixture the effects of every rule
the usage of Mamdani technique. This manner is known as defuzzification which unearths the threat price
of each node to choose head node. In our proposed we use centroid method has been used for
defuzzification.
The following components constitute the type-2 fuzzy logic model is done in 6 steps for Scenario 2
used in this work.
a. Fuzzification module: This module maps the crisp input to a type-2 fuzzy set using the gaussian2
membership function.
b. Inference engine: This module evaluates the rules in the knowledge base against the type-2 fuzzy set
gotten from the fuzzification module to produce another type-2 fuzzy set.
c. Type reducer: Type reducer uses Karnik-Mendel algorithm to reduce an interval type-2 fuzzy set to
type-1 fuzzy set.
d. Defuzzification module: It maps the fuzzy set produced by the type of reducer to a crisp output using the
center of gravity defuzzification method.
e. Fuzzy knowledge base: This is a database of rules to be used by the inference engine.
f. Membership function: This mathematical equation helps the fuzzification module convert the crisp input
into a fuzzy set.
Figure 2 represents pseudocode for the proposed algorithm.

505
Table 1. The fuzzy if then rules
Rule no Residual energy Cost Distance Chance
1 High High Low High
2 High Medium Medium Very high
3 High Low High Medium
4 High High Low Medium
7 High High Low Medium
10 Medium High Low High
11 Medium Medium Medium Medium
12 Medium Low High High
19 Low High Low Low
20 Low Medium Medium Medium
21 Low Low High Very low
22 Low High Low Very low
23 Low Medium Medium Medium
25 Low High Low Very low
26 Low Medium Medium High
Figure 2. The pseudocode for the proposed approach
3. RESULTS AND DISCUSSION
All the following results in this paper are executed using MATLAB R2018a, which system
configuration is Intel i5 processor (2.7 GHz) with 16 GB memory running on Windows 10 operating system.
During the simulation process of data transmission between nodes from the source, through intermediate

 ISSN: 2088-8708
506
nodes and to the final destination nodes, each node uses its limited power, causing depletion. Any node
which has reached a specific limit value of user choice is considered dead. The simulation parameters for
performing our experiment are shown in Table 2.
Table 2. Simulation parameters
Type Parameter Value
Network topology Number of nodes 100, 200, 500, 1000
Number of clusters 20
Network coverage 100, 100, 50, 175
Deployment Random
Radio model Initial energy 2 J
Energy consumption per bit 50 nJ/bit
Energy loss in free space 100 pJ/bit/m2
Energy loss in multipath 0.0013 pJ/bit/m4
Application Simulation rounds 5000
Packet header times 25 bytes
Broadcast packet size 16 bytes
Data packet size 3200
Competition radius 25 m
Bandwidth 1 Mb/s
Here we compared three protocols fuzzy LEACH, multi-criteria cluster head delegation based on
fuzzy logic (MUCH) and the proposed fuzzy logic LEACH. Simulation was done in MATLAB simulator and
initially a total of 100 nodes are randomly scattered in a 100 m–by–100 m square area. Depicts the number of
sensor nodes alive in the network.
3.1. First node die
Figure 3 illustrates the point in time at which the first node is removed from the graph (FND). Based
on the findings of the study, we are able to conclude that the FND can be found using the existing approaches
even at the early rounds when compared with the methods that we have provided.
Figure 3. First node die
3.2. Quarter node die
Figure 4 illustrates the round at which a quarter of the nodes are removed from the graph (QND).
Based on the findings of the investigation, we can conclude that, in comparison to our suggested technique,
the existing methods produce at earlier rounds.
3.3. Half-node die
Figure 5 illustrates the round at which the half nodes are considered dead (HND). The findings of
the study allow us to conclude that, in comparison to the way that we have presented, the existing methods
produce HNDs at earlier rounds.
100 200 500 1000
179 178 143 119
358
178 145 129
183 171 160 138
1009
719
415
223
1599
1269
1096
1011
1779
1652
1494
1352
First Node Die
LEACH
LEACH USING FUZZY
MUCH
FEECA
Scenario1
Scenario2

507
Figure 4. Quarter node die
Figure 5. Half-node die
3.4. Number of nodes survived
Figure 6 shows the total number of nodes alive after completion of a certain number of simulation
rounds. It is observed that in initial fuzzy LEACH and one of the improved fuzzy LEACHs termed MUCH,
has 99% of nodes die after completing of 5000 rounds but in our proposed methods only 81% and 93% of
nodes die these results better energy efficiency of the nodes as well as improved network lifetime. The
comparison is made based on residual energy, lifetime of sensor nodes, and throughput. These three
parameters are used as comparison parameters. Figures 7 to 9 show the comparative analysis in the following
subsections, respectively.
Figure 6. Nodes alive after completion of 5,000 rounds
LEACH
LEACH
USING
FUZZY
MUCH
FEECA
Scenario1
Scenario2
279 548
261
1141
2344
2228
209
275 308
855
1801
2136
263
264
269 497
1698
2028
262 263
252 289
1668
1819
Quarter Node Die(QND)
100 200 500 1000
LEACH
LEACH
USING
FUZZY
MUCH
FEECA
Scenario1
Scenario2
455
915
449
1201
2798
2562
460
464
512
896
2303 2378
430
439
441 520
2084 2224
380 389 384
309
2042 2003
Half Node Die(HND)
100 200
500 1000
LEACH
LEACH USING FUZZY MUCH
FEECA
Scenario1
Scenario2
1
1
1
1
19
7
0
0
0 1
22
2
0
0
0
0
14
1
0
0
0
0
15
1
Number of Nodes Alive 100 200 500 1000

 ISSN: 2088-8708
508
3.5. Throughput
The term “universal performance” or “throughput” refers to the amount of packets that are received
by the sink using its available resource. As can be seen in Figure 7, our suggested protocol has a higher
throughput in comparison to LEACH, LEACH with fuzzy, MUCH, fuzzy-based energy efficient clustering
approach (FEECA), and both of our proposed methods, which are Scenario 1 and Scenario 2, respectively.
Figure 7. Performance of the node based on data transmission among nodes to mote
3.6. Lifetime of sensor nodes
The average network lifetime of the wireless network has been calculated using three mentioned
routing protocols. Here, the forwarder node is regarded in each round to be the node with the most
considerable rest energy. As Figure 8 shows, the average network life will be extended when the information
is transferred from nodes to sinks through our suggested protocol routing. In other words, in terms of average
network life, our proposed plan outperformed existing schemes.
Figure 8. Lifetime of the sensor nodes in the network
Round
Round

509
3.7. Residual energy
In this experiment, we have considered the average residual energy of all the nodes as a measure of
performance and compared our protocol to three others. Higher residual energy is essential to extend the
network life. From Figure 9, we can see that this residual average power is above the three mentioned
protocols.
Figure 9. Total energy dissipated among the nodes during each round
4. CONCLUSION
Wireless sensor networks are becoming relevant in a broad range of emerging technologies. One of
the challenges to WSNs is to reduce the use of resources and increase the networks' existence, for which
routing may be a remedy. As the propagation energy is proportional to the distance between the sender and
the receiver, the clustering mechanism minimizes energy use in routing. Using fuzzy reasoning, WSN can
resist complicated mathematical models and provide considerable stability in the networks life to deal with
uncertainty and interpretation. These suggested strategies described in both scenarios are a revision of the
option of LEACH to select the optimal number of head node selection and select the best head node selection
in any round during each cluster. The simulation findings indicate that our proposed solution delivers more
robust results than four other existing state-of-the-art algorithms and proves to be more scalable after
completing rounds in FND, QND, HND, and the number of nodes alive.
REFERENCES
[1] R. T. Ai-Zubi, N. Abedsalam, A. Atieh, and K. A. Darabkh, “Lifetime-improvement routing protocol for wireless sensor
networks,” in 2018 15th International Multi-Conference on Systems, Signals & Devices (SSD), Mar. 2018, pp. 683–687, doi:
10.1109/SSD.2018.8570628.
[2] J. N. Al-Karaki and A. E. Kamal, “Routing techniques in wireless sensor networks: a survey,” IEEE Wireless Communications,
vol. 11, no. 6, pp. 6–28, Dec. 2004, doi: 10.1109/MWC.2004.1368893.
[3] J. A. Patel and Y. Patel, “The clustering techniques for wireless sensor networks: a review,” in 2018 Second International
Conference on Inventive Communication and Computational Technologies (ICICCT), Apr. 2018, pp. 147–151, doi:
10.1109/ICICCT.2018.8473153.
[4] H. Yetgin, K. T. K. Cheung, M. El-Hajjar, and L. Hanzo, “A survey of network lifetime maximization techniques in wireless
sensor networks,” IEEE Communications Surveys & Tutorials, vol. 19, no. 2, pp. 828–854, 2017, doi:
10.1109/COMST.2017.2650979.
[5] K. A. Darabkh, W. S. Al-Rawashdeh, R. T. Al-Zubi, and S. H. Alnabelsi, “C-DTB-CHR: centralized density- and threshold-based
cluster head replacement protocols for wireless sensor networks,” The Journal of Supercomputing, vol. 73, no. 12, pp. 5332–5353,
Dec. 2017, doi: 10.1007/s11227-017-2089-4.
[6] L. XingGuo, W. JunFeng, and B. LinLin, “LEACH protocol and its improved algorithm in wireless sensor network,” in 2016
International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), Oct. 2016,
pp. 418–422, doi: 10.1109/CyberC.2016.87.
[7] V. Kadrolli and J. Agarkhed, “Soft computing routing techniques in wireless sensor network,” in 2016 2nd International
Conference on Advances in Electrical, Electronics, Information, Communication and Bio-Informatics (AEEICB), Feb. 2016,
pp. 748–751, doi: 10.1109/AEEICB.2016.7538395.
[8] B. Bhushan and G. Sahoo, “Routing protocols in wireless sensor networks,” in Computational intelligence in sensor networks,
2019, pp. 215–248.
Round

 ISSN: 2088-8708
510
[9] M. F. S. Yagoub, J. J. P. C. Rodrigues, O. O. Khalifa, A. B. Mohammed, and V. Korotaev, “Service redundancy and cluster-based
routing protocols for wireless sensor and mobile ad hoc networks: A survey,” International Journal of Communication Systems,
vol. 33, no. 16, 2020, doi: 10.1002/dac.4471.
[10] H. S. Bazzi, A. M. Haidar, and A. Bilal, “Classification of routing protocols in wireless sensor network,” in International
Conference on Computer Vision and Image Analysis Applications, Jan. 2015, pp. 1–5, doi: 10.1109/ICCVIA.2015.7351790.
[11] A. Krishnamoorthy and V. Vijayarajan, “Energy aware routing technique based on Markov model in wireless sensor network,”
International Journal of Computers and Applications, vol. 42, no. 1, pp. 23–29, 2020, doi: 10.1080/1206212X.2017.1396423.
[12] J. Tan et al., “An adaptive collection scheme-based matrix completion for data gathering in energy-harvesting wireless sensor
networks,” IEEE Access, vol. 7, pp. 6703–6723, 2019, doi: 10.1109/ACCESS.2019.2890862.
[13] D. Kandris, C. Nakas, D. Vomvas, and G. Koulouras, “Applications of wireless sensor networks: An up-to-date survey,” Applied
System Innovation, vol. 3, no. 1, Feb. 2020, doi: 10.3390/asi3010014.
[14] K. A. Darabkh and J. N. Zomot, “An improved cluster head selection algorithm for wireless sensor networks,” in 2018 14th
International Wireless Communications & Mobile Computing Conference (IWCMC), Jun. 2018, pp. 65–70, doi:
10.1109/IWCMC.2018.8450446.
[15] I. A. T. Hashem et al., “The role of big data in smart city,” International Journal of Information Management, vol. 36, no. 5,
pp. 748–758, Oct. 2016, doi: 10.1016/j.ijinfomgt.2016.05.002.
[16] D. P. Agrawal, “Applications of sensor networks,” in Embedded Sensor Systems, vol. 8, no. 9S3, Singapore: Springer Singapore,
2017, pp. 35–63.
[17] B. Rashid and M. H. Rehmani, “Applications of wireless sensor networks for urban areas: A survey,” Journal of Network and
Computer Applications, vol. 60, pp. 192–219, Jan. 2016, doi: 10.1016/j.jnca.2015.09.008.
[18] S. R. Jino Ramson and D. J. Moni, “Applications of wireless sensor networks — A survey,” in 2017 International Conference on
Innovations in Electrical, Electronics, Instrumentation and Media Technology (ICEEIMT), Feb. 2017, pp. 325–329, doi:
10.1109/ICIEEIMT.2017.8116858.
[19] T. Khan et al., “A novel and comprehensive trust estimation clustering based approach for large scale wireless sensor networks,”
IEEE Access, vol. 7, pp. 58221–58240, 2019, doi: 10.1109/ACCESS.2019.2914769.
[20] S. S. Desai and M. J. Nene, “Node-level trust evaluation in wireless sensor networks,” IEEE Transactions on Information
Forensics and Security, vol. 14, no. 8, pp. 2139–2152, Aug. 2019, doi: 10.1109/TIFS.2019.2894027.
[21] D. Agrawal and S. Pandey, “Optimization of the selection of cluster‐head using fuzzy logic and harmony search in wireless sensor
networks,” International Journal of Communication Systems, vol. 34, no. 13, Sep. 2021, doi: 10.1002/dac.4391.
[22] A. Shahidinejad and S. Barshandeh, “Sink selection and clustering using fuzzy-based controller for wireless sensor networks,”
International Journal of Communication Systems, vol. 33, no. 4, Aug. 2020, doi: 10.1002/dac.4557.
[23] A. Sujith, D. R. Dorai, and V. N. Kamalesh, “Energy efficient zone‐based clustering algorithm using fuzzy inference system for
wireless sensor networks,” Engineering Reports, vol. 3, no. 4, Apr. 2021, doi: 10.1002/eng2.12310.
[24] S. Bagga, A. Goyal, G. Gupta, and D. K. Sharma, “FLBCR: Fuzzy logic based clustering routing protocol,” in 2019 10th
International Conference on Computing, Communication and Networking Technologies (ICCCNT), Jul. 2019, pp. 1–7, doi:
10.1109/ICCCNT45670.2019.8944547.
[25] S. Sharma and N. Mittal, “An improved LEACH-MF protocol to prolong lifetime of wireless sensor networks,” in 2018 IEEE 8th
International Advance Computing Conference (IACC), Dec. 2018, pp. 174–179, doi: 10.1109/IADCC.2018.8692096.
BIOGRAPHIES OF AUTHORS
Chandrika Dadhirao is a research scholar in the School of Computer Science
and Engineering at VIT-AP University, near Vijayawada. Her areas of interest are wireless
sensor networks, soft computing, and cloud computing. She can be contacted at email:
chandrikad10@gmail.com.
Ravi Sankar Sangam is an associate professor in the School of Computer
Science and Engineering at VIT-AP University, near Vijayawada. His specialization areas are
data clustering and mining, wireless sensor networks. He can be contacted at email:
srskar@gmail.com.

Ameliorate the performance using soft computing approaches in wireless networks

More Related Content

Similar to Ameliorate the performance using soft computing approaches in wireless networks (20)

More from IJECEIAES (20)

Recently uploaded (20)

Ameliorate the performance using soft computing approaches in wireless networks