International Journal of Scientific & Engineering Research, Volume 5, Issue 12, December-2014 1217
ISSN 2229-5518
Survey of Taguchi Loss Function in Mobile
Ad hoc Network
Dheeraj rawat, Prof. Nitesh gupta, Prof. Sini Shibu
Abstract— In this paper we presents a method for handling multiple metrics and different network parameters simultaneously to analyze the loss factor of routing protocols in mobile ad hoc network(MANET) environments. We have used Taguchi’ losses function to determine the best parameters and routing over head simultaneously for AOMDV protocol. We have consider various different mobile ad hoc network parameters such as Terrain size, No of Nodes, No of source nodes, Packet transmission rate, Node speed, Pause time, Transmission range, Queue size, Antenna height and receiving power on a multiple signal to noise ratio (MNSR), performance and contribution level of parameters have been analyzed by analysis of variance (ANOVA).
Index Terms— AOMDV, Performance metric, Taguchi’s loss function
—————————— ——————————
A mobile ad hoc network is an autonomous communication system of mobile nodes having radio transmitters and receiv- ers. The device is free to move in any direction independently and links among these devices changed normally. Ad hoc is a Latin word and it standing for “for this purpose”. Mobile ad hoc network could be a wireless network that transmits from pc to pc. In ad-hoc networks, some pairs of terminals might not be able to communicate directly with one another and re- laying of some messages is needed, in order that they are de- livered to their destinations. Such networks square measure usually remarked as multi-hop or store-and-forward net- works. Mobile hosts and wireless working hardware have be- come wide out there and in depth work has been done recent- ly in group action these parts into ancient networks like the web. Usually events square measure used as means that of communications between simulation entities.
MANET is a form of independent dynamic structured net- work, where each node treats like router and freely moves in the environment so that dynamic behavior a rises the problem for measuring quality of service dependent parameter. This problem motivates the work for identification of quality of service dependent parameter using Taguchi loss function and provides solution for that problem.
Taguchi’s loss perform parameter style could be a powerful technique to see the best combination parameters. The most objective is to use Taguchi style for predicting the higher pa- rameters which will optimize the performance metric through the setting of style parameters and cut back the sensitivity of the system performance to the supply of variation. Taguchi parameter style uses a special style of orthogonal arrays (OAs) to check the complete factors with little variety of experiment solely. The world organization have a balanced property dur- ing which each parameter setting happens an equivalent vari- ety of times for each setting of all alternative parameters with-
in the experiment. The world organization permits researchers or designers to check several parameters at the same time and might be accustomed estimate the consequences of every pa- rameter freelance of the opposite parameters. Taguchi used a loss perform to calculate the deviation between the experi- mental price and therefore the desired price. The loss perform is completely different for various objective functions. Typical- ly, higher turnout and lower the quantity of packet drop and routing overhead area unit want ready in ad-hoc networks system. Therefore, to get best ad-hoc network style, the larger- the-better performance metric for turnout should be taken. Taguchi methodology emphasizes the importance of the cen- ter (parameter style) stage within the total style process; a stage that is commonly neglected in industrial design observe. The methodology involves the identification of these parame- ters that area unit underneath the management of the design- er, then the institution of a series of experiments to ascertain that set of these parameters that has the best influence on the performance and variation of the planning. The sty leer so is ready to spot the elements of a design that most influence the required outcome of the planning method.
The second connected side of the Taguchi methodology - the Taguchi loss perform or quality loss perform maintains that their 'associate increasing loss each for producers and for soci- ety at massive, that could be a perform of the deviation or var- iability from the best or target price of any style parameter. The larger the deviation from target, the larger is that the loss. The idea of loss being keen about variation is well established in style theory, and at a systems level is expounded to the ad- vantages and price related to responsibility.
In this section the previous work that has done in this field is
IJSER © 2014 http://www.ijser.org
International Journal of Scientific & Engineering Research, Volume 5, Issue 12, December-2014 1218
ISSN 2229-5518
dicuussed.
Hazura Mohamed, Muhammad Hisyam Lee, Shaharuddin
Salleh, Bahrom Sanugi and Mazalan Sarahintu [1] “Ad-Hoc
Network Design with Multiple Metrics Using Taguchi’s Loss
Function” in this title we presents an approach for tackling
multiple metrics and various network parameters simultane-
ously to investigate the performance of wireless ad-hoc net-
work routing protocols. The study uses Taguchi’s loss function
to determine the best condition in yielding maximum
throughput and minimum packet drop and routing overhead
simultaneously for dynamic source routing (DSR) protocol.
Studying the parameters one at a time or by trial and error
until a first feasible design is found seems to be a common
approach to design optimization. In this title, the impact of ad-
hoc network parameters such as terrain, network size, number
of sources, packet transmitted rates, node speed and pause
time on a multiple signal to noise ratio are investigated simul-
taneously.
Pushpraj Pate, Vijay Prakash [2] “Review of Dependent Pa- rameters Using Taguchi Loss Function of AOMDV Routing Protocol in MANET Environment” In this title we presents a method for handling multiple metrics and different network parameters simultaneously to analyze the loss factor of rout- ing protocols in mobile ad hoc network(MANET) environ- ments. We have used Taguchi’ loss function to determine the best parameters giving maximum throughput, packet delivery ratio (PDR), average delay, DROP and routing over head sim- ultaneously for AOMDV protocol. In this title we have consid- er various different mobile ad hoc network parameters such as Terrain size, No of Nodes, No of source nodes, Packet trans- mission rate, Node speed, Pause time, Transmission range, Queue size, Antenna height and receiving power on a multiple signal to noise ratio (MNSR), performance and contribution level of parameters have been analyzed by analysis of variance (ANOVA).
Hazura Mohamed, Muhammad Hisyam, Bahrom Sanugi, [3] “Taguchi Approach for Performance Evaluation of Routing Protocols in Mobile Ad Hoc Networks” In this title we evalu- ate the performance of Dynamic Source Routing (DSR) proto- col in mobile ad hoc network for single-performance metric and multi-performance metrics. Using Taguchi design of ex- periment, we quantify the main effects of six influential factors (terrain, network size, node speed, pause time, number of sources and transmission rates) on two performance metrics (throughput and end-to-end delay). The analysis of means (ANOM) and analysis of variance (ANOVA) on single and multi-response signal to noise ratio are employed to determine the best conditions required and to identify the level of im- portance of factors in order to obtain the best performance of DSR protocol.
Raghuraman S, Thiruppathi K,Panneerselvam T Santosh S [4] “Optimization Of Edm Parameters Using Taguchi Method And Grey Relational Analysis for Mild Steel Is 2026” This title aims to investigate the optimal set of process parameters such as current, pulse ON and OFF time in Electrical Discharge Ma- chining (EDM) process to identify the variations in three per-
formance characteristics such as rate of material removal, wear rate on tool, and surface roughness value on the work material for machining Mild Steel IS 2026 using copper electrode. Based on the experiments conducted on L9 orthogonal array, analysis has been carried out using Grey Relational Analysis, a Taguchi method. Response tables and graphs were used to find the optimal levels of parameters in EDM process. The confirma- tion experiments were carried out to validate the optimal re- sults.
S. Kamaruddin, Zahid A. Khan and S. H. Foong [5] “Applica- tion of Taguchi Method in the Optimization of Injection Moulding Parameters for Manufacturing Products from Plas- tic Blend” This title we presents a study in which an attempt has been made to improve the quality characteristic (shrink- age) of an injection molding product (plastic tray) made from blends plastic (75% polypropylene (PP) and 25% low density polyethylene (LDPE)) by optimizing the injection molding parameters using the Taguchi method. The performance of the plastic trays is evaluated in terms of its shrinkage behavior. An orthogonal array (OA), main effect, signal-to-noise (S/N) ratio and analysis of variance (ANOVA) are employed to analyze the effect of injection molding parameters on the shrinkage behavior of the product.
Uğur Eşme [6] “Application of Taguchi Method for the Opti- mization of Resistance Spot Welding Process” This title reports on an investigation of the effect and optimization of welding parameters on the tensile shear strength in the resistance spot welding (RSW) process. The experimental studies were con- ducted under varying electrode forces, welding currents, elec- trode diameters, and welding times. The settings of welding parameters were determined by using the Taguchi experi- mental design method. The level of importance of the welding parameters on the tensile shear strength is determined by us- ing analysis of variance (ANOVA). The optimum welding pa- rameter combination was obtained by using the analysis of signal-to-noise (S/N) ratio. The confirmation tests indicated that it is possible to increase tensile shear strength significantly by using the Taguchi method.
Mr. Vinod Mahor, Prof. Sandeep Raghuwanshi [7] “Taguchi’s Loss Function Based Measurement of Mobile Ad-Hoc Net- work Parameters under AODV Routing Protocol” This title presents the application of Taguchi’s loss function approach, a multi-response optimization method, for achieving better per- formance during routing process of ad-hoc on demand dis- tance vector (AODV) routing protocol. Seven parameters namely terrain size, network size, number of sources, trans- mitted packet rates, pause-time, node speed, and transmission range are optimized with considerations of multiple perfor- mance metrics including maximum packet delivery ratio and minimum routing overhead, packet drop and end-to-end de- lay. Based on multiple signal-to noise ratio (MNSR), optimum levels of parameters have been identified and significant con- tribution of parameters is determined by analysis of variance (ANOVA).
IJSER © 2014 http://www.ijser.org
International Journal of Scientific & Engineering Research, Volume 5, Issue 12, December-2014 1219
ISSN 2229-5518
A routing protocol maintains the network topology for a Wireless Ad hoc Network. If a link breaks [3], routing protocols has the responsibility to repair that link in order to maintain the consistency of the network. Different routing protocols have various strategies to repair a broken link. The repair strategy is quite specific to each strategic routing protocol; therefore it is quite hard to analyze the pros and cons of each protocol. What we can do is to find the link break probabilities of different categories of routing protocols since the problem greatly influence the efficiency of a routing protocol. We will analyze the link break problem, the influence of the problem on each categories of routing protocol, and the incurred routing table update to them. The categories of most popular routing protocols, table-driven, on-demand and hybrid routing protocols, are discussed in this article [8, 9].
The pro-active routing protocols are the same as current Internet routing protocols such as the Routing Information Protocol, Distance-Vector, Open Shortest Path First and link- state. They attempt to maintain consistent, up-to-date routing information of the whole network. Each node has to maintain one or more tables to store routing information, and response to changes in network topology by broadcasting and propagating. Some of the existing pro-active ad hoc routing protocols are: Destination Sequenced Distance Vector (DSDV), Wireless Routing Protocol (WRP).
These protocols try to eliminate the conventional routing tables and consequently reduce the need for updating these tables to track changes in the network topology. When a source requires to a destination, it has to establish a route by route discovery procedure, maintain it by some form of route maintenance procedure until either the route is no longer desired or it becomes inaccessible, and finally tear down it by route deletion procedure. In pro-active routing protocols, routes are always available (regardless of need), with the consumption of signaling traffic and power. Some of reactive routing protocols are Ad hoc On-Demand Distance Vector (AODV), Dynamic Source Routing (DSR).
Hybrid protocols combine the features of reactive and proactive protocols. These protocols have the advantage of both proactive and reactive routing protocols to balance the delay which was the disadvantage of Table driven protocols and control overhead (in terms of control packages). Main feature of Hybrid Routing protocol is that the routing is
proactive for short distances and reactive for long distances. The common disadvantage of hybrid routing protocols is that the nodes have to maintain high level topological information which leads to more memory and power consumption. Examples: ZRP (Zone Routing Protocol).
Ad hoc On Demand Distance Vector (AODV) [10] is source initiated reactive protocol. It discovers and maintains routes only if and when necessary. Route discovery works as follows. When the source requires a path to a particular destination, it broadcasts a route request (RREQ) packet in the Wireless Ad hoc Network. Nodes receiving RREQ record a reverse route back towards the source, using the node from which the RREQ was received as the next-hop, and then re-broadcasts the RREQ. If the same RREQ is received more than once (via different routes), it is ignored. This way the RREQ packets are flooded to every node in the connected part of the network.
When the RREQ packet reaches the destination, it sends a route reply (RREP) packet back to the source, using the reverse route. If an intermediate node has an up-to-date route to the destination, it may also send a RREP packet back to the source on behalf of the destination. As the RREP packet follows the path back to the source, the corresponding forward route is created at each intermediate node towards the destination. Once the RREP packet reaches the source, data traffic can now flow along this forward route.
To prevent routing loops, AODV maintains a sequence number on each node. Any routing information transmitted on routing packets or maintained on a node is tagged with the last known sequence number for the destination of the route. AODV protocol guarantees the invariant that the destination sequence numbers in the routing table entries on the nodes along a valid route are always monotonically increasing. Other than preventing loops, sequence numbers also ensure freshness of routes. Given a choice of multiple routes, the one with a newer sequence number is always chosen.
An important feature of AODV is maintenance of timer based states in each node, regarding utilization of individual routes. A route is “expired” if not used recently. A set of predecessor nodes is maintained for each routing table entry, indicating a set of neighboring nodes that use that entry to route data packets. These nodes are notified with route error (RERR) packets when the next hop link breaks. Each predecessor node, in turn, forwards the RERR to its own set of predecessors, thus effectively erasing all routes using the broken link. This RERR is thus propagated to each source routing traffic through the failed link, causing the route discovery process to be reinitiated if routes are still needed.
IJSER © 2014 http://www.ijser.org
International Journal of Scientific & Engineering Research, Volume 5, Issue 12, December-2014 1220
ISSN 2229-5518
Mobile Ad-hoc network is depends on different service and parameter, such the service is routing independent decision, movement aware, energy information etc. and parameter is antenna type, height of antenna, receiving power, queue length, terrain size, number of node, source node’s, speed and data size etc. so all the characteristic are form of dynamicity of communication network than our proposed research is to identifies the maximum depended parameter to increase and decrease the performance of the network and on the bases of performance we state the equation for ideal network condition in various circumstances.
In our approach we create scenario in two level namely level1
and level2with 10 routing parameter and 5 Metrics like
throughput, packet delivery ratio (PDR), average delay, DROP and routing over head according to that we can create 210 design points but here we create only 10 design points and analyze the result and apply Taguchi loss function equation to measure the maximum loss dependent parameter.
In this paper, The Taguchi’ loss function is applied to accom- plish the more important parameters of the mobile ad hoc network under the consideration of multiple metrics. The most significant parameter followed by Receiving power, Source node, Transmission rate, Antenna height, Transmission range, Node speed, Pause time, No of nodes and Terrain size.
Routing Protocol” IEEE 4th ICCCNT – 2013 July 4-6, 2013, Tiruchengode, India.
[8] Anuj K. Gupta, Harsh Sadawarti, & Anil k. Verma, (2011) “Review of
various Routing Protocols for MANETs,” International Journal of
Information and Electrical Engineering, ISSN: 1109-2742, Vol. 1 No. 3, pp.
– 251-259.
[9] Anuj K. Gupta, Harsh Sadawarti, and Anil K. Verma “A Review of Routing Protocols for Mobile Ad hoc Networks” ACM Journal on WSEAS Transactions on Communications, ISSN: 1109-2742, Volume 10 Issue11, pp. 331-340, 2011, November 2011.
[10] Charles Perkins and Elizabeth Royer. Ad hoc on-demand distance vector routing. In Proceedings of the 2nd IEEE Workshop on Mobile Computing Systems and Applications, pages 90–100, Feb 1999.
[1] Hazura Mohamed, Muhammad Hisyam Lee, Shaharuddin Salleh,
Bahrom Sanugi and Mazalan Sarahintu“Ad-Hoc Network Design with Multiple Metrics Using Taguchi’s Loss Function” 2011 International Con- ference on Electrical Engineering and Informatics 17-19 July 2011, Ban- dung, Indonesia.
[2] Pushpraj Pate, Vijay Prakash “Review of Dependent Parameters Using Taguchi Loss Function of AOMDV Routing Protocol in MANET Environ- ment” International Journal of Innovative Research In Technology & Sci- ence | Volume 2, Number3 ISSN: 2321-1156.
[3] Hazura Mohamed, Muhammad Hisyam, Bahrom Sanugi, “Taguchi Approach for Performance Evaluation of Routing Protocols in Mobile Ad Hoc Networks” Journal of Statistical Modeling and Analytics Vol. 1 No. 2,
10-18, 2010.
[4] Raghuraman S, Thiruppathi K,Panneerselvam T Santosh S “optimiza- tion of edm parameters using taguchi method and grey relational analysis for mild steel is 2026” International Journal of Innovative Research in Science, Engineering and Technology Vol. 2, Issue 7, July 2013.
[5] S. Kamaruddin, Zahid A. Khan and S. H. Foong “Application of Taguchi Method in the Optimization of Injection Moulding Parameters for Manufacturing Products from Plastic Blend” IACSIT International Journal of Engineering and Technology, Vol.2, No.6, December 2010 ISSN: 1793-
8236.
[6] Uğur Eşme “Application of Taguchi Method for the Optimization of Resistance Spot Welding Process” The Arabian Journal for Science and Engineering, Volume 34, Number 2B 519.
[7]Mr.Vinod Mahor, Sandeep Raghuwanshi, “Taguchi’s Loss Function
Based Measurement of Mobile Ad-Hoc Network Parameters under AODV
IJSER © 2014 http://www.ijser.org