Disclaimer: This is an example of a student written essay.
Click here for sample essays written by our professional writers.

Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of UKEssays.com.

Energy Efficient Firefly Scheduling in Green Networking

Paper Type: Free Essay Subject: Computer Science
Wordcount: 3403 words Published: 26th Mar 2018

Reference this

An energy Efficient Firefly Scheduling in Green Networking with Packet Processing Engines

  • S.S.Saranya
  • S.Srinivasan


Abstract-The investigation of force sparing system gadgets has been situated as of late on Theoretical With the point of controlling force consumption in center systems, we consider energy mindful gadgets ready to lessen their energy prerequisites by adjusting their execution. We propose new algorithm for scheduling the errand to diverse pipelines to adjust the energy consumption in systems administration. The firefly algorithm (FA) is a meta heuristic algorithm, propelled by the blazing conduct of fireflies. The main role for a firefly’s blaze is to go about as a sign framework to pull in different fireflies. blended whole number straight programming structure that takes care of the virtual topology issue under the correspondence delay imperative. A self-assertive optical system has been considered with distinctive separations between the hubs and diverse connection limits. We are utilizing after ventures to minimize the energy consumption (1) Packet Segmentation for maintaining a strategic distance from the impact in single pipeline. (2) Firefly Algorithm for streamlining the distinguishing the pipe line. The motivation behind our work is to minimize the energy consumption in general system.

KeywordsPacket Segmentation, Green network technologies, Firefly Algorithm.


The likelihood of adjusting system energy prerequisites to the real movement load. In fact, it is extraordinary that system connections and gadgets are by and large provisioned for occupied or surge hour load, which normally surpasses their normal usage by a wide edge. In spite of the fact that this edge is at times arrived at, system gadgets are composed on its premise and, subsequently, their energy consumption stays pretty much steady even in the vicinity of fluctuating activity load. In this manner, the key of any best in class force sparing criteria lives in alertly adjusting assets, gave at the system, connection, or supplies level, to current movement necessities and burdens. In this admiration, current green network technologies approaches[1] have been taking into account various energy related criteria, to be connected specifically to system gear and part interfaces.

Get Help With Your Essay

If you need assistance with writing your essay, our professional essay writing service is here to help!

Essay Writing Service

Green network technologies [3] is the act of selecting energy productive systems administration advancements and items, and minimizing asset use at whatever point conceivable. Green network technologies is an expansive term alluding to methods used to enhance systems administration or make it more proficient. This term reaches out to and spreads forms that diminish energy consumption, and additionally forms for rationing transfer speed or some other methodology that will at last decrease energy consumption and, in a roundabout way, cost. The issue of green network technologies has numerous critical applications, particularly as energy gets to be more lavish and individuals get to be more aware of the negative impacts of energy consumption on nature. A portion of the fundamental techniques connected with green network technologies include solidifying gadgets or generally streamlining an equipment setup.

Programming virtualization [4] and proficient server consumption can add to this general objective. Green network technologies could likewise incorporate such differing thoughts as remote work area, energy use in structures lodging equipment, or other fringe parts of a system foundation. Thoughts connected with green network technologies likewise address tech administrations or client connections that may at last be based on a system. This incorporates green pursuit or investigations of the energy consumption of web indexes, alongside numerous different sorts of examination of cutting edge systems and frameworks. As per various studies, IT can devour

up to 2 percent of a country’s aggregate energy generation. A great part of the exploratory information conveyed by ESnet and individual exploration and instruction (R&E) systems is C Gang et al. pick blaze stations which possess certain flame spread capacity and moderately minimal effort for separation as target blend. Fire stations touch base at mischance focuses and behavior salvage work, to minimize the misfortune in entire mishap. In routing , the forwarding engine [9], sometimes called the data plane, defines the part of the router architecture that decides what to do with packets arriving on an inbound interface.

Transmit data as fast as possible, return to Low-Power Idle– Highest rate provides the most energy-efficient transmission (Joules/bit)– LP_IDLE consumes minimal power (Watts).Energy savings come from cycling between Active & Low-Power Idle – Power is reduced by turning OFF unused circuits during LP_IDLE (e.g. portions of PHY, MAC, interconnects, memory, CPU).Energy consumption scales with bandwidth consumption. Raffaele Bolla et al. [10] raise the same concern in their work save energy by scaling their traffic processing capacities through AR and LPI mechanisms.

The rest of the paper is organized as follows: Section II describes the Related work of less energy consumption Based on Green network technique. Section III portrays the Investigation of proposed methods. The Test results are shown in the Section IV.


FLARE strategy [10] is conceivable to methodicallly cut a TCP stream crosswise over numerous ways without creating packet reordering. Srikanth Kandula et al. (2007) FLARE, another movement part algorithm. FLARE misuses a straightforward perception. Consider burden adjusting movement more than a set of parallel ways. On the off chance that the time between two progressive packets is bigger than the greatest deferral contrast between the parallel ways, one can course the second packet and resulting packets from this stream on any accessible way with no danger of reordering. In this way, as opposed to exchanging packets or streams, FLARE switches packet blasts, called owlets. Element burden adjusting needs conspires that part activity crosswise over various ways at a fine granularity. Current movement part plots, be that as it may, display a tussle between the granularity at which they segment the activity and their capacity to stay away from packet reordering. Packet based part rapidly doles out the sought burden offer to every way.

Power administration abilities [2] inside architectures and segments of system gear. R. Bolla et al.(2007) considering the two principle sorts of force administration equipment help, today accessible in the biggest piece of COTS processors and under quick improvement in other equipment advances [11] (e.g., system processors, ASIC and FPGA). These force administration advancements individually permit minimizing force consumption when no exercises are performed (in particular, “unmoving” enhancements), and to change the exchange off in the middle of execution and energy when the equipment is dynamic and performing operations (specifically, “power state” improvements). These sorts of force administration backing are by and large acknowledged at the equipment layer by fueling off sub-segments, or by changing the silicon working recurrence and voltage.

Load Migration technique [8] With remote asset virtualization, numerous Mobile Virtual Network Operators (MVNOs) can be upheld more than an imparted physical remote system and movement stacks in a Base Station. Xiang Sheng et al. a general enhancement system to guide algorithm outline, which takes care of two sub issues, pipe task and burden distribution, in arrangement. For pipe task, this paper exhibit a rough guess algorithm For burden allotment, we introduce a polynomial-time ideal algorithm for an extraordinary situation where BSs are force relative and in addition two successful heuristic algorithms for the general case. Furthermore, this paper exhibit a successful heuristic algorithm that mutually tackles the two sub issues.

Fire asset scheduling model[15] on the ground of significant perils, where time constraint of real dangers and genuine circumstance of flame asset can be considered on all sides. Along these lines, in accordance with the bear capable misfortune and time restriction of significant risks, GOU Gang et al. pick flame stations which claim certain blaze spread capacity and generally ease for separation as target mix. Fire stations touch base at mischance focuses and behavior salvage work, to minimize the misfortune in entire mishap.

Linux piece system subsystem [12] the Tx/Rx Soft IRQ and Q plate are the connectors between the system stack and the net gadgets. A configuration confinement is that they accept there is just a solitary passage point for every Tx and Rx in the hidden equipment. In spite of the fact that they function admirably today, they won’t later on. Present day system gadgets (for instance, E1000 and IPW 2200 prepare two or more equipment Tx lines to empower transmission parallelization or MAC-level QoS. These equipment characteristics can’t be upheld effectively with the current system

subsystem. Z. Yi et al. (2007) depicts the outline and execution for the system multi line patches submitted to mailing records early not long from now, which included the progressions for the system scheduler, Q circle, and non specific system center APIs.


A pipeline is a situated of information transforming components joined in arrangement, where the yield of one component is the info of the following one.

Op 1

In 1


In 2

In 3

Op 2

In 4

Fig 1.Parallel pipeline

Fig 1.shows the components of a pipeline are regularly executed in parallel or in time-cut manner; all things considered, some measure of cradle stockpiling is frequently embedded between components. The packet preparing framework is particularly intended for managing the system movement.

Pipe 1



Pipe 2


Pipe 3


Pipe 4

Fig 2. Framework Architecture

Fig2. shows System Architecture speaks to Parallel Processing of diverse pipe lines. In this framework, Fire fly Scheduling algorithm for viably plan the info movement load for burden adjusting. The Distributed Load transformed by the distinctive pipelines.

Packet segmentation enhances system execution by part the packets in got Ethernet outlines into discrete cushions. Packet segmentation may be in charge of part one into different so that solid transmission of every one can be performed exclusively. Segmentation may be obliged when the information packet is bigger than the most extreme transmission unit backed by the system.

The packet preparing framework can be prepared in any layer of the system, either in the top of the line center switches or in the LAN switches. The adaptability of the framework originates from the programmable components inside it, i.e. NPs. Furthermore a progression of stacked system conventions ensure its capacity to accomplish the execution particular.

Fire fly algorithm is utilized for packet scheduling. The firefly algorithm [14] is a meta heuristic algorithm, enlivened by the blazing conduct of fireflies. The main role for a firefly’s blaze is to go about as a sign framework to draw in different fireflies. In assignment task process, packets appropriate crosswise over parallel pipe lines. In this Module, divided Data lumps appointed into Queue for transforming of information. This oversees Work load dissemination to different parallel pipelines. This module words at transmitting end.


The firefly algorithm is a meta heuristic algorithm [16], roused by the blazing conduct of fireflies. The basic role for a firefly’s blaze is to go about as a sign framework to pull in different fireflies. Xin-She Yang [17]formulated this firefly algorithm by accepting:

1. All fireflies are unisexual, so that one firefly will be pulled in to all different fireflies;

2. Engaging quality is relative to their shine, and for any two fireflies, the less brilliant one will be pulled in by (and subsequently move to) the brighter one; then again, the splendor can diminish as their separation increments;

3. On the off chance that there are no fireflies brighter than a given firefly, it will move arbitrarily.

The splendor ought to be connected with the target capacity.

Firefly algorithm is a nature-enlivened meta heuristic enhancement algorithm.

B. Algorithm Description

The pseudo code can be summarized as:


1) Objective function:

2) Generate an initial population of fireflies

3) Formulate light intensity so that it is associated with f

(for example, for maximization problems, or simply

4) Define absorption coefficient

While (t < Max Generation)

for i = 1 : n (all n fireflies)

for j = 1 : n (n fireflies)

if ,

move firefly i towards j;

end if

Vary attractiveness with distance r via exp ;

Evaluate new solutions and update light intensity;

end for j

end for i

Rank fireflies and find the current best;

end while

Post-processing the results and visualization;


The main update formula for any pair of two fireflies and is

where is a parameter controlling the step size, while is a vector drawn from a Gaussian or other distribution.

It can be shown that the limiting case corresponds to the standard Particle Swarm Optimization (PSO). In fact, if the inner loop (for j) is removed and the brightness is replaced by the current global best , then FA essentially becomes the standard PSO.

The should be related to the scales of design variables. Ideally, the term should be order one, which requires that should be linked with scales. For example, one possible choice is to use where is the average scale of the problem. In case of scales vary significantly, can be considered as a vector to suit different scales in different dimensions. Similarly, should also be linked with scales. For example,

Find Out How UKEssays.com Can Help You!

Our academic experts are ready and waiting to assist with any writing project you may have. From simple essay plans, through to full dissertations, you can guarantee we have a service perfectly matched to your needs.

View our services

The pipe line is a customer server transforming framework. Approaching streams can be taken care of by any subset of the pipelines. Every customer sent the information to server for preparing. The preparing is held in server and returns the outcome once more to server. The AR and LPI components for every pipeline to rapidly deal with the motor setup keeping in mind the end goal to ideally adjust its energy consumption regarding system execution.


This area portrays the execution investigation to accept the proposed algorithm. Exploratory results show the proficiency of the proposed Firefly algorithm.

Fig 3. Energy Consumption

Fig 3 delineates the Energy Consumption in parallel pipe line .The Energy consumption shifts in parallel pipelines as per time. In this work, Incoming packet are sectioned into various little packets and apportioned to diverse pipelines. These packets doled out to pipe lines taking into account size of the pieces by utilizing fire fly algorithm. The information packet 4 take 18 sec for handling and the information packet 5 take 18 sec for preparing. The less measure of time speak to the low energy consumption. Information packet 4,5 expend less energy.

Fig 4. Busy-Idle cycle

Fig4. Delineates the busy-idle state in parallel pipe line. We propose new scheduling algorithm that timetable the packets to diverse pipe lines in light of the limit of pipeline and pieces.


In this paper, we propose new scheduling algorithm to minimize the energy consumption in Parallel Pipe line System. The firefly algorithm (FA) is a meta heuristic algorithm, roused by the glimmering conduct of fireflies. The main role for a firefly’s glimmer is to go about as a sign framework to draw in different fireflies. Firefly-based algorithms for scheduling undertaking diagrams and occupation shop scheduling obliges less figuring than all other meta heuristics. Firefly algorithm can tackle streamlining issues in dynamic situations proficiently. The accomplished results show how the proposed model can viably speak to energy and system mindful execution files. In addition, additionally an improvement system in view of the model has been proposed and tentatively assessed.


[1] Raffaele Bolla, Roberto Bruschi, Alessandro Carrega, and Franco Davoli “Green Networking With Packet Processing Engines: Modeling and Optimization” IEEE/ACMTransaction Networking,Vol.22,No.1,Feb2014.

[2] A.Bolla and R. Bruschi, “Energy-aware load balancing for parallel packet processing engines,” in Proc. 1st IEEE GREENCOM, Sep. 2011, pp. 105–112.

[3] “LowEnergyConsumptionNETworks(ECONET)project,”2010[Online]. Available: http://www.econet-project.eu

[4] “Energy eFFIcient teChnologIEs for the Networks of Tomorrow (EFFICIENT) project,” 2010 [Online]. Available: http://www.tnt.dist. unige.it/efficient

[5] “GreeningtheNetwork(GreenNet)project,”2012[Online].Available: http://www.tnt.dist.unige.it/greennet

[6] B. Heller et al. , ElasticTree: saving power in data center networks, Proceedings of USENIX NSDI’2010.

[7] S. Kandula, D. Katabi, S. Sinha, and A. Berger, “Dynamic load balancing without packet reordering,” Comput. Commun. Rev., vol. 37, pp. 51–62, Mar. 2007.

[8] R.Bolla,R.Bruschi,A.Carrega,andF.Davoli,“Greennetworktechnologies and the art of trading-off,” in Proc. 30th IEEE INFOCOM Workshops, Shanghai, China, Apr. 2011, pp. 301–306.

[9] R. Bolla, R. Bruschi, F. Davoli, and F. Cucchietti, “Energy efficiency in the future Internet: A survey of existing approaches and trends in energy-aware fixed network infrastructures,” IEEE Commun. Surveys Tut., vol. 13, no. 2, pp. 223–244, 2nd Quart., 2011.

[10] Z. Yi and P. Waskiewicz, “Enabling Linux network support of hardwaremultiqueuedevices,”inProc.LinuxSymp.,Ottawa,ON,Canada, Jun. 2007, vol. 2, pp. 305–310.

[11] J. Kennedy and R. Eberhart, Particle swarm optimisation, in: Proc. of the IEEE Int. Conf. on Neural Networks, Piscataway, NJ, pp. 1942-1948 (1995).

[12] S. Nandy, P. P. Sarkar, A. Das, Analysis of nature-inspired firefly algorithm based back-propagation neural network training, Int. J. Computer Applications, 43(22), 816 (2012).

[13] S. Palit, S. Sinha, M. Molla, A. Khanra, M. Kule, A cryptanalytic attack on the knapsack cryptosystem using binary Firefly algorithm, in: 2nd Int. Conference on Computer and Communication Technology (ICCCT), 15-17 Sept 2011, India, pp. 428432 (2011).

[14] R.Bolla,R.Bruschi,F.Davoli,andA.Ranieri,“Energy-awareperformanceoptimizationfornext-generationgreennetworkequipment,”in Proc. 2nd ACM SIGCOMM PRESTO, Barcelona, Spain, Aug. 2009, pp. 49–54.

[15] X. S. Yang, Nature-Inspired Metaheuristic Algorithms, Luniver Press, UK, (2008).

[16] X. S. Yang, Firefly algorithms for multimodal optimisation, Proc. 5th Symposium on Stochastic Algorithms, Foundations and Applications, (Eds. O. Watanabe and T. Zeugmann), Lecture Notes in Computer Science, 5792: 169-178 (2009).

[17] X. S. Yang, Engineering Optimisation: An Introduction with Metaheuristic Applications, John Wiley and Sons, USA (2010).


Cite This Work

To export a reference to this article please select a referencing stye below:

Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.

Related Services

View all

DMCA / Removal Request

If you are the original writer of this essay and no longer wish to have your work published on UKEssays.com then please: