Projects

On Modeling, Analysis, and Optimization of

In packet communication systems, a header is attached to the transmitted packet at each layer. The overhead due to the transmission of the individual header can have a significant impact on the performance of the communication system especially when the system operates in heavy load. In order to increase data throughput, a number of packets sharing a single header can be aggregated into a frame. In this paper, we present a mathematical model for a packet aggregation system assuming a general distribution for the packet length. For a given header size, we obtain the minimum system utilization where packet aggregation improves the system performance. We also analyze the asymptotic behavior of such systems leading to a simple heuristic policy on the optimum aggregation level. It is shown that the impact of the variability of the packet length distribution on different system performance measures is rather insignificant when the system load is low or moderate.

Existing System:

Existing Packet queuing and Aggregation model with batch service which describes a packet aggregation process for Poisson arrivals and Phase-type service time distributions of the transmitted packets.. it is Simple expressions for bounds on the average total delay of a packet are obtained. Based on results of experiments with the analytical model, we provide the minimum header size for which packet aggregation improves the system performance. Didn’t show the accuracy of the bound on the average total packet delay and queuing status...

Proposed System:

In this paper, we present a mathematical model and it analysis of packet aggregation systems. Our model consists of a queuing system with batch service, where a complete performance analysis is provided.

This paper gives a detailed analysis of the packet aggregation system assuming that the packet arrivals follow a Poisson process. Although the generalization to other arrival processes is possible in principle, such analysis is quite space-intensive and is not presented here. We assume a general packet and header length distribution, where the Supplementary Variable Technique is used for the analysis. Therefore, constant header size is readily analyzed as a special case, which is the most common in packet communication systems.

The proposed model, we provide the analysis of the end-to-end delay of a packet and the distribution of the frame size. System performance measures. In addition, a simple heuristic supported by numerical results is provided to determine the optimum level of aggregation in such systems

Modules:

1. Packet transmission (Or) communication Module:
2. Packet aggregation Module:
3. Packet Queuing Model and analysis Module
4. Packet optimum level of aggregation Module:

1. Packet transmission (Or) communication Module:

Impact on the performance of a packet communication system especially when the system operates in heavy load. In order to reduce the overhead and increase data throughput, a number of packets can be aggregated into a frame at the time of encapsulation when the bit error rate is not very high. Otherwise, in a very noisy environment, the cost of frame retransmission due to transmission error may offset any performance gain from packet aggregation, since a frame consisting of a number of packets needs to be retransmitted instead of a single packet.

2. Packet aggregation Module:

Packet aggregation in real systems is Frame Relay (FR) systems, where every packet which is transmitted over the system is aggregated into the FR frame. FR also allows packing of small packets into a single Frame.

Fig: Packet Aggregation Network Measurements

We assume that the service (transmission) times of the header and the packet have general distributions and are independent. Let Y0 and Y1 be the service times of the header and the packet, respectively. The distribution function Bk(x) of the service time Yk is given by.

where ηk(t) is the intensity function. Let hn(mn) be the nth moment of the service time Y0(Y1). Conditioning that the server is busy at time t, we define the state of the server by

As described in more details in the next section, the number of packets in a frame (batch) is dictated by the number of the packets arriving during the service time of the previous frame. Therefore, in our model, the service times of successive frames (batches) are dependent, which indicates a major difference from the existing queuing models.

3. Packet Queuing Model and analysis Module

Arriving packets are stored in an infinite buffer until they are transmitted to the destination peer. The transmission over the data link layer is done frame by frame. Data packets received from the network layer can be aggregated in a single frame. An overhead packet (header) is then appended in front of the
Frame. Therefore, each frame consists of a header and a number of data packets.

4. Packet optimum level of aggregation Module:

We showed that in the heavy load, system performance can be significantly improved if packet aggregation takes place. For a given header size, we found the minimum system utilization where aggregation improves the system performance. We also provided a simple heuristic result for the optimum level of aggregation. Our results were in close agreement with the exact numerical results derived from our mathematical model for such systems.

System Requirements:

Hardware Requirements:

PROCESSOR : PENTIUM IV 2.6 GHz
RAM : 512 MB DD RAM
MONITOR : 15” COLOR
HARD DISK : 20 GB
FLOPPY DRIVE : 1.44 MB
CDDRIVE : LG 52X
KEYBOARD : STANDARD 102 KEYS
MOUSE : 3 BUTTONS

Software Requirements:

Front End : Java, Swing
Tools Used : Eclipse 3.3
Operating System: WindowsXP/7



Tags :
4.5
Your rating: None Average: 4.5 (2 votes)