# Hybrid optimization with group learning to ensure stability of the VANET network based on performance analysis

### Section 1

Section 1 contains the results and discussion of proposed and implemented methods for improving machine learning using a mixed optimization strategy for predicting mobility in VANET. Project implementation (HFSA-VANET) is evaluated and compared with the current method (CRSM-VANET). Measured values ​​of delay, power consumption, projection, throughput and fairness are calculated and compared with proposals (HFSA-VANET) and current values ​​(CRSM-VANET)29 Methods. In addition, it is implemented by inducing NS2 and comparing the proposed algorithm with these two platforms, combined with a windows 10 PRO computer, the total RAM capacity is 10 GB, the processor used is Intel® Processor Core (7M) i3-6100CPU @ 3.70GHz. Performance metrics are examined in the next section.

#### performance metrics

Delays occur while a packet is traveling from its source to its destination.

$$delay = frac {length} {bandwidth}.$$

(19)

It is the number of packets lost as a result of a rogue node (DoS attack).

$$Drop = frac{Send; packet-Received ; packet} {Send; Package} (20) The throughput refers to the amount of data packets generated through the destination, which corresponds to the total value of packets generated by the sender node over a certain period of time. The formula is as follows:$$mathrm{productivity}hspace{0.17em} =hspace{0.17em}mathrm{received; data ; packet } times 8 / mathrm { data ; packet ; transition ; a period}

(21)

#### The results obtained through the node

The performance measures of the current technology and the proposed method are compared in the table below.

The primary objective of the performance measures is to assess the ability of the proposed model to predict mobility in VANET. According to Table 1, when compared and examined with the current methodology, the proposed method optimizes machine learning using a hybrid optimization strategy to predict that VANET navigation is more successful.

The lag, power consumption, decline, productivity, and fairness index for HFSA-VANET and CRSM-VANET are compared below.

The proposed technique achieves 99 J, 0.093690, 0.897708 for power consumption, delay value and drop value at node 20. Moreover, the new technology achieves a throughput of 31341, which is higher than the previous approach. The proposed method has a fairness of 7.000000, while the current method has a value of 8.000000. For power consumption, delay value, and drop value at node 60, the proposed approach achieves 47 J, 9.752925, 0.472094. In addition, the new method obtains a throughput of 31341, which is greater than the previous method. The proposed strategy has a fairness score of 3.000000 compared to 4.000000 for the current method. The proposed technique achieves 36 J, 10.902826, 0.376633 for power consumption and delay value and drop value at node 60. Moreover, the proposed technique achieves throughput of 28,423 compared to 26749 for the current method. The equity index value of 2.000000 for the proposed method is achieved against 4.000000 for the current method. For the power consumption, delay value and drop value at node 80, the proposed method achieves 11 J, 15.287826, 0.116375. Moreover, compared to the previous approach, the proposed strategy has a yield of 18,197. The proposed method has an equity index of 1.000000, while the current method has a fairness score of 2.000000. fig. 3, 4, 5, 6 and 7 are the delay, and the power consumption, drop, throughput, and fairness index are obtained through the node, respectively.

#### The results obtained by speed

The speed of the proposed technology is compared with the current technologies in terms of delay, power consumption, drop, throughput, and equity index. The measured values ​​are shown in the table below. Table 2 shows the velocity values ​​for both current and proposed techniques.

Speed ​​is compared to the delay shown in Figure 8, Speed ​​versus power is shown in Figure 9, Speed ​​is compared to the drop in Figure 10, Speed ​​versus productivity is shown in Figure 11, and Speed ​​versus Equity is shown in Figure 12 Speed ​​is compared with the delay, power, drop and productivity index In fairness, a graphic representation is presented below.

At speed 20, the proposed approach achieves 1980 J, 1.873793, 19.954160 in terms of power consumption, delay value, and drop value. In addition, the new method achieves a throughput of 150, which is greater than the previous method. The proposed method has a fairness score of 6.000000, while the current method similarly has a number of 6.000000. The proposed technique achieves 1880 J, 390.117000 and 18.883762 power consumption, delay value and speed drop value 40. Moreover, the new method achieves a transmission rate of 35, which is higher than the current method. The recommended method has a fair value of 3.000000, but the current method has a degree of 4.000000. At speed 60 the proposed method achieves 2220 J, 654.169557 and 22.597974 in terms of power consumption, delay, and drop value. In addition, the proposed strategy results in a yield of 22 versus 16 for the current method. The proposed method has an equity index of 2.000000, while the current method has an equity index of 3.000000. The recommended method achieves 880 J, 1223.026093, 9.309993 power consumption, delay value, speed drop value 80. Moreover, the new technique achieves throughput of 8 and the current technique achieves throughput of 6. The proposed technique has a degree of fairness of 0.000000, while the current method It has 2.000000. fig. 8, 9, 10, 11 and 12 are the delay, and the power consumption, drop, throughput, and fairness index are obtained by speed, respectively. Section 2 covers the results obtained through the MATLAB program.

### Section 2

This section covers empirical results obtained with MATLAB (Version 2020a) for performance evaluation using the NS2 tool. Furthermore, we also include an additional parameter to ensure the network lifetime of the proposed model. Therefore, it can be shown that the performance is very effective as the current technology. Here, the performance of the proposed model is evaluated using different machine learning approaches such as ANN-HFSA-VANET, SVM-HFSA-VANET, NB-HFSA-VANET, and DT-HFSA-VANET. Thus, the results of the proposed model can be compared and proven to be more effective than all other existing techniques.

Initially, the proposed model was evaluated using ANN-HFSA-VANET, SVM-HFSA-VANET, NB-HFSA-VANET and DT-HFSA-VANET separately. Next fig. Figures 13, 14, 15 and 16 show the graphical results for ANN, SVM, NB, and DT, respectively. On the other hand, to show the comparison based on the compilation of different machine learning techniques that compare the proposed method with individual graphical results.

#### ANN-HFSA-VANET Parameter Analysis

This section deals with the different types of ANN-HFSA-VANET parameters and is analyzed in the graph shown in Figure 13.

The above figure 13 shows the different performance analysis based on ANN-HFSA-VANET where (a) shows that the proposed technique has obtained minimum leakage, (b) shows that the maximum F1 score is obtained using the proposed technique, (c) shows That the maximum packet delivery ratio was obtained for ANN-HFSA-VANET and (d) and (e) show that the proposed ANN-HFSA-VANET generated high throughput and minimum delay, respectively.

#### Parameter analysis of a decision tree (DT) – HFSA-VANET

This section deals with the different types of decision tree parameters and they are analyzed in the graphs shown in Figure 14.

Figure 14 shows the analysis of DT-HFSA-VANET parameters. (a) shows the minimum dropout ratio of DT-HFSA-VANET, (b) deals with the maximum F1 score of DT-HFSA-VANET and analyzed, (c) shows the package delivery ratio for DT-HFSA-VANET and its plotted values, ( d) deals with the throughput ratio of DT-HFSA-VANET, (e) deals with the end-to-end delay of DT-HFSA-VANET. Standard parameters are analyzed and plotted in a graph and the values ​​are increased at the end of each parameter graph.

#### Navie Baves Parameter Analysis (NB) -HFSA-VANET

This section deals with the different types of Navie Baves parameter and they are analyzed in the graph shown in Figure 15.

Figure 15a shows the minimum dropout, (b) shows the maximum degree F1, (c) provides the maximum packet delivery ratio, (e) shows the minimum delay, respectively for the proposed NB-HFSA-VANET.

#### SVM Parameter Analysis

This section deals with the different types of SVM parameter and is analyzed in the graph shown in Figure 16.

In Fig. 16a, the dropout ratio was obtained with the minimum, (b) the F1 score was obtained with the maximum, (c) the packet delivery ratio was obtained with a maximum, and (e) shows the minimum delay.

### Parameters for analyzing different data types

This section deals with various data parameters and their analysis. The values ​​are plotted in a graph.

From Figure 17, the parameter analysis value for data types is checked and plotted in a graph where (a) it indicates the network lifetime obtained per second, (b) deals with the power consumption of data packets used per second, (c) deals with the input ratio Data types and their performance, (d) Deals with the packet delivery ratio for different types of data performance.