Analysis of Workload Orchestrator for Vehicular Edge Computing

Performance Analysis of Workload Orchestrator for Vehicular Edge Computing

Implementation plan:
—————————

Scenario 1: ( with Transmission Power Control TPC)
————————————————————–

Step 1: Initially, we constructed a network with 1000 vehicles , 28 Edge data centers and one cloud server.

Step 2: Next, we generate Workload Data, Network Data , Vehicle Movement Data and Energy Data and store it as a dataset.

Step 3: Next, we implement Dynamic Power Scaling (DPS) with high, balanced and low power modes.

Step 4: Next, we Enhance Feature Engineering for ML Training to optimize energy-aware workload distribution, Also draw Confusion Matrix.

Step 5: Next, we dynamically adjust the transmission power and time spent in communication between edge nodes and base station using (TPC) Algorithm.

Step 6: Next, we offload and schedule the tasks using quality of service (QoS) to balance energy efficiency.

Step 7: Finally, we plot the following performance metrics,

7.1: Number of Vehicles Vs. RSSI(%)

7.2: Number of Vehicles Vs. Energy Consumption (J) For Vehicles/Edge Devices/Cloud (energy consumption at three layers)

7.3: Number of Vehicles Vs. Packet Delivery Ratio(%)

7.4: Number of Vehicles Vs. Task Completion Rate(%)

7.5: Number of Vehicles Vs. Packet Loss Ratio(%)

7.6: Number of Vehicles Vs. Latency(ms)

7.7: Number of Vehicles Vs. Failed Tasks for Navigation

7.8: Number of Vehicles Vs. Failed Tasks for Danger Assessment

7.9: Number of Vehicles Vs. Failed Tasks for Infotainment

7.10: Number of Vehicles Vs. Average QoS (%)

Scenario 2: ( without Transmission Power Control TPC)
——————————————————————-

Step 1: Initially, we constructed a network with 1000 vehicles , 28 Edge data centers and one cloud server.

Step 2: Next, we generate Workload Data, Network Data , Vehicle Movement Data and Energy Data and store it as a dataset.

Step 3: Next, we implement Dynamic Power Scaling (DPS) with high, balanced and low power modes.

Step 4: Next, we Enhance Feature Engineering for ML Training to optimize energy-aware workload distribution.

Step 5: Next, we offload and schedule the tasks using quality of service (QoS) to balance energy efficiency.

Step 6: Finally, we plot the following performance metrics,

6.1: Number of Vehicles Vs. RSSI(%)

6.2: Number of Vehicles Vs. Energy Consumption (J) for Vehicles/EDGE Devices /Cloud

6.3: Number of Vehicles Vs. Packet Delivery Ratio(%)

6.4: Number of Vehicles Vs. Task Completion Rate(%)

6.5: Number of Vehicles Vs. Packet Loss Ratio(%)

6.6: Number of Vehicles Vs. Latency(ms)

6.7: Number of Vehicles Vs. Failed Tasks for Navigation

6.8: Number of Vehicles Vs. Failed Tasks for Danger Assessment

6.9: Number of Vehicles Vs. Failed Tasks for Infotainment

6.10: Number of Vehicles Vs. Average QoS (%)

Software Requirements:
—————————–

1. Development Tool: Eclipse 2024 with EdgeCloudsim and Java -21.0.5

2. Operating System: Windows – 11 (64-bit)

Note:
——-

1. We make a simulation based process only, not a real time process.

2. If the above plan does not satisfy your requirement, please provide the processing details, like the above step-by-step.

3. Please note that this implementation plan does not include any further steps after it is put into implementation.

4. If the above plan satisfies your requirement, please confirm us soon.

Related Pages