Load the dataset

Extract and Normalize features

Simulate Latency and Energy Efficiency Values

Define RL agent (DQN or LQN) -State & Action spaces -Neural Network Architecture -Reward Function(Latency + EE)

Train RL Agent for a specific Number of Episodes (5000)

Compare Latency and Energy Efficiency values before and after using the RL agent.

Test Model with New Network State

Plot Training Rewards Trend