First, the IDRF offline phase corrects the vehicle's historical trajectory information using the vehicle trajectory continuity algorithm and trains the DQN model. Then, the IDRF real-time phase judges whether vehicles can meet each other and makes a real-time routing...
Packet scheduling and resource allocation using machine learning As a result of recent advancements inAI, Machine Learning (ML) has become a helpful tool for building solutions and learning models to improveQoS parametersinIoTand wireless networks[34]. To improve 5G service quality, machine learning,...
Table 2. The most frequent (state, action) pairs for the DQN scheduler. 5. Related Work As one of the core technologies supporting the IoT, the WSN has attracted much attention among researchers. Most of the early relevant studies focused on designing different routing schemes and communication...
Table 2. The most frequent (state, action) pairs for the DQN scheduler. 5. Related Work As one of the core technologies supporting the IoT, the WSN has attracted much attention among researchers. Most of the early relevant studies focused on designing different routing schemes and communication...
3.2. DQN-Based Scheduling Algorithm The scheduling of transmission parameters in our WSN model is formulated as a sequential decision-making problem under the RL framework. In this formulation, the agent corresponds to the master node, and everything beyond the master node is considered the ...