5G TSN Joint Scheduling via DDPG Reinforcement Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The 5G-TSN architecture faces challenges in scheduling multiple services, including time-sensitive and video streams, at base stations, where resource allocation must consider radio channel state, base station queue, and gate control, to ensure timely and efficient transmission.
Innovation Solution
A 5G TSN joint scheduling apparatus and method based on Deep Deterministic Policy Gradient (DDPG) reinforcement learning, which includes a state information acquisition module, scheduling decision-making module, and configuration module to allocate resources effectively across queues, using channel quality, queue length, and gate control state to optimize resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple services (time-sensitive and video streams) are scheduled at the base station simultaneously, then service coverage and functionality are improved, but resource allocation complexity and scheduling difficulty increase
Solution Approach 1:
The patent segments the scheduling problem into two distinct parts: gate control list (GCL) scheduling for time-sensitive services and base station resource allocation for video streams. The GCL schedules time-sensitive packets with strict delay requirements, while the base station schedules video streams with higher throughput requirements. This segmentation allows each scheduling mechanism to be optimized independently for its specific service type, reducing overall scheduling complexity while maintaining multi-service support
Solution Approach 2:
The patent implements dynamic scheduling by adjusting GCL parameters (gate timing, duration) and base station resource allocation based on real-time channel conditions, queue states, and service requirements. The scheduling policy dynamically adapts to changing network conditions, allowing the system to handle multiple service types efficiently without requiring static, overly complex scheduling mechanisms
2Reliability
If gate control of NW-DS-TT is enabled to ensure time-sensitive service delivery, then delay assurance is improved, but resource utilization efficiency deteriorates due to traffic waiting at DS-TT
Solution Approach 1:
The patent applies preliminary action by pre-configuring the Gate Control List (GCL) with scheduled gate timing and duration parameters before time-sensitive traffic arrives. The GCL is prepared in advance to open gates at optimal times for transmitting time-sensitive packets, ensuring delay assurance without requiring traffic to wait indefinitely at the DS-TT. This preliminary configuration enables efficient resource utilization while maintaining reliability
Solution Approach 2:
The patent implements feedback mechanisms where the base station monitors queue lengths, channel conditions, and gate control states in real-time. Based on this feedback, the scheduling policy dynamically adjusts GCL parameters and resource allocation to balance delay assurance and resource utilization. When queues are short or channels are good, resource allocation is optimized for efficiency; when delays approach thresholds, the system prioritizes time-sensitive traffic to maintain reliability
3Speed
If air interface resources are allocated without considering gate control state, then resource allocation speed is improved, but transmission timeliness deteriorates as traffic waits at DS-TT
Solution Approach 1:
The patent merges the gate control scheduling function with the base station resource allocation function into a unified joint scheduling framework. The GCL and base station scheduler work together as an integrated system, where gate control decisions and resource allocation decisions are coordinated to ensure that time-sensitive traffic is both gated appropriately and allocated resources efficiently. This merging eliminates the time loss that would occur if these functions operated independently, while maintaining fast allocation through the integrated decision-making process
Data Source
AI summary
A 5G-TSN resource joint scheduling apparatus includes: a state information acquisition module, a scheduling decision making module, and a configuration module. The state information acquisition module is configured to acquire bottom-layer network information, and process the acquired bottom-layer network information to obtain state information, the bottom-layer network information includes channel information, gate control list information of a TSN domain, and queue information in a base station. The scheduling decision making module is configured to obtain a result of decision making based on the state information output by the state information acquisition module using a DDPG-based reinforcement learning model, the result of decision making includes whether to allocate resources for a current queue and a number of resources actually allocated to the current queue. The configuration module is configured to convert the result of decision making to one or more instructions understandable by the base station to configure the base station.