17870212. TRAFFIC SCENARIO CLUSTERING AND LOAD BALANCING WITH DISTILLED REINFORCEMENT LEARNING POLICIES simplified abstract (Samsung Electronics Co., Ltd.)
Contents
TRAFFIC SCENARIO CLUSTERING AND LOAD BALANCING WITH DISTILLED REINFORCEMENT LEARNING POLICIES
Organization Name
Inventor(s)
Gregory Lewis Dudek of Westmount (CA)
TRAFFIC SCENARIO CLUSTERING AND LOAD BALANCING WITH DISTILLED REINFORCEMENT LEARNING POLICIES - A simplified explanation of the abstract
This abstract first appeared for US patent application 17870212 titled 'TRAFFIC SCENARIO CLUSTERING AND LOAD BALANCING WITH DISTILLED REINFORCEMENT LEARNING POLICIES
Simplified Explanation
The present disclosure describes a method, apparatus, and computer-readable storage media for load balancing traffic scenarios by a network device.
- The method involves training multiple learning agents to load balance different traffic scenarios and obtain control policies.
- The method includes performing clustering iterations where pairs of control policies are merged into a clustered control policy.
- The clustering iterations continue until a predetermined number of control policies remain.
- The resulting control policies are then deployed to each base station in a network.
Potential applications of this technology include:
- Load balancing network traffic in telecommunications systems.
- Optimizing resource allocation in wireless networks.
- Improving network performance and efficiency.
Problems solved by this technology include:
- Uneven distribution of network traffic leading to congestion and poor performance.
- Inefficient allocation of network resources.
- Lack of adaptability to changing traffic patterns.
Benefits of this technology include:
- Improved network performance and reliability.
- Efficient utilization of network resources.
- Adaptability to changing traffic conditions.
- Reduced congestion and improved user experience.
Original Abstract Submitted
The present disclosure provides for methods, apparatuses, and non-transitory computer-readable storage media for load balancing traffic scenarios by a network device. In an embodiment, a method includes training a plurality of learning agents to load balance a respective plurality of traffic scenarios to obtain a plurality of control policies. The method further includes performing at least one clustering iteration. Each clustering iteration includes selecting a pair of control policies and merging the pair of control policies into a clustered control policy that replaces the pair of control policies. The method further includes determining to stop the performing of the at least one clustering iteration when a quantity of control policies remaining in the plurality of control policies meets a predetermined value. The method further includes deploying to each base station of a plurality of base stations a corresponding control policy from the plurality of control policies.