Xiaofeng Cheng

Title: Innovations of Xiaofeng Cheng in Distributed Computing

Introduction

Xiaofeng Cheng is a notable inventor based in Hangzhou, China. He has made significant contributions to the field of distributed computing, particularly through his innovative patent. His work focuses on enhancing the efficiency of network flow scheduling systems.

Latest Patents

Xiaofeng Cheng holds a patent for a "DQN-based distributed computing network coordinate flow scheduling system and method." This patent discloses a method that includes establishing environmental feature data based on distributed computing task information and the congestion situation of a port queue in a programmable forwarding platform on a data plane. The method involves training a deep reinforcement learning intelligent agent based on an action value network and a target network in DQN. The agent outputs abstract actions, which are then mapped into an executable coordinate flow scheduling policy. The programmable forwarding platform executes this policy and updates the congestion situation of the port queue. Additionally, the policy gainer records the completion time of a distributed computing task as a real-time reward for the intelligent agent, allowing for iterative optimization.

Career Highlights

Xiaofeng Cheng is currently associated with Zhejiang Lab, where he continues to work on innovative solutions in distributed computing. His expertise in deep reinforcement learning and network scheduling has positioned him as a key figure in his field.

Collaborations

Xiaofeng collaborates with talented individuals such as Yuan Liang and Geyang Xiao, contributing to a dynamic research environment that fosters innovation.

Conclusion

Xiaofeng Cheng's contributions to distributed computing through his patent demonstrate his commitment to advancing technology in this area. His work not only enhances network efficiency but also showcases the potential of deep reinforcement learning in practical applications.