A Routing Optimization Method for Software-Defined Optical Transport Networks Based on Ensembles and Reinforcement Learning.

Optical transport networks (OTNs) are widely used in backbone- and metro-area transmission networks to increase network transmission capacity. In the OTN, it is particularly crucial to rationally allocate routes and maximize network capacities. By employing deep reinforcement learning (DRL)- and software-defined networking (SDN)-based solutions, the capacity of optical networks can be effectively increased. However, because most DRL-based routing optimization methods have low sample usage and difficulty in coping with sudden network connectivity changes, converging in software-defined OTN scenarios is challenging. Additionally, the generalization ability of these methods is weak. This paper proposes an ensembles- and message-passing neural-network-based Deep Q-Network (EMDQN) method for optical network routing optimization to address this problem. To effectively explore the environment and improve agent performance, the multiple EMDQN agents select actions based on the highest upper-confidence bounds. Furthermore, the EMDQN agent captures the network's spatial feature information using a message passing neural network (MPNN)-based DRL policy network, which enables the DRL agent to have generalization capability. The experimental results show that the EMDQN algorithm proposed in this paper performs better in terms of convergence. EMDQN effectively improves the throughput rate and link utilization of optical networks and has better generalization capabilities.

Concentrated growth factor intradermal injection assisted super-thin flap expansion for repairing skin defects: A randomized, single blinded, split-site study.

BACKGROUND: The super-thin skin flap formed by skin and soft tissue expansion has large area and good ductility, so it can be used to repair skin defects. However, because the flap is thin, the blood flow in the dermis of the super-thin expanded flap is weakened, and flap rupture and necrosis after secondary flap transfer may occur. OBJECTIVE: To compare the skin thickness difference between the expanded ultrathin flaps injected with concentrated growth factor (CGF) and the blank group or saline group. METHODS: From June 2021 to December 2023, 10 patients (44 sites) with large-area scars or skin tumors were treated, and a single center half randomized controlled trial was conducted. The test site of expander implantation was divided into three groups: intradermal injection of CGF group, normal saline group and blank group. The same amount of expansion was performed every 1-2 weeks, and CGF or normal saline was injected into the dermis every 4 weeks, a total of three times. After 2-3 months of expansion, color Doppler ultrasound was used to measure the skin thickness of each group. RESULTS: Compared with the blank group, the skin thickness of CGF group was 1.75 ± 0.08 mm, and that of BLA blank group was 1.42 ± 0.07 mm, with statistically significant difference (p < 0.0001); In the other group, compared with the saline group, the skin thickness of the CGF group was 1.54 ± 0.08 mm, and the average skin thickness of the saline group was 1.40 ± 0.08 mm, with significant difference between the two groups (p = 0.0067). CONCLUSION: CGF intradermal injection can increase the skin thickness of super-thin skin flap in the process of soft tissue expansion, which is a safe and effective auxiliary method of skin expansion.