|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | A Trusted Edge Resource Allocation Framework for Internet of Vehicles显示文摘With the continuous progress of information technique,assisted driving technology has become an effective technique to avoid traffic accidents.Due to the complex road conditions and the threat of vehicle information being attacked and tampered with,it is difficult to ensure information security.This paper uses blockchain to ensure the safety of driving information and introduces mobile edge computing technology to monitor vehicle information and road condition information in real time,calculate the appropriate speed,and plan a reasonable driving route for the driver.To solve these problems,this paper proposes a trusted edge resource allocation framework for assisted driving service,which includes two stages:the blockchain generation stage(the first stage)and assisted driving service stage(the second stage).Furthermore,in the first stage,a delay-and-throughput-oriented block generation model for the mobile terminal is designed.In the second stage,a balanced offloading algorithm for assisted driving service based on edge collaboration is proposed to solve the problems of unbalanced load of cluster mobile edge computing(MEC)servers and low resource utilization of the system.And this paper optimizes the throughput of blockchain and delay of the transportation network through deep reinforcement learning(DRL)algorithm.Finally,compared with joint computation and communication resources’allocation(JCCR)and resource allocation method based on binary offloading(RAB),our proposed scheme can optimize the delay by 7.4%and 26.7%,and support various application services of the vehicular networks more effectively. | Yuxuan Zhong Siya Xu Boxian Liao Jizhao Lu Huiping Meng Zhili Wang Xingyu Chen Qinghan Li | 2023 | Computers, Materials & Continua2023，77，11： | 0 |
| 2 | A DRL-Based Container Placement Scheme with Auxiliary Tasks显示文摘Container is an emerging virtualization technology and widely adopted in the cloud to provide services because of its lightweight,flexible,isolated and highly portable properties.Cloud services are often instantiated as clusters of interconnected containers.Due to the stochastic service arrival and complicated cloud environment,it is challenging to achieve an optimal container placement(CP)scheme.We propose to leverage Deep Reinforcement Learning(DRL)for solving CP problem,which is able to learn from experience interacting with the environment and does not rely on mathematical model or prior knowledge.However,applying DRL method directly dose not lead to a satisfying result because of sophisticated environment states and huge action spaces.In this paper,we propose UNREAL-CP,a DRL-based method to place container instances on servers while considering end to end delay and resource utilization cost.The proposed method is an actor-critic-based approach,which has advantages in dealing with the huge action space.Moreover,the idea of auxiliary learning is also included in our architecture.We design two auxiliary learning tasks about load balancing to improve algorithm performance.Compared to other DRL methods,extensive simulation results show that UNREAL-CP performs better up to 28.6%in terms of reducing delay and deployment cost with high training efficiency and responding speed. | Ningcheng Yuan Chao Jia Jizhao Lu Shaoyong Guo Wencui Li Xuesong Qiu Lei Shi | 2020 | Computers, Materials & Continua2020，，9： | 0 |
| 3 | Heterologous biosynthesis of medicarpin using engineered Saccharomyces cerevisiae显示文摘Medicarpin is an important bioactive compound with multiple medicinal activities,including anti-tumor,anti-osteoporosis,and anti-bacterial effects.Medicarpin is associated with pterocarpans derived from medicinal plants,such as Sophora japonica,Glycyrrhiza uralensis Fisch.,and Glycyrrhiza glabra L.However,these medicinal plants contain only low amounts of medicarpin.Moreover,the planting area for medicarpin-producing plants is limited;consequently,the current medicarpin supply cannot meet the high demands of medicinal markets.In this study,eight key genes involved in medicarpin biosynthesis were identified using comparative transcriptome and bioinformatic analyses.In vitro and in vivo enzymatic reaction confirmed the catalytic functions of candidate enzymes responsible for the biosynthesis of medicarpin and medicarpin intermediates.Further engineering of these genes in Saccharomyces cerevisiae achieved the heterologous biosynthesis of medicarpin using liquiritigenin as a substrate,with a final medicarpin yield of 0.82±0.18 mg/L.By increasing the gene copy numbers of vestitone reductase(VR)and pterocarpan synthase(PTS),the final medicarpin yield was increased to 2.05±0.72 mg/L.This study provides a solid foundation for the economic and sustainable production of medicarpin through a synthetic biology strategy. | Chujie Lu Rui Du Hao Fu Jizhao Zhang Ming Zhao Yongjun Wei Wei Lin | 2023 | Synthetic and Systems Biotechnology2023，8，4： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员