Search

As a part of cloud computing technology, algorithms for cloud task scheduling place an important influence on the area of cloud computing in data centers. In our earlier work, we proposed DeepEnergyJS, which was designed based on the original version of the policy gradient and reinforcement learning algorithm. We verified its effectiveness through simulation experiments. In this study, we used the Proximal Policy Optimization (PPO) algorithm to update DeepEnergyJS to DeepEnergyJSV2.0. First, we verify the convergence of the PPO algorithm on the dataset of Alibaba Cluster Data V2018. Then we contrast it with reinforcement learning algorithm in terms of convergence rate, converged value, and stability. The results indicate that PPO performed better in training and test data sets compared with reinforcement learning algorithm, as well as other general heuristic algorithms, such as First Fit, Random, and Tetris. DeepEnergyJSV2.0 achieves better energy efficiency than DeepEnergyJS by about 7.814%. [ABSTRACT FROM AUTHOR]

The major goal of this paper is to analyze the interactive impact of China's high-tech policies on university-industry (UI) collaboration and firm innovation by a network-based approach. Introducing high-tech policy to traditional innovative networks, we constructed a policy-induced UI collaboration network and applied social network analysis (SNA) method to empirically study the role of high-tech policies and the underlying mechanisms in firm innovation in the Greater Bay Area (GBA). This policy-induced innovative network consists of over 2000 innovative entities in GBA from 2012 to 2021, which reflects dynamic characteristics of innovative activities in this region. Based on this network, we find that high-tech policies play a positive and key role in regional innovation and we also clarify some potential mechanisms and routes in the effect of policies on UI collaboration and firm innovation. This paper advances our understanding of innovative networks and policy-induced regional innovation, which has implications for innovation policymaking in world-class innovative centers. • This paper analyzes the interaction among policies, university-industry collaboration and firm innovation in the Greater Bay Area. • This paper clarifies the paths of high-tech policies' effect by a network-based approach. • We construct a novel policy-induced collaborative knowledge network with a unique dataset by mapping policies. • Our research brings about some practical implications to policy makers in GBA. [ABSTRACT FROM AUTHOR]

This study examines factors influencing cancer-related heath information seeking on the Internet. Knowing influences on health information seeking on the Internet can help health care and public health professionals understand how people find information sources through computer network and hence enhance their working efficiency. A model of cancer-related health information seeking was proposed. A total response of 5480 participants from the Health Information National Trends Survey (HINTS) was used for this analysis. Individuals' media exposure and the credibility of the online health information were found to predict the Internet use. And utility significantly mediated the effect of other predictors on the Internet use. The overall model fit was acceptable. [ABSTRACT FROM AUTHOR]