Abstract
Based on big data and cloud computing technology, the development process of this system includes hardware cluster deployment of the delivery system, optimization of website delivery strategy, and development of the delivery management background system. The main functions in the following aspects are realized: first, we built the website back-end delivery subsystem and data collection and analysis subsystem to realize the control of website delivery and data collection; second, we designed and developed a process management subsystem for booking, management, and delivery of website resources and developed the contract management and order management subsystems to realize the accurate placement of user portraits on the website; then, the placement data monitoring and effect feedback subsystems, and the data inventory subsystem of the website system were designed and developed. Finally, based on the research of Android and based on the Eclipse platform, this article has completed the construction of the Android 4.0.3 version environment, successfully used the Java development language to develop a website information intelligent analysis and navigation system, and analyzed the various functional modules of the entire system. Experimental results show that the system not only realizes ordinary route and site query functions but also combines map API, integrates big data and cloud computing technology, and realizes congestion avoidance query, time optimal query, population heat map, and real-time viewing. The nearby use of this software’s personnel density distribution and other functions provides great convenience for personal travel, which can facilitate the real-time planning of travel plans, and has great practical and practical significance. Through the different levels of testing of various subsystems, the website delivery system meets the functional and nonfunctional requirements proposed by the network and on this basis realizes the use of group wisdom based on Pearson correlation coefficient, Cosine similarity, and Tanimoto coefficient for collaborative filtering website recommendation algorithm.
Highlights
In recent years, cloud computing technology has developed rapidly, and virtualization technology, as the key technology of cloud computing, has always been one of the hot research issues [1]
Virtualization technology includes multiple aspects, such as network virtualization, virtual machine placement, and virtual machine migration. is paper mainly focuses on the related issues of virtual machine placement in data centers. e online website delivery system is developed with the rapid development and gradual improvement of the online website market and big data technology
As a leading video sharing website, online websites have played more than tens of millions of times a day. e company built an online website delivery management system with the purpose of using the cloud computing platform to strictly control the website delivery process to ensure accurate delivery of the website
Summary
Cloud computing technology has developed rapidly, and virtualization technology, as the key technology of cloud computing, has always been one of the hot research issues [1]. In a cloud data center, in order to improve resource utilization, a scheme of placing multiple virtual machines on the same physical server is usually adopted, and the placement of virtual machines will consider many factors, including reliability, energy consumption, and network resources. Yao et al [12] proposed an energy-aware virtual machine placement algorithm based on the hybrid genetic algorithm, which comprehensively considers the energy consumption of physical servers in the data center and the resource consumption of network communication. Focusing on the security issues in virtual machine placement, in response to attacks on virtual machines that have occurred in recent years, researchers have proposed a security-aware multiobjective optimization virtual machine placement algorithm to reduce the security risk of data centers in the cloud environment. Is paper selects the classic FFD algorithm and the adopted algorithm as the comparison algorithm and evaluates the performance of the proposed algorithm model. e experimental data show that the performance of the algorithm can meet expectations, and the improved algorithm based on the multimodel decision mechanism has obtained better performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
