With the acceleration of the Internet in Web 2.0, Cloud computing is a new paradigm to offer dynamic, reliable and elastic computing services. Efficient scheduling of resources or optimal allocation of requests is one of the prominent issues in emerging Cloud computing. Considering the growing complexity of Cloud computing, future Cloud systems will require more effective resource management methods. In some complex scenarios with difficulties in directly evaluating the performance of scheduling solutions, classic algorithms (such as heuristics and meta-heuristics) will fail to obtain an effective scheme. Deep reinforcement learning (DRL) is a novel method to solve scheduling problems. Due to the combination of deep learning and reinforcement learning (RL), DRL has achieved considerable performance in current studies. To focus on this direction and analyze the application prospect of DRL in Cloud scheduling, we provide a comprehensive review for DRL-based methods in resource scheduling of Cloud computing. Through the theoretical formulation of scheduling and analysis of RL frameworks, we discuss the advantages of DRL-based methods in Cloud scheduling. We also highlight different challenges and discuss the future directions existing in the DRL-based Cloud scheduling.

The aviation industry which aircraft manufacturing dominates is an important sector to measure a nation’s air power. The application of new technologies to optimize the process, increase the speed and upgrade the quality of airplane assembly, a crucial link in its manufacturing, is an effective method to improve the capacity. The combination of traditional processes and emerging technologies greatly improves its efficiency, reduces its labor costs and promotes the innovation and upgrade of traditional technologies. For aircraft manufacturers, the Assembly Outline (AO) refers to an essential document used for the guidance of the assembly process. Low efficiency and under-structuration of compilation, which is also difficult to upgrade, put a limit on the application of information and digitization technologies and has an impact on the overall airplane production cycle, due to present manual work in quantity and imbalance of informationization. Via sequential-pattern-based data mining introduced in this paper, patterns of AO processes are dug up to form a set based on which it is possible to quickly make a recommendation of the optimal process for the compiler, effectively reducing the duration of compilation and modification and improving the efficiency.

Amidst the era of big data, data is not only a crucial asset for countries and businesses but also a key driver for economic and social development as well as innovation in management mechanism. Any occurrence of data security issues can lead to significant losses for countries, enterprises, and individuals, resulting in substantial social impact. Therefore, it is highly important to conduct thorough research on data security protection strategies for petrochemical enterprises. This paper first analyzes the risks associated with data security under the backdrop of big data and proposes a framework for designing data security protection strategies based on the Data Security Capability Maturity Model. The framework consists of two main components: management framework design and technical framework design. This paper primarily focuses on studying the design of the technical framework. By conducting targeted risk analysis throughout the entire lifecycle of data including acquisition, transmission, storage, application, sharing, and destruction stages; it aims to align each identified risk with corresponding measures for ensuring data security protection. Additionally, this paper suggests protection strategies tailored to enterprise scenarios dimensions to provide robust security guarantees for petrochemical enterprise's valuable datasets.