Search

With the promotion and development of oversized data technology, many data analysis platforms based on super large data storage and computing frameworks have emerged in the industry. While the platforms with oversized economic data analysis combined with machine learning models are still relatively lacking. And oversized data also brings a new problem, that is the security of economic development. It is an important and difficult task to analyse and detect risks from oversized economic data. Based on machine learning, data analysis, economic market and other multidisciplinary fields, this paper proposes a machine learning method, which is a genetic algorithm (GA) based feature selection method: FSGA. This method abstracts every possible feature selection result into an individual in GA, generates a population through genetic operation, and measures the merits of the individual through fitness. In addition, this paper has conducted multitudinous simulation experiments on the GA‐based FSGA method and the traditional LSTM data analysis method respectively. The accuracy rate and other indicators are obtained by comparing the training. The experimental results show that the GA‐based FSGA machine learning method has higher prediction accuracy when analysing oversized economic data. And it is practical to accelerate the development of digital economy. [ABSTRACT FROM AUTHOR]

TE is a critical and difficult problem that tries to map traffic with various requirements to paths in dynamic communication networks. The emerging SDN enables centralized TE optimization with a global view. From the architectural viewpoint, ICN facilitates TE from many aspects, such as in-network caching which can reduce redundant traffic and content-awareness which can extract prior knowledge of content type directly. Thus, we leverage ICN to optimize SDN TE. However, ICN brings more complexities and dynamics to the network environment, which makes model-based TE methods inefficient. Inspired by recent advances in applying artificial intelligence techniques to solve complex online control problems, we investigate deep learning for content-awareness and DRL for TE decision. In addition, we propose a parallel online learning mechanism to safely utilize DRL which has trial-and-error nature. Results show that our proposal significantly improves network performance in terms of total network throughput, bandwidth utilization, and load balance. [ABSTRACT FROM AUTHOR]