Data space is a technology system that allows data to be connected securely and efficiently. In the full life cycle of data space data, data collection, data storage, processing, transmission, exchange and destruction, and provision of services according to the dynamic changes of the subject's needs, is a brand-new data management model. This article first starts from the data security risk assessment of the data space of the electric power manufacturing industry, has analyzed the data characteristics of the data space of the electric power manufacturing industry, and sorted out the actual needs of data security. Then, based on the data life cycle process, the risk index of data space data security of electric power manufacturing enterprises are screened out. And used the method of combining Likert five-level scale and questionnaire to assess the amount of risk, graded risk index and proposed corresponding management measures, and constructed a dynamic cycle data security risk assessment model. Finally, a security governance system for data collection, data fusion and data transmission and other data full life cycle multi-faceted collaborative governance was established, and the data security risk of a Beijing electric power manufacturing company was evaluated, and put forward suggestions on how to coordinate the management of data security risks of power manufacturing enterprises.

The manufacturing industry is currently in a critical period of intelligent change, and the generation of massive amounts of data makes data management and data integration increasingly important. With the continuous upgrading of data management technology, how to handle diversified data and effectively collect multi-source heterogeneous data while ensuring data security has become the key to intelligent data management in current manufacturing enterprises. This paper analyzes the factors influencing the supply value chain in multi-value chain synergy, taking the external supply value chain of an electric power manufacturing company as an example. The gray correlation method is used to sort out the factors. Then the к-means method is used for data mining and cleaning. A dataset of key factors affecting the external value chain is established, and a data integration architecture for the dataspace of power manufacturing enterprises is constructed and empirically analyzed. The research results show that the data integration architecture can effectively tap into the management potential of power manufacturing enterprises in the external supply value chain and provide information solutions for the operation and management of power manufacturing enterprises.

The arrival of data space marks that all kinds of data applications can be recorded, stored and continuously expanded. The changes of data's source, volume and type have been increasing the difficulty of statistical analysis undoubtedly. In order to cope with the high-dimensional characteristics of data in data space, this paper discusses the challenges brought by high-dimensional data and high-dimensional models to traditional methods. The development of sparse modeling, the role of selection mechanism and the theoretical nature of penalty function method have also been combed in this paper. Finally, as an application, this paper discusses the feasibility of using high-dimensional sparse vector autoregressive model (HDS-VAR) to predict the profitability of manufacturing enterprises represented by electrical machinery and equipment manufacturing enterprises under the synergy of manufacturing value chain and service value chain.