ALBERT

Description: The integrity of data is an essential basis for analyzing power system operating status based on data. Improper handling of measurement sampling, information transmission, and data storage can lead to data loss, thus destroying the data integrity and hindering data mining. Traditional data imputation methods are suitable for low-latitude, low-missing-rate scenarios. In high-latitude, high-missing-rate scenarios, the applicability of traditional methods is in doubt. This paper proposes a reconstruction method for missing data in power system measurement based on LSGAN (Least Squares Generative Adversarial Networks). The method is designed to train in an unsupervized learning mode, enabling the neural network to automatically learn measurement data, power distribution patterns, and other complex correlations that are difficult to model explicitly. It then optimizes the generator parameters using the constraint relations implied by true sample data, enabling the trained Generator to generate highly accurate data to reconstruct the missing data. The proposed approach is entirely data-driven and does not involve mechanistic modeling. It can still reconstruct the missing data in the case of high latitude and high loss rate. We test the effectiveness of the proposed method by comparing three other GAN derivation methods in our experiments. The experimental results show that the proposed method is feasible and effective, and the accuracy of the reconstructed data is higher while taking into account the computational efficiency.

Description: The automatic identification of the topology of power networks is important for the data-driven and situation-aware operation of power grids. Traditional methods of topology identification lack a data-tolerant mechanism, and the accuracy of their performance in terms of identification is thus affected by the quality of data. Topology identification is related to the link prediction problem. The graph neural network can be used to predict the state of unlabeled nodes (lines) through training on features of labeled nodes (lines) with fault tolerance. Inspired by the characteristics of the graph neural network, we applied it to topology identification in this study. We propose a method to identify the topology of a power network based on a knowledge graph and the graph neural network. Traditional knowledge graphs can quickly mine possible connections between entities and generate graph structure data, but in the case of errors or informational conflicts in the data, they cannot accurately determine whether the relationships between the entities really exist. The graph neural network can use data mining to determine whether a connection obtained between entities is based on their eigenvalues, and has a fault tolerance mechanism to adapt to errors and informational conflicts in the graph data, but needs the graph data as database. The combination of the knowledge graph and the graph neural network can compensate for the deficiency of the single knowledge graph method. We tested the proposed method by using the IEEE 118-bus system and a provincial network system. The results showed that our approach is feasible and highly fault tolerant. It can accurately identify network topology even in the presence of conflicting and missing measurement-related information.

Description: Background: Gene expression and alternative splicing (AS) can promote cancer development via complex mechanisms. We aimed to identify and verify the hub AS events and splicing factors associated with the progression of colorectal cancer (CRC).Methods: RNA-Seq data, clinical data, and AS events of 590 CRC samples were obtained from the TCGA and TCGASpliceSeq databases. Cox univariable and multivariable analyses, KEGG, and GO pathway analyses were performed to identify hub AS events and splicing factor/spliceosome genes, which were further validated in five CRCs.Results: In this study, we first compared differentially expressed genes and gene AS events between normal and tumor tissues. Differentially expressed genes were different from genes with differentially expressed AS events. Prognostic analysis and co-expression network analysis of gene expression and gene AS events were conducted to screen five hub gene AS events involved in CRC progression: EPB41L2, CELF2, TMEM130, VCL, and SORBS2. Using qRT-PCR, we also verified that the gene AS events SORBS2 were downregulated in tumor tissue, and gene AS events EPB41L2, CELF2, TMEM130, and VCL were upregulated in tumor tissue. The genes whose mRNA levels were significantly related to the five hub gene AS events were significantly enriched in the GO term of cell division and Notch signaling pathway. Further coexpression of gene AS events and alternative splicing factor genes revealed NOVA1 as a crucial factor regulating the hub gene AS event expression in CRC. Through in vitro experiments, we found that NOVA1 inhibited gene AS event SORBS2, which induced the migration of CRC cells via the Notch pathway.Conclusion: Integrated analysis of gene expression and gene AS events and further experiments revealed that NOVA1-mediated SORBS2 promoted the migration of CRC, indicating its potential as a therapeutic target.