Abstract: A blockchain sharding method combining spectral clustering and a reputation value mechanism includes: obtaining, every other account grouping cycle Ta, account transaction data recorded during operation of a blockchain to generate an account transaction graph; obtaining an adjacency similarity matrix W and a degree matrix D based on the account transaction graph; generating a Normalized Laplace matrix L based on the adjacency similarity matrix W and the degree matrix D, performing dimension reduction on L to obtain a feature matrix F, and then clustering the feature matrix F with a clustering dimension of k by row through a K-means clustering method; and dividing blockchain accounts into k groups based on an obtained clustering result, and allocating accounts in the k groups to k blockchain shards.

Abstract: Disclosed are a method and apparatus for compressing a topology recognition model, an electronic device, and a medium. The method includes: pruning a to-be-compressed model to obtain a pruned model, and training the pruned model to obtain a trained pruned model; quantifying a bit quantity of a weight parameter of each neural network layer in the trained pruned model from a first bit quantity to a second bit quantity to obtain a highly-quantified pruned model, and training the highly-quantified pruned model to obtain a trained highly-quantified pruned model; using the trained highly-quantified pruned model as the to-be-compressed model, continuously pruning and quantifying the to-be-compressed model until a compressed topology recognition model is obtained, and deploying the compressed topology recognition model on an Internet of Things in Power Systems (IOTIPS) terminal, to reduce a size of the topology recognition model while ensuring the topology recognition model meets an accuracy requirement.

Abstract: A CO2 desorption system suitable for limited space in a complex sailing region comprises an exhaust boiler, a compact CO2 absorber, a compact CO2 lean-rich liquid heat exchanger, a compact CO2 desorber, a compact CO2 rich liquid preheating device, a compact CO2 rich liquid reboiling pre-desorption device and an intelligent control platform. Further, a global optimization control method for the CO2 desorption system suitable for limited space in a complex sailing region is further established based through a knowledge and data-driven exhaust extraction flow accurate-prediction model for a heat source of a CO2 rich liquid preheating device and a steam extraction flow accurate-prediction model for a heat source on an upper section of a CO2 rich liquid reboiling pre-desorption device to realize flexible control of operation parameters of the desorption system under different operating conditions of an engine.