Abstract: A fault-tolerant control method and apparatus of a floating wind turbine are provided. The fault-tolerant control method and apparatus of a floating wind turbine can acquire a low-order nonlinear model of a pre-established floating wind turbine, establish a switching linear model of the floating wind turbine based on the low-order nonlinear model, acquire a modal parameter of the current floating wind turbine, and determine based on the modal parameter a sub-model that the floating wind turbine currently satisfies, so as to establish a switching sliding mode surface and a full-order state observer of the floating wind turbine based on the sub-model and the modal parameter, and further calculate a feedback output of a controller of the floating wind turbine according to the switching sliding mode surface and the full-order state observer.

Abstract: Provided are control method and device of an energy-storage coordinated floating wind turbine, relating to the technical field of wind turbines. The control method of an energy-storage coordinated floating wind turbine can construct a primary frequency regulation model of a floating wind farm based on a frequency response unit, construct a second frequency regulation model according to an energy storage system, further construct, according to the primary frequency regulation model and the second frequency regulation model, a frequency regulation model of a hybrid power system containing the floating wind farm, the energy storage system, and a pre-set thermal power unit, and design an overall frequency regulation control strategy of the hybrid power system based on the frequency regulation model of the hybrid power system.

Abstract: The present invention provides a frequency modulation dynamic modeling method and device for a wind farm, and an electronic device. The method includes: acquiring first frequency modulation data measured at a grid-connected point of the wind farm under a plurality of preset working conditions; establishing a state space model corresponding to each of the plurality of working conditions according to the first frequency modulation data; measuring the nonlinearity between the state space models corresponding to each two of the plurality of working conditions by using a gap measurement method; combining the first frequency modulation data according to the nonlinearity to obtain second frequency modulation data; and training a preset initial LSTM neural network according to the second frequency modulation data until a preset training requirement is met, and obtaining a trained frequency modulation dynamic model of the wind farm.

Abstract: The present invention discloses an intelligent soft measurement method for wind speed in front of a wind turbine. The method includes: first using laser radar data as a data sample, judging delay orders between input and output by using an AIC or BIC criterion, defining a dynamic difference regression vector according to the delay orders, dividing hyperplanes according to a clustering result by using a machine learning algorithm, and performing dynamic differential input/output nonlinear mapping modeling in a global scope and sub-scopes by using an artificial intelligence dynamic regression algorithm, respectively. Empirical mode decomposition and power spectral density analysis are performed on the wind speed in front of a laser radar measuring machine and the wind speed in front of a soft measurement machine, thereby further verifying the estimation performance of intelligent soft measurement for the wind speed in front of a wind turbine.

Abstract: Disclosed is a federated learning-based regional photovoltaic power probability forecasting method, mainly comprising steps of: pinpointing all photovoltaic power stations in a region which participate in a federated learning framework for probability forecasting, collecting information within a period of time and corresponding photovoltaic power variables, and sampling the variables according to time sequence into a sample dataset; processing missing values and outliers in the sample dataset resulting from the step; splitting the sample data set of the photovoltaic power stations into a training set and a testing set according to a preset proportion; normalizing the training set and the testing set, respectively; creating a federated learning framework; building, by a central server, a global forecasting model based on forecast requirements, defining a training error function and a precision requirement, and distributing the network architecture and initialized parameters to all photovoltaic power stations.

Abstract: The present application provides an optimized regulating and controlling method and system for an integrated electricity and heat system with heat pumps, relating to the technical field of energy operation. According to the present application, regulating and controlling can be performed by regarding units as different agents and taking maximization of the self-interest of each agent as the objective, so that the load demands of heat and power consumers can be met, and each unit agent can be satisfied with its payoff to the greatest extent. The method includes: S1. establishing a composition and structure framework of the integrated electricity and heat system with heat pumps, and establishing an output model of each unit; S2. establishing a payoff function model of each unit in the integrated electricity and heat system with heat pumps; S3. establishing a non-cooperative game model of the integrated electricity and heat system with heat pumps; and S4.