125 results about "Random optimization" patented technology

The invention relates to the technical field of data processing, and particularly provides a low-altitude aircraft power supply facility cooperative control method, system and device and a medium, and the method comprises the steps: predicting the renewable energy power generation power of a power supply facility and the charging load power of a low-altitude aircraft based on obtained multi-source information, and generating a prediction scene set representing uncertainty; based on the prediction scene set, through a multi-time scale optimization strategy, solving a scheduling model with optimal operation cost as a target, and successively obtaining a pre-scheduling plan of a day-ahead stage and a real-time control instruction of an intra-day stage; the multi-time scale optimization strategy comprises random optimization based on a scene and feedback optimization based on a rolling time domain; according to the real-time control instruction, power distribution is conducted on the hybrid energy storage system, and a power type energy storage unit preferentially responds to the transient power requirement for charging of the low-altitude aircraft. The comprehensive operation cost is effectively reduced, and particularly, the service life of equipment is prolonged through quantitative energy storage degradation.

The invention discloses an optimization method and system for aviation equipment storage and a medium, and the method comprises the steps: collecting multi-dimensional dynamic data, carrying out the fusion cleaning and structural feature extraction, and generating a high-dimensional feature set; outputting a dynamic demand prediction value and uncertainty measurement by using a hybrid intelligent prediction model fusing time sequence prediction and ensemble learning; calculating an optimal inventory control parameter through a stochastic optimization model in combination with the aviation material key grade and the stockout loss cost; and generating an inventory operation instruction according to the optimal inventory control parameter and the real-time inventory state, and outputting a strategy report with confidence evaluation and key influence factor analysis. According to the method, multi-dimensional accurate prediction of the aerial material demand and dynamic optimization of the inventory strategy are realized, the inventory control precision and the resource utilization efficiency are remarkably improved, the stockout risk and the overstocked cost are effectively reduced, and the reliability and the economical efficiency of aviation equipment guarantee are enhanced.

The invention discloses a self-adaptive photovoltaic energy storage comprehensive optimization method and system, and belongs to the technical field of photovoltaic energy storage optimization control. According to the method, a system operation model is established based on historical and real-time operation data of a photovoltaic unit, an energy storage unit and a load side, a hybrid robust-stochastic optimization framework is introduced, a collaborative optimization model with energy balance and system stability as targets is constructed, and an initial control parameter set is solved; in the system operation process, a power fluctuation mode and energy storage response characteristics are identified through a multi-layer agent algorithm, and a dynamic energy storage control instruction is generated and corrected; and according to the cross-cycle change trend of the operation performance index, adaptively adjusting the weight and step length of the control parameter, and realizing strategy evolution and dynamic closed-loop optimization. According to the invention, cooperative operation of photovoltaic and energy storage can be realized under complex operation conditions, and the energy utilization rate and the operation stability are improved.

The invention relates to a power grid side energy storage two-stage locating and sizing method in a sea wind access scene considering the influence of temperature on a tide safety domain. The method comprises the following steps: adopting a temperature trend prediction model combining LSTM and TCN; a Gaussian mixture model is adopted to calculate a temperature variable capacitance expectation coefficient, and a power flow safety domain is reconstructed; establishing a random optimization scene set of source-load space-time coupling by adopting a typical source-load daily trajectory clustering method; establishing a power distribution network energy storage locating and sizing planning layer model taking the maximum comprehensive utility as a target; a power distribution network energy storage locating and sizing operation layer model with the minimum voltage fluctuation quadratic sum as the target is established; constructing a DistFlow multi-period optimal power flow model under the sea wind access scene; and solving the planning layer by adopting second-order cone relaxation, and carrying out secondary optimization on a charge-discharge and capacity configuration strategy on the operation layer by adopting a target cascade algorithm on the basis of anchoring a locating and sizing decision variable of the planning layer. According to the method, planning and operation targets can be more effectively coordinated, and comprehensive optimal configuration of power grid side energy storage is realized.

The invention discloses a shared energy storage and new energy station cooperative operation method and system, and relates to the field of power market and energy storage optimization management in a power system, and the method comprises the following steps: extracting historical wind and light scene data of a new energy station; according to historical wind and light scene data, a wind and light prediction error probability model is established, and after sampling and scene reduction, a limited typical scene is extracted and an uncertainty set is constructed; and on the basis of the limited typical scene and the uncertainty set, by taking the benefit maximization of the new energy station as a target and combining a virtual energy storage operation mode, constructing a shared energy storage and new energy station collaborative operation framework, and generating a double-track system optimal collaborative strategy. The method is used for solving the problems that stochastic optimization calculation is complex, traditional robust optimization benefits are limited, and energy storage resource configuration efficiency is low.

The application provides a mobile energy storage optimal configuration method and equipment for distribution network under typhoon disaster considering fault evolution, and belongs to the field of mobile energy storage optimal configuration for distribution network. The method firstly establishes a typhoon disaster space-time evolution model according to typhoon meteorological prediction information, and constructs a space-time characteristic matrix of distribution line failure rate; then determines the vulnerable line based on the space-time characteristic matrix of the line failure rate, and builds a pre-disaster mobile energy storage pre-scheduling model to prepare for the post-disaster system rapid recovery; then, the optimal configuration and operation strategy of the mobile energy storage under the probability scenario are found by using random optimization to minimize the economic loss of the disaster distribution network during the typhoon disaster, a random optimization model of the mobile energy storage optimal configuration and operation is established, and the flexibility of the mobile energy storage is fully utilized to provide phased power support for the distribution network during the typhoon disaster, effectively solving the problem that the distribution network is difficult to guarantee safe and reliable power supply under the typhoon extreme disaster, and improving the flexibility of the distribution network.

The invention relates to the technical field of data center optimization, and particularly discloses a data center two-stage stochastic optimization method and system considering wind and light uncertainty, and the method comprises the steps: carrying out the modeling of a data center energy supply system, generating a wind and light output sample based on Monte Carlo simulation, enabling the generated random sample to meet wind power and photovoltaic output complementation through Corisky decomposition; introducing a first-order autoregression model, generating random scenes in combination with multivariate normal distribution, and obtaining a wind and light output curve in each scene; a two-stage stochastic optimization model containing computing power scheduling and multi-energy coordination is constructed by taking the minimum expected operation cost of a system as a target, the model is solved, and an optimal time sequence operation strategy of a computing power task is decided. According to the two-stage random optimization, the adjustment cost caused by prediction errors is covered with low risk premium, and effective support is provided for reliable operation of the data center under new energy output fluctuation and computing power load time sequence mismatch.

The present application relates to the technical field of power grid and electrical equipment operation and maintenance, and discloses a power grid safety control device opportunity maintenance decision method based on multi-layer random optimization. The method comprises the following steps: according to the state transition process after the safety control device is put into operation, the correlation between the internal hardware of the safety control device, between the safety control devices, and between the safety control device and the primary equipment is considered, the functional correlation, the economic correlation and the random correlation of the safety control device are planned from three levels, a nested compound objective function is first constructed, a multi-level safety control device opportunity maintenance decision model is established, and thus the best maintenance strategy of the safety control device is formulated, the maintenance efficiency of the safety control device can be improved, and the effective balance between the safety control device maintenance and the power system operation is realized.

The invention discloses an airport operation robustness decision-making method and device based on stochastic optimization. The method comprises the following steps: constructing a low-altitude intrusion situation feature space through multi-source heterogeneous sensing data; on the basis of the feature space, constructing a runway recovery time Wasserstein uncertainty set capable of dynamically adjusting the boundary so as to describe uncertainty; establishing a distribution robust optimization model for coupling aircraft position distribution and ground support facility scheduling; a column constraint generation algorithm is used for solving, and decision making and closed-loop feedback are executed in a rolling time domain mode. The method does not need to depend on prior probability distribution of interference events, adaptive balance of decision robustness and economical efficiency can be achieved, the problem of space-time mismatching is effectively avoided through resource coupling scheduling, and improvement of the operation recovery efficiency and safety of an airport under high uncertainty is facilitated.

The application discloses a building energy consumption real-time control method based on DQN, generates multiple groups of scenes based on building photovoltaic power generation and building rigid load prediction data, optimizes building energy consumption behavior by using a DQN algorithm, reasonably designs a DQN reward function by using the concept of random optimization, and makes the optimization result have good robustness to the uncertainty of building power generation and load. The application makes the building maintain high comfort all day, increases the flexibility of building energy consumption by scheduling energy storage equipment, and reduces the building energy consumption cost.

The invention relates to the technical field of power system operation and control, discloses a mountainous area power distribution network multi-source coordinated optimization scheduling method, system, equipment and medium, and constructs a mountainous area power distribution network multi-source coordinated optimization scheduling framework based on a stochastic optimization theory and a decomposition coordination algorithm. A three-dimensional power grid model is established through a geographic information system, accurate prediction of new energy output is realized in combination with a meteorological prediction technology, and overall consideration of economy, reliability and environmental protection is realized by applying a multi-objective optimization method.

The application discloses a kind of 6G network multidimensional resource AI model dynamic deployment optimization methods based on category theory, belongs to intelligent collaborative optimization technical field;Method is: the cross-layer consistency dependency of end-to-end AI reasoning service is formalized by functor form;Establish the joint optimization model with long-term average end-to-end delay minimization as target, while being constrained by multidimensional resource and service quality;Convert long-term random optimization problem into time-slot online decision problem;Get AI model dynamic deployment and task scheduling result.The application realizes cross-layer consistency description to task scheduling and model deployment through category theory unified modeling and functor composite mechanism, reduces the inconsistency and redundant constraint caused by hierarchical modeling, improves the structured degree and explainability of joint decision;Under the constraint of multidimensional resources such as calculation, memory, storage and bandwidth, dynamic adaptive optimization is realized, node resource over-limit and load imbalance are effectively avoided, and congestion and queuing delay are reduced.

The invention relates to the technical field of EV scheduling, and discloses a multi-zone-area electric vehicle cluster scheduling optimization method and device and electronic equipment, which are used for solving the technical problem of poor scheduling effect of the existing EV cluster scheduling scheme. Comprising the steps that minimization of the sum of power grid operation cost and user comprehensive cost is taken as an optimization target, power grid security constraints, user demand constraints, adjustable potential constraints and power boundary constraints are taken as constraint conditions, and the adjustable potential of a single transformer area is combined to construct a day-ahead initial scheduling model; when a preset condition is triggered, generating an uncertain scene, and based on the uncertain scene, constructing a rescheduling model by taking minimization of rescheduling cost and conditional value-at-risk as an optimization target and taking an adjustment amplitude constraint, a power grid security constraint and a user demand constraint as constraint conditions; generating a two-stage stochastic optimization rescheduling model by adopting the day-ahead initial scheduling model and the rescheduling model; and solving the two-stage stochastic optimization rescheduling model to obtain a multi-zone-area electric vehicle cluster optimization scheduling scheme.

The application provides a kind of intelligence calculation fusion network heterogeneous resource elasticity adaptation and deterministic scheduling system and method, belongs to industrial internet of things technical field, comprising: the system of establishing distributed management and centralized control under the scene of intelligence calculation fusion network;According to the distributed management and centralized control system, the two-stage random optimization problem of different time scales is established;For large-scale resource adaptation problem, a resource elasticity adaptation scheme based on heuristic algorithm is adopted;For small-scale scheduling sub-problems, a deterministic scheduling scheme based on deep reinforcement learning is adopted;Using the resource elasticity adaptation scheme and deterministic scheduling scheme, the optimal resource adaptation and scheduling result is obtained.The application can meet the resource flexible configuration demand under high dynamicity and uncertainty environment, ensure low delay and high reliability in data scheduling process.

The application discloses a kind of hydrogen energy storage's electric heating gas hydrogen comprehensive energy system random optimization scheduling method, and comprehensive energy system mainly includes four subsystems of electricity, heat, gas, hydrogen.The dynamic efficiency model of electrolytic cell, fuel cell is analyzed in the application, and the energy conversion equipment, energy storage equipment etc. between multiple energy in system are established corresponding mathematical model.The energy purchase cost, load loss compensation cost, environmental cost and wind and light penalty cost are comprehensively considered, and the total operation cost of electric heating gas hydrogen comprehensive energy system minimization is taken as objective function to carry out scheduling to the generation, heating, gas supply and electrolytic hydrogen production involved in system.The optimization scheduling method proposed in the application can effectively consume wind power, reduce operating cost, reduce environmental pollution, and has good economy and environmental protection.

The invention provides a space-air-ground integrated network resource management method and system and a storage medium, and belongs to the technical field of wireless communication and network resource dispatch. The method comprises the steps that a space-air-ground integrated network is constructed, a GU is provided with an energy collection module and a backscatter circuit, and the backscatter circuit is connected with the GU; low-power-consumption data transmission and energy collection are realized by reflecting a radio frequency carrier signal emitted by the UAV; the UAV carries a mobile edge computing server to process a task, and the task is unloaded to the LEO when the task is overloaded; a central controller collects network state and channel state information in real time, a random optimization function is constructed by taking minimization of long-term average energy consumption of a system as a target and combining constraints such as task queue stability and energy sustainability, a Lyapunov optimization framework is adopted to convert the problem into a single time slot problem, and the problem is solved through alternate optimization and concave-convex process technologies. According to the method, the stability of the task queue is guaranteed, the system energy consumption is remarkably reduced, the resource utilization rate is improved, and reliable support is provided for remote area power emergency communication.

The application discloses an edge intelligent body flexible scheduling method based on Lyapunov optimization and Stackelberg game. The application constructs a cloud-edge-end three-layer edge intelligent body federated learning network architecture to complete distributed collaborative training under the premise of protecting data privacy. In view of the problems of heterogeneous edge intelligent body network nodes, non-independent and identically distributed data and limited communication resources, a long-term joint optimization model of client selection and bandwidth allocation is established, and model accuracy, time delay and energy consumption are considered. Lyapunov optimization is used to decouple long-term random optimization into real-time decision-making per time slot, and to convert constraints into virtual queue stability control. Dynamic client selection is realized based on Stackelberg game, and high-quality nodes are adaptively selected. Adaptive bandwidth allocation is completed through an evolutionary algorithm, and communication requirements of key clients are preferentially guaranteed. The application can significantly improve model accuracy, reduce time delay and energy consumption, guarantee long-term stability of the system, and is suitable for high-dynamic edge intelligent body federated learning scenes.

The invention discloses a rural power distribution network photovoltaic access capacity improvement method based on hybrid energy storage system dual-time scale adjustment capability. The method comprises the following steps: step 1, analyzing rural power consumption demands and seasonal distribution characteristics of illumination resources; step 2, establishing a random scene generation method for generating load and illumination intensity based on a Latin hypercube sampling method; step 3, establishing a hybrid energy storage system dual-time scale operation model; step 4, establishing a two-stage optimization model with the goal of maximizing the photovoltaic absorption capability; 5, solving the two-stage stochastic optimization model by using an improved step-by-step hedging algorithm; and 6, outputting a two-stage optimization decision: determining the access capacity and position of the distributed photovoltaic power supply and the hybrid energy storage system, and making a dual-time-scale optimal operation decision of the hybrid energy storage system. According to the method, the rural load demand and the photovoltaic resource mismatch problem can be reduced to the maximum extent, and the renewable energy utilization efficiency and the operation economy of the rural power distribution network are improved.

The application discloses a kind of based on material absorption spectrum's terahertz time-domain signal horizontal axis matching method, the terahertz time-domain signal of measured material is obtained using terahertz time-domain spectroscopy system, obtains the sampling point number of terahertz time-domain signal;From the standard frequency domain signal of measured material in terahertz standard database is acquired, obtains the multiple absorption peaks of material and each absorption peak position;The frequency domain signal of test is obtained by fast fourier transform to measured terahertz time-domain signal;Equivalent sampling interval of time-domain signal is set as optimization target, the sum of the difference of all absorption peaks of the frequency domain signal of test and standard frequency domain signal is as error function and set error function convergence condition;Error function is optimized by random optimization algorithm, until error function reaches convergence condition, and the optimized time-domain equivalent sampling interval is output;Through the optimized time-domain equivalent sampling interval, frequency domain equivalent sampling range is calculated and obtained, combined with sampling point number, obtain the matched time, frequency domain horizontal axis.

The invention discloses a micro-grid operation random optimization method based on source load probability prediction. The method comprises the following steps: firstly, performing energy-sensitive self-organizing segmentation on source-load historical time sequence data, and extracting morphological fingerprint features; and adopting an improved affinity propagation clustering algorithm fused with a power system operation constraint penalty mechanism to identify a typical operation mode. Secondly, a quantile regression model based on a gated pulse neural P system is established in each mode for probability prediction, and a probability scene library with weights is generated; and finally, constructing a two-stage stochastic optimization model with the goal of minimizing the expected operation cost, and solving by adopting a Benders decomposition algorithm to obtain a fixed equipment plan and a flexible operation strategy. According to the method, through refined mode recognition and probability modeling, on the basis of fully considering the uncertainty of the source load, robust optimization of economic operation of the micro-grid is realized, and the expected operation cost of the system is effectively reduced.

The invention provides a day-ahead multi-grid transaction method considering multiple uncertainty factors, provides a joint modeling method comprehensively considering interval inflow and load multiple uncertainty, and accurately describes spatial correlation among multi-basin inflow through a copula function; a conditional value-at-risk-based regret degree minimization decision model is constructed, and the problem that the risk of a traditional expected value criterion is out of control in an extreme scene is solved; a complete two-stage random optimization framework is established, and effective coordination of a day-ahead plan and real-time adjustment is realized; an adjustable risk control mechanism is developed, and economy and safety are flexibly balanced through risk coefficients. Compared with a traditional method, the method has the advantages that the robustness and practicability of multi-power-grid transaction decision making are remarkably improved, and an effective risk management tool is provided for multi-power-grid collaborative operation in an electricity market environment.

The invention discloses an island micro-grid optimization scheduling method and system considering a frequency response whole process, and belongs to the field of island micro-grid optimization scheduling, and the method comprises the steps: generating a photovoltaic output typical day scene through K-means clustering, and constructing an island micro-grid basic random optimization scheduling model; dividing the frequency response of the island micro-grid after disturbance into three parts; constructing an island microgrid disturbance power and mechanical inertia expression based on frequency response characteristics under generator N-1 off-grid disturbance; and aiming at the three parts of frequency response, linear frequency stability constraints are respectively constructed by coordinating multiple frequency modulation resources, and the linear frequency stability constraints are integrated into a basic random optimization scheduling model of the island micro-grid, so that the island micro-grid optimization scheduling method considering the whole process of frequency response is formed. According to the method, the stable frequency under the N-1 event is guaranteed, the source-load-storage response potential is mined, the operation cost and the dependence on the generator are reduced, and safe and efficient operation of the island microgrid is supported.

The invention discloses a rural integrated energy system optimization scheduling method considering multi-energy coupling and microclimate. The method comprises the following steps: S1, constructing an electricity-gas-heat-hydrogen multi-energy flow coupling system model; s2, microclimate modeling and scene extraction are carried out, and a dynamic correction model of meteorological variables on photovoltaic and wind power output, user load behaviors and electric heat pump energy efficiency under microclimate is established; extracting a typical scene set according to the collected historical microclimate data; s3, establishing a unified time sequence constraint model for various heterogeneous flexible resources, and constructing a'operation area polyhedron 'of the heterogeneous flexible resources in a multi-dimensional space; s4, constructing a day-ahead-real-time two-stage random optimization scheduling model which comprises a day-ahead decision-making stage and a real-time scheduling stage; and S5, constructing a cloud edge collaborative hierarchical distributed optimization framework, solving a day-ahead-real-time two-stage random optimization scheduling model, and finally outputting a multi-time scale scheduling decision covering a day-ahead plan and real-time adjustment.

This invention discloses a distributed task offloading method and apparatus suitable for AI inference on mobile devices. The method involves a performance evaluator that obtains the execution time of the AI ​​model on both an edge server and the mobile device, and comprehensively assesses the offloading gain of offloading the AI ​​model's execution task to the edge server, considering the difference in inference accuracy. A workload predictor constructs a load prediction model based on historical load data periodically pushed by the edge server through polynomial fitting, and predicts the future workload of the edge server using this model, obtaining a load prediction result. A distributed task scheduler combines the offloading gain and the load prediction result to construct a stochastic optimization problem, and determines the optimal execution position of the AI ​​model on the local machine or the edge server by solving the stochastic optimization problem. This invention meets the high performance and low overhead requirements of AI inference on mobile devices.

This invention discloses a client selection method and system for multi-task federated learning. Addressing the shortcomings of client selection and insufficient consideration of task urgency in multi-task dynamic federated learning scenarios, this invention first constructs a multi-task federated learning system model, defining a utility function that includes learning quality and penalty terms. Second, it establishes fairness constraints and introduces a fairness queue to transform the problem into a queue stability problem. Then, based on Lyapunov optimization theory, it constructs a drift-plus-utility function, transforming a long-term stochastic optimization problem into a deterministic optimization problem for each round of communication by minimizing its upper bound. Finally, it constructs an auxiliary bipartite graph to transform client selection into a minimum-weight bipartite graph matching problem. This invention, by jointly optimizing fairness, learning quality, and task urgency through the Lyapunov framework, transforms long-term constraints into a solvable problem for each round, reducing computational complexity and achieving efficient and fair dynamic client selection.

The invention provides a micro-grid emergency scheduling method and system based on a data-driven security domain. According to the method provided by the embodiment of the invention, the active learning mechanism guided by the information entropy is introduced, so that the real security boundary can be efficiently approached by a small number of high-value samples, the modeling cost is remarkably reduced, and the description precision of the security domain is improved. On the basis, a high-precision dynamic security boundary is used as a hard constraint to be embedded into a two-stage stochastic optimization framework, and collaborative optimization of security and economy is realized in combination with fault prediction and island operation capability. And through simulation verification and performance evaluation feedback, a closed-loop optimization mechanism is formed, finally, the load removal amount is effectively reduced in a disaster scene, and the running toughness and the power supply reliability of the micro-grid are comprehensively improved.

The invention relates to a high and new energy power system balance risk assessment method based on mean value risk coordination, and the method comprises the steps: building a balance risk stochastic optimization model integrating expected operation cost and tail risk control based on a preset mean value-conditional value-at-risk stochastic optimization framework; based on the balance risk stochastic optimization model, constructing a balance risk index system comprising universal indexes and special indexes; and evaluating the overall risk level of the power system based on the universal indexes in the balance risk index system, and evaluating the multi-time scale balance risk of the power system in short-time power imbalance, medium-term power shortage and long-term structural rigidity based on the special indexes in the balance risk index system. According to the method, the economical efficiency and the tail risk can be effectively balanced, the index system has good sensitivity and distinction degree for the system vulnerability under different time scales, and quantitative support is provided for risk assessment and flexible resource planning of the high-proportion renewable energy system under the extreme meteorological condition.

The application provides an optical storage and charging random optimization method based on a multi-port flexible interconnection device, comprising: obtaining community storage system parameter information; constructing a two-stage random energy sharing optimization model, and constructing a benefit distribution model based on cooperative game by using the optimization result of the model; constructing a two-stage robust optimization model according to the two-stage energy sharing optimization model, and constructing an uncertainty probability confidence constraint set by using 1-norm and inf-norm; dividing the two-stage robust optimization model into a main problem and a sub-problem for solving, and outputting a set of optimal scheduling strategies. The application improves the optimal result obtained, and calculates the profit obtained by each community through the energy sharing optimization system by using the benefit distribution model based on game, so that the optimal profit of each community is reasonably and effectively distributed.

According to the distributed optical storage aggregator multi-stage random optimization method, the price and photovoltaic output uncertainty are processed through the process of historical data statistics-Monte Carlo simulation-scene construction, a generated random sample conforms to actual fluctuation characteristics, and the practicability of decision making is improved; quantifying the bidirectional influence of frequency modulation power on the additional income of the electric energy market and the performance income of the frequency modulation market; the frequency modulation power is dynamically optimized by taking multi-market comprehensive income maximization as a target, the added value of the frequency modulation behavior on the electric energy market is quantified through the income linkage model, and the income of the aggregator is remarkably improved.

The application discloses a photovoltaic power generation typical scene extraction method based on multi-dimensional similarity and adaptive graph fusion, and belongs to the technical field of new energy consumption and random optimization of power systems. The method firstly carries out standardization and time aggregation pretreatment on historical photovoltaic output data of multiple power stations; secondly, a comprehensive similarity (PEST) measurement model integrating four dimensions of power, energy, form and time sequence is constructed; then, an adaptive graph fusion clustering (MAGFC) unified optimization model is established, each power station is regarded as an independent view, the similarity subgraph, fusion weight, global consensus graph and spectral embedding matrix of each view are automatically learned through optimization, and the optimal clustering number is automatically determined based on graph theory; finally, an alternating direction optimization algorithm is used to solve the model, and representative daily curves and their probabilities are extracted according to the spectral embedding result to form a multi-dimensional typical scene set. The application overcomes the defects of single similarity measurement, poor multi-station cooperation and preset clustering number of traditional methods, and significantly improves the physical fidelity, adaptive ability and engineering practicability of scene extraction.