13 results about "Sequential monte carlo methods" patented technology

The invention discloses a comprehensive assessment method for weak links of a power system involving multi-dimensional indexes in extreme weather. The method comprises the following steps: firstly, establishing a multi-dimensional index system containing safety and optimized operation, wherein the system covers the line outage probability, the load loss probability, the electric energy insufficiency expectation, the line heavy load rate and the network loss rate; secondly, constructing a line fault model and a cascading fault model under extreme storm weather, describing fault probability change in combination with a Gaussian function and Weibull distribution, and simulating line segment failure by adopting Poisson distribution; a system state after a fault is calculated through a direct-current optimal power flow model, and a large amount of simulation data is obtained in combination with a non-sequential Monte Carlo method. Furthermore, a fuzzy analytic hierarchy process and a CRITIC method are adopted to calculate subjective and objective weights respectively, subjective and objective comprehensive evaluation is realized through weight fusion, and weak links of the system are identified. The method gives consideration to evaluation scientificity and calculation efficiency, and is suitable for real-time risk evaluation and weak link identification of a large-scale power system in extreme weather.

The invention provides an energy management dynamic planning method for a light storage system under time-of-use electricity price, and the method comprises the steps: building a user behavior feature matrix through collecting and normalizing the start-stop sequence, power change, frequency and other multi-dimensional behavior data of electric equipment, quantifying the uncertainty of a user load through a Bayesian inference and sequential Monte Carlo method, and carrying out the optimization of the user behavior feature matrix. The calculation of the regional level load uncertainty index is realized in combination with a weighted variable coefficient; based on an S-shaped response curve and a moving average mechanism, dynamically adjusting the weights of economical and stable targets, driving multi-target dynamic planning to solve an energy scheduling strategy, and considering both the economical efficiency and the scheduling stability; user behavior modeling and parameter adaptive adjustment are optimized through closed-loop residual analysis feedback, and the accuracy of the model for dealing with load fluctuation and equipment state change and the real-time performance and robustness of scheduling optimization are greatly improved.

The present disclosure relates to a kind of multi-extreme weather adapted offshore electric-hydrogen-alcohol system multi-energy flow failure modeling and supply-demand evaluation method and device.The method includes: constructing system success flow model based on GO method, identifying key equipment failure transmission chain;GO chart is converted into fault tree, combined with the minimum cut set method and sequential Monte Carlo method Quantification system failure probability and equipment contribution;Build wind and light hydrogen alcohol power model, introduce operation control strategy, dynamically evaluate power and fuel supply and demand reliability index;Establish fault-supply coupling mechanism, under the extreme weather such as typhoon, cold wave, strong wind and rain, the output of wind and light and equipment failure rate are doubly corrected, and a three-dimensional comprehensive reliability index system is constructed.The present application realizes the complete causal chain modeling from equipment failure to supply shortage, improves the accuracy and comprehensiveness of system comprehensive reliability evaluation under multi-extreme weather scenario, and can be used for system optimization design, operation decision and risk prevention and control.

The invention discloses an auditable asset allocation system and method based on time-varying risk preference estimation. The system comprises a data acquisition and preprocessing module; the time-varying risk preference estimation module is used for carrying out online Bayesian estimation on the risk preference time-varying hidden state by adopting a sequential Monte Carlo method based on the state space model; the dynamic asset allocation optimization module is used for taking the estimated value as an endogenous variable to be embedded into an optimization model to solve the optimal weight; and the compliance and auditing module is used for recording the full-link log in a tamper-proof manner and generating an interpretable report. According to the method, closed-loop optimization from dynamic risk preference estimation to asset allocation decision is realized, and auditing performance of the whole process is ensured.

The application discloses a kind of virtual power plant energy storage optimization configuration methods for reliability improvement, the method first establishes electric-gas coupling virtual power plant system model, constructs the multi-dimensional reliability index system including self-balancing probability, total missing load expectation and energy storage adequacy probability, then the sequential Monte Carlo method is used to simulate the whole year time sequence of new energy unit random failure, and combined with analytic hierarchy process and maximum minimum normalization method, the comprehensive evaluation model of reliability and economy is constructed, finally with energy storage capacity as decision variable, with the maximum of comprehensive score as target, global optimization is carried out under a variety of operating constraints using particle swarm optimization algorithm, and the optimal energy storage configuration scheme is obtained;The application realizes the reliability improvement and economic balance of energy storage configuration under complex operating environment through dynamic fault modeling and multi-objective collaborative optimization mechanism, greatly enhances the accommodation capacity and energy supply safety of virtual power plant to high proportion of renewable energy.

The invention provides a configuration reliability optimization method, device and equipment for an AC / DC hybrid power distribution network, and relates to the technical field of power distribution networks. The method comprises the following steps: carrying out load type division on loads in a target area, and determining photovoltaic output time sequence characteristics in the target area and load time sequence characteristics of each load type; obtaining an initial configuration scheme of the AC / DC hybrid power distribution network of the target area; taking the initial configuration scheme as an initial solution, and optimizing a preset to-be-optimized item in the initial configuration scheme based on a preset constraint condition to obtain a target configuration scheme of the AC / DC hybrid power distribution network of the target area; wherein in the optimization process, based on photovoltaic output time sequence characteristics and load time sequence characteristics of each load type, a sequential Monte Carlo method is adopted to simulate each configuration scheme and solve a reliability index, and the reliability index is used as a fitness function value. According to the invention, the planning quality and operation benefits of the AC-DC hybrid power distribution network can be improved.

The invention discloses a data center centralized standby power energy storage optimal configuration method based on a cluster sharing architecture. Comprising the steps of collecting historical operation data; constructing a reliability evaluation module which is used for performing fault time sequence simulation through a sequential Monte Carlo method to obtain a reliability value of each data center; constructing a centralized standby power energy storage configuration optimization model according to the reliability evaluation module; taking energy capacity and power capacity as energy storage configuration parameters, taking reliability constraint and energy storage configuration constraint as constraint conditions, taking minimization of energy storage cost as a target function, and taking a combined function of a reliability penalty function and the target function as a fitness function; and solving the centralized standby power energy storage configuration optimization model to obtain optimal energy storage configuration parameters. According to the invention, the problem of shared centralized standby power energy storage configuration of the data center cluster under the reliability constraint can be solved.

The application discloses a risk feature extraction method for a main microgrid, and comprises the following steps: firstly, constructing a new energy output probability model and a system element operation model, and generating multiple system operation scenarios by using a sequential Monte Carlo method; then, determining an active power and reactive power dispatching optimization model, wherein the active power optimization takes the minimum system operation cost as an objective function, and the reactive power optimization takes the minimum system operation network loss as an objective function; subsequently, determining decision variables and constraint conditions of the dispatching evaluation model, and solving system state physical quantities by power flow calculation; then, constructing a risk criterion, determining a risk state data set of each scenario, inputting a random forest algorithm model to quantitatively analyze the risk importance of system features. Finally, determining a risk quantification evaluation method, and constructing a multi-level risk index system according to system risk features. The application can identify key influencing factors under a risk scenario.

The invention provides a coastline trend prediction method based on time sequence analysis, and belongs to the technical field of coastline trend prediction.The coastline trend prediction method comprises the steps that a multi-scale observation data set is constructed, a fractal dimension driving algorithm is adopted to extract coastline features to establish a fractal parameter time sequence, and extreme events are detected through a sliding window; fractal parameters are input into a space-time coupling causal prediction model to train and extract a cross-scale dependency relationship, an extreme event response function is established, a wavefront evolution trajectory is calculated by adopting a spiral wavefront tracking algorithm, and topographic topological features are extracted through a persistent coherence method of topological data analysis; and a prediction result and a topology invariant sequence are fused to generate a probability prediction product containing a confidence interval through a Bayesian hierarchical model and a sequential Monte Carlo method, and the technical problem of inaccurate uncertainty quantization of coastline long-term evolution prediction under the impact of an extreme event is solved based on an artificial intelligence technology.

The invention discloses a multi-radiation source target direct tracking method, which is characterized in that a plurality of spatially distributed receiving arrays perform data acquisition on an unknown number of targets, each receiving array is composed of a plurality of array elements, and snapshot data are synchronously acquired and received, so that a receiving signal model under a multi-array collaborative observation condition is established. For the model, a plurality of spatial covariance matrixes are constructed, noise subspace information of the spatial covariance matrixes is extracted, and a MUSIC spatial spectrum is formed in combination with a subspace decomposition theory. According to the method, a spatial spectrum value is used as an observation likelihood function, and a generalized Labeled Multi-Bernoulli (GLMB) filtering framework is embedded, so that joint estimation of the number and the state of multiple targets is realized. And finally, performing propagation and weighted updating on the state particle set by combining a sequential Monte Carlo method to obtain the position of the target.

The invention relates to a method and system for efficiently evaluating the reliability of a wind power plant system based on a graph neural network, and the method comprises the steps: modeling the uncertainty and spatial correlation of a wind speed through Weibull distribution and a t-Copula function, and capturing time correlation in combination with a vector autoregression model, so as to generate a wind speed sequence with time-space correlation; adopting a non-sequential Monte Carlo method to sample a wind power plant output state and an element fault scene, and constructing a minimum output reduction mixed integer linear programming model considering standby cable switching; a graph neural network based on double-graph topology is introduced, a mapping relation between a fault scene and output reduction is established through cooperative training of a complete set edge supervision graph and a closed edge propagation graph, and rapid regression of EWOL and edge level classification of branch switch states are realized; and balancing the precision of the graph-level task and the edge-level task through a weighted joint loss function. Compared with the prior art, the method has the advantages of efficiently estimating the average loss power of the sample and the like.

The application discloses a centralized standby power energy storage optimization configuration method for a data center based on a cluster sharing architecture. The method comprises the following steps: collecting historical operation data; constructing a reliability evaluation module, which is used for obtaining the reliability values of various data centers through sequential Monte Carlo method for fault timing simulation; constructing a centralized standby power energy storage configuration optimization model according to the reliability evaluation module; taking the energy capacity and the power capacity as the energy storage configuration parameters, taking the reliability constraint and the energy storage configuration constraint as the constraint conditions, taking the minimization of the energy storage cost as the objective function, and taking the combination function of the reliability penalty function and the objective function as the fitness function; and solving the centralized standby power energy storage configuration optimization model to obtain the optimal energy storage configuration parameters. The application can solve the centralized standby power energy storage configuration problem of the data center cluster sharing under the reliability constraint.

The application discloses a kind of mountainous area distribution network long-term risk assessment method, system, equipment and medium, comprising: obtaining historical meteorological data, the average duration of each type of extreme weather and normal weather is counted, the Markov state transition rate is calculated, and the state transition rate set is constructed;Based on the set, the sequential Monte Carlo method is used to generate independent weather state sub-sequence for each type of extreme weather, and is merged according to unified time axis, to form the multi-type composite weather time sequence covering the long-term evaluation period;Combined with the sequence, the segmented modeling is obtained, and the element operating state scene set is aligned with the weather sequence;On this basis, active distribution network optimization operation simulation is executed every time period, the total cycle load shedding power and new energy power abandonment quantity are summarized, the power shortage expectation and new energy power abandonment expectation are calculated respectively, and the long-term risk assessment result is finally output.The application significantly improves the meteorological coupling, physical consistency and operation practicability of risk assessment.