227 results about "Uncertainty model" patented technology

The invention relates to the technical field of Internet of Vehicles, and discloses a holographic road network and Internet of Vehicles fusion method and device, equipment and a storage medium. The method comprises the steps of obtaining multi-source heterogeneous data collected by a target sensor, and performing adaptive multi-modal preprocessing on the multi-source heterogeneous data; performing space-time alignment and hierarchical structure recombination on the preprocessed multi-source heterogeneous data to obtain multi-source traffic recombination data; extracting multi-scale spatio-temporal features in the multi-source traffic recombination data, and performing multi-level semantic association, deep probability fusion and uncertainty modeling on the multi-source traffic recombination data based on the extracted traffic feature vector set and the preliminary dynamic traffic knowledge representation to obtain traffic perception probability distribution; and a high-precision dynamic semantic map is constructed based on traffic perception probability distribution, and fused multi-resolution map representation is obtained. According to the invention, the fusion of the holographic road network and the Internet of Vehicles multi-source data is realized, and the accuracy of the traffic characteristic data in the fusion result is improved.

The invention relates to the field of manufacturing execution systems, intelligent production scheduling and industrial data integration, in particular to a clothing regulation and control production method and system based on MES, by integrating production state data and clothing order data which are collected in real time, a production graph model is constructed, Bayesian variational inference is adopted to carry out uncertainty modeling to generate graph representation data, and the production state data and the clothing order data are integrated. And constructing a hypergraph model based on graph representation data, generating a scheduling command by using non-Euclidean embedding and agent collaborative decision, issuing the scheduling command to each production unit for execution, collecting execution data and monitoring abnormality, triggering dynamic rescheduling according to abnormality feedback, and realizing continuous closed-loop optimization of the garment production process. The production efficiency and the resource utilization rate are remarkably improved, and the production risk is reduced.

The invention relates to the technical field of medical image processing, and discloses a human body abdominal fat analysis method based on a medical image, which comprises the following steps: acquiring multi-modal medical image data such as CT (Computed Tomography), MRI (Magnetic Resonance Imaging) and ultrasonic images, constructing a fusion database through multi-scale affine transformation alignment, de-noising by using a model based on a residual self-encoder, and enhancing a boundary in combination with Canny edge detection. A segmentation model is constructed based on an improved U-Net architecture, multi-modal features are fused, and a dynamic convolution kernel and a channel attention mechanism are used for optimization. A quantitative analysis model is established by adopting a multi-task joint learning framework, gradient conflicts are solved, and a lightweight sub-network is searched and generated. Carrying out uncertainty modeling on the segmentation model, and carrying out active learning annotation to optimize the performance. A multi-granularity feature fusion framework is designed, anatomical priori knowledge is embedded to construct an association graph, a structured analysis report is generated, abdominal fat can be accurately analyzed, and diagnosis and treatment of obesity-related diseases are assisted.

The invention relates to the technical field of information retrieval, in particular to an artificial intelligence digital science and technology platform based on big data analysis, which comprises a data uncertainty modeling module for receiving a big data stream, determining a confidence interval boundary for each data item to represent the uncertainty of the data item, generating a data item uncertainty parameter set, and combining each data item with the corresponding data item uncertainty parameter set, and then storing the data item and the corresponding data item uncertainty parameter set to form a structured probability data record. According to the method, by independently establishing an uncertain parameter structure for each data item in the data stream, tight binding of the data items and the corresponding uncertain parameters is realized, a structured probability data record is generated, the precision and reliability of the data in the query and calling process are guaranteed, and retrieval errors caused by isolated storage of the data items are avoided; through probability attribute grouping of a preset space and a numerical range and establishment of a multi-dimensional probability index structure, the search space and the filtering difficulty of probability data are reduced.

A method that includes receiving user input associated with identifying a threshold point associated with a classification task, identifying, a machine learning model, in the first set of visual data, a machine placement candidate point associated with identifying the threshold point, and identifying, based on the machine placement candidate point, a set of baseline confidence values via a baseline uncertainty model. The method includes training the machine learning model based on a determined state space by identifying, subsequent sets of visual data additional threshold points, receiving user feedback indicating an accuracy, comparing the baseline confidence values with locations associated with the additional threshold points, generating reward values based on an identified amount of error, and configuring the machine learning model based on the reward values. The method includes identifying in a second set of visual data, via the trained machine learning model, a visual feature associated with the classification task.

The invention discloses a building integrated energy system optimization scheduling method giving consideration to the comfort level of a light storage soft environment, and relates to the field of building energy system optimization scheduling, and the method comprises the steps: building a photovoltaic output uncertainty model based on Beta distribution according to typical daily solar radiation intensity data; secondly, constructing an energy storage model; thirdly, a comfort level quantitative model considering temperature regulation and control of the indoor air conditioner and the electric water heater is constructed, and the influence on the environmental comfort level is reflected laterally; and finally, according to the various formed models, constructing a building integrated energy system optimization scheduling model considering the light storage soft comfort degree, and performing solving based on a mixed integer linear programming method. The environment comfort level of the building integrated energy system can be quantified, the flexibility of the building integrated energy system is improved by introducing photovoltaic and energy storage equipment, flexible scheduling of load resources is facilitated, peak load shifting is better achieved, the operation cost of the building integrated energy system is reduced, and the operation efficiency of the building integrated energy system is improved.

The invention relates to an uncertainty perception passive multi-target field adaptive image classification method, which is used for image recognition of autism spectrum disorder patients. According to the method, firstly, source domain model parameters are obtained and used for initializing a target model, then resting state functional magnetic resonance images of a plurality of imaging centers are preprocessed, and a plurality of target domains are constructed. On this basis, a current most representative target domain is selected through a minimum inter-domain difference strategy, an uncertainty modeling method based on evidence deep learning is adopted to train a target model, and class feature consistency is improved through domain contrast learning based on a class prototype in combination with a dynamically expanded auxiliary data set; and generating a pseudo tag to relieve the influence caused by tag noise. And finally, a trained target model is obtained through fine tuning optimization, and accurate classification of unknown images is realized. The method does not need to access source domain data, has the advantages of high robustness, high generalization ability and the like, and is suitable for actual cross-center medical image analysis scenes.

The invention provides a virtual power plant dynamic regulation and control method based on deep reinforcement learning. The method comprises the following steps: constructing a virtual power plant dynamic model; the virtual power plant dynamic model comprises a network dynamic model and an equipment dynamic model; constructing a wind power output uncertainty model according to the wind power historical data; constructing a virtual power plant scheduling model based on the virtual power plant dynamic model and the wind power output uncertainty model; the virtual power plant scheduling model is divided into two stages of day-ahead optimization and intra-day adjustment; and optimizing the virtual power plant scheduling model based on a deep reinforcement learning optimization strategy so as to improve the economical efficiency and the real-time performance of scheduling by learning the dynamic characteristics and the scheduling strategy of the equipment. According to the method, the virtual power plant dynamic model containing the wind turbine generator, the combined heat and power generation unit, the heat pump and the electric energy storage unit is established, the accuracy of the model is improved, cooperative regulation and control of all devices in the virtual power plant are achieved, and real-time requirements and economical efficiency are guaranteed.

The invention discloses a multi-energy load prediction method considering multiple uncertainties and suitable for an integrated energy system, and belongs to the technical field of energy load prediction. According to the method, a multi-task learning framework is used for multi-load prediction, the complex coupling relation among electricity, heat and hydrogen loads is captured, and the prediction precision of each prediction task is enhanced; considering the influence of uncertainty factors on prediction, specifically including input uncertainty and model parameter uncertainty, respectively performing uncertainty modeling on the input uncertainty and the model parameter uncertainty, and quantifying the uncertainty risk of the uncertainty factors on load prediction; and in combination with an attention mechanism, the model is helped to pay attention to important time step feature information, and unnecessary information interference is reduced. According to the multi-load prediction method provided by the invention, the coupling relationship between the loads can be captured under the condition that uncertainty factors are considered, and accurate prediction of the multi-energy loads is realized.

The invention belongs to the field of photovoltaic technology, and discloses a distributed photovoltaic and energy storage combined planning method based on deep learning, comprising the following steps: step 1, data collection: collecting a multi-source heterogeneous data set affecting distributed photovoltaic power generation and energy storage system planning; and 2, data processing: carrying out data cleaning, normalization, denoising and feature extraction operations on the multi-source heterogeneous data. According to the invention, a self-adaptive variational auto-encoder model is adopted to carry out deep feature extraction and uncertainty modeling on multi-source heterogeneous data, and a dynamic feature weighting module is introduced to carry out self-adaptive weighting according to the influence of different features of photovoltaic power generation, load demand and electricity price fluctuation, so that the feature characterization capability is optimized; potential nonlinear distribution characteristics in data are accurately captured, the fitting capability of high-dimensional data is effectively improved by combining KL divergence constraint and a dynamic weighting mechanism, and meanwhile, the robustness of the model in an extreme scene is enhanced.

An electrothermal coupling probabilistic load flow calculation method considering time correlation characteristics of an input variable comprises the following steps: introducing an adaptive window width reflection kernel density estimation method to fit wind speed data, and establishing an uncertainty model of the input variable; a Sobol random sequence obeying [0, 1] uniform distribution is generated, a random number sequence considering time correlation is generated by using a position sorting method according to input actual measurement data, and finally a wind speed sequence sample is obtained through a cubic spline interpolation method. Inputting structural parameters of a power system, introducing a heat balance equation, and establishing an electrothermal coupling probabilistic load flow calculation model by being combined with a probabilistic load flow calculation model; and initializing the model, inputting a wind temperature sequence of each scene, and carrying out electrothermal coupling probabilistic load flow calculation by utilizing a Monte Carlo simulation method distribution based on a Sobol sequence. Uncertainty modeling is carried out according to a model output result, the result is evaluated and analyzed, and a conclusion is obtained. The method is of great significance in analyzing the operation condition of the power system and further guaranteeing safe and stable operation of the power system.

The invention relates to the technical field of anti-collision systems, in particular to an offshore wind power construction safety pre-warning system based on AIS (automatic identification system) data, which comprises a ship dynamic uncertainty modeling module for acquiring AIS signal updating frequency and positioning precision marks of a target ship and generating a ship future position probability ellipse. According to the invention, the position coordinate, the speed value and the course angle of the ship are obtained in real time based on the AIS data, the reliability and the motion trend of ship position prediction are determined by combining the AIS signal updating frequency and the positioning precision mark, and the future position probability ellipse of the ship is accurately generated; a protection area is dynamically constructed, comprehensive calculation is carried out in combination with the spatial relation between a ship future position probability ellipse and the positions of surrounding fan pile foundations, and a hourly dynamic collision risk index sequence is obtained; and further according to the statistical deviation between the current motion state of the ship and the standard parameter of the function partition, combining with path difference analysis to obtain a navigation abnormity comprehensive index.

The invention discloses an optimization system and method for participation of an electric vehicle cluster in an electric power standby market, and is applied to the field of an electric power auxiliary service market, and the system comprises a market uncertainty modeling module which is used for constructing a joint uncertainty model of market price and standby calling probability, wherein the model comprises a probability distribution model and a conditional probability model; the risk quantitative evaluation module is used for evaluating risk exposure degrees of different decision-making schemes, including establishing a multi-period risk accumulation model, and comprehensively evaluating balance indexes of expected income, risk openness and opportunity cost; the robust optimization decision-making module constructs a decision-making model according to the market uncertainty modeling module and the risk quantitative evaluation module, and generates an optimal strategy that the electric vehicle cluster participates in the standby market; the adaptive learning optimization module is used for optimizing the decision model through reinforcement learning; according to the invention, risk-controllable revenue maximization can be realized, so that the electric vehicle cluster can efficiently participate in the electric power standby market.

The invention relates to the technical field of collaborative optimization operation of a power system, in particular to an electricity-carbon dispersion collaborative optimization operation method considering source side uncertainty, which comprises the following steps of: coping with fluctuation of wind and light energy in day-ahead scheduling based on a DRO model of a data-driven probability density Wasserstein distance; establishing an uncertainty scheduling model of the source side of the electricity-carbon cooperative system; establishing a DRO day-ahead scheduling model of the multi-zone power system by combining the DRO uncertainty model; the DRO day-ahead scheduling model is converted into a single-layer linear programming model through out-of-sample approximation and constraint dual conversion; and designing a power system electricity-carbon point-to-point transaction distributed coordinated optimization architecture containing grid security constraints, and solving the single-layer linear programming model by adopting an ADMM under a dynamic penalty factor updating strategy to obtain a coordinated operation scheme. According to the method, the data privacy of the multi-zone power system is protected on the premise of ensuring the calculation accuracy, and meanwhile, the solving speed is remarkably increased.

A design and optimization method for a thermal protection system of a high-speed aircraft considers uncertainty of physical property parameters, heat flux density, geometric shape and the like and probability distribution characteristics of the parameters in design and application of the thermal protection system, the uncertainty and the probability distribution characteristics are embedded into a design process, and uncertainty analysis and design optimization of the thermal protection system are achieved; the method comprises the following steps: performing uncertainty modeling on small subsample characteristic parameters such as material attribute parameters, input environment parameters and machining process parameters in thermal protection design by utilizing a nuclear density theory to realize accurate modeling of input parameter uncertainty distribution characteristics; design parameters are optimized through the agent model based on physical information, so that a design model and a result have interpretability, and very high extrapolation and generalization capabilities are achieved.

The invention discloses a power electronic equipment radiation emission level evaluation method and device based on a reverberation chamber, a medium and equipment. The method comprises the following steps: acquiring a reverberation chamber radiation receiving power sample and a transmission coefficient sample; obtaining a radiation power calculation model of the to-be-tested power electronic equipment, constructing a radiation power function of the to-be-tested power electronic equipment, and obtaining a probability density function of a radiation power estimation value and an uncertainty model based on the radiation power function of the to-be-tested power electronic equipment; evaluating a first radiation emission level of the to-be-tested power electronic equipment based on the radiation power calculation model and the uncertainty model; the second radiation emission level is determined according to the radiation power function of the power electronic equipment to be measured, so that the statistical distribution characteristics of the electromagnetic field in the reverberation chamber can be accurately described, and the influence of the independent sampling number on the measurement uncertainty can be quantitatively analyzed; effective evaluation of statistical characteristics and measurement uncertainty of radiation emission of power electronic equipment is realized.

The invention relates to an optimized regulation and control method based on a model considering an uncertain source load operation scene, and the method comprises the steps: solving a predicted value of conventional load power through a load power prediction method, such as a neural network method, and solving predicted values of wind power output and photovoltaic output through a distributed power output prediction method, such as a data statistics prediction method; a prediction error distribution function of wind power output and load power is combined, a source load operation scene generation model considering prediction errors is established, a large number of original source load operation scenes are generated, an improved hierarchical K-means clustering algorithm is used for extracting the original source load operation scenes, and a source load uncertainty model based on the multi-scene technology is established; compared with the prior art, the method has the advantages that the calculation complexity is simplified while the uncertainty influence caused by prediction errors is fully considered, the dependence of a traditional clustering algorithm on the number of target scenes is avoided, and the strong uncertainty of the source side and the load side of the power distribution network is accurately described.

The invention discloses a receiving-end power grid multi-source collaborative optimization method based on an information gap decision theory, and relates to the technical field of power system dispatching. The method comprises the following steps: establishing a multi-source collaborative optimization scheduling model of a receiving-end power grid by taking the minimum operation cost of the receiving-end power grid as a target function; establishing an implicit uncertainty model of an information gap decision theory by taking maximized adverse disturbance of uncertain parameters of wind power output and load demand as a target; an implicit uncertainty model is used as an upper objective function, a multi-source collaborative optimization scheduling model is used as a lower objective function, and an information gap decision theory model considering wind power output and load uncertainty is established; and solving the information gap decision theory model to obtain a receiving-end power grid multi-source cooperative scheduling scheme. According to the method, the receiving end network multi-source collaborative optimization model considering wind power output and load uncertainty is provided based on the information gap decision theory, it is guaranteed that decision takes economical efficiency and robustness into consideration, and the power receiving capacity and the consumption capacity of a receiving end power grid are improved.

The invention provides a rehabilitation nursing planning method and system for plastic burn of a patient, and the method comprises the steps: collecting the physiological parameters, psychological state information and skin healing conditions of the patient, obtaining the basic information of the patient, and carrying out the analysis to generate a health condition score; based on the health condition score and the personalized rehabilitation target, a genetic algorithm is adopted to generate a rehabilitation activity scheme; constructing an uncertainty model by using a Bayesian network, and predicting result distribution of different treatment paths; performing global optimization on the rehabilitation activity scheme by using a mixed integer programming algorithm in combination with the optimization target, the constraint condition and the result distribution to obtain a rehabilitation activity combination implementation strategy; in the implementation process, a closed-loop feedback mechanism is used for regularly collecting and analyzing the actual reaction condition of a patient, and a deep reinforcement learning algorithm is used for adjustment to obtain a target rehabilitation activity combination implementation strategy; according to the invention, highly personalized rehabilitation nursing of the plastic burn patient is realized, the adaptability and the flexibility are high, and the rehabilitation experience and the treatment effect of the patient are improved.

Embodiments of the present disclosure may include a method for processing a spectrum image measurement, the method including receiving a spectrum image measurement. In some embodiments, the spectrum image measurement may include a plurality of power-frequency data values as a function of time and time data. Embodiments may also include selecting a prediction result based at least in part on the time data and an uncertainty model. Embodiments may also include generating a residual error image by applying the prediction result to the power-frequency data. Embodiments may also include scanning the residual error image for an anomaly. In some embodiments, an anomaly may be based at least in part on a portion of the residual error image exceeding a threshold range between a prediction result value and the power-frequency measured data value.

The invention discloses an automatic wharf import container position distribution method with embedded deep reinforcement learning. The method comprises the steps that firstly, for a container lifting area, an objective function is established based on the total processing time of a current batch of containers and the total turnover time of all containers in the future; then, robust peer-to-peer conversion is carried out on the established mathematical model, an uncertainty model is converted into a deterministic model, and constraints of position layout selection are correspondingly added; thirdly, carrying out statistics and simplification on the possible layout of the bay positions so as to greatly reduce the number of constraint conditions in the model; and solving a container turnover upper bound value in the objective function after robust peer-to-peer conversion through a deep reinforcement learning method, and finally obtaining a container position distribution scheme by utilizing a commercial solver. According to the method, on the basis of remarkably improving the solving efficiency of the container position distribution strategy, it is ensured that the wharf has higher stability and reliability when facing the import container operation with high uncertainty, and powerful decision support is provided for wharf operation management.

The invention discloses an electric power and electric quantity balance analysis scene generation method and system considering source load uncertainty, and the method comprises the steps: carrying out the fitting of the distribution of new energy output and load in each time period through employing kernel density estimation according to the historical data of new energy and load, so as to obtain an uncertainty model of a source load prediction error; historical net load data is calculated based on source load historical data, a K-means clustering algorithm is adopted to cluster net load curves, typical net load curve types are obtained, and the occurrence probability of each type is calculated; on the basis of different types of net load curves, according to the new energy and load proportion superposition source load prediction error uncertainty, obtaining a typical scene of power system operation under the high-proportion new energy; and constructing an optimization model with the aim of minimizing the power and electric quantity balance gap of the local power grid / maximizing the new energy consumption, and analyzing the power and electric quantity balance problem of the local power grid researched under the access of the high-proportion new energy by taking the typical scene as input. The method can efficiently and reasonably construct the operation scene of the power system.

The invention relates to the technical field of cloud computing and multi-source data fusion, and discloses a multi-source data fusion method and system based on cloud computing, and the method comprises the steps: obtaining source scene data and target scene data, carrying out the modeling of the uncertainty distribution of a source scene through a Bayesian neural network, and obtaining the target scene data; network parameters with probability distribution are obtained; calculating the domain difference between the source scene and the target scene, and determining the distribution offset degree; uncertainty perception knowledge migration is executed, parameter probability distribution of a source scene model is migrated to a target scene, and the migration intensity is adaptively determined by domain differences; using the migration result to generate a fusion result with a confidence interval, and providing decision reliability evaluation; on the basis of actual feedback of the target scene, uncertainty model parameters are updated, and a migration strategy is optimized; according to the multi-source data fusion method for Bayesian uncertainty migration, knowledge migration can be carried out while uncertainty is reserved and adjusted.

The invention discloses a two-stage optimization scheduling method for a mine energy system. The method comprises the following steps: constructing a mine comprehensive energy system model; establishing a distributed photovoltaic output uncertainty model, quantitatively predicting error space-time correlation through a gamma function and a Gaussian mixture distribution model, and decomposing a regional error by using a node weight coefficient; a distributed ADMM coordination algorithm is designed according to a distributed photovoltaic output uncertainty model, spatial-temporal correlation compensation is realized through a local layer error transfer function and coordination layer global variable updating, and a voltage out-of-limit probability constraint is introduced; and designing a day-ahead-day two-stage optimization scheduling framework, taking the minimum sum of the power generation cost of the gas turbine in the mine integrated energy system model and the photovoltaic light abandoning penalty as a day-ahead stage target, and dynamically adjusting the power deviation through virtual energy storage in the day-ahead stage. The method can effectively solve the problem of mine energy system scheduling under distributed photovoltaic access, and is suitable for a mine comprehensive energy scene with high-proportion new energy access.

Method and device for ship collision avoidance decision-making in restricted waters based on uncertainty modeling. The method includes: combining a ship motion model with a random variable representing the uncertainty of ship maneuverability to construct a motion model considering the uncertainty of ship maneuverability; constructing a ship observation model considering observation uncertainty using a Gaussian distribution; simulating the steering and speed changes of the ship using a Gaussian distribution to construct an uncertainty model for the ship's compliance with rules; capturing the motion uncertainty of other ships during navigation through a deep Gaussian process model and constructing a prediction model for the trajectories of other ships considering motion uncertainty; constructing an optimization model for ship collision avoidance behavior decision-making based on the above uncertainty models and solving the optimal collision avoidance behavior decision for the ship during navigation. The present invention comprehensively considers various uncertainty factors encountered by ships during navigation in complex and dynamic restricted waters, and establishes an optimization model for ship collision avoidance behavior decision-making with strong adaptability to effectively make ship collision avoidance decisions.

The invention belongs to the technical field of power distribution network reconstruction, and particularly relates to a power distribution network multistage reconstruction method and device considering main-distribution linkage under source load uncertainty, and the method comprises the steps: constructing a photovoltaic output model and a load model, and forming a source load uncertainty model; constructing a source load scene, and performing optical load scene generation based on Latin hypercube sampling and Cholesky decomposition through correlation modeling; performing scene reduction; dividing time periods by adopting a fuzzy C-means clustering method; constructing a reconstruction level evaluation double-layer model with the goal of minimizing light abandoning and load loss cost; converting the reconstruction level evaluation double-layer model into a single-layer model through integrated correlation modeling, and setting constraint conditions; and solving the single-layer model to obtain a multi-stage dynamic reconstruction scheme of the power distribution network. According to the method, through multi-scene modeling, time period dynamic division and multi-level collaborative optimization, efficient and stable operation of the power distribution network is realized, and the light abandoning and load loss cost is remarkably reduced.

The invention discloses a mangrove forest protection effect intelligent evaluation and scene prediction system, and relates to the field of ecological environment information intelligence, and the system comprises a key driving factor recognition module which is used for determining a core variable influencing the protection effect and a dynamic response interval of the core variable based on a statistical analysis and nonlinear fitting method; the protection effect quantitative evaluation module is used for calculating a net improvement effect of protection intervention by comparing ecological index differences inside and outside the protection area; the causal effect analysis module is used for separating independent contributions of natural factors and artificial protection by adopting a dual machine learning framework; the space-time dynamic modeling module is used for performing uncertainty modeling on the space-time evolution of the ecological indexes by using a Bayesian hierarchical structure; and the multi-scene prediction module is used for realizing ecological response prediction under multi-factor driving and supporting input and simulation of user-defined scenes. According to the scheme, multi-dimensional and high-precision evaluation and future trend reliable prediction of mangrove forest protection effects can be realized.

The invention discloses a wind power system low-carbon optimization scheduling method considering demand response, and the method comprises the following steps: collecting the prediction data and prediction deviation information of the day-ahead wind power output and load of a wind power system, and building an uncertainty model of a source load; performing random sampling on the wind power and the load by using a Latin hypercube sampling method to obtain an initial scene set of the wind power and the load; reducing the initial scene set of the wind power and the load by adopting a heuristic synchronous back substitution method, generating typical scenes of the wind power and the load, and simultaneously obtaining occurrence probability information of each typical scene; establishing a demand side respondable load model; based on the established demand side responsible load model, establishing an improved stepped demand response excitation mechanism model; constructing a two-stage optimization model by adopting a multi-scene stochastic optimization method, wherein the two-stage optimization model comprises a demand response upper-layer optimization model and a power system lower-layer optimization model; and solving the two-stage optimization model by adopting a Cplex solver, and outputting an optimization scheduling result of the wind power system. Through demand response and multi-element energy coordinated optimization, the supply and demand curve matching degree of the system is improved, and the wind power consumption rate and the low-carbon and economic performance of operation of the system are effectively improved.

The invention discloses a thermal hydraulic flow field prediction method based on an evidence physical information neural network, and the method comprises the specific steps: collecting different physical quantity data sets in a thermal hydraulic system, and carrying out the preprocessing of the data; constructing data loss; constructing physical loss; constructing an evidence uncertainty modeling mechanism, and dynamically allocating evidence weights according to the reliability of different data and physical constraints; constructing a total loss function by integrating the data error, the physical residual error and the evidence reliability; and outputting the trained neural network model and prediction. According to the invention, by introducing an evidence learning mechanism, the uncertainty of the model is dynamically estimated in the network training process, and the adaptability of the model to data with inconsistent noise sensitivity degrees is significantly improved; the uncertainty of the evidence is mapped into a physical quantity weighting coefficient, a uniform normalized weighting loss function is constructed, and the subjectivity and robustness problems caused by manual setting of hyper-parameters for each physical quantity in a traditional physical information neural network are effectively avoided.

The invention discloses a multi-disaster power distribution network recovery method and device considering source load uncertainty, a storage medium and computer equipment, and the method comprises the steps: obtaining meteorological data under a current disaster, determining the fault probability of each line through a preset line fault probability calculation formula based on the meteorological data, and determining a fault line; according to the fault line, identifying a to-be-restored power supply area from the target power distribution network, according to a preset load uncertainty model, determining a predicted load demand of each load node in the to-be-restored power supply area, and based on the predicted load demand, determining a rigid load demand and a flexible load demand of the to-be-restored power supply area; generating a plurality of predicted disaster scenes corresponding to the to-be-restored power supply area according to the meteorological data under the current disaster; according to the network topology of the to-be-restored power supply area, constructing an objective function and constraint conditions; and solving the target function in each predicted disaster scene to obtain a power supply recovery scheme in each predicted disaster scene.