766 results about "Power dispatch" patented technology

The invention discloses a renewable energy power generation power prediction and power dispatching method and system, and the method comprises the steps: collecting the historical power generation data and real-time meteorological data of renewable energy power generation, carrying out the linear interpolation of the historical power generation data and the real-time meteorological data, and carrying out the missing value filling and box plot anomaly detection, obtaining a normalized training data set; constructing a hybrid prediction model by using the normalized training data set and adopting a neural symbol acceleration technology with time logic constraints, extracting medium and long term space time features, and generating a renewable energy power generation power prediction result; and according to the renewable energy power generation power prediction result and the system constraint condition, adopting a linear one-dimensional projection constrained distribution robust control method to formulate a scheduling strategy, and utilizing the scheduling strategy to solve an optimal scheduling scheme through mixed integer linear programming. According to the method, the renewable energy power generation power prediction precision and the power dispatching robustness are remarkably improved.

The invention belongs to the technical field of electric energy dispatching, and particularly relates to a virtual power plant electric energy dispatching scheme optimization method based on intelligent decision analysis, which comprises the following steps: acquiring multi-source related parameter data; constructing a cascade prediction model based on the equipment basic data and the external environment data to obtain prediction results of all levels; constructing a risk assessment model based on prediction results of all levels in combination with equipment basic data and external environment data, generating a risk map in combination with a network vulnerability analysis method, and forming a schedulable resource pool; market risk data are acquired, a market risk comprehensive score is obtained, and a corresponding safety alternative scheme is triggered; and constructing a decision tree, determining a decision path in combination with the risk map, and generating a final optimization strategy. According to the method, through multi-dimensional means such as cascade prediction, risk quantitative evaluation, resource optimization screening and market risk response, high precision, high adaptability and intelligentization of virtual power plant electric energy scheduling are realized.

The invention relates to the technical field of wind power prediction, and particularly provides a generation power prediction method and system for a wind generating set, and the method comprises the steps: firstly obtaining a continuous operation data sequence of equipment state parameters and environment parameters containing timestamp marks, and then carrying out the time sequence feature analysis, generating an equipment state feature sequence and an environmental condition feature sequence, then performing correlation modeling on the two features through feature collaborative analysis operation to obtain a coupling feature sequence reflecting multi-factor collaborative influence, and inputting the coupling feature sequence into a pre-trained power prediction model to obtain a power prediction result; an initial power prediction sequence of a target time period is generated through time context learning and power value mapping operation, finally, an error calibration model is constructed based on historical data, the initial power prediction sequence is dynamically adjusted, and a calibration power prediction sequence is generated and output to a power dispatching system for power generation plan arrangement. And the accuracy of generating power prediction of the wind generating set is effectively improved.

The invention relates to the technical field of power dispatching, in particular to a power distribution network photovoltaic energy storage collaborative optimization dispatching decision-making system based on big data and artificial intelligence. Comprising a source network load storage full-dimension data acquisition unit; a multi-source heterogeneous data fusion processing unit; the dynamic multi-target intelligent optimization decision-making unit is used for constructing a power distribution network photovoltaic energy storage collaborative scheduling strategy through an improved non-dominated sorting multi-target grey wolf optimization algorithm with adaptive weight adjustment; and a closed-loop control execution unit. According to the invention, photovoltaic, energy storage, load and power grid operation data in the power distribution network are comprehensively captured through the source-network-load-storage full-dimension data acquisition unit, and spatial correlation mapping of topological nodes of the power distribution network in a multi-source heterogeneous data fusion processing process is combined; and constraint conditions such as power balance and node voltage during dynamic multi-objective optimization decision making are included, so that neglect on topology and operation constraints of the power distribution network is effectively made up.

The invention discloses a source network load storage oriented regional collaborative scheduling method and system, and relates to the technical field related to power resource scheduling, and the method comprises the steps: traversing target region source network load storage to carry out real-time data collection, and constructing a source network load storage multi-dimensional data set to carry out multi-scale layered optimization; operation constraint conditions are set, limitation is carried out in combination with a power grid topological structure, a cooperative scheduling instruction set is determined, cooperative control feedback is carried out, and regional power scheduling feedback parameters are generated; and multi-channel dynamic correction is carried out, and a cooperative scheduling optimization strategy is generated to carry out energy balance cooperative scheduling on the source network load storage in the target area. The technical problems that in the prior art, intermittent fluctuation of new energy is difficult to consume, the collaboration of all links of source network load storage is poor, the dispatching flexibility of a power system is insufficient, and the resource configuration efficiency is low are solved. The technical effects of optimizing regional energy resource allocation and improving the clean energy consumption level, the power grid operation stability and the source grid load storage cooperative response capability are achieved.

The invention provides a multi-data center computing power-electric power cooperative scheduling and demand response declaration capacity optimization method, which comprises the following steps of: firstly, acquiring multi-dimensional historical time sequence data of a data center; a machine learning algorithm is used to predict the workload of each data center in each time period of a future single day in a future scheduling period and the power market price of the place where each data center is located, and then a space-time coupling-oriented multi-data center computing power-power cooperation model considering uncertainty is constructed; the collaborative model comprises a joint optimization framework of computing power scheduling and power scheduling, and takes actual profit maximization as a target, then the established collaborative model is converted into a mixed integer linear programming problem and solved, and the optimal declaration capacity of each data center participating in demand response is obtained; and each data center carries out scheduling according to the task load of space migration and time migration, the charging and discharging power of an energy storage system and the power generation amount of renewable energy sources, so that overall optimization of demand response declaration capacity of the multiple data centers is realized.

The invention discloses a micro-grid automatic power regulation and control method, and relates to the technical field of micro-grid power regulation and control and resource management. In order to solve the defects of poor new energy consumption capability, high distributed resource management difficulty, poor power grid regulation and control flexibility, poor resource cooperation effect and poor power and load prediction accuracy of an existing micro-grid power regulation and control method, grid-connected and off-grid flexible switching of a power grid A and a power grid B is realized by constructing an integrated construction framework. And multi-source data are integrated, and new energy power generation and load demands are intelligently predicted through data center management. And during grid connection, the distribution and dispatching integrated system determines power dispatching, and the micro-grid management system B makes a dispatching plan. And during off-grid, power is supplied according to the user priority. And in the grid-connected and off-grid mode, power distribution, load regulation and control and resource optimization configuration are carried out, and distributed resources are regulated and controlled in real time through the coordination controller, so that stable operation of the power grid is ensured. The method is mainly used for flexibly regulating and controlling the micro-grid.

The invention belongs to the technical field of power dispatching control, discloses an intelligent dispatching accident plan optimization method based on deep learning, and aims to solve the problems that traditional power accident dispatching depends on artificial experience, the plan generation efficiency is low, and the current situation of wide application of distributed photovoltaic and energy storage is difficult to adapt. According to the core technical path, on the basis of massive historical dispatching accident data, accident processing key features are automatically mined through a deep learning model, distributed photovoltaic output and energy storage charging and discharging features are fused, and a multi-source feature learning framework considering power flow balance in the accident state is constructed; and generating a dynamically optimized structured plan. By applying the method, the generation efficiency and accuracy of the accident plan can be remarkably improved, the accident handling speed is increased, the power failure duration and the economic loss are effectively reduced, meanwhile, the power flow stability of the power system after distributed energy access is guaranteed, and finally the overall reliability and the safe operation level of the power system are improved.

The invention discloses an intelligent power prediction method considering dynamic load change, and relates to the technical field of power grid load prediction, and the method comprises the steps: collecting original load data, carrying out the preprocessing, constructing a VMD constraint optimization model, carrying out the four-stage improvement of optimization parameters through employing an improved dung beetle optimization algorithm, so as to generate IMF components, reconstructing the IMF component by calculating a sample entropy to obtain a low-frequency component and a high-frequency component; establishing a Kalman filtering state space model based on the low-frequency component, and decomposing the low-frequency component into a residual component and a pseudo trend component through a Kalman filtering recursive algorithm; external features are obtained, the high-frequency component, the residual component and the pseudo trend component are aligned and spliced with the external features, multi-component collaborative prediction is carried out through a local-global interactive attention mechanism, and a final load prediction result is obtained; and generating a power demand visualization chart based on the final load prediction result. And reliable decision support is provided for power dispatching and energy management.

The invention relates to the technical field of power dispatching management and control, and discloses a power distribution network power dispatching method based on a virtual power plant AI large model and demand response, and the method comprises the steps: collecting the operation data of a power distribution network, and constructing a feature vector; an AI large model is adopted to calculate and predict load output, and joint uncertainty information is output; calculating a system power unbalance amount, and generating a scheduling strategy; issuing a scheduling instruction corresponding to the scheduling strategy and executing the scheduling instruction; comprehensive performance evaluation indexes are calculated, and whether a performance reduction reason diagnosis mechanism is started or not is judged; according to the method, the AI large model is adopted, the load power, the photovoltaic output and the wind power output are predicted at the same time through a multi-task learning strategy, and the correlation among multiple variables is fully utilized; by constructing a multi-objective optimization model, comprehensively considering economy, safety and reliability and adopting an improved particle swarm optimization algorithm for solving, coordinated optimization configuration of demand response resources is realized, power grid fluctuation is effectively reduced, and power supply reliability is improved.

The invention discloses a power system fault tracing method and system based on data analysis, and relates to the technical field of fault detection, and the method comprises the following steps: collecting multi-source operation data in a target power dispatching system, carrying out the abnormal mode preprocessing, and generating a local abnormal feature sequence of each subsystem; constructing an abnormal feature incidence matrix based on the local abnormal feature sequence, and identifying matrix features based on causal correlation analysis of multi-source operation data to distinguish homologous anomalies and pseudo-synchronization anomalies; based on the identification result, fault boundary identification and anomaly tracing are carried out, and the anomaly level of each subsystem and the corresponding fault source node are output; and generating fault response indication information for scheduling control according to the abnormal level and the fault source node. According to the method, fault traceability and response indication generation are realized through feature association and causal analysis of subsystem abnormity, so that the abnormity judgment precision is improved, and the problems of inaccurate traceability and untimely response of a traditional method are solved.

The invention provides a photovoltaic access power distribution network voltage stability evaluation method, which comprises the following steps: acquiring ship docking time, staying duration and crane working frequency in a port area in real time, fusing obtained meteorological information, identifying a photovoltaic power generation output power change trend, and obtaining a daily power load peak-valley time period and a load fluctuation amplitude; according to the adjusted voltage value of each node, generating a switch operation instruction and a power adjustment instruction of the shore power supply equipment, identifying load abrupt change by executing the instructions, and determining a real-time power dispatching scheme by combining the power adjustment instruction and the ship arrival time; and according to the target voltage control value, determining the power utilization safety state of the port power distribution network, and evaluating the voltage stability of the photovoltaic access power distribution network through the operation data of the photovoltaic power generation access point.

The invention provides a power grid energy efficiency optimization and load prediction management method and device, relates to the field of energy and power, and solves the technical problem of data storage and processing delay caused by poor database expansibility and low algorithm efficiency. The method comprises the following steps: integrating various sensor data and intelligent sensing terminal data to form multi-dimensional data; and sending the multi-dimensional data to an edge computing node for preprocessing, and storing the multi-dimensional data in a distributed storage cluster. Load data and multi-dimensional influence factors in the multi-dimensional data stored in the historical distributed storage cluster are acquired, and a prediction model is constructed. And analyzing the multi-dimensional data stored in the distributed storage cluster through an artificial intelligence analysis engine, capturing nonlinear and non-stationary change characteristics of the load, and obtaining real-time prediction data. And acquiring real-time operation data of each link of the power grid from the distributed storage cluster, and optimizing a scheduling strategy in combination with a dynamic loss characteristic model of the equipment. The method and the device are used in the power dispatching process.

The invention relates to the technical field of power dispatching, in particular to a photovoltaic power generation and energy storage electric cabinet power optimization distribution method based on artificial intelligence. Carrying out meteorological prediction to obtain a future meteorological data sequence in a future time window, and collecting a current operation moment; performing photovoltaic power generation prediction and power consumption demand prediction according to the future meteorological data sequence and the operation time to obtain a future power generation data sequence and a future power consumption data sequence; according to the operation time, analyzing the confidence of the future meteorological data sequence and the future power consumption data sequence, and obtaining a meteorological confidence sequence and a power consumption confidence sequence; according to the future power generation data sequence, the future power utilization data sequence, the meteorological confidence coefficient sequence and the power utilization confidence coefficient sequence, power distribution parameter configuration and optimization are carried out, optimized power distribution parameters are obtained, and power distribution power supply and power storage of the energy storage electric cabinet are carried out in a future time window. And the stability and the economical efficiency of the power system are obviously improved.

Embodiments of the present application provide a flexible resource partitioning method and system based on power flow distribution. The method comprises: using a flexible resource aggregation model partitioning method to perform topological aggregation on flexible resources to obtain aggregation units; using the aggregation units as the basic unit for aggregating the adjustable capacity of the flexible resources, using an adaptive robust optimization algorithm to construct an aggregated resource adjustable capacity calculation model considering network constraints, and performing aggregation calculation on a power adjustment range that can be provided by all the flexible resources within an aggregation area for power dispatch; and solving the aggregated resource adjustable capacity calculation model considering the network constraints, so that feasible upper and lower power bounds of the aggregated resource adjustable capacity calculation model can be decomposed and executed among the flexible resources, thereby implementing flexible resource partition aggregation in continuous time periods.

The invention discloses a power grid equipment intelligent numbering and anti-error checking method and system constructed based on a dispatching numbering agent, equipment and a medium, and belongs to the technical field of power systems and intelligent dispatching. The method comprises the steps that a knowledge graph is constructed through semantic analysis of a power dispatching standard document; extracting equipment attributes and topological contexts and organizing the equipment attributes and the topological contexts into structured prompts; the scheduling numbering agent generates a candidate number with an interpretable reasoning chain based on the knowledge graph; and verifying the number compliance through multi-dimensional introspection check and outputting a final number. According to the method, the intelligent workflow is constructed, the progress from rule matching to standard understanding is realized, and the traceability and logic consistency of the numbering process are ensured while the rule priority and the topology context are precisely processed by utilizing interpretable thinking chain reasoning and auto-reflection check closed loop.

The invention discloses an electric power resource hierarchical scheduling method based on dual-time scale deep reinforcement learning, and relates to the technical field of electric power scheduling, and the method comprises the following steps: S1, dual-time scale definition and constraint setting: dividing a scheduling period into a macroscopic time period (delta T) and a microscopic time step (delta t), and satisfying delta T = M * delta t (M is an integer); setting a resource constraint relationship, wherein the resource constraint relationship is a resource budget upper limit of the region r; s2, unified optimization target modeling: constructing a small-time-scale instant reward function based on time division of S1: coupling the macroscopic resource budget of S1, and designing a large-time-scale target function: S3, large-time-scale strategy modeling: based on the target function of S2, defining a regional state vector, and being capable of considering long and short-term scheduling requirements.

The invention relates to the technical field of power dispatching, in particular to an energy storage combined frequency modulation control method and system in a source-network-load-storage integrated regional power grid, and the method comprises the steps: dynamically calculating the adjustable capacity of each resource, dynamically aggregating the total adjustable capacity of the system, sensing the multi-dimensional frequency situation and calculating the adjusting power, and selecting a frequency modulation mode and generating a power distribution strategy. And generating a splitting and isolated network frequency modulation stability control strategy and performing system grid-connected resynchronous operation. The method is suitable for guiding power supply, energy storage and load all-resource collaborative frequency modulation strategy generation in a regional power grid. For consistency of frequency deviation, frequency change rate and active power flow direction, multi-dimensional frequency situation awareness is constructed, power distribution strategies in different modes are generated based on a total adjustable capacity interval of a system, and a frequency stability control and grid-connected resynchronization strategy after splitting is given when the frequency and the adjustable interval exceed limits. Accurate matching of all-resource collaborative frequency modulation and strategies in a regional power grid is realized, and the frequency modulation response speed of the system is improved.

The invention discloses a power flow out-of-limit elimination method and device based on section sensitivity and source load characteristics, terminal equipment and a storage medium, and belongs to the technical field of power flow out-of-limit elimination. The method comprises the following steps: acquiring unit output data, bus load data, section sensitivity data and section power flow data of the power dispatching system in a preset full time period; dividing the section into a new energy output section, a load center feed-in section and a network loop section according to section sensitivity data, and respectively constructing a new energy output prediction adjustment optimization model, a bus load prediction adjustment optimization model, a non-new energy output adjustment optimization model and corresponding constraint conditions; and solving to obtain an optimal new energy output predicted value, a bus load predicted value and a non-new energy output value, and performing out-of-limit adjustment. By implementing the method and the device, the problem of low out-of-limit elimination efficiency caused by huge calculated amount when the scheduling system is subjected to overall modeling solution in the prior art can be solved.

The invention discloses an electric power dispatching method and device fusing multi-modal data and dual verification, electronic equipment and a storage medium, and belongs to the field of intelligent dispatching of an electric power system.The method comprises the steps that multi-modal dynamic data, including equipment images, load time sequences, logs, dispatching instructions, meteorological early warning and electricity price data, of an electric power system are obtained; visual, time sequence and semantic features are extracted, cross-modal alignment is carried out, and a joint representation vector is generated; based on the vector and the real-time data, an initial scheduling strategy is generated through a reinforcement learning model; and through historical scheme matching and physical constraint verification, determining a target scheduling strategy and executing scheduling. Therefore, by implementing the method and the device, the problems of incomplete power grid state perception caused by insufficient multi-modal data fusion and low reliability caused by lack of automatic credibility verification of the AI scheduling strategy in the prior art can be solved.

The invention discloses a park micro-grid energy prediction and correction method based on a fuzzy language function. According to the method, a park micro-grid photovoltaic power generation capacity is taken as a prediction target, illuminance, temperature and air visibility are taken as core indexes to construct a park micro-grid photovoltaic power generation system prediction model, and the characteristics of high calculation speed and high responsiveness of a fuzzy language function are creatively utilized to track system prediction errors and error change rates. Core parameter indexes of the model are corrected in real time after fuzzy reasoning calculation, so that the model always tracks real-time environment characteristics to realize evolution, the park microgrid energy state is effectively predicted, a basis is provided for power dispatching and the like of the whole system, the charging and discharging time sequence of an energy storage system is guided, and the energy efficiency is improved. Therefore, a scientific solution is provided for the problem.

The invention provides a wind power prediction method based on improved Diffusion-Q. According to the method, a diffusion model and a Q-learning reinforcement learning mechanism are deeply fused through a data preprocessing module, a diffusion model forward process, a Q-learning module, a diffusion model reverse process, an output prediction module and a feedback and optimization module; a generative prediction system with a dynamic strategy optimization capability is constructed, a future wind power sequence is generated through probability distribution of modeling time sequence data in a forward diffusion process and a reverse diffusion process, online dynamic adjustment of diffusion process parameters is realized, and dynamic prediction of the wind power sequence is realized by defining a state space, an action space and a reward function. The model can automatically select the optimal sampling path according to current input and historical performance, prediction precision and robustness are remarkably improved, and the method can be widely applied to wind power plant short-term power prediction, power dispatching system and intelligent power grid energy management and has good engineering application prospects.

The invention belongs to the field of large-model retrieval, and discloses a large-model knowledge retrieval enhancement method and a related system for the field of power dispatching. A dynamic weighting mechanism of time sensitivity and credibility factors is introduced on the basis of a traditional knowledge retrieval enhancement RAG retrieval framework, so that a retrieval result not only depends on semantic similarity, but also depends on credibility factors; and the timeliness and the source reliability of the information can be comprehensively considered. In traditional knowledge retrieval enhancement (RAG), document sorting often mainly depends on semantic similarity, and differentiation processing of content release time and credibility is lacked, so that the problem that information is outdated although the information is similar or the content source is unreliable easily occurs in a scheduling scene. According to the method, after keyword retrieval and vector retrieval are combined to obtain initial semantic related data, the timeliness weight is calculated through the interval between the timestamp of the query content and the current time, and it is ensured that high-timeliness knowledge such as real-time trend data and an operation mode is preferentially presented in sorting.

The invention discloses a lightweight low-delay quantum key distribution method and system adaptive to an electric power scene, and belongs to the technical field of quantum communication and electric power communication crossing. The method comprises the steps cooperatively executed by a sending end and a receiving end: the sending end determines a basis vector based on a pre-associated quantum fingerprint sequence and a timestamp, sends a key through polarization-phase two-dimensional coding, generates a selection mark and executes privacy amplification; and a receiving end synchronizes a timestamp to determine a basis vector, compares the basis vector with the quantum fingerprint to complete authentication, decodes through an integrated module, performs collaborative error correction and executes privacy amplification. The system comprises functional modules of a sending end and a receiving end, is integrated on a miniaturized board card, and supports common-fiber transmission and protocol conversion. According to the method, the problems of high time delay, high deployment cost and poor adaptability of the traditional QKD are solved, the end-to-end time delay is reduced to 14 microseconds, the deployment cost is reduced by more than 60%, the requirements of high safety, low time delay and lightweight deployment of a power system are met, and the method is suitable for key services such as power dispatching and relay protection.

The invention provides a power dispatching data asset full life cycle management method and system. The method comprises the following steps: firstly, collecting power grid real-time operation basic data, calculating a power grid risk grade by means of a power grid risk assessment model, formulating a matching collection strategy according to the grade, and collecting to obtain initial data assets; recognizing and processing abnormal data through a collaborative quality diagnosis algorithm in combination with the real-time state of the power grid, and screening effective data assets; and inputting into a power dispatching decision algorithm, and fusing risks and constraints to generate a power dispatching scheme. And then comprehensively evaluating the scheme by using the data asset utility index, analyzing and determining contribution data assets with remarkable scheduling contribution, and finally dynamically adjusting acquisition and decision algorithm parameters according to an evaluation result and the contribution data assets. According to the invention, full-process collaborative management and control of power dispatching data assets are realized, and the data utilization rate and the scientificity and reliability of dispatching decision are improved.

The invention discloses a power distribution network risk management method, system and device in extreme weather and a medium, and the method comprises the following steps: obtaining meteorological data through detecting weather conditions, and predicting a weather development trend; analyzing the fault risk of each node of the power distribution network according to the meteorological data and the weather development trend; and generating a decision scheme according to the analysis result of the fault risk, and coordinately executing power dispatching and emergency disposal by combining the decision scheme with an emergency communication network for power supply guarantee. According to the invention, the comprehensive management method integrating meteorological monitoring, risk assessment, emergency communication, power dispatching and power supply guarantee is constructed, so that the risk management capability of the power distribution network under the extreme weather condition is remarkably improved; and the precision and timeliness of weather prediction are improved.

The invention discloses a photovoltaic power generation power prediction and power system scheduling method and a system for realizing the method. The method comprises four steps of data acquisition and preprocessing, similar day selection and training set construction, GA (Genetic Algorithm)-fuzzy RBF (Radial Basis Function) neural network modeling and power scheduling plan generation. The method comprises the following steps: selecting a meteorological variable with high correlation degree through a Spearman rank correlation coefficient, and constructing a time sequence feature; similar days are utilized to construct training samples, and the generalization ability of the model is improved; a fuzzy RBF network optimized by GA is adopted to enhance the nonlinear modeling precision; and inputting a prediction result into the power system simulation model, and generating an optimal scheduling instruction by adopting dynamic programming. According to the method, the photovoltaic power prediction accuracy and scheduling efficiency can be remarkably improved, the power grid stability is enhanced, and the new energy consumption capability is promoted.

The invention belongs to the technical field of power dispatching, and particularly relates to a regional data center low-carbon dispatching method and system based on electricity-carbon calculation collaboration.The method comprises the steps that distributed data centers in a region are aggregated to construct a computing power cluster, and then the schedulable power range of the computing power cluster is calculated; then, an upper-layer optimization model of power grid and computing power cluster cooperative scheduling is constructed by taking maximization of scheduling income, electric quantity cost caused by computing power transfer and an error between total scheduling power of the computing power cluster and a power instruction of the power grid as targets, and the upper-layer optimization model of power grid and computing power cluster cooperative scheduling is constructed by taking minimization of regional total carbon emission penalty, task delay penalty and unbalanced load penalty as targets; and constructing a lower-layer optimization model of the internal power distribution of the computing power cluster, substituting the total scheduling power of the computing power cluster obtained by solving the upper-layer optimization model into the lower-layer optimization model, and obtaining the power adjustment amount of each distributed data center for realizing low-carbon scheduling. According to the method, the multi-dimensional information of the electric carbon calculation can be deeply fused, and economy, low-carbon property and reliability are achieved.

The invention relates to the technical field of electric energy dispatching, in particular to an electric energy dispatching method based on an energy storage system. The method comprises the following steps: deploying a distributed sensor array in a battery module to collect multi-source heterogeneous data, and carrying out standardization processing to generate a standardized energy storage data set; performing tensor completion on the standardized energy storage data set to generate energy storage tensor completion data; time-space dimension analysis is carried out on the energy storage tensor complemented data, cross-modal feature fusion is carried out, and an energy storage cross-modal feature space is generated; therefore, through structural processing of multi-dimensional fusion data and dynamic feedback optimization of the digital twinborn model, the problems that traditional cold chain storage environment prediction lags behind and the model adaptability is poor are solved, and the precision of temperature prediction and the intelligent level of storage management are improved.

The invention discloses a virtual power plant optimization scheduling method and device and a medium, and relates to the technical field of virtual power plant optimization, and the method comprises the steps: building a dynamic association map according to electric power resource operation preprocessing data, carrying out the space-time alignment and coupling analysis of the power grid state preprocessing data and the dynamic association map, and obtaining a dynamic credible capacity; by taking the dynamic credible capacity as a power operation constraint and taking the minimum total operation cost of the virtual power plant as an optimization target, constructing an MILP optimization model and solving to generate a power dispatching scheme; calculating the reactive power demand intensity of each power node according to the power grid state preprocessing data, generating a reactive power support demand thermodynamic map, cooperatively solving active and reactive power decision variables of the power dispatching scheme and the reactive power support demand thermodynamic map through a particle swarm optimization algorithm, and outputting a power resource dispatching instruction set; the scheduling efficiency is improved, the operation cost is reduced, and the overall economy and flexibility of the virtual power plant are enhanced.