1055 results about "Power dispatch" patented technology

The invention provides an optical storage charging and discharging station aggregation control and optimization method based on a virtual power plant, and aims to solve the problems of multi-target collaborative optimization, dynamic resource response and uncertainty robustness. By introducing a Markov decision process and an adaptive clustering algorithm, the system can dynamically aggregate photovoltaic, energy storage and charging pile resources according to equipment characteristics, and power dispatching is optimized. A multi-objective optimization model is adopted, economical, technical and environmental objectives are combined, a dynamic weight factor is introduced, and optimal scheduling is generated in combination with a fuzzy decision theory. And real-time compensation is carried out by adopting a rolling time domain control framework and deep reinforcement learning, so that the scheduling precision and the response speed are improved. The edge computing and cloud collaboration mechanism reduces the communication load through a lightweight federated learning model, and improves the scheduling response efficiency. According to the invention, the scheduling efficiency of the optical storage charging station can be obviously improved, the operation cost is reduced, the system stability is improved, and the system has good adaptability and expandability.

The invention relates to the technical field of smart power grids, and discloses a smart power grid power dispatching optimization method, which comprises the following steps of: firstly, acquiring power grid operation data, and processing data missing and noise problems by utilizing federal learning; and constructing a load prediction model through a dynamic time warping algorithm and a specific network. A multi-energy coupling scheduling model and a demand response game model are constructed, and a multi-time scale rolling optimization framework is established. And carrying out sensitivity analysis on scheduling parameters, designing a hierarchical collaborative optimization mechanism, and constructing a robust optimization model to cope with the power flow uncertainty. And integrating a scheduling instruction verification module, and deploying an online incremental learning mechanism. The method can effectively process data, accurately predict load, optimize multi-energy scheduling, guide demand response, deal with uncertainty, verify scheduling instructions and update the model in real time, improves the safety, reliability and economy of smart grid power scheduling, and realizes optimal configuration of power resources.

The invention discloses an energy storage and power grid coordination control system based on photovoltaic preferential energy supply, and relates to the technical field of power system dispatching automation, and the method comprises the steps: collecting the output power of a photovoltaic module, the charge state value of an energy storage unit and a load power demand in real time; dynamically calculating a photovoltaic and energy storage power distribution weight based on a preset photovoltaic priority energy supply strategy, and determining target output power of a photovoltaic module and an energy storage unit; when photovoltaic and energy storage cannot meet load requirements, power grid access control is automatically judged and triggered, so that continuity and stability of power supply are guaranteed. The problems that in the prior art, in the power dispatching process of an optical storage integrated system, dynamic reflection of the photovoltaic priority energy supply principle is lacked, the power distribution mode is not flexible, the power grid access response lags behind, and self-adaptive adjustment of dynamically adjusting the output current according to the real-time operation state is lacked are solved.

The invention discloses a power system load dynamic optimization method based on reinforcement learning. The method comprises the following steps: S1, collecting power system data to construct a state space; s2, constructing a hierarchical reinforcement learning model based on the state space, and dividing a high-level decision and a low-level execution task; s3, training a high-level decision model, and outputting a scheduling task target category instruction in a high-level state; s4, training a low-layer execution model, and outputting a control action in combination with a current node state and a high-layer instruction; s5, introducing an evolutionary mechanism to generate a strategy population and optimizing a low-layer execution model; s6, fusing an evolutionary mechanism and a strategy gradient to synchronously optimize individuals with excellent performance; s7, deploying the trained model to a power dispatching system; s8, performing model parameter fine tuning based on scheduling feedback; and S9, continuously applying the fine-tuned model to load scheduling control. According to the invention, power load accurate scheduling and strategy efficient adaptive optimization are realized, and system responsiveness and operation stability are improved.

The invention relates to the technical field of power dispatching management, in particular to a power grid operation and maintenance intelligent dispatching system based on big data, which comprises a data acquisition module, an anomaly identification module, a state grading module, a trend prediction module and a path planning module. According to the method, the dynamic data of the power grid equipment are collected in real time, state monitoring and fault diagnosis of the power equipment are optimized, the abnormal state of the equipment is detected in real time according to the voltage data, the fault time node is recognized, the accuracy and efficiency of fault diagnosis are improved, and the fault diagnosis accuracy and efficiency are improved by combining the voltage phase deviation value and the temperature gradient rising rate of the equipment. According to the method, the equipment state is judged in time, the equipment overheating risk is monitored, the reliability and safety of a power grid system are improved, efficient execution of operation and maintenance tasks is ensured by predicting the equipment aging condition, optimizing the maintenance strategy, reducing the equipment outage risk and utilizing task cluster path planning and resource scheduling, and the power grid operation and maintenance efficiency and the reasonability of resource configuration are improved.

The invention relates to the technical field of energy dispatching, in particular to a power dispatching optimization method based on optical energy storage, which comprises the following steps: extracting photovoltaic output and charge state fluctuation based on partitions, synchronously identifying abnormal intervals, analyzing direction matching and energy connectivity, screening abnormal units, and extracting linkage units in combination with load and power utilization characteristics. Evaluating power flow deviation, determining an unbalance level, matching a response list, and outputting an automatic linkage scheduling adjustment instruction set. According to the method, photovoltaic output and energy storage state fluctuation are identified in partitions, the accuracy of capturing an abnormal space-time coupling phenomenon is enhanced, the identification depth of scheduling imbalance hidden danger is improved, regional load distribution and power utilization behavior consistency judgment are combined, dynamic load feature evaluation of abnormal units is completed, the abnormal units are scheduled in a layered mode according to risk levels, and the scheduling efficiency is improved. The scheduling range is accurately adjusted, and the response precision and the handling capacity of the scheduling mechanism to the dynamic difference of the load side under new energy fluctuation are improved.

The invention relates to the field of energy management, and discloses an industrial park load prediction method based on artificial intelligence, and the method comprises the steps: collecting historical load, production plan, weather and holiday and festival information through multi-source data; through data preprocessing, a time sequence feature extraction module fusing an attention mechanism and LSTM and a deep learning model integrating a sudden change adaptation module are constructed, and high-precision load prediction is realized. Wherein the abrupt change adaptation module dynamically adjusts model parameters to cope with load abrupt change through sliding window statistical feature monitoring, incremental learning and GAN simulation abrupt change scenes; and a real-time feedback mechanism further optimizes the prediction result, and generates a power dispatching suggestion in combination with a dynamic electricity price strategy. According to the method, the problems of large prediction deviation and poor adaptability of a traditional model in a load sudden change scene are solved, and the efficiency and stability of industrial park energy management are remarkably improved.

The invention relates to the technical field of energy storage systems, in particular to a power dispatching method of an energy storage system and the energy storage system.The power dispatching method comprises the steps that by deploying edge computing nodes and building a cloud global optimization engine, data support is provided for follow-up precise regulation and control, and timeliness and integrity of data acquisition are guaranteed; energy storage equipment capacity and power grid requirements are analyzed by means of an intelligent algorithm, a reasonable response priority is set, tasks are dynamically allocated, and efficient utilization of resources and accurate execution of the tasks are ensured; an MPC algorithm is adopted to take power grid frequency deviation as an optimization target, output instructions are optimized in a rolling mode, prediction errors are corrected, power grid frequency fluctuation adjustment of the energy storage system is achieved, and power grid stability is enhanced; and the long-time energy storage charging and discharging plan is optimized by taking the full life cycle cost minimization as the target, so that the stability of the power grid and the operation economy of the energy storage equipment are effectively improved.

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 provides a power network state recognition method and system based on data feature analysis, which are used for continuously improving the power network state recognition precision through a data-driven optimization mechanism, providing full-process intelligent decision support for power grid operation and maintenance, and effectively promoting the power network to be converted from a passive operation and maintenance mode to an active prevention and control mode. The method comprises the following steps: acquiring a multi-dimensional power data set of a target power network, performing dynamic feature extraction processing on the multi-dimensional power data set to generate a power network operation feature set, and inputting the power network operation feature set into a debugged power state recognition model, and carrying out conjoint analysis on the voltage fluctuation characteristics, the current phase deviation characteristics and the equipment health degree characteristics through a power state identification model to generate a power network state classification result, and generating a network operation and maintenance strategy according to the power network state classification result. And the network operation and maintenance strategy is sent to the power dispatching terminal so as to activate corresponding equipment maintenance operation or load adjustment operation.

The invention discloses a privacy protection federated basic model continuous learning method in a multi-source new energy main body collaborative scheduling scene, and the method comprises a device, a system and a medium, and aims to solve the security defect of user power data transmission, reduce the communication overhead in the transmission process and improve the generalization performance of a federated learning model. Differential privacy protection is carried out on power data of a new energy main body power terminal device, and a homomorphic encryption technology is adopted, so that safe sharing of data and power dispatching optimization are completed under the condition that user privacy is not leaked.

The invention discloses an electric power dispatching system fault detection method based on multi-source data analysis, which relates to the technical field of electric power dispatching system automation and is characterized in that electric power dispatching related data is collected, feature extraction is carried out, a delay fluctuation coefficient Ys is calculated, a delay fluctuation threshold Ysyz is combined, an early warning mechanism is triggered, and fault analysis is carried out. According to the method, scheduling errors or response delay caused by communication link delay abnormity are reduced, potential fault risks are recognized in advance, a packet loss change factor # imgabs0 # and an equipment load change coefficient # imgabs1 # are obtained through calculation, power scheduling system fault reasons are judged, each communication link section is analyzed, risk link sections are marked, a communication link section risk report table is constructed, and a power scheduling system risk report table is established. And executing the fault repair operation.

The invention relates to a power supply quantity self-repairing method based on deep learning, and the method comprises the following steps: S1, obtaining power multi-dimensional data through an intelligent sensor and terminal equipment, and carrying out the preprocessing of the data; s2, constructing a power network graph model based on the power multi-dimensional data, and optimizing the power network graph model by introducing a graph attention mechanism and a time dynamic model to obtain power grid topology dynamic dependency information; s3, based on the processed electric power multi-dimensional data and power grid topology dynamic dependency information, using deep learning to fuse multi-modal information, detecting abnormal behaviors of power supply quantity, and determining abnormal types and grades; s4, according to key nodes identified in the power network graph model and an abnormal grading result, dynamically distributing a repair priority, and outputting a repair value; and S5, performing restoration based on the restoration value and a predetermined execution sequence, and returning the power supply curve to the power dispatching center after restoration is completed. According to the invention, rapid positioning and grading of power supply abnormity and accurate generation of a restoration scheme are realized.

The invention relates to the technical field of charging pile management and power dispatching, and particularly discloses a charging pile operation management method and system. The method comprises the following steps: acquiring charging request data and power grid load data, and generating and cleaning a task vector data set; predicting a charging demand based on the data set and generating electricity price gradient information; a multi-objective optimization scheduling function is constructed and solved, and a task allocation scheduling scheme is generated; executing power control according to the scheduling scheme and collecting charging state data; executing dynamic contract charging and incentive generation according to the state data; and finally, performing Hash packaging and privacy processing on an execution result, and performing uplink to generate a credible record. According to the method, the resource allocation efficiency and the charging incentive intelligence level in a multi-user multi-period concurrent charging scene can be improved, and efficient cooperation and credible execution of the whole charging scheduling and settlement process 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 relates to the technical field of intelligent power system optimization scheduling, and discloses a power load optimization distribution method and system based on an intelligent algorithm, and the method comprises the steps: collecting historical load data of a power system, and carrying out the preprocessing; the fractal dimension of the load time sequence is calculated, a load change critical point is identified, and the size of a time window for load prediction is dynamically adjusted. And inputting the dynamically adjusted time window data into an LSTM model for load prediction. And according to a load prediction result, carrying out intelligent optimization distribution on the power load by adopting an optimization algorithm. According to the method, the optimal distribution of the power load not only has high precision, but also can flexibly cope with various sudden fluctuations and complex constraint conditions in a power system. Through the steps, the operation efficiency, the stability and the economical efficiency of the electric power system are improved, meanwhile, the uncertainty and the risk in load distribution of the electric power system are reduced, and a new thought and technical support are provided for a future intelligent power grid and an electric power dispatching system.

The invention relates to the technical field of electric power information security, in particular to an abnormal behavior detection method and system for electric power sensitive data flow. The method comprises the following steps: acquiring user operation behavior characteristics and data circulation track information through multi-source data acquisition; carrying out joint modeling on the behavior pattern by utilizing short time sequence Markov modeling and a long time sequence Informer structure; multi-dimensional features such as operation frequency, access paths and data types are integrated through a feature fusion module; a plurality of scoring mechanisms are introduced to judge the influence of data exception on the power system; further mining a data interaction relationship among multiple subjects by utilizing graph structure modeling; and a model structure search method is combined to carry out performance optimization on the whole detection process. The method can effectively improve the detection accuracy and real-time response capability of abnormal circulation of sensitive data in complex scenes such as power dispatching, power distribution automation and terminal access, and is suitable for data protection requirements of a power system in a high-safety-requirement environment.

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 relates to an equipment topology layout method and system based on a machine account of an electric power local dispatching system, belongs to the technical field of data processing, and solves the problems that node positions are disordered and connecting lines are crossed easily in the topology layout of existing electric power local dispatching equipment. Comprising the following steps of: perfecting a topological relation among equipment in a machine account of the electric power local dispatching system by utilizing a graph convolutional neural network; to-be-arranged equipment and the topological relation thereof are obtained and put into a candidate equipment set; clustering the candidate device set and initializing the coordinate of each candidate device according to the clustering result; optimizing the initialized coordinates of the candidate devices by using a coordinate optimization model to obtain optimized coordinates of the candidate devices; detecting whether the optimized coordinates of the candidate devices meet topological layout conditions or not, and if yes, rendering to generate a topological graph; otherwise, after the genetic algorithm is adopted to adjust the optimized coordinates of the candidate devices which do not meet the topological layout condition again, a topological graph is rendered and generated. And the layout quality of the equipment topology is improved.

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 electric power dispatching, in particular to an electric power optimization dispatching method and system based on reinforcement learning, and the method comprises the steps: obtaining the operation data, load prediction data and renewable energy output data of an electric power system; based on the operation data, the load prediction data and the renewable energy output data, constructing a power system scheduling optimization model; generating an optimization scheduling strategy based on the power system scheduling optimization model by using a deep reinforcement learning algorithm; calculating the scheduling cost, the environmental influence and the system reliability index of the power system according to the optimal scheduling strategy; and outputting the optimal scheduling strategy and the corresponding scheduling cost, environmental influence and system reliability indexes, so that the operation cost of the power system can be reduced, the utilization rate of renewable energy sources can be improved, and safe and stable operation of a power grid is ensured.

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 discloses an electric power resource scheduling method and device suitable for extreme weather, terminal equipment and a storage medium, and belongs to the technical field of electric power scheduling, and the method adopts nonparametric kernel density estimation to construct a wind and light output joint probability distribution function representing output characteristics of wind power output and photovoltaic output in extreme weather. When flexibility demand analysis is carried out, the advantages of nonlinear correlation between variables and tail risks can be analyzed by means of a joint distribution probability function, wind power prediction errors and photovoltaic prediction errors are accurately analyzed, and then adjustment demand risks of net load flexibility demands are quantified in combination with convolution operation. The problems that the joint probability distribution characteristics of wind and light output in extreme weather cannot be accurately described and the regulation demand risk cannot be ignored in the current flexibility demand evaluation method depending on the normal distribution independent assumption are solved. And the power supply reliability and the operation stability of the power system in extreme weather can be ensured by the formulated power dispatching plan.

The invention relates to the technical field of power dispatching, and discloses a water-wind-light complementary dispatching optimization method and system, and the method comprises the steps: obtaining meteorological data and reservoir water level data, and carrying out the alignment segmentation of the data, and forming a corresponding data sequence; a multi-time-scale coupling prediction model is constructed, and the aligned data sequences are predicted on the corresponding output; establishing a hybrid nonlinear programming objective function, configuring constraint conditions, and minimizing the comprehensive cost of hydropower, wind power and photoelectricity; and setting a plurality of hierarchies according to the predicted duration, and solving the hybrid nonlinear programming objective function. According to the invention, a multi-meteorological-element-multi-energy-form coupling prediction model is established, a coordinated scheduling optimization architecture suitable for complex weather is further constructed, and water-wind-light complementary scheduling optimization is realized in combination with a dynamic optimization weight mechanism based on a meteorological risk coefficient. The method is suitable for peak regulation scheduling of a multi-energy complementary micro-grid and a power grid in a large-scale renewable energy source grid-connected scene.