90results about How to "Accurate modeling" patented technology

The invention discloses a multi-agent spatio-temporal dynamic system intrusion tolerance and fault tolerance cooperative security consistency control method. The method comprises the following steps: constructing mathematical models of a leader and a follower of a multi-agent spatio-temporal dynamic system based on a partial differential equation; constructing a mathematical model of actuator faults and spoofing attacks; defining a consistency condition to obtain an error system; constructing a proper Lyapunov functional, and obtaining a system stability criterion by using a Lyapunov stability theory; and the error of the multi-agent space-time dynamic system tends to zero by using the state feedback controller, so that the system realizes safety consistency control. The invention comprehensively considers that a multi-agent space-time dynamic system is easy to have actuator faults in a complex environment and is easy to suffer from network attacks in network communication, introduces an intrusion tolerance and fault tolerance cooperative security consistency control method, improves the robustness of the system, and improves the reliability of the system. And the multi-agent space-time dynamic system can achieve a safety consistency control target.

The invention discloses a blue-green algae growth prediction method and an intelligent regulation and control device, and relates to the field of blue-green algae growth prediction and regulation and control, and the method comprises the steps: carrying out the collection of blue-green algae growth related data, data preprocessing, random forest model construction, SVM model construction, and model weight fusion of a final random forest prediction model and a final SVM prediction model to obtain a fusion model. And dynamically optimizing the fusion model, finally obtaining the dynamically optimized fusion model, obtaining a real-time prediction result according to the dynamically optimized fusion model by using the blue-green algae growth related data collected by the sensor module in real time, and adjusting the blue-green algae growth culture conditions in real time. According to the method, the advantages of the random forest model and the SVM model are combined, a fusion model with dynamic optimization and real-time adjustment functions is developed, and the accuracy and adaptability of blue-green algae growth prediction are remarkably improved. And meanwhile, data acquisition, processing and prediction modules are integrated, so that the accuracy of blue-green algae growth prediction and the automation degree of the system are remarkably improved.

The invention discloses a multi-satellite task scheduling method and system for a dynamic observation task. The method comprises the following steps: judging a task type, if the task is a regional task, taking sampling points with the number in direct proportion to the size of a task region at a random position of the task region, and generating a point task set with multiple time windows; calculating all visible time window lists of each satellite for each task in workable time, constructing an optimized objective function according to a multi-time window meta-task set, task constraints, resource constraints and a relationship between the task constraints and the resource constraints, and establishing a multi-satellite task planning mathematical model; performing optimization solution on the multi-satellite task planning mathematical model by utilizing a genetic search algorithm to generate an executable observation plan scheme; and performing dynamic task window insertion verification, determining a dynamic task execution window, and generating a final multi-satellite dynamic task scheduling scheme. According to the method, dynamic task planning can be completed, satellite resources are effectively utilized, and task planning efficiency is improved.

The invention relates to the technical field of electric power fault detection, and discloses a fault monitoring system and method based on an electric power acquisition terminal, and the method comprises the steps: constructing a non-linear relation between the power consumption and the temperature through analyzing the historical power consumption data of a user and the weather temperature; the method comprises the following steps: dividing a user electricity consumption day into a plurality of time periods, and setting a time interval threshold value; and in each time period, data are acquired through the electric power and temperature acquisition devices, an electric quantity and temperature scatter diagram is constructed, and nonlinear data fitting is carried out. Thirdly, the similarity between the temperature nonlinear relational expressions of different time periods is calculated, the time periods are divided into sets, and a temperature retrieval set is established; and searching a corresponding electric quantity relation set by matching the temperature nonlinear relational expression of the user in the current time period, and judging whether electric power fluctuation and fault exist or not according to the priority ranking and the relation similarity.

The invention discloses an intelligent driving planning method for a pedestrian interaction scene, and belongs to the technical field of intelligent driving, and the method comprises the steps: building a park environment pedestrian interaction driving scene, and defining the observation and perception states of a vehicle sensor, a target function, and a bottom layer transverse and longitudinal controller; initializing model parameters and an experience playback pool; a human expert drives a vehicle in the simulation scene to generate a driving data sequence, and the driving data sequence is stored in an experience playback pool; training the model by using data in the experience playback pool; deploying a trained model in a simulation scene, planning a vehicle running track, and using a vehicle bottom layer transverse and longitudinal controller to control the vehicle to run according to the planned track; judging whether the model performance reaches the standard or not, and if not, continuing training; and obtaining the model updated at the last time as a training result. According to the invention, the safety and operation efficiency of the intelligent driving planning task in the pedestrian interaction scene can be effectively improved.

The invention relates to the technical field of compressors, in particular to a compressed air energy storage compressor all-working-condition modeling method which comprises the steps that the modeling requirement of a compressor to be modeled is obtained; determining a first rotating speed performance curve of the to-be-modeled compressor, determining at least one state variable according to the modeling demand, building an initial compressor model based on the at least one state variable and a preset constraint relationship, and operating the initial compressor model to obtain a second rotating speed performance curve of the to-be-modeled compressor; a first performance curve is determined according to the first rotating speed performance curve, a second performance curve is determined according to the second rotating speed performance curve, a third performance curve is determined according to the first performance curve and the second performance curve, and the performance curve of the full-working-condition rated rotating speed is obtained through combination. Therefore, the problems of inaccurate modeling, poor universality and low economical efficiency of the compressor are solved, the method is simple and high in economical efficiency, and all-working-condition modeling can be carried out on the compressor with unknown performance.

The invention discloses a power system deep peak regulation method for assisting a thermal power generating unit to provide fast frequency response by combining an energy storage system, which comprises the following steps: collecting system parameters of the thermal power generating unit and the energy storage system, and establishing a model for characteristics of providing frequency modulation resources and inertia resources for the thermal power generating unit and providing fast frequency modulation resources for energy storage equipment; collecting frequency parameters of the system and output data of renewable energy sources, and establishing a model in which the system participates in deep peak regulation and performs frequency and inertia response; integrating the frequency modulation resource and inertia resource model of the thermal power generating unit, the energy storage rapid frequency modulation resource model and the deep peak regulation and frequency and inertia response model of the system into system scheduling to form an energy storage-containing power system scheduling model integrated with deep peak regulation and frequency and inertia response functions; system parameters are imported, and a solver is used for solving the scheduling model, so that an optimized system scheduling strategy is obtained. According to the method, the performance condition of the energy storage-containing power system in deep peak regulation and frequency and inertia response is more accurately considered, so that the optimal scheduling decision conforming to the actual condition can be solved.

The invention discloses an electric vehicle charging demand prediction method based on traffic balance, and the method comprises the steps: firstly building an electric vehicle and a road network model in two dimensions of time and space, and constructing an effective path set for the travel of the electric vehicle through employing an A * algorithm; the finite rationality of a user is considered, time-of-use electricity price is introduced to formulate the electricity price of a charging station, and a semi-dynamic traffic balance model based on a random utility theory is established in combination with traffic flow constraints to solve traffic flow distribution. And then, based on a probability numerical calculation method of a combined state of charge (CSOC), the charging load of the electric vehicle is solved, the charging demand of the electric vehicle is predicted, and the influence of the travel characteristics of the electric vehicle on the traffic capacity condition of a traffic network is comprehensively considered. And the defects of the driving path selection of the vehicle individuals and the path selection under the interaction among the vehicle groups are made up.

The invention discloses an electric power system power supply planning method based on electricity-carbon-hydrogen cooperation and a terminal, and the method comprises the steps: building a first objective function which takes the minimum total investment cost of a system planning period of an electric power system as an objective, and setting an installation scale constraint, an electric power margin constraint and an annual investment net profit constraint which belong to the first objective function; establishing a second objective function, wherein the second objective function comprises a cost function with minimum operation cost and carbon emission cost as a target and a market clearing function with minimum market transaction income as a target; creating a new energy output prediction error constraint corresponding to the power system, and integrating the first target function, the second target function and the new energy output prediction error constraint to obtain a system planning model; and obtaining an input variable, and solving the system planning model. The new energy consumption is promoted while the economic cost is controlled, the uncertainty of new energy output is fully considered, and the safety of the power grid and the economical efficiency of a power generation main body are comprehensively planned.

The invention provides a method and device for constructing a motor fault diagnosis model and a motor fault diagnosis method. The method provided by the invention comprises the following steps: constructing an initial model; acquiring multiple groups of health state data of the motor in a health state, and taking the multiple groups of health state data as a training sample set; based on an adversarial training technology, training the initial model by using the training sample set to obtain a motor fault diagnosis model; and the motor fault diagnosis model is used for outputting the coding loss corresponding to the state data and the classification result corresponding to the state data based on the input state data so as to carry out fault diagnosis based on the coding loss and the classification result. According to the method and device for constructing the motor fault diagnosis model and the motor fault diagnosis method provided by the invention, training is carried out only by relying on the health state data, and the generator optimizes the multiple loss functions, so that the modeling of the model on the health state data is more accurate, and potential faults can be accurately detected and diagnosed.

The invention discloses a TEC distribution reconstruction method and device based on a diffusion model, and the method comprises the steps: preprocessing TEC data, constructing a diffusion model, inputting the TEC data into the diffusion model, and carrying out the forward diffusion and reverse denoising training; after training is completed, random noise is input into a diffusion model for reverse denoising to obtain an unknown area image, TEC observation data with missing are input into the diffusion model for forward diffusion, random noise is added to obtain a known area image, and the unknown area image and the known area image are combined to obtain a first intermediate image; and inputting the first intermediate image and the missing TEC observation data into the diffusion model, performing forward diffusion and reverse denoising again, circularly combining the unknown region image and the known region image, and performing iteration for limited times to obtain TEC reconstruction data. According to the method, the TEC data coverage rate is increased, full coverage in the global range is achieved, the TEC data generation precision and reliability are improved, and TEC distribution is accurately reconstructed.

The invention discloses an electric power system prediction auxiliary state estimation method and device based on deep learning. The method comprises the following steps: firstly, collecting power system data and inputting the power system data into a pre-training neural network integrated with a CNN, an attention mechanism and an LSTM to predict a system state; and an innovation correction amount is determined by using a difference value between a predicted value and an actually measured value, so that a measurement and process noise covariance matrix is adjusted. And finally, in combination with the adjusted covariance matrix and a Kalman filtering algorithm, real-time and accurate estimation of the state of the power system is realized, so that the problem that the state of the power system cannot be accurately estimated in the prior art is solved.

The invention relates to a multilevel semantic perception map construction method for a distributed slam system, and the method comprises the steps: collecting site information, and obtaining an alternative matching frame based on the site information; extracting a feature value from the alternative matching frame, generating a vector as a segment description of the feature value, processing the segment description, and obtaining processed point cloud data; based on the processed point cloud data, constructing a probabilistic 3D occupancy grid map, performing plane segmentation on the probabilistic 3D occupancy grid map, and constructing a 2D grid map; inputting the 2D grid graph into a convolutional neural network model for image depth estimation and semantic segmentation to obtain depth information and semantic information; fusing the depth information and the semantic information to obtain three-dimensional semantic point cloud data; and based on the three-dimensional semantic point cloud data and the camera attitude, obtaining and optimizing a three-dimensional semantic graph. According to the method, the advantages of geometric information of a traditional slam system and the deep learning technology are combined, and efficient sensing and modeling of the environment are achieved.

The invention discloses a special-shaped curved surface concrete roof board construction method, which belongs to the technical field of building construction, and comprises the following steps: S1, designing a special-shaped curved surface concrete structure roof board formwork, deepening a formwork, establishing a curved surface formwork through rhinoceros UV grid fitting, and then designing a support system; and S2, construction of the special-shaped curved surface concrete structure roof panel formwork is conducted, specifically, formwork machining is conducted firstly, specifically, modeling wood secondary keel machining and panel machining are conducted, then on-site splicing construction is conducted, the machined formwork is installed, and concrete pouring is conducted after formwork installation is completed. The formwork and the supports are designed through the rhinoceros UV grids, a manufacturer manufactures the formwork according to a machining drawing, the manufactured formwork is installed on site, concrete pouring is conducted after installation, and the effect of facilitating construction is achieved.

The invention provides a vehicle mileage fuel consumption integral compensation and longitude and latitude compensation method. A vehicle-mounted terminal, a cloud end and a map navigation system are included. Comprising the following steps: S1, data acquisition: collecting the running state and environment information of a vehicle; s2, the vehicle-mounted terminal uploads the collected data to a cloud end at a fixed frequency; s3, performing cloud analysis; s4, performing off-line statistical analysis, and correcting the acquired data; whether abnormal data points exist in the collected data or not is judged, averaging or interpolation is conducted on the abnormal data points through data of a plurality of moments before and after the abnormal data points, reasonable values of the abnormal data points at the moments are estimated, and the collected data are updated and corrected; according to the method, abnormal conditions in T-Box uploading data can be effectively processed, and the accuracy and reliability of mileage and fuel consumption data are ensured by using an integral method and a latitude and longitude compensation method. The method is of great significance to applications such as vehicle remote monitoring, motorcade management and driving behavior analysis.

The invention discloses an aero-engine unit bearing fault diagnosis method based on deep learning. The method comprises the following steps: (1) extracting vibration signal data of an aero-engine unit bearing and preprocessing original data; (2) preprocessing the original data by adopting EMD and SG filters, and constructing an SWAFormer-FMNet diagnosis model by fusing SWAFormer with FMNet so as to diagnose a bearing vibration signal; (3) applying Tent chaotic mapping, a Gaussian random walk strategy and a differential variation strategy to obtain an improved dung beetle optimization algorithm; (4) using the improved dung beetle algorithm to optimize three parameters of a learning rate, a hidden layer number and a batch processing size in the diagnosis model; and (5) establishing an SWAFormer-FMNet diagnosis model based on the improved dung beetle algorithm. Compared with the prior art, the method can be applied to the aero-engine unit bearing fault diagnosis modeling process, has the advantage of high optimization precision, and finally ensures the accuracy of aero-engine unit bearing fault diagnosis.

The invention discloses an MEMS vibration sensor resonant frequency self-checking method, system and device, and the method comprises the following steps: employing time domain continuous signal excitation as a response input signal, and collecting a dynamic response signal of an MEMS vibration sensor; establishing a dynamic response mathematical model of the MEMS vibration sensor; the collected dynamic response signals serve as identification data, and resonant frequency parameters in the dynamic response mathematical model are subjected to high-precision identification through a BP neural network optimized through an improved particle swarm optimization algorithm; and calculating the mechanical sensitivity of the MEMS vibration sensor based on the identification result of the resonant frequency parameter. The invention relates to the technical field of MEMS vibration sensor dynamic model parameter identification, and can effectively improve the identification precision of the resonant frequency of an MEMS vibration sensor.

The invention discloses a five-degree-of-freedom electromagnetic positioning system and method, and the system comprises a transmitting unit which comprises a plurality of single-axis transmitting coils and is used for generating a magnetic field in a three-dimensional space; the receiving unit is used for collecting field intensity information in a three-dimensional space; the control and data processing unit is used for inputting the field intensity information collected by the receiving unit into a pose initial value prediction network and outputting initial pose information of the receiving unit; inputting the initial attitude information into a coil magnetic field modeling network to obtain theoretical field intensity; and the iterative optimization module acquires a field intensity difference according to the theoretical field intensity and the acquired field intensity information, updates the attitude information according to the field intensity difference, and returns to execute the step of acquiring the theoretical field intensity until a preset iteration termination condition is reached, thereby acquiring the final attitude information. The method can reduce the complexity of a traditional electromagnetic positioning algorithm, improves the positioning precision and speed, can be widely applied to the fields of auxiliary medical treatment, man-machine interaction and motion tracking, and achieves a multi-degree-of-freedom electromagnetic positioning function.

The invention relates to the technical field of sewage treatment, and discloses a sewage biochemical treatment process abnormity intelligent early warning method and system based on image recognition, and the method comprises the steps: periodically collecting a sludge image and water quality sensing data; extracting floc form, bubble distribution and color texture features of the image, and performing space-time alignment fusion with the sensing data to construct a multi-source fusion feature matrix; inputting the matrix into a pre-trained digital twin evaluation model, calculating a dynamic deviation degree between a current state and a normal working condition, and identifying an abnormal mode; and generating a graded early warning signal according to the deviation degree and the abnormal mode and pushing the graded early warning signal. The system comprises an online image acquisition unit and a water quality sensor array which are used for data acquisition, and a feature processing module used for feature processing and fusion. According to the scheme, early-stage, accurate and intelligent early warning of abnormality in the sewage biochemical treatment process is realized, the false report and missing report rate is reduced, and the accuracy and the reliability of the system are improved. And the operation stability and the regulation and control efficiency of the system are improved.

This invention discloses an efficient formal verification method for masked circuits with multi-output composable security. The steps include: generating a complete set of internal probes for the masked circuit using a security model, traversing each security level; enumerating all possible probe sets according to the current security level; calculating the corresponding leakage set for each enumerated probe set using the security model; simplifying the current leakage set if it is not empty; if a simulation set is found based on the simplified leakage set such that the probability distributions of the variables in the middle are statistically independent, then the next probe set is enumerated and the corresponding leakage set is calculated; if no suitable simulation set is found, the masked circuit is determined not to meet the given security concept, and the current leakage set is used as a counterexample, returning to the maximum security level. This invention provides accurate and reliable detection results and higher verification efficiency.

The present invention provides an offline payment financial system and method based on blockchain, including: when one or both of a payment communication terminal or a payment communication terminal are offline, the payment communication terminal establishes a connection with the payment communication terminal and communicates with the payment communication terminal, the payment communication terminal receives payment data and payment account information sent by the payment communication terminal, the payment communication terminal verifies transaction information based on the payment data and the payment account information, the payment communication terminal completes payment processing based on the transaction information verification conclusion and feeds back the payment result and payment account information to the payment communication terminal, by establishing offline short-range communication, receiving payment data and payment account information, completing the processing of transaction bills in the offline state, and uploading the bill information, payment account information, and payment account information to the blockchain system, completing mobile payment in the offline state, and ensuring the normal operation of mobile payment in the absence of a network.

The invention relates to a multi-layer network state prediction method based on multi-mode spatio-temporal data modeling. The method comprises the following steps: acquiring spatio-temporal multi-mode data capable of reflecting interaction of nodes in a multi-layer dynamic network; associating connectivity and attribute information of nodes with a network group through Bernoulli distribution and Poisson distribution on the basis of space-time multi-modal data, establishing a multi-layer space-time Hawkes process with a shared group so as to capture interaction between each layer of nodes from historical events to subsequent events, and constructing a multi-modal space-time model; and solving parameters of the multi-modal space-time model by using a hierarchical expectation-maximum algorithm with local convergence to obtain a network state prediction result. Compared with the prior art, the method has the advantages of accurate modeling, accurate prediction and the like.

The invention relates to the technical field of scanning devices, in particular to a quick response X-ray scanning device based on a micro-electro-mechanical chip, which comprises a detection table, a photoelectric sensor is arranged in the detection table, a plurality of positioning blocks are arranged on the detection table, and a table top of the detection table is used for bearing an object to be imaged; the X-ray source is arranged above the detection table and can emit X-rays to the direction of the detection table, and the X-ray source is connected with a movable support capable of driving the X-ray source to move; the detector is connected with the detection table and can receive the X-rays penetrating through the object to be imaged and convert the X-rays into digital signals; the detection table fixes the position of an object to be imaged through the positioning block, the image acquisition module acquires an image of the detection table, and the control module adjusts the position of the X-ray source according to the position of the object to be imaged on the image so as to completely scan the object to be imaged. By accurately positioning the position of the object to be imaged and standardizing the image of the object to be imaged, the accuracy and reliability of the whole scanning process are improved, and the scanning efficiency and the imaging quality are improved.

This invention discloses a mobile firefighting equipment specifically designed for lithium battery fires, comprising an autonomous firefighting robot, a guide hose, and a trailer. Based on multi-sensor data fusion, it achieves automatic fire source identification and location, automatic mapping, autonomous navigation, and automatic firefighting, making it suitable for scenarios requiring rapid response and safe firefighting. The mobile chassis houses an industrial control computer, a GNSS navigation module, a mobile power supply module, and a heat dissipation module. Sensors and signal receiving equipment are located on top of the chassis. A thermal imager identifies the fire source, and combined with lidar and a depth camera, it achieves environmental modeling and autonomous obstacle avoidance in complex fire scenes. The industrial control computer calculates the target pose in real time based on sensor data and controls the high-pressure water cannon to aim at the fire. The trailer integrates a high-pressure water pump to provide continuous firefighting power. This solves the problem of limited perception in dense smoke and high-temperature environments. While ensuring a high water capacity, it enhances the robot's intelligence level and has extremely high practical application value.

The invention relates to the technical field of ocean platform pipeline design, in particular to an ocean platform pipeline laying method based on reinforcement learning, and the method comprises the following steps: S1, dispersing a pipeline laying region into a three-dimensional grid matrix according to the physical size of an actual cabin of an ocean platform, and marking a pipeline starting point, a pipeline ending point and an impassable region; s2, performing Q-Learning algorithm parameter initialization configuration, defining an action space adaptive to the linear movement characteristics of the ocean platform pipeline, constructing a Q value matrix adaptive to three-dimensional space coordinates and actions, and performing initialization; s3, entering a training round, and continuously updating the value evaluation matrix by dynamically adjusting a greedy criterion, a multi-dimensional reward mechanism and a time sequence difference learning rule; and S4, after the training is completed, starting from the starting point based on the converged Q value matrix, selecting an optimal action through a greedy to generate a final pipeline path, and improving the quality and search efficiency of pipeline laying on the ocean platform.

This invention provides a method for optimizing cooperative detection array positions for underwater vehicles (AUVs). It constructs a target optimization function for AUV cooperative detection array positions by coupling AUV detection errors with their own positional errors, aiming to minimize the global average detection error. This ensures that passively detected AUVs construct array positions with maximum cooperative detection accuracy. An improved HS-DPSO fusion algorithm iteratively optimizes the target optimization function. During local optimization, a dynamic inertial weight adjustment strategy combining normal distribution randomness and an adaptive expectation mechanism is employed. This allows the inertial weights to fluctuate dynamically and regularly in each iteration, enhancing the algorithm's ability to escape local optima. Furthermore, the adaptive random weight expectation value is dynamically adjusted using random numbers, avoiding the limitations of manually pre-setting fixed random weight expectation values ​​and improving the algorithm's adaptability to different detection scenarios. This method enables each passively detected AUV to quickly obtain its optimal cooperative detection position, improving the efficiency and accuracy of AUV formation cooperative detection.

A method for controlling a modeling device correcting a target position of a welding torch includes: a step of acquiring a reference profile prepared in advance and including a shape of a positioning index body implemented by at least a part of a base metal or a weld bead; a step of measuring a shape of the positioning index body by a shape measurement unit attached to the welding torch or the manipulator to acquire an actual profile; a step of comparing the reference profile with the actual profile of the positioning index body to obtain a deviation amount of the target position of the welding torch based on a positional deviation of the positioning index body between the reference profile and the actual profile; and a step of outputting an operation correction command of the manipulator for correcting the target position of the welding torch according to the deviation amount.

The application discloses a kind of based on deep separable convolution improved remote sensing image road extraction method and system, it is related to remote sensing image processing technical field.A kind of based on deep separable convolution improved remote sensing image road extraction system, including have: data acquisition module, tree crown shadow compensation module, model construction module, model training module, road extraction module, storage module and display module.The application is compensated by constructing tree crown translucent shadow compensation module, and the shadow attenuation priori graph generated based on radiation transmission physical model DART is fused with original image channel cascade, so that the model can understand the formation process of tree crown shadow from the physical mechanism level, effectively restore the occluded road information, solve the technical problems that traditional deep learning method lacks explicit modeling of translucent shadow, and it is difficult to distinguish real road dark area and shadow false dark area.

The application provides a three-level converter overall power loss calculation and optimization method, and belongs to the technical field of power electronic converters.The application is aimed at the problem that the traditional three-level converter ignores the filter inductance current in loss evaluation, and is based on accurate modeling of the amplitude of the filter inductance current ripple component, and models the overall power loss of the three-level power electronic converter as a mathematical function about the switching frequency, which is composed of the conduction loss power and switching loss power of the semiconductor power device, the filter inductance loss power and the bus capacitor loss power.The application can be used not only for converter loss evaluation, but also for guiding the switching frequency optimization, and further improves the operation efficiency of the converter.

The invention discloses a thermal power and energy storage combined deep peak shaving method with an inertia supporting function. The method comprises the steps that firstly, related system parameters of a thermal power generating unit and energy storage are collected, and corresponding models are established according to the characteristics of inertia resources provided by an energy storage system and the thermal power generating unit; secondly, collecting frequency parameters of the system and output data of renewable energy sources, and establishing a model in which the system participates in deep peak regulation and performs inertia response; then, integrating the inertia standby model of the energy storage and thermal power generating unit and the deep peak regulation and inertia response model of the system into system scheduling to form an energy storage-containing power system scheduling model integrated with deep peak regulation and inertia response; and finally, based on system parameters, solving the scheduling model to obtain an optimized system scheduling strategy. According to the method, the performance of the energy storage-containing power system in deep peak regulation and inertia response can be more accurately considered, so that an optimal scheduling decision which better conforms to the actual situation is obtained.