356 results about "Power optimization" patented technology

The invention discloses a multi-modal perception and optimization method and system for a low-power-consumption AR device, and the method comprises the steps: collecting multi-modal data, task demands, resource state data and environment data for the AR device; lightweight processing is carried out on the multi-modal neural network model through model pruning, parameter quantification and distillation technologies; inputting the collected data into a lightweight multi-modal neural network model for dynamic reasoning to obtain a multi-modal recognition result; comprising the steps of executing modal adaptive weight acquisition based on task requirements and environment data; executing energy consumption constraint scheduling according to the equipment resource state data, dynamically selecting a reasoning path strategy, and obtaining corresponding modal feature output; multi-modal feature fusion is carried out, task reasoning is completed, and a multi-modal recognition result is obtained; early-leaving control is executed based on a middle-layer confidence coefficient threshold value in the reasoning process; and interactively outputting a real-time multi-mode identification result. According to the invention, energy efficiency and precision balance and multi-mode fusion low-power-consumption optimization can be realized.

The invention discloses a hydroelectric generating set speed regulation control method considering excitation coordination. The method comprises the steps that 1, system state information is collected and preprocessed; step 2, on-line identification of excitation speed regulation coupling characteristics; 3, decomposing a multi-time-scale control target; step 4, designing a self-adaptive multivariable controller; 5, working condition self-adaptive parameter optimization; step 6, intelligently inhibiting the water attack effect; 7, multi-machine cooperative reactive power optimization control is carried out; 8, optimizing and executing a control strategy in real time; the technical problems that excitation speed regulation dynamic coupling, multi-time scale response mismatch, multi-machine cooperative control and the like in a hydroelectric generating set control system cannot be comprehensively solved in the prior art are solved, and the regulation response speed and the system operation safety are improved while the frequency and voltage stability is ensured.

According to the large power grid reactive power optimization method and device, the storage medium and the computer equipment provided by the invention, the advantages of the two algorithms are fully exerted through the hybrid chaos quantum particle swarm optimization algorithm and the dimension-by-dimension convex space search algorithm. According to the chaotic quantum particle swarm algorithm, the global search capability and the capability of jumping out of local optimum of a particle swarm are enhanced by utilizing the characteristics of quantum behaviors and chaotic mapping, and the problem of premature convergence of a traditional heuristic intelligent algorithm is avoided. And according to the dimension-by-dimension convex space search algorithm, fine search is carried out on each excellent particle in different dimensions, a local optimal solution is determined, and the search precision and efficiency are further improved. According to the design of the hybrid algorithm, special optimization is carried out aiming at the characteristics of a reactive power optimization problem model, such as variable property difference, constraint complexity and the like, and the technical defects of poor optimization effect and optimization efficiency of an optimization solution algorithm in the prior art are effectively overcome.

The invention discloses a multi-energy fusion system cooperative scheduling method and device in a port dynamic scene, and relates to the field of port energy system optimization scheduling, and the method comprises the steps: constructing a dynamic coupling relation model according to port data; according to the energy system power of each area at the current time point, a multi-objective optimization model is constructed, and objective functions of the multi-objective optimization model include operation cost minimization, total carbon emission minimization, energy storage equipment service life maximization, energy storage equipment power optimization and energy storage equipment power optimization. The constraint conditions of the multi-objective optimization model are power balance, energy storage charge state, electric hydrogen equipment capacity, berth distribution continuity and load demand priority; according to the multi-target optimization model and the port data of each region at the current time point, determining a target collaborative scheduling operation strategy of each region at the current time point, the target collaborative scheduling operation strategy comprising a multi-energy output distribution scheme, a load response instruction and an equipment operation parameter; and executing the target collaborative scheduling operation strategy of each region at the current time point.

The invention relates to the technical field of indoor 5G network optimization, and discloses an indoor 5G network optimization system based on ray tracing, which is characterized in that a network signal state parameter set is dynamically acquired through a signal parameter acquisition module, a signal coverage risk is judged, and a collaborative analysis instruction is triggered to execute a ray tracing analysis module and an interference characteristic analysis module; and respectively acquiring a propagation stability index and an interference evaluation value. And the multi-source fusion judgment module receives the two values to carry out cooperative analysis on the network coverage adaptability, and generates antenna adjustment and power optimization signals. And the optimization parameter generation module is matched with the strategy to generate antenna angle adjustment and power correction parameters. The system further comprises a coverage coupling analysis module monitoring signal and building structure coordination and a dynamic feedback execution module to form a closed-loop control link, and intelligent optimization of an indoor 5G network is achieved.

The invention relates to a station domain control method and system and a storage medium. The station domain control method comprises the steps of data acquisition and state monitoring, wherein the information of electric power flow, vehicle charging state, power grid load and energy storage state of a charging station is mainly acquired; load prediction and electricity price analysis: predicting an ultra-short-term load change trend by adopting a time sequence model LSTM to predict a future load, judging a time period in which the electricity price is located, and judging which time period the current time is in, namely, a peak time period, a flat time period and a valley time period; transformer load evaluation: making a control strategy by calculating available power headroom; power optimization distribution is carried out, and power dynamic adjustment is carried out according to different conditions; a charging pile strategy and an energy storage strategy are adjusted according to the load condition and the electricity price condition; executing a charging and discharging control strategy; the real-time dynamic adjustment refers to periodical adjustment of a charging strategy; according to the invention, electric energy transmission and state monitoring in the charging station can be effectively managed, and the real-time performance, reliability and safety of vehicle network interaction are improved.

The invention discloses a multi-mode local voltage control method and system based on a deep neural network, and relates to the technical field of power system operation optimization, and the method comprises the steps: constructing a multi-mode sample set comprising node voltage, photovoltaic output and load data, setting a voltage upper limit, a voltage lower limit and a hysteresis interval, and dividing operation modes; establishing a control mode selection unit by using a deep neural network, and establishing a reactive power output prediction model by using a convolutional neural network; and performing localized deployment based on the trained controller model, and performing node-level adaptive voltage control and real-time reactive power optimization according to the hysteresis interval and the residence time. According to the method, stable division and feature layering of voltage states are achieved, representativeness of model training samples and precision and stability of voltage mode recognition are improved, collaborative optimization of mode judgment and adjustment output is achieved, stable switching and dynamic optimization of the voltage states are achieved, and system immunity and stability of multi-node operation are improved.

The invention discloses a multi-area cooperative new energy consumption control optimization method and system, and relates to the technical field of new energy power generation, and the method comprises the steps: firstly calling historical operation data of a plurality of power supply areas, constructing a mutual assistance cooperation matrix through the source network load storage cooperation analysis, and building a mutual assistance power distribution topology according to the mutual assistance cooperation matrix; and each transformer area collects and uploads dynamic operation data to the absorption control middle transformer area, the middle transformer area carries out real-time optimization to obtain an absorption mutual transformer area combination, topology local area authority is reconstructed to obtain real-time flexible interconnection topology, and cross-transformer-area power flexible control is executed after the combination is sorted. The technical problems that in the prior art, intermittency and volatility of new energy are difficult to deal with, cross-zone-area resource optimal configuration cannot be achieved through a single-zone-area regulation and control mode, and consequently the new energy consumption efficiency is low are solved, and the technical effects of cross-zone-area power optimal allocation and improvement of the new energy consumption efficiency and the power grid operation stability and economical efficiency are achieved.

The invention discloses a rolling time domain reactive power optimization method and system containing a distributed photovoltaic power distribution network, and the method comprises the steps: firstly, employing a probabilistic prediction model to carry out the prediction of photovoltaic active power, and obtaining a future output expected value and an uncertainty interval; secondly, the prediction result is substituted into a multi-objective optimization problem with line loss, voltage deviation and reactive compensation as optimization objectives, and opportunity constraints are established by using the uncertainty interval so as to ensure the safety margin of the power grid voltage; and finally, performing rolling solution on the problem by adopting a multi-objective evolutionary algorithm guided by a power grid sensitivity index to obtain an optimal reactive compensation scheme. According to the method, through a closed-loop rolling mechanism of prediction, modeling and solving, prospective, collaborative and robust control of reactive power resources is realized, and the stability and economical efficiency of operation of the power distribution network under high-proportion photovoltaic access are improved.

The invention discloses an energy storage cluster auxiliary thermal power frequency modulation and peak regulation collaborative optimization method considering dynamic balance, and belongs to the technical field of power system operation and control. Comprising the following steps: constructing a double-layer collaborative optimization control model; comprising the following steps: an energy storage cooperative thermal power frequency modulation and peak regulation power distribution layer introduces a frequency modulation demand in a peak regulation process, designs a power distribution and frequency modulation distribution strategy for peak regulation and peak regulation stages, and completes thermal power-storage frequency modulation and peak regulation power distribution by constructing a thermal power-storage frequency modulation and peak regulation power optimization distribution model; the multi-type energy storage power station power distribution layer constructs a multi-type energy storage power station power optimization distribution model by adopting a dynamic equilibrium coefficient; obtaining an energy storage power station power distribution value and an SOC state through a target function of the multi-type energy storage power station power optimization distribution model; and performing optimization scheduling on the new energy power system based on the power distribution value of the energy storage power station and the SOC state. According to the invention, the balance control of the calling degree and the SOC of the multi-type energy storage power station is realized.

The invention discloses a microprocessor dynamic power consumption optimization system based on deep learning, which belongs to the technical field of microprocessor power consumption management, and comprises a working load feature extraction module, a neural network prediction module, a dynamic core distribution module and a particle size power supply management module, the working load feature extraction module extracts feature parameters of calculation intensity, memory access intensity and input and output intensity of an application program in real time through a hardware circuit; the neural network prediction module predicts future power consumption and performance requirements based on a deep reinforcement learning network; the dynamic core distribution module intelligently selects an optimal core combination; the particle size power supply management module independently executes dynamic voltage frequency regulation on each core; according to the invention, accurate power consumption optimization of the heterogeneous multi-core processor is realized through deep coupling and closed-loop cooperation of the four modules, and compared with the prior art, the energy efficiency ratio is improved by more than 40%, and the power consumption prediction error is reduced to be within 5%.

The invention provides a power distribution network reactive power optimization method and device based on deep reinforcement learning, and the method comprises the steps: building a mixed integer second-order cone programming model according to the state parameters of low-speed reactive power regulation equipment in a power distribution network, solving the mixed integer second-order cone programming model, and obtaining the day-ahead optimal scheduling result of each piece of low-speed reactive power regulation equipment; based on the day-ahead optimal scheduling result and the operation characteristics of the current power distribution network, establishing a multi-agent reinforcement learning model with the goal of minimizing the current operation cost of the power distribution network; a multi-agent depth deterministic strategy gradient algorithm is adopted to train the multi-agent reinforcement learning model, and an intra-day multi-agent real-time scheduling strategy is generated; and fusing the day-ahead optimal scheduling result with the intra-day multi-agent real-time scheduling strategy, and outputting a multi-time-scale coordinated power distribution network reactive power optimization control instruction. According to the technical scheme, a multi-time-scale coordinated reactive power optimization mechanism considering day-ahead economical efficiency and intra-day real-time performance is realized.

The invention provides a control method of a dual-active bridge converter, and relates to the technical field of power electronics, the method comprises the following steps: firstly collecting output electrical parameters to calculate real-time power, and determining critical power according to a voltage transmission ratio; comparing the real-time power with the critical power, and carrying out segmented optimization control: when the real-time power is not greater than the critical power, solving a phase shift by adopting minimum backflow power optimization control; when the real-time power is greater than the critical power, adopting backflow power and current stress collaborative optimization control, constructing an objective function through weighted summation, and introducing a momentum method to carry out iterative optimization so as to solve an optimal phase shift ratio; and finally, according to the solved phase shift ratio, generating a PWM driving signal to control a switch tube. According to the invention, through a segmented optimization strategy, the backflow power and the current stress are effectively reduced in a wide working condition range, so that the transmission efficiency and the reliability of the converter are improved.

The invention provides a two-stage power distribution network reactive power optimization method based on model-data hybrid driving, and aims to improve voltage quality and operation efficiency in a renewable energy source high-permeability scene. According to the method, the advantages of deterministic optimization and deep learning are combined, and precise regulation and control are realized in stages; solving a tap position optimization scheme of the on-load tap changing transformer (OLTC) in the day-ahead stage; in the real-time control stage, a deep learning framework based on a Transform architecture is designed, three typical scenes of wind power daytime photovoltaic and night photovoltaic are adapted respectively, and a dynamic reactive power compensation decision under a fast time scale is realized. Through a double-layer cooperation mechanism of'day-ahead pre-scheduling + real-time deep learning correction ', calculation efficiency and control precision are effectively balanced, and a reactive power optimization solution considering economical efficiency and safety is provided for a power distribution network with high-proportion new energy access.

The invention provides an automobile electronic chip parallel burning control method and system for multi-protocol dynamic switching, electronic equipment and a storage medium, and relates to the technical field of automobile electronic chip burning. A protocol power consumption association library is constructed, and a current sudden change interval in the protocol switching process is recognized; performing phase inversion processing to generate reverse compensation current, and performing active offset processing on transient fluctuation of a power supply layer of the automobile electronic chip by using the current to generate a power supply optimization enable signal; performing load period configuration processing on the multi-protocol burning time slot to generate a protocol distribution strategy; obtaining a multi-path protocol switching request, and performing priority sequence recombination processing based on the request to generate a recombination burning queue; and performing dynamic switching control processing by combining the recombined burning queue, the protocol distribution strategy and the power optimization enable signal to generate a multi-protocol parallel burning control signal. Cooperative control of multi-protocol dynamic switching and parallel burning can be realized, and burning efficiency and stability are improved.

The invention discloses a power distribution network-micro-grid collaborative dual-time scale scheduling method in combination with topological optimization. According to the method, a long-time-scale scheduling period is set at the hierarchy of the power distribution network, a scheduling model combining topology reconstruction and active optimization is adopted, and unified regulation and control of global operation characteristics such as grid power flow, line heavy load and node voltage are achieved; an ultra-short time scale real-time scheduling period is set in a micro-grid level, and new energy fluctuation is rapidly tracked and compensated based on rapid adjustable resources; and through a multi-level information interaction mechanism, power distribution network scheduling constraint downloading and micro-grid feedback uploading are realized, and friendly interaction and cooperative operation between the power distribution network and the micro-grid are realized. According to the method, the flexibility and the new energy consumption capability of the power distribution system are remarkably improved through a topology flexible regulation and control means, meanwhile, the rapid response capability of the system to the time-varying uncertainty is enhanced through a double-level scheduling mode, the operation loss and the safety risk of the power distribution network are reduced, and the method has good engineering application value.

The invention relates to the technical field of power system operation and control, and discloses an active power distribution network distributed reactive power optimization control method, which comprises the following steps: independently establishing a second-order cone branch power flow model by each regional controller, and constructing an augmented Lagrange objective function based on an alternating direction multiplier method; and executing a distributed iterative solution process. The process comprises the following steps that: a region controller executes local optimization solution to obtain a local boundary coupling variable; executing an information exchange operation, and exchanging the boundary coupling variable with an adjacent region; dual variable updating operation is executed, and the Lagrange multiplier is updated according to the residual error of the consistency constraint; and executing convergence discrimination, and outputting a reactive power optimization control strategy if the condition is satisfied. A non-convex problem is converted into a convex optimization problem by adopting second-order cone relaxation, the solution optimality is ensured, and a distributed node decoupling architecture is combined, so that the communication burden is reduced, and the expandability and robustness of the system are improved.

The invention relates to an intelligent network source collaborative optimization control method, device and equipment for a power system and a medium, and the method comprises the steps: collecting the operation data of a target power system, and triggering a two-stage collaborative optimization control strategy in response to the condition that the state quantity is greater than a preset threshold value; responding to a cross iteration optimization control strategy until the regional control deviation and the hub node voltage deviation meet a preset deviation target, and generating an active adjustment amount instruction; in response to a reactive power optimization and compensation active power distribution optimization control strategy, generating an update instruction of a hub node voltage and a distribution instruction of a compensation active power adjustment amount; and responding to the active adjustment amount instruction, the updating instruction and the distribution instruction until a preset optimization target is met. Therefore, the problems that the problem of mutual restriction cannot be solved, the coordination of active power and reactive power is difficult to realize, the operation safety and economical efficiency are influenced and the like due to the fact that the problem of bidirectional coupling cannot be effectively processed and the real-time control level is not fully considered in the related technology are solved.

The invention relates to the technical field of power system frequency control, and particularly discloses a power optimization distribution control method based on a wind storage combined frequency modulation system, which comprises the following steps of: synchronously acquiring a power grid frequency modulation instruction, wind power output, an energy storage charge state and adjustable power capacity data; extracting wind power fluctuation frequency and amplitude characteristics and energy storage charge and discharge depth and response rate characteristics; by taking the features as state constraints, constructing a multi-objective optimization model taking the highest frequency modulation tracking precision and the minimum energy storage life loss as objectives, and solving the multi-objective optimization model to obtain a power optimal distribution coefficient; generating a wind power smoothing instruction and an energy storage amplitude limiting instruction according to the coefficient, and issuing and executing; collecting actual response data to calculate deviation, and dynamically correcting a weight coefficient and a constraint boundary of the optimization model; according to the invention, dynamic collaborative optimization of wind storage power is realized, and energy storage cycle loss and response deviation can be reduced.

A power-imbalanced multi-level decoding method for sparse code multiple access includes: encoded bits of all users are mapped to multi-dimensional sparse codewords through predetermined codebooks; a factor graph matrix is constructed using the predetermined codebooks, all users are classified according to the factor graph matrix under predetermined constraints to determine Z levels; based on a predetermined total transmission power, a progressive multi-level power optimization algorithm is employed to perform power-imbalanced allocation for all users according to the Z levels, thereby determining a locally optimal power vector; transmission signals corresponding to the multi-dimensional sparse codewords are transmitted according to the locally optimal power vector; SCMA detection and power-oriented decoding are sequentially performed for users each level, and outputs decoded bit sequences for the L levels.

The present disclosure discloses a rail transit power system edge device computing power optimization method, comprising the following steps: obtaining a plurality of rail transit power system data calculation tasks; obtaining a feasible calculation node set corresponding to each data calculation task based on a constraint condition; sorting the plurality of data calculation tasks according to the size of all feasible calculation node sets, and assigning priority to the feasible calculation node set with a small number of feasibility strategies to complete the data calculation task unloading; optimizing each feasible calculation node set to obtain an optimal calculation node; and obtaining the minimum calculation resource required by the optimal calculation node based on a monotonic optimization method to complete the computing power optimization of the rail transit power system edge device.

The wind turbine generator power optimization control method comprises the steps of collecting operation data of a wind turbine generator; the rotating speed of the generator is compared with the cut-in rotating speed and the rated rotating speed, and the running state of the wind turbine generator is divided into a standby state, a maximum power tracking area and a constant power control area; in the maximum power tracking area, based on the rotating speed and power change relation of the previous control period and the current control period, a first torque instruction is generated through dynamic step length tentative logic; in the constant power control area, the power upper limit set value is adjusted to generate a second torque instruction based on comparison between the state parameters of the generator and the converter and the preset temperature boundary; when the vibration amplitude enters the early warning interval, avoiding adjustment is executed in combination with the rotating speed or the variable pitch rate of the generator to generate a third torque instruction; and taking the minimum value of the torque instruction meeting the boundary constraint as a final control instruction. Under the condition that a complex mathematical formula and an AI model are not used, the thermal capacity margin and the mechanical vibration margin of the unit are used for dynamically adjusting a power output target, and the potential power generation capacity of the excavator unit is guaranteed under the condition that safety is guaranteed.

The invention discloses a power distribution network reactive power optimization decision-making method and system based on knowledge and data fusion, and the method comprises the steps: constructing a power distribution network optimal power flow model of high-proportion photovoltaic access, and generating a reactive power optimization decision-making data set; preprocessing the data set, removing repeated samples and screening key features; constructing and screening a machine learning regression model based on the preprocessed data set; further optimizing the model performance by adopting a data quality improvement method, and determining the decision tree model based on Gaussian noise enhancement as an optimal decision model; and performing real-time reactive power optimization control on the power distribution network by using the model, and outputting an optimal reactive power output set value. Through the fusion thought of model-driven sample generation and data-driven learning decision making, rapid and accurate decision making of reactive power optimization is realized, and the voltage out-of-limit problem under high-proportion photovoltaic access is effectively relieved.

According to an embodiment, disclosed is a system comprising an energy management module, electrically coupled to a utility meter, energy consuming devices and energy producing devices, comprising, a communication module configured to receive input energy data from utility meter, and energy information of energy consuming devices and energy producing devices; a processor storing instructions in a non-transitory memory that, when executed, cause the processor to: determine energy consumption data of the devices; identify a first device based on a first set of predefined priority values which requires energy; identify a second device based on a second set of predefined priority values which has excess energy; establish a connection and control energy transfer from the second device to the first device based on the energy consumption data and the input energy data to enable smart scheduling and power optimization among the energy consuming devices and the energy producing devices.

The invention discloses a new energy model test method and system based on grid-side power supply optimization, and the method comprises the steps: calculating the unit voltage of a new energy grid-connected system after the equivalence of a power grid, and the active power and reactive power emitted by a new energy unit; analyzing the relationship between the terminal voltage of the new energy unit and the active power and reactive power; calculating an infinite power supply voltage amplitude based on the relationship between the terminal voltage of the new energy unit and the active power and the reactive power; and based on the infinite power supply voltage amplitude, obtaining the machine end short-circuit ratio of the new energy unit i, and calculating the system impedance and the infinite system voltage under full power.

The invention relates to the technical field of new energy power grid system optimization operation, in particular to a power grid reactive voltage optimization method and system. The method comprises the steps that the shared energy storage and micro-grid alliance collaboratively establishes a mathematical model of a power grid and each device in the micro-grid; on the basis of a mathematical model, a game result is determined through day-ahead multi-round games, in the intra-day stage, the micro-grid alliance optimizes charging and discharging behaviors in a rolling mode according to a charging and discharging strategy, shared energy storage is based on the game result, and an improved Shapley value method is adopted to share the shared energy storage cost; the power grid combines the interaction power, constructs day-ahead and intra-day reactive power optimization models and solves the day-ahead and intra-day reactive power optimization models to obtain an optimization result of network loss and voltage deviation minimization; and based on an optimization result, realizing the control of the node voltage of the power grid by utilizing a photovoltaic inverter. The method can solve the problems that in the prior art, the power grid voltage fluctuation is large, the network loss is increased, the micro-grid energy consumption characteristic difference is large, the allocation is not fair, and the multi-main-body cooperation capability is poor.

The invention discloses a reactive power optimization control method suitable for a series resonance dual active bridge, relates to the technical field of power electronic converter control, and solves the problem that an effective compensation scheme is not provided for an incomplete soft switching problem caused by dead time in the prior art. And the requirement of all-working-condition efficient operation in engineering application is difficult to meet. Based on triple phase shift control, the optimal phase shift angle combination is accurately solved through the power factor Lagrange function and the KKT condition, the reactive power of the primary side or the secondary side can be counteracted in a targeted manner, and the energy circulation of the resonant cavity is effectively inhibited; meanwhile, soft switching boundary analysis and critical phase compensation are combined, so that zero-voltage switching of all main switching tubes in a full-voltage gain and full-load range can be ensured, and switching loss is reduced; and a mode switching mechanism is designed in control logic to adapt to dynamic working condition response requirements, so that the energy transmission efficiency and working condition adaptability of the series resonance dual-active bridge converter are greatly improved.

The invention relates to the technical field of modern communication, and discloses a wireless network card power adaptive control method and system. The method comprises the following steps: acquiring real-time interference data, performing spectrum change according to the real-time interference data to obtain an interference intensity distribution diagram, performing interference correlation analysis and power optimization calculation according to the interference intensity distribution diagram to obtain a power configuration scheme, performing parameter updating according to the power configuration scheme to obtain a preliminary power correction result, and performing power optimization calculation according to the preliminary power correction result. The method comprises the steps of obtaining a preliminary power correction result, carrying out interference comparison evaluation according to the preliminary power correction result to obtain deviation information, carrying out power optimization according to the deviation information to obtain an optimized power configuration scheme, and carrying out synchronous configuration and index feedback analysis according to the optimized power configuration scheme to obtain a final regulation command set. According to the method, the problem that interference chain reaction is easily caused by equipment power adjustment can be solved, so that stable communication and interference suppression in a complex network environment are realized.

The application relates to the technical field of automatic voltage control of power systems, and discloses a wind power grid-connected regional power grid AVC cooperative control method and system. The method constructs a three-layer dynamic logic architecture: a regional power grid AVC master station layer, a wind power plant cluster logic coordination layer, and a single plant station on-site execution layer. The master station layer constructs a comprehensive coupling degree index based on voltage sensitivity and electrical distance, performs adaptive dynamic partitioning, and generates a corresponding logic coordination unit for each partition; the master station layer periodically solves a multi-objective reactive power optimization model and issues a total reactive power instruction to each partition; the logic coordination unit finely allocates the adjustment amount according to the voltage regulation sensitivity, reactive power margin and response characteristics of each reactive power source; and the on-site execution layer executes the instruction. The application realizes linkage reconstruction of dynamic partitioning and logic coordination units, solves the problems of severe voltage fluctuation and difficult multi-resource coordination under wind power grid connection, and improves voltage stability, economy and equipment operation life.

The present disclosure relates to the field of power system optimization scheduling, and particularly relates to a renewable energy power optimization scheduling cost prediction and decomposition method and device and storage medium. The method comprises: obtaining power system operation data, the power system operation data comprising operation data and cost data of multiple renewable energy devices in a power system; determining power optimization scheduling data and cost analysis results according to the power system operation data through a pre-trained target model, the power optimization scheduling data being used to indicate a predicted operation combination scheme of the multiple renewable energy devices with the minimum total system cost, and the cost analysis results comprising a total system cost corresponding to the power optimization scheduling data and / or a cost decomposition result of the total system cost. The present disclosure uses a pre-trained target model to realize the optimization scheduling of a renewable energy power system, accurately predicts and decomposes the cost, and improves the accuracy of power optimization scheduling and cost analysis.