313 results about "Electrical network frequency" patented technology

The invention provides a power grid frequency modulation power energy coordination control method and system based on a super capacitor, and relates to the technical field of power grid frequency modulation, and the method comprises the steps: carrying out the time-frequency analysis of a collected power grid frequency signal, obtaining a frequency disturbance characteristic value, and determining power control data through combining with an electrical parameter value of a super capacitor group; and performing nonlinear programming calculation based on the power control data to obtain a power distribution sequence, dividing the power distribution sequence into a quick response section, a dynamic transition section and a steady state maintenance section according to a preset threshold value, and solving a control value by adopting an augmented Lagrange equation, recursive least square operation and a Lyapunov function respectively. Obtaining a power control instruction; and inputting a power control instruction into the disturbance observer, calculating a dynamic error value, constructing a nonsingular terminal equation, and outputting a power regulation signal in combination with recursive minimum entropy calculation and a superhelix algorithm.

The invention relates to the technical field of steam turbine testing, in particular to a testing system for mismatch correction of a wide-load-interval thermal power generating unit speed regulation model, which comprises a thermodynamic system component, a speed regulation system device, a dynamic signal acquisition device and a control device, a dynamic signal processing module analyzes the relevance between main steam pressure sudden change and control valve opening oscillation in real time, a dynamic response database including a time sequence is constructed, and a control valve opening feed-forward compensation instruction and a combustor fuel distribution gradient adjustment signal are generated according to correction parameters. Power over-modulation wave crests caused by sudden load change are suppressed, and primary frequency modulation action delay is reduced; and the simulation verification module compares measured data with model output through an error feedback mechanism, dynamically adjusts high-pressure cylinder flow characteristic curve calibration parameters, optimizes a control strategy in combination with a network-related safety margin evaluation result, and realizes improvement of dynamic response precision in a full peak regulation interval and enhancement of power grid frequency stability.

The invention discloses a generator non-inductive access grid-connected method, device and equipment, and provides a reliable data basis for subsequent operation by collecting a power grid state and generator operation monitoring parameters in real time. Power grid frequency is calculated at multiple time points, and a real-time frequency curve is constructed and used for analyzing stability, predicting changes, comparing generator current output frequencies to identify frequency differences and evaluating coordination. Frequency synchronization is realized by using minimum difference time point detection, the time point is marked to optimize frequency control, and grid-connected stability and safety are guaranteed by combining dynamic frequency adjustment and synchronous frequency error estimation. In the aspect of power control, power fluctuation is reduced through transient power suppression optimization, and the adaptability of the generator is enhanced through dynamic feed-forward compensation control. In addition, manual intervention is reduced through intelligent non-inductive grid-connected optimization, an intelligent grid-connected engine is constructed, seamless butt joint of a generator and a power grid is achieved, grid-connected efficiency and safety are comprehensively improved, and system complexity and risks are reduced.

The invention discloses a resource adjustment method and system based on power grid frequency deviation, and relates to the technical field of AGC control, and the method comprises the following steps: obtaining environment state data, and constructing an environment state vector; initializing a control agent according to a preset control mode, taking the environment state vector as input, training the control agent through a reinforcement learning reward function, and outputting a strategy action; dynamically switching the strategy action into a control strategy of the AGC controller based on a soft switching and strategy interpolation mechanism; a model prediction control method is adopted, and the power set value of the AGC control unit is optimized in a rolling mode; according to the method, the trained control agent is integrated into the AGC controller through reinforcement learning, so that the AGC controller can dynamically switch the control strategy of the AGC controller, self-adaptive selection of control actions is realized, and the power grid frequency is controlled to be stable by correcting the set value of the unit in the AGC controller and improving the control precision.

The invention relates to the technical field of prediction algorithms, and discloses a high-precision active power filtering and prediction algorithm for a three-phase ammeter, which comprises the following steps: acquiring original signals of three-phase voltage and current for baseline correction, performing time-frequency analysis on non-stationary harmonic waves and noise of the original signals, and dynamically adjusting filtering parameters; voltage and current phase alignment is carried out through FIR phase shift and zero crossing point detection, a phase-locked loop is constructed by using GRU to track the frequency of a power grid, the sampling frequency is dynamically adjusted, and frequency mutation is detected; iapFFT transformation is optimized to suppress spectrum leakage, a phase error is corrected through a deep learning network, and weak harmonic detection is enhanced by using an attention mechanism; classifying harmonic waves, and adaptively calculating total active power; dimensionality reduction is carried out on historical power and environmental parameters through an auto-encoder, and future active power is predicted; low-power-consumption hardware is adapted, and training efficiency and data security are optimized; three-phase signals are processed in parallel, and FPGA storage and FFT / FIR cores are optimized for filtering processing; and dynamically adjusting parameters of the phase-locked loop.

The invention discloses a distributed phase modifier locating and sizing method considering frequency stability improvement, and belongs to the field of power system stability and control. Comprising the following steps: performing quantitative evaluation on the inertia supporting capacity of a power grid by node inertia, analyzing the influence of access of the phase modifier on the frequency of the power grid, and performing a distributed phase modifier locating and sizing configuration strategy considering the frequency stability constraint. According to the method, aiming at the frequency stability problem of a new energy sending end power grid caused by a large disturbance fault of the system, the frequency supporting capacity of the system is improved to the maximum extent by solving the optimal model with the minimum configuration capacity as an optimization target.

The invention discloses a hierarchical optimization scheduling method for an electric power system containing a large-scale water electrolysis hydrogen production device, and relates to the technical field of hierarchical optimization scheduling of the electric power system.A gradient heterogeneous compensation unit fuses covariance alignment and differential privacy encryption, and on the premise that original data does not need to be shared, the optimal scheduling of the electric power system is achieved. The federal learning convergence speed is improved to a practical level; after each hydrogen production station uploads the encryption gradient, a coordinator corrects and eliminates equipment difference interference through statistical distribution, and generates a global consistent frequency modulation strategy, so that commercial sensitive information is protected, and model oscillation failure is avoided; the knowledge distillation unit further compresses the volume of the model to guarantee the real-time response capability of edge nodes, and when the frequency of the power grid changes suddenly, a quick response protocol automatically triggers a dynamic priority distribution mechanism; the regional aggregation layer directly broadcasts a frequency modulation instruction based on a historical performance label, and skips a federated learning iteration process, so that a hydrogen production cluster forms an adjusting resultant force in a second level.

The invention discloses an inertia support control method and system for a high-inertia energy storage type synchronous phase modifier, and the method comprises the steps: determining the frequency deviation of a power grid based on the frequency of the power grid when the voltage of the power grid is greater than or equal to a preset voltage threshold value, judging whether the frequency deviation exceeds a dead zone range or not, and obtaining a judgment result; when the judgment result indicates that the frequency deviation exceeds a dead zone range, disturbance, inertia support and primary frequency modulation function input of the system frequency occur, an active current instruction value is generated according to the frequency deviation, and the power grid frequency is controlled based on the active current instruction value; the rotor speed is obtained in real time, when the rotor speed reaches the rotor speed limit value, the active output instruction is set to be zero, the dead zone range is adjusted till the rotor speed is recovered to the preset range, the dead zone range is recovered to be normal, and the active output instruction is unlocked.

The invention provides a method for identifying a power grid frequency signal assessment standard, and the method comprises the steps: constructing a system architecture composed of a master station, a substation and a communication network, and achieving the initialization of equipment through a finite-state machine; the method comprises the following steps: collecting power grid frequency, power generation side frequency difference and communication state multi-dimensional data, processing signals by applying median filtering, a sliding window and an EWMA algorithm, introducing fuzzy logic to evaluate a system state, and dynamically adjusting a response strategy; an improved PID algorithm is adopted to track frequency change, feed-forward compensation and PSO parameter optimization are combined, a hidden Markov model is utilized to predict a communication fault, and local mode switching is triggered in advance; main station, mixing and local three-state switching is carried out according to communication states and load changes, and a frequency modulation dead zone is automatically adjusted according to power grid loads through a dynamic threshold value self-adaptive algorithm; the control effect is verified by using a digital twinning technology; and the safety and reliability of the system are guaranteed by optional quantum encryption and active-active redundancy design. The whole scheme effectively reduces the power loss of power generation enterprises, and maintains the safe and stable operation of a power grid.

The invention belongs to the field of power distribution automation, and relates to a power grid equipment frequency adaptive resampling method based on a dynamic scale factor, and the method comprises the steps: carrying out the point compensation through employing a linear interpolation method when a power grid equipment detects that the number of continuous lost points is smaller than or equal to 3; selecting a voltage signal channel or a current signal channel to carry out zero crossing point detection and real-time frequency calculation; when the real-time frequency obtained through calculation deviates from the nominal frequency, the power grid equipment introduces a dynamic scale factor for resampling, sampling points are increased when the real-time frequency is higher than the nominal frequency, and sampling points are reduced when the real-time frequency is lower than the nominal frequency; writing data obtained by resampling into a calculation annular cache region of the power grid equipment; and performing FFT calculation on the data in the calculation annular cache region to obtain power grid parameters. The sampling interval of the data acquisition unit is dynamically adjusted by increasing or reducing the sampling points, so that the sampling time sequence and the actual signal period are synchronized, the sampling frequency and the real-time frequency are adaptively matched, and the sampling distortion problem under the power grid frequency fluctuation is solved.

The invention provides a power grid frequency detection method, system and device and a medium, and the method comprises the steps: carrying out the narrowband signal decomposition of an obtained input voltage signal of a power grid through a null-space tracking algorithm, and obtaining a fundamental main mode component of the input voltage signal; performing low-pass processing on the fundamental wave main mode component to obtain a fundamental wave signal of the fundamental wave main mode component; performing discrete Fourier transform on the fundamental wave signal to obtain phase information of the fundamental wave signal; according to the phase information of the fundamental wave signal, calculating phase deviation information of the fundamental wave signal in pre-selected adjacent cyclic waves to obtain frequency estimation information of the power grid; according to the invention, narrow-band decomposition is carried out on an input voltage signal through a null-space tracking algorithm, so that a fundamental main mode can be accurately extracted; and phase deviation information can be determined based on discrete Fourier transform, so that when the interference frequency of the power grid is close to the fundamental frequency, high separation precision can be kept, and the accuracy of power grid frequency estimation can be improved.

The invention relates to the technical field of wind power generation. The invention provides a network security protection method and system of main control equipment for wind power generation. The method comprises the following steps: receiving a control instruction, performing syntax tree analysis on an industrial control protocol, extracting an operation code and a parameter value, verifying the operation code, and verifying the parameter value; dynamically calculating a threat value based on the control instruction frequency, the cross-protocol request ratio and the deviation between the actual parameter value and the predicted value, and judging an attack risk according to the threat value level; establishing a normal operation baseline of the main control equipment or the remote terminal, and detecting the abnormal probability of the control instruction sequence in real time; calculating the physical rationality probability of the control instruction through a Bayesian network in combination with the environmental parameters of the wind speed, the power grid frequency and the equipment operation state; and according to the threat value level, the abnormal probability and the physical rationality probability, executing a multi-level response action. The problems of protocol protection superficial layer, environment correlation deficiency, emergency mechanism stiffness and the like in existing wind power generation main control equipment network security protection are solved.

The invention relates to the technical field of oscillation suppression, in particular to a control method and device for a subsynchronous oscillation suppression device, and the method comprises the following steps: collecting the frequency of a power grid, load fluctuation, the rotating speed of a generator and the excitation state of the generator, and recognizing subsynchronous oscillation frequency signals in a power system based on real-time operation state data; the subsynchronous oscillation frequency signal comprises oscillation frequency, oscillation amplitude and oscillation phase; analyzing the time-varying characteristics of the subsynchronous oscillation frequency signal through a time-varying analysis algorithm, wherein the time-varying characteristics comprise the time-varying characteristics of the oscillation frequency, the time-varying characteristics of the oscillation amplitude and the time-varying characteristics of the oscillation phase; the frequency suppression parameters are corrected according to the time-varying characteristics, and through an adaptive controller in the subsynchronous oscillation suppression device, based on the corrected frequency suppression parameters, real-time adjustment is carried out, a control effect is applied in real time, and subsynchronous oscillation is suppressed. According to the invention, the limitation of the traditional fixed frequency hypothesis is avoided, and the risk of misjudgment and insufficient suppression is greatly reduced.

The hybrid energy storage frequency modulation method based on two-dimensional mode decomposition comprises the following steps: acquiring an original frequency modulation instruction signal; generating a primary modal subsequence according to the frequency modulation instruction signal based on a two-dimensional modal decomposition algorithm; generating a plurality of secondary modal subsequences from the undecomposed frequency modulation instruction signal based on a two-dimensional modal decomposition algorithm through loop iteration; distributing the primary modal sub-sequence and the plurality of secondary modal sub-sequences to different energy storage units in the hybrid energy storage system for power regulation and control; when the power grid frequency of the power plant fluctuates, response can be made in time, the optimal decomposition sub-sequence is obtained through the two-dimensional mode decomposition algorithm, frequency modulation instruction distribution is more accurate, the problem of inaccurate frequency modulation instruction signal distribution caused by mode aliasing is solved, the cost of an energy storage system is reduced, and the income of the power plant is improved.

The invention belongs to the technical field of power systems, and discloses a quick-response unit compatible frequency modulation method and system, and the method comprises the steps: obtaining the real-time frequency data of a power grid, and calculating the deviation between the frequency of the power grid and the standard frequency; determining a frequency adjustment amplitude by using the fuzzy control rule base, and selecting a corresponding unit response mode according to the real-time frequency change to perform frequency adjustment; on the basis of a particle swarm optimization algorithm, the optimal unit response time and power output are determined by combining the unit response capability, the frequency modulation power range and the start-stop time; and generating a frequency control instruction according to the optimal unit response time and power output, and controlling the frequency modulation unit to perform power adjustment based on the frequency control instruction to realize adjustment of the power grid frequency. According to the method, the optimal unit response time and power output can be accurately determined, the response speed and precision of frequency adjustment are remarkably improved, and the intelligent level and the overall operation efficiency of a power grid frequency modulation system are effectively improved.

The invention discloses a safety control method and system for an emerging control main body, and belongs to the technical field of power system active control, and the method comprises the steps: carrying out the bidirectional data interaction through a master station AGC and a field station AGC, and carrying out the bidirectional data interaction based on a bidirectional data interaction result and a cooperative anti-error parameter; whether the emerging control main body is in a controllable state or not is judged in real time through collaborative security locking logic; if the control main body is in the controllable state, active measurement data of the emerging control main body are obtained, and jump detection and multi-source checking are carried out on the active measurement data; after verification is passed, a pre-control instruction is generated based on the control strategy, and reasonability verification and control effect simulation verification are carried out; and after the control effect simulation verification is passed, the pre-control instruction is taken as a final control instruction to be issued to the emerging control main body for execution. The method can greatly improve the safety control capability of AGC on an emerging control main body, guarantees the frequency operation safety of a power grid, and improves the safe and reliable power supply capability of the power grid.

The invention discloses a frequency response modeling method, system and device based on power grid planning and a storage medium, and relates to the field of power system planning operation, and the method comprises the steps: employing an improved K-means algorithm based on data intensity, and carrying out the clustering of water, fire, wind and light units according to characteristic parameters; predicting a long-sequence meteorological scene based on historical meteorological data by using a three-layer BP neural network and reducing the long-sequence meteorological scene to obtain a typical operation scene; establishing an optimization model to obtain a power supply total output plan by combining unit clustering, a typical scene and a power grid boundary condition; a mixed integer optimization model is constructed to determine a synchronous unit starting scheme, equivalent inertia is calculated, new energy and stored energy equivalent inertia is calculated, and system frequency response model identification parameters are established and simplified; the method can improve the frequency stability of the power grid, reduce the operation risk caused by new energy access, optimize the power supply and net rack configuration in the planning stage, reduce the frequency out-of-limit and load loss during a fault, and enhance the safety and economy of the power grid.

The invention discloses a photovoltaic power generation frequency response control method considering different time scales, and relates to the field of power system automation control, and the method comprises the steps: integrating a frequency deviation feature and an illumination load disturbance feature to obtain a state feature vector, and determining a disturbance type according to the state feature vector; adaptively selecting a frequency response control mode based on the judgment result of the disturbance type, and reasoning and outputting an optimal control parameter combination in the frequency response control mode by using a pre-constructed disturbance-response causal atlas; a four-state progressive switching control strategy is generated in combination with a spectrum analysis technology, and smooth switching between frequency response control modes is realized through the four-state progressive switching control strategy. According to the invention, the response capability and the adjustment precision of the photovoltaic system under the power grid frequency disturbance can be improved, the dynamic coordination of fast frequency response and slow frequency response and parameter self-optimization control are realized, and the whole-process supporting capability of the photovoltaic system to the frequency disturbance is effectively improved.

The invention discloses a power grid frequency balance intelligent control system based on a distributed architecture, relates to the technical field of power grid control, and is used for solving the problems that the existing WLS / UKF and other methods are generally assumed to be good in synchronization, are insensitive to heteroscedasticity time delay and missing measurement, and are difficult to ensure robustness under real communication and equipment conditions. Through a through link, under the real clock misalignment, time delay jitter and packet loss conditions, measurement of a unified time axis and quality quantification are realized, and frequency estimation bias and uncertain transmission are significantly reduced. Reconstruction, filtering and triggering are penetrated with the same confidence degree, and abnormal measurement suppression and effective information utilization are improved; the fusion efficiency and timeliness of asynchronous arrival data are improved by utilizing graph prior and information domain incremental updating; and regional measurement abnormity and real power imbalance are discriminated through double-model causality, and error event reporting is reduced.

The invention relates to the technical field of power system frequency modulation control, in particular to a thermal power generating unit collaborative frequency modulation method and system based on block chain federated learning. According to the method, a decentralized P2P network is constructed through a block chain technology, and model parameters are initialized based on a secret sharing mechanism; carrying out local training by adopting an adaptive federal near-end optimization algorithm, measuring data isomerism through KL divergence and dynamically adjusting a regular coefficient; carrying out noise addition on a sample by adopting differential privacy, and carrying out homomorphic encryption to realize parameter encrypted transmission; selecting representative nodes based on a block chain consensus mechanism to execute parameter aggregation in the encryption domain; and multi-unit collaborative frequency modulation is realized through model prediction control. According to the method, the problems of data privacy protection, heterogeneous data adaptation and decentralized cooperative training are solved, and the stability of power grid frequency regulation and control is improved.

The invention discloses a power grid frequency prediction method and system based on a time sequence prediction algorithm, and the method mainly comprises the steps: constructing an adjacent matrix of a prediction power grid based on the topological relation between power grid sites; historical data of the power grid are selected and preprocessed, wherein the preprocessing comprises data cleaning, standardization processing and time alignment; constructing a power grid frequency prediction model which comprises an improved dynamic graph learning module, a linear space convolution layer and a time convolution layer; and inputting the adjacency matrix and the preprocessed data into a trained power grid frequency prediction model, so that the power grid frequency change in the future 10 seconds can be predicted with high precision. According to the method, the accuracy of power grid frequency prediction is improved by enhancing the learning ability of the model for dynamic characteristics.

The invention discloses a primary frequency modulation optimization control method and system based on adaptive gain adjustment, and the method comprises the steps: obtaining and preprocessing the operation state parameters of a power grid and the historical data of the frequency of the power grid, and constructing a power grid frequency stability classification model; power grid operation parameters are obtained in real time and normalized, and a power grid operation state classification result is obtained according to normalized data; preliminarily judging the stability based on the power grid operation parameters and the classification model, and if not, calculating a power grid frequency stability index and judging whether the power grid frequency stability index is lower than a threshold value; and a self-adaptive gain adjustment model is constructed, if the power grid operation state classification result does not meet the requirement or is lower than a threshold value, the optimal gain parameter of primary frequency modulation control is obtained based on the power grid frequency stability index and the self-adaptive gain adjustment model, and optimization control is realized according to the optimal gain parameter. Accurate adaptive control of the power grid frequency is realized, and a powerful guarantee is provided for safe and stable operation of a power system.

The invention belongs to the technical field of source network load storage monitoring, and particularly provides a source network load storage real-time monitoring cooperation system based on edge calculation, and the system mainly comprises a data collection and standardization module which obtains the collected output power of a photovoltaic inverter, the frequency deviation of a power grid, the switching state of an important load, and the charging and discharging rate data of an energy storage system, performing multi-source data fusion to obtain a system monitoring data set; the dynamic characteristic evaluation module is used for carrying out multi-dimensional characteristic analysis based on the system monitoring data set and obtaining a system adjustment parameter set through dynamic characteristic evaluation; and the coordination control construction module is used for constructing control logic according to the system adjustment parameter set and outputting a coordination control task scheme through a coordination control generation process. According to the method, the multi-source data fusion precision is improved, the dynamic characteristic matching capability of the system is enhanced, the source-network load-storage collaborative response efficiency is improved, the coping capability for power mutation is enhanced, and stable operation of the power grid frequency is effectively guaranteed.

The invention relates to the technical field of power system frequency control, in particular to an intelligent control inertia support power grid system and method, and the system comprises an edge calculation unit which is used for carrying out the real-time collection of power grid data, carrying out the processing of the power grid data, obtaining the frequency deviation data, carrying out the characteristic analysis of the power grid data, and obtaining the frequency deviation data; meanwhile, detecting frequency deviation data; when in use, the method is beneficial to accurately identifying and coping with the fluctuation problem of the power grid frequency, rapidly detecting the frequency deviation and harmonic interference, rapidly responding to the frequency fluctuation, effectively reducing the frequency deviation, keeping the power output stable and avoiding overhigh-power impact, and is beneficial to improving the reliability of the system through virtual mechanical inertia support. Effective suppression capability is provided for power grid frequency fluctuation, system stability is improved, self-adaptive adjustment is facilitated, frequency modulation smoothness is guaranteed, real-time response is realized, node power output is dynamically adjusted, impact on a power grid is reduced, a frequency modulation model is continuously optimized, and accuracy and applicability of frequency modulation response are guaranteed.

The embodiment of the invention discloses a control method and a control device of a virtual synchronous generator, and a network-forming inverter, which are used in the technical field of electrical control. According to the embodiment of the invention, the method comprises the steps: obtaining a damping gain coefficient of a virtual synchronous generator during transient fluctuation; adjusting a damping coefficient of an active ring in the virtual synchronous generator based on the damping gain coefficient to obtain a transient damping coefficient after gain; and when the virtual synchronous generator is in a steady state and the power grid frequency is changed, suppressing the change of the active power in the active loop based on the transient damping coefficient. The transient damping coefficient can control the active power not to change when the power grid frequency only has steady-state change, that is, primary frequency modulation is not carried out, so that the damping coefficient in an active ring is decoupled from a primary frequency modulation coefficient, and the accuracy of the primary frequency modulation of the virtual synchronous generator is ensured.

The invention provides a receiving-end power grid minimum inertia demand evaluation method considering different fault types, and the method comprises the steps: S1, collecting the system data of a receiving-end power grid, and enabling the system data to comprise the data of a power generator and a line; constructing a first model according to the generator and the line data; the first model is a multi-machine frequency response model comprising multiple types of units of a receiving-end power grid and an alternating-current tie line; s2, discretizing the first model based on Laplace transform and a backward difference operator to obtain a second model; and S3, setting a first condition for the second model, and calculating the minimum inertia demand of the receiving-end power grid based on the first condition and the second model in combination with an improved Newton-Raphson algorithm. The method can ensure safe and stable operation of the receiving-end power grid, enhance the frequency stability of the power grid, and guarantee stable operation of the system in different scenes.

The invention relates to the field of load control, in particular to a non-fixed load accurate removal method based on load control fairness and effectiveness consideration. Comprising the following steps: acquiring the frequency of a power grid system, calculating the frequency change rate, judging whether to send a'preparation for load shedding 'instruction to all substations by monitoring the frequency of the power grid system and the frequency change rate, entering a load shedding amount calculation stage, and calculating the load amount needing to be cut off in each region through a dynamic weighted load precise cutting algorithm, calculating a total load shedding amount; based on the load capacity needing to be cut off in each area, the substation optimizes the cut-off combination of the load lines in the areas, after optimization is completed, the substation executes cut-off, and the master station monitors the frequency and the frequency change rate of the power grid system after cut-off and judges whether a locking condition is met or not so as to stop further cut-off. The technical problems that power grid frequency monitoring mostly depends on low-sampling-rate equipment, the rapidly-changing frequency dynamic state is difficult to capture, and instability detection lags or misjudgments are caused are solved.

The invention discloses a hydroelectric generating set power active control method, system and device based on frequency prediction and a medium, and belongs to the technical field of power control, and the method comprises the steps: collecting basic operation data of a hydroelectric generating set adjusting system in real time, and carrying out the preprocessing of the basic operation data; time sequence characteristics of the power grid frequency data are extracted, and a neural network is adopted to generate a power grid frequency prediction sequence in a future time window; the power grid frequency prediction sequence is converted into a dynamic power feed-forward compensation amount, feed-forward compensation amount optimization calculation is carried out, the feed-forward compensation amount is superposed to the output end of a feedback controller, and a composite power instruction input value hydroelectric generating set is formed; and updating a neural network input sequence in each control period by adopting a rolling time domain prediction strategy, dynamically correcting a future prediction result, and realizing controlled quantity updating based on actual frequency deviation. According to the method, the compensation weight is dynamically updated by using the online adaptive algorithm, the prediction error and the system performance target are considered, and the compensation amount distribution is optimized.

The invention discloses a power system critical inertia prediction method based on a deep belief network. The method comprises the following steps: constructing a deep belief network DBN model; determining an input characteristic value xk and an output characteristic value yn of a deep belief network DBN model according to main factors influencing the critical inertia Hmin; constructing a sample database for predicting the critical inertia Hmin, and generating a training sample set and a test sample set; and setting each layer of neurons of the deep belief network DBN model, and evaluating a model prediction result. According to the method, the scheduling background can quickly and accurately take effective measures when the actual equivalent inertia of the power grid is smaller than the critical inertia, so that the power grid frequency is safe and stable.

The invention provides a self-adaptive intelligent power grid regulation and control method and system, and belongs to the technical field of electric power. The method comprises the steps of firstly collecting historical operation data of a power grid, including power grid frequency fluctuation, a distributed energy output state and external disturbance information, then constructing a fractal chaotic attractor model, and deeply understanding a complex structure of dynamic behaviors of the power grid by calculating fractal dimensions and correlation coefficients of power grid state variables. Based on the model, the system can predict the stability boundary of the power grid, design fractal control signals of a self-similar structure, and inject the fractal control signals into the distributed energy control system to actively control the disturbance of the power grid. The operation state of the power grid and the external environment change are monitored in real time, fractal control parameters are dynamically adjusted through reinforcement learning, it is ensured that the control strategy is always matched with the actual working condition, and therefore the system performance is maximized. The anti-disturbance performance and the self-healing capability of the power grid are remarkably enhanced, and the energy utilization rate and the power supply quality are improved.