2341 results about "Frequency regulation" patented technology

A method for actuating a DC-to-DC converter, in particular a clocked buck-boost converter that includes at least two switch elements and an inductor or throttle and via which an input voltage is converted into a regulated output voltage, wherein the switch elements are actuated with a variable switch frequency using pulse- and frequency-modulated control signals, where the pulse- and frequency-modulated control signals are derived from a manipulated variable from a regulator, a voltage curve on the switch elements is continuously ascertained or monitored to determine the activation time of the switch elements and to start a new switch cycle, the switch elements are activated if a specified minimum period duration has been exceeded upon detecting a voltage minimum of the ascertained voltage curve on the switch elements.

The invention provides a task load scheduling optimization method and system for distributed network nodes, and the method comprises the steps: determining a task transmission path between the distributed network nodes according to historical task congestion data and a real-time link load prediction result; adjusting a modulation coding strategy in a task transmission process according to the channel quality parameter on the task transmission path to obtain an adjusted modulation coding strategy; according to an energy consumption demand corresponding to the adjusted modulation coding strategy, combining load distribution of each communication link and each node on the task transmission path to generate a voltage frequency adjustment instruction corresponding to the distributed network node; performing collaborative optimization on the task transmission path, the channel quality parameter and the voltage frequency regulation instruction to generate a task load scheduling strategy; according to the invention, through collaborative optimization of dynamic path selection, adaptive modulation coding adjustment and precise energy consumption regulation, the transmission reliability, energy efficiency balance and system stability of the distributed network in a high dynamic environment are improved.

The invention relates to the technical field of power generation equipment control, and discloses an intelligent control method and system for a hydroelectric generating set speed regulator, and the method comprises the steps: employing an introduction variable structure and variable parameter control technology, and dynamically adjusting the control parameters of a power closed loop and an opening closed loop; real-time calculation and feedback control are carried out, and a speed regulator responds to a power grid frequency modulation Operating data of key parts of the speed regulator are collected in real time through a sensor, feature extraction and mode recognition are conducted on the data in combination with an artificial intelligence algorithm, and the operating state and potential faults of the speed regulator are recognized; constructing a fault tree model based on the speed regulator state monitoring parameters, carrying out hierarchical analysis on the speed regulator, and positioning the specific position and reason of the fault; and verifying and optimizing the fault diagnosis result, and generating a targeted fault processing suggestion. The system comprises a dynamic adjustment module, a state evaluation module and a fault analysis module. According to the invention, the operation efficiency and safety of the hydroelectric generating set speed regulator in a complex power grid environment are obviously improved.

Disclosed are a second-level optimal control method and apparatus for joint frequency regulation of heterogeneous load resources, and an electronic device, a storage medium, a computer program product and a computer program. The method comprises: establishing a standardized operation model for heterogeneous load resources; on the basis of parameters of the standardized operation model for the resources and historical frequency regulation signal data of a frequency regulation market, predicting frequency regulation signal distribution and price distribution over a future time period; solving an optimal operation model involving the joint participation of multiple heterogeneous resources in energy and frequency regulation markets, in order to determine a baseline energy output and a frequency regulation capacity; constructing an optimal decomposition problem of load resources and performing variable substitution, and calculating the marginal cost and adjustable range of power adjustment for each resource; and in response to receiving a frequency regulation signal sent by a power grid, starting dispatching from the resource having the lowest marginal regulation cost, and updating the power of each load-side resource until power adjustment requirements are met.

Disclosed in the present invention are a method and system for full-range participation of energy storage charging and discharging in power grid frequency regulation. The method comprises: collecting operating power and frequency data of a power grid, so as to construct a full-range droop coefficient; setting constraints for an upper limit value and a lower limit value of a frequency dead band; obtaining an actual output power instruction value by means of a constraint function constructed on the basis of a theoretical power instruction value and a charging / generated power rated value, and controlling the power grid to operate on the basis of the actual output power instruction value; setting a hysteresis range on a power instruction of an energy storage system, and when a power demand of the power grid exceeds an upper limit threshold value of the hysteresis range, switching the energy storage system from a charging mode to a discharging mode; and when the power demand of the power grid is lower than a lower limit threshold value of the hysteresis range, switching the energy storage system from the discharging mode to the charging mode. In the present invention, when the frequency of the power grid is increased, generated power is reduced until power is absorbed from the power grid, and when the frequency of the power grid is reduced, the absorption of power from the power grid is reduced until electrical power is delivered to the power grid, thus achieving full-range participation of energy storage in power grid frequency regulation control, and satisfying regulation requirements of power grids.

A frequency regulation control method and apparatus, a device, and a storage medium. The method comprises: according to the frequency at a current moment and the calibration frequency of a wind / photovoltaic grid-connected system, determining the frequency deviation value at the current moment and, according to the frequency at the current moment and the frequency at the previous moment, obtaining a frequency deviation change rate (S110); if the absolute value of the frequency deviation value is greater than the absolute value of a preset frequency regulation threshold value, then, according to the frequency deviation value and the frequency deviation change rate, determining inertia response power (S120); according to the frequency deviation value, the preset frequency regulation threshold value, and a preset system maximum frequency deviation, determining droop response power (S130); according to the state of charge of battery energy storage, the inertia response power, and the droop response power, determining battery energy storage target charging and discharging power (S140); and, according to the battery energy storage target charging and discharging power, regulating the frequency of the system (S150).

The invention relates to the technical field of signal analysis, and discloses a primary frequency modulation large disturbance signal peak value analysis method, which comprises the following steps: collecting a primary frequency modulation large disturbance signal and carrying out filtering processing of multi-band noise separation; performing multi-scale decomposition on the filtered disturbance signal, extracting a dynamic entropy of a multi-scale signal sequence, and performing dynamic entropy denoising on the disturbance signal to obtain a denoised disturbance signal; and calculating a potential peak position of the denoised disturbance signal, and carrying out multi-condition verification on the potential peak position to obtain peak information for frequency modulation disturbance analysis. Based on spectrum energy distribution, specific wavelet bases are selected for different noise frequency bands for noise reduction, the wavelet noise reduction performance is improved, the energy distribution complexity and the structure complexity of the disturbance signals on different scales are extracted, the dynamic characteristics of the disturbance signals are captured more comprehensively, the noise reduction precision is improved, and the noise reduction efficiency is improved. And the accuracy of wind power integration fault identification and equipment life monitoring in the peak value analysis process is improved.

The invention discloses a collaborative optimization scheduling method and system considering energy storage frequency modulation reserve. The method comprises the following steps: acquiring basic data of a power system; based on the basic data, a collaborative optimization scheduling model considering energy storage frequency modulation reserve is established, and the collaborative optimization scheduling model takes the minimum sum of the coal consumption cost, the unit start-stop cost and the wind curtailment cost of the thermal power generating unit as a scheduling target under multiple constraint conditions; the multiple constraint conditions comprise a lithium battery power constraint, a charging and discharging state constraint, an SOC constraint, a frequency modulation response constraint, a frequency safety constraint, a frequency modulation standby constraint, a flywheel energy recovery constraint, a thermal power generating unit operation constraint and a power balance constraint; solving the collaborative optimization scheduling model to obtain an optimal scheduling scheme of the power system; by comprehensively utilizing the advantages of a traditional unit, flywheel energy storage and lithium battery energy storage, the safety and operation economy of the system during frequency disturbance are improved.

The present disclosure provides a weakly-centralized frequency regulation control method of a charge station cluster based on virtual leader and a medium. Firstly, based on the control strategy of the virtual synchronous generator and the requirements of the electric vehicles and the charge stations, an architecture of the virtual synchronous generator of the electric vehicles and the charge stations is established. Secondly, based on the control strategy of the collaborative topology design of multiple charge stations, a virtual leader is determined and a weakly-centralized consistency algorithm is designed. Finally, a control strategy of the collaborative frequency regulation of the charge station cluster is proposed to achieve the weakly-centralized frequency regulation control of the charge station cluster.

The invention relates to the technical field of power plant resource scheduling, and provides a cross-regional virtual power plant frequency modulation resource collaborative scheduling optimization method combined with a large model. The method comprises the following steps: establishing a cross-regional resource pool and performing label identification, and establishing a resource sharing architecture; calling a high-frequency sensor to monitor the load and frequency of each region, and establishing a real-time demand data set; activating the adversarial network to expand the historical data set of each region, performing time sequence prediction of the real-time demand data set, and establishing a time sequence prediction result; generating a connection stable value according to the connected identifier, and performing collaborative scheduling optimization based on the time sequence prediction result, the tag identifier and the connection stable value to generate an optimization result; and reconstructing a resource sharing architecture according to an optimization result, and performing power plant frequency modulation resource cooperative scheduling management, so as to solve the technical problems of low resource utilization rate and difficulty in cooperative scheduling among regions due to non-uniform resource distribution and inconsistent response speed of each region, and achieve the effect of improving the cooperative response speed and the resource utilization rate of the frequency modulation resources.

The invention relates to the technical field of power system frequency, and discloses a thermal power generating unit-energy storage coupling frequency modulation system for improving power grid frequency stability, which comprises a thermal power generating unit module, an energy storage system module, an energy management and distribution control module and a communication and monitoring module. The thermal power generating unit provides a frequency stabilization basis through inertia response and power regulation, and the energy storage system compensates frequency deviation in a quick response mode. And the energy management module dynamically adjusts the power distribution proportion between the thermal power generating unit and the energy storage system based on the optimized objective function to realize efficient collaborative frequency modulation. The output power and the state of charge of the energy storage system are controlled by constraint conditions. The communication and monitoring module collects power grid frequency, load fluctuation and energy storage state data in real time, generates frequency modulation control signals and issues the frequency modulation control signals to each module. By combining the stability of the thermal power generating unit and the quick response characteristic of the energy storage system, the response speed and the adjustment precision of power grid frequency adjustment are remarkably improved, and meanwhile the frequency adjustment cost is reduced.

The invention discloses a VSG adaptive control method, which comprises the following steps: establishing an inverter model based on VSG control, introducing a virtual rotational inertia J and a damping coefficient D into the inverter model, introducing an SG2-order rotor motion equation to simulate the rotational inertia and realize primary frequency modulation characteristics, and deducing a control equation; establishing a VSG active-frequency loop small signal model, and introducing a transfer function of reference power-frequency and output power reference power to determine a variation range corresponding to the virtual inertia J and the damping coefficient D; and designing a fuzzy controller to dynamically adjust the virtual inertia J and the damping coefficient D in a variation range corresponding to the virtual inertia J and the damping coefficient D so as to realize real-time adjustment of the virtual inertia J and the damping coefficient D. According to the VSG adaptive control method, parameter adjustment is more sensitive in the face of small errors, and the selection range of J and D can be fully utilized and adjusted in real time.

The invention relates to the field of power system frequency stability control, and discloses a virtual synchronous machine energy storage frequency modulation method and system based on model prediction and adaptive control, and the method comprises the steps: constructing a prediction model of a virtual synchronous machine, wherein a virtual inertia coefficient and a virtual damping coefficient are included; designing a cost function, wherein the cost function is a weighted sum of squares of the frequency increment and the input power increment; solving the optimal control sequence by using quadratic programming, and further correcting the input power of the VSG in real time; and in combination with the dynamic characteristics of the energy storage device, the virtual inertia coefficient and the damping coefficient are adaptively adjusted according to the frequency deviation and the frequency change rate. The method focuses on the combination of model prediction control and adaptive control, is applied to the energy storage frequency modulation of the virtual synchronous machine, and aims to effectively solve the problem of frequency stability caused by the access of high-proportion renewable energy to a power system.

The invention discloses a control system and method for a thermal power generating unit and flywheel energy storage to cooperatively participate in power grid frequency modulation and a power grid frequency modulation method. According to the method, a low-pass filtering algorithm is abandoned, a tracking differentiator is used for decomposing a primary frequency modulation instruction of the thermal power generating unit, and decomposed low-frequency power components are distributed to the thermal power generating unit; high-frequency power components are distributed to the flywheel for energy storage, action times and output abrasion of the thermal power generating unit are reduced, and the service life of the unit is prolonged. A gain coefficient which adaptively changes along with the state of charge (SOC) and frequency deviation is introduced into the decomposed high-frequency power component, so that accurate matching requirements are facilitated, the energy utilization efficiency is improved, the frequency fluctuation of a power grid is better stabilized, and the quality of the power grid is improved; and meanwhile, a Logistic function for preventing the flywheel from being overcharged and overdischarged is introduced to restrain the theoretical response power of flywheel energy storage, deep charging and discharging of the flywheel are avoided, and therefore the loss of the flywheel is reduced.

The invention relates to the technical field of energy storage frequency modulation, in particular to a prediction method and system for an energy storage frequency modulation instruction, and the method comprises the steps: decomposing a frequency modulation instruction sequence Pt through VMD, and obtaining a plurality of IMF subsequences; according to the total area Sii of the current IMF sub-sequence and the test group error Wi, judging whether the current IMF sub-sequence is a false sequence or not by using an activation function; and improving the IMF sub-sequence of which the judgment result is false, and performing prediction output of a frequency modulation instruction by utilizing the improved IMF sub-sequence. The method has the advantages that false sequences possibly generated in the variational mode decomposition process can be effectively recognized and improved. According to the method, the false sequence can be accurately found out and processed by calculating the area defined by the adjacent data points in the subsequences and the X axis, the prediction error is reduced, and the prediction precision is improved. In addition, a false sequence is optimized by means of generating a random sequence, performing mirror image transformation and the like, and the response speed and the frequency modulation efficiency of the system are further improved.

The embodiment of the invention provides a flywheel energy storage system energy management method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring flywheel data, power grid data and maximum allowable charging and discharging power in real time; constructing a multi-objective optimization function according to the flywheel data, the power grid data and the maximum allowable charging and discharging power of the flywheel; and dynamically adjusting a weight coefficient of the multi-objective optimization function according to a power grid response effect, and generating an optimal flywheel charging and discharging power instruction in real time by adopting a model prediction control algorithm. According to the embodiment of the invention, through the model prediction control algorithm, the real-time flywheel state and the power grid demand data are combined, the charging and discharging power instruction is dynamically optimized, the charging and discharging switching loss is reduced, and the comprehensive efficiency of the system is improved; flywheel mechanical stress constraint is carried out in real time, flywheel fatigue damage is reduced, and the service life of the flywheel is prolonged; by adding the power grid frequency deviation and the load tracking penalty term, the frequency modulation demand of the power grid can be quickly responded.

The invention relates to a multi-target operation optimization method and system for a green electricity hydrogen production grid-connected system considering multi-scale flexibility of a power grid, and the method comprises the steps: obtaining the power output of new energy at a grid side and the historical data of user load power, and obtaining typical operation days at the grid side and a load side through a clustering algorithm; establishing physical models of an electrolytic cell, a hydrogen storage tank, a fuel cell and the like in the system; considering the transferable characteristic of an electric load and the requirements of system peak regulation and new energy consumption, and formulating a day-ahead peak regulation optimal scheduling strategy according to typical operation days of a source side and a load side; an electricity-hydrogen operation optimization strategy with a primary frequency modulation capability is established based on self-adaptive droop control by considering factors such as an electrolytic bath rotation strategy, a wide-power operation characteristic and a transferable characteristic of a hydrogen load; power grid frequency deviation and electrolytic cell operation power are used as decision variables, multi-target operation optimization with the power grid frequency deviation rate and the new energy consumption rate as target functions is established, a non-dominated sorting genetic algorithm is adopted for solving, and an optimal operation scheme is obtained.

The invention discloses a secondary frequency modulation optimization control method under a low-load working condition, relates to the technical field of power grid resource optimization, and is used for solving the problem that a control strategy under the low-load working condition is not fully considered in the prior art. The current load interval is recognized, and control parameter correction is conducted on the unit located in the low load interval; calculating a total output power reference value; carrying out calculation by adopting a self-adaptive optimization algorithm, and carrying out power fine distribution to obtain an optimal charging and discharging instruction of each energy storage unit; and the output power is adjusted in real time through double-closed-loop control. The invention further discloses a secondary frequency modulation optimization control device under the low-load working condition, electronic equipment and a computer storage medium. By dynamically correcting the control parameters of the low-load thermal power generating unit and cooperatively distributing the hybrid energy storage power in combination with the adaptive optimization algorithm, the safety and economical efficiency of the energy storage system are guaranteed.

The invention provides an optical storage parallel network control method, which comprises the following steps: calculating the current load rate percentage of each residual unit according to the connection relation and electrical path information of the residual units after isolation; evaluating the available margin capacity and the frequency regulation bearing capacity of the remaining units, matching the available margin capacity and the frequency regulation bearing capacity with a specific power value and a frequency regulation requirement which need to be compensated, and determining a feasible unit combination scheme for fault recovery; generating a power redistribution list and a frequency adjustment responsibility distribution table according to the direct current bus connection mode of the optimal unit recombination, and obtaining an output power set value and a frequency adjustment parameter of each unit after adjustment; and extracting the continuous power supply time value of the optical storage parallel network, updating the total power supply capacity value of the optical storage parallel network, and maintaining the continuous power output and frequency stability after the fault of the optical storage parallel network.

The invention discloses an intelligent energy storage system multi-target hierarchical scheduling method and system oriented to source network load storage cooperation, and belongs to the technical field of energy storage system optimization control. The method comprises three levels of day-ahead layer multi-objective game optimization, intra-day layer rolling correction optimization and real-time layer adaptive droop control. The day-ahead layer establishes three objective functions of economy, environmental protection and smoothness, and solves and outputs a day-ahead charging and discharging power plan by using a Nash negotiation algorithm. And the intra-day layer obtains ultra-short-term prediction data of the source load, performs rolling correction on the day-ahead plan by adopting a model prediction control method, and outputs a corrected real-time power instruction. The real-time layer collects power grid frequency deviation and a battery health state value, calculates an adaptive droop coefficient according to the health state value, and superposes and outputs primary frequency modulation response power and a real-time power instruction. According to the invention, source network load storage collaborative optimization is realized through multi-time scale hierarchical scheduling, and the service life of an energy storage system is prolonged through adaptive droop control based on health state perception.

The invention discloses a high-power all-gallium nitride LED driving power supply circuit which comprises an EMI filtering and rectifying circuit, a GaN active power factor correction circuit, a GaN half-bridge LLC resonant converter circuit and a GaN synchronous rectifying and filtering circuit. The PFC and LLC combined control module integrates a power factor correction function and a resonance circuit frequency regulation function, the GaN active power factor correction circuit is connected with the PFC and LLC combined control module to realize power factor correction, and the GaN half-bridge LLC resonant converter circuit is connected with the PFC and LLC combined control module to realize output power regulation; and a constant-current voltage-limiting feedback circuit for outputting current and voltage detection feedback is arranged between the GaN synchronous rectification filter circuit and the PFC and LLC combined control module. The advantages of high efficiency of the GaN switching tube and high working frequency of the circuit are utilized, so that power loss and heat dissipation requirements are reduced, and the efficiency and power density of the LED power supply are improved. The invention has the advantages of high efficiency, high power density, high reliability and the like.

The invention discloses a radio frequency power adjusting system, an adjusting method thereof and semiconductor process equipment. The adjusting system comprises an interference monitoring module which obtains a time domain signal of radio frequency power in a reaction cavity and obtains interference data based on frequency domain characteristics of the time domain signal; the adaptive control module takes the interference data as a state input variable, updates an action output variable by learning an optimal strategy, and determines an optimal action output variable based on an objective function of interference suppression and energy consumption, and the action output variable comprises a frequency regulation variable, an amplitude regulation variable and a pulse width regulation variable; and the feedback adjusting module is used for dynamically adjusting a plurality of process parameters in the reaction cavity based on the optimal action output variable so as to enable the process parameters to reach the target process parameter range. According to the invention, the radio frequency power density in the reaction cavity can be adaptively adjusted, and the optimal dynamic balance between interference suppression and energy consumption is realized, so that the radio frequency interference suppression effect, the process stability and the equipment efficiency are improved.

The invention discloses an efficient variable-frequency low-temperature compressor system and a compression method thereof. The method comprises the steps that the actual oil-gas separation efficiency is obtained; inputting the working condition parameters of the compressor into a preset neural network prediction model to obtain an oil-gas separation efficiency prediction value and a theoretical solubility reference value; according to the actual oil-gas separation efficiency, the oil-gas separation efficiency predicted value and the theoretical solubility reference value, working condition deviation data is calculated, the comprehensive performance of the compressor at different frequency points is evaluated and calculated through an optimization algorithm, and a frequency adjustment curve is generated; according to the frequency adjusting curve, the operation frequency of the compressor is divided into a plurality of adjusting intervals, the operation frequency is adjusted in a stepped mode according to the adjusting intervals, the temperature and vibration parameters of the bearing are monitored in the adjusting process, and frequency adjusting feedback data are obtained; and according to the frequency adjustment feedback data, oil-gas separation efficiency deviation is periodically calculated, and compensation adjustment is conducted on the frequency adjustment curve. According to the technical scheme, insufficient lubrication and energy efficiency reduction of the compressor can be avoided.

The invention discloses a grid-connected inverter control method based on second-order linear active disturbance rejection, and particularly relates to the field of grid-connected inverter control. Voltage and frequency error signals between the output side of the inverter and the power grid are obtained, a pre-synchronization control model is constructed, and voltage amplitude and frequency synchronization is achieved; a second-order linear active-disturbance-rejection controller is introduced in the frequency synchronization control process, an extended state observer is adopted to estimate the output frequency, the frequency change rate and a disturbance term, and a state error feedback control law is combined to generate a frequency regulation control quantity, so that accurate frequency control is realized; after grid connection, a dual-channel LADRC power regulation controller is constructed, and decoupling tracking control is carried out on active power and reactive power; meanwhile, on the basis of fast Fourier transform processing as a stable grid-connected state criterion, the method has the advantages of being high in control precision, high in anti-interference capability, good in current waveform quality, high in adaptability and the like, and is suitable for various grid-connected application scenes.

The invention relates to the technical field of electric power system regulation and control, and particularly discloses an electric power active balance control method for coupling multi-element energy storage of a coal power unit, which is used for solving the problem that the existing static active safety margin evaluation method cannot evaluate the safety of the coal power unit under the complex working conditions of high wind power penetration, large disturbance, system inertia decline and the like. The method solves the problems that multi-stage frequency response cannot be accurately described, online self-adaptive power distribution and continuous smooth scheduling are lacked, and consequently frequency drop is large, recovery is slow and output suddenly changes, and comprises the steps of building a collaborative characteristic model, calculating dominant characteristics on line, optimizing scheduling in a segmented mode and updating parameters in a closed loop. According to the method, by constructing a hierarchical inertia and multi-stage frequency modulation collaborative model, and adopting multi-scale online feature extraction and adaptive power distribution, segmented gradient optimization scheduling and closed-loop online parameter updating, quick response, smooth connection and accurate optimization of frequency support and economic scheduling in a wind power high-permeability scene are realized.

The invention relates to a high-proportion new energy power grid frequency rotational inertia control method and system. The method comprises the following steps: establishing a virtual rotor motion equation; performing frequency droop control on the active power to obtain an active-frequency droop equation; the active-frequency droop equation is substituted into the virtual rotor motion equation, and a virtual speed regulator control model is obtained; meanwhile, an output reactive power regulation equation of the new energy grid-connected current converter is obtained; establishing an equivalent impedance equation; based on the Kirchhoff voltage law and introducing a dq-axis current coupling component, obtaining a mathematical model of the output voltage of the VSG control system in a dq two-phase coordinate system; the output power of the VSG is further obtained; analyzing a transient energy change process during VSG frequency regulation by adopting an energy composition function; according to the relation between the current angular frequency and the initial angular frequency, the frequency change rate is introduced to represent the virtual inertia, and the self-adaptive virtual inertia is obtained; and the adaptive virtual inertia is substituted into the virtual rotor motion equation to obtain a high-proportion new energy power grid frequency rotational inertia control equation.

The invention relates to the technical field of wind power plants, and discloses a cooperative optimization control strategy for dynamic load of a transmission chain of a fan set and frequency response of a power grid to realize frequency stabilization and dynamic load relief of the transmission chain. The method comprises the steps that firstly, a dynamic model of a wind turbine generator is established and linearized, a power system frequency regulation model is constructed and participates in power grid frequency regulation, and meanwhile the power system frequency regulation model further comprises a thermal power generating unit model; subsequently, a hybrid controller is designed for simultaneously considering frequency response and transmission chain load fluctuation suppression.

The invention relates to the field of power system automatic control and new energy grid-connected operation, and provides an energy storage-containing new energy field station frequency modulation optimization method based on deep reinforcement learning. The method comprises the following steps: firstly, establishing a frequency response model containing an energy storage new energy field station, constructing a frequency modulation problem into a Markov decision process, and defining a state space containing a charge state and frequency deviation, an action space taking a charge and discharge power instruction as an element, and a multi-target reward function fusing a frequency regulation effect and charge state management; and then designing an intelligent agent network based on a long short-term memory network and an improved soft actor-commentator algorithm, constructing an online training framework with priority experience playback and a sliding time window, and realizing adaptive optimization of the strategy. And finally, generating a robust frequency modulation instruction in real time based on the trained model. Simulation shows that the frequency long-term regulation and control capability and the intelligent level can be remarkably improved, and the frequency modulation performance and the frequency modulation margin are effectively coordinated.

The invention discloses a method for preventing power reverse peak regulation by coupling primary frequency modulation and virtual inertia of a network-forming type fan, and the method effectively prevents power reverse peak regulation by dynamically decoupling the coupling effect of primary frequency modulation and virtual inertia and adjusting an amplitude limiting threshold value based on a real-time working condition. The adaptive amplitude limiting control strategy adjusts an amplitude limiting threshold value in real time according to parameters such as power grid frequency deviation, frequency change rate and fan operation state, optimizes fan power output, and avoids excessive power fluctuation. The virtual inertia compensation module simulates inertia response of a traditional generator set, provides extra inertia support and stabilizes frequency fluctuation of a power grid. The hierarchical control architecture realizes the balance of virtual inertia and frequency modulation control through the synergistic effect of an upper decision layer and a bottom execution layer, and avoids the phenomenon of reverse peak regulation of power. The control strategy not only improves the frequency modulation response speed and precision, but also enhances the adaptive capacity of the fan to the frequency fluctuation of the power grid, and has important application value and wide market prospect.

The invention discloses a power system real-time scheduling method and system considering multivariate novel energy storage characteristics, and the method comprises the steps: building a deviation probability model according to historical new energy power generation prediction deviation data, and calculating the new energy power generation deviation; frequency modulation power output of frequency modulation resources is calculated according to the new energy power generation deviation, the frequency modulation resources comprise a traditional unit and multi-element novel energy storage, and the multi-element novel energy storage comprises compressed air energy storage, gravity energy storage and electrochemical energy storage; and establishing an optimization probability scheduling model by taking minimization of the operation cost of the power system as a target, and solving the optimization probability scheduling model to obtain a power generation plan of the power system. According to the method, the actual operation characteristics of multi-element novel energy storage are combined, corresponding opportunity constraint conditions and mathematical expectation cost are designed based on the dynamic corresponding requirements of the actual frequency modulation process of the power grid, the new energy system probability scheduling model combining the operation characteristics of the multi-element novel energy storage is constructed, and the reliability and the resource utilization rate of the power grid are improved.