133 results about "Automatic Generation Control" patented technology

A distributed photovoltaic regulation method considering safety verification includes acquiring power transmission or power substation equipment limit value, load condition, and distributed photovoltaic aggregation information under equipment, calculating load rate of equipment, calculating total maximum regulation amount or the total over-limit correction amount of distributed photovoltaic power under equipment based on the load rate of equipment and a threshold value, and decomposing total maximum regulation amount or total over-limit correction amount to obtain respective total maximum regulation amount or total over-limit correction amount of each load point; and decomposing respective total maximum regulation amount or total over-limit correction amount of each load point to obtain respective maximum regulation amount or over-limit correction amount of each automatic power generation control unit, correcting respective regulation requirement and generating respective regulation target of each automatic power generation control unit, and sending respective regulation target to each automatic power generation control unit for execution.

The invention provides an automatic generation control (AGC) collaborative optimization method based on time sequence deep reinforcement learning PID (Proportion Integration Differentiation) control. Comprising the following steps: establishing a three-area multi-source interconnected power system with participation of hydroelectric power, thermal power, wind power, photovoltaic power and energy storage, and bringing wind and light storage resources into an automatic power generation control loop. The invention provides a novel AGC adaptive PID controller based on time sequence deep reinforcement learning by utilizing the time sequence perception capability of a long short-term memory neural network and combining a double-delay depth deterministic strategy gradient algorithm, and provides an efficient time sequence deep reinforcement learning solution for intelligent power grid frequency control.

The invention discloses a rapid communication and redundancy control method for an AGC substation of a distributed photovoltaic power station, and the method comprises the following steps: S1, receiving an automatic power generation control instruction from a power grid dispatching system in parallel and uploading real-time operation data of the photovoltaic power station through two independent communication links; according to the invention, the reliability and robustness of the system are fundamentally improved; by constructing a physical basis of parallel work of two paths of independent communication links and combining real-time state monitoring and a millisecond-level rapid switching mechanism, the method thoroughly changes the fragile situation that the whole substation is disconnected and the function is paralyzed due to a single communication channel or a power supply fault of a traditional system; when the main optical fiber link is interrupted due to construction damage or equipment failure, the system can automatically and seamlessly switch all communication services to the standby Ethernet or wireless link without depending on manual intervention, and it is ensured that the transmission path of the scheduling control instruction is always smooth.

The embodiment of the invention provides a hybrid energy storage thermal power generating unit frequency modulation strategy and system based on hierarchical adaptive control, and the strategy comprises the steps: detecting the reserve capacity and hybrid energy storage charge state of a thermal power generating unit in real time, and obtaining an automatic power generation control instruction, obtaining interregional tie line exchange power and system frequency deviation, and calculating a regional control deviation frequency modulation instruction; the outer layer control is based on the relation between the residual energy of the hybrid energy storage system and a hybrid energy storage distribution scaling factor K, and self-adaptive distribution is carried out on a power grid real-time area control deviation frequency modulation instruction between the thermal power generating unit and the hybrid energy storage system; the inner layer control decomposes a regional control deviation signal distributed to the hybrid energy storage system between flywheel energy storage and battery energy storage, and calculates a rated output power instruction of each energy storage; a battery energy storage unit is divided into a charging sub-unit and a discharging sub-unit, and when any sub-unit reaches a state-of-charge boundary, a charging state and a discharging state are switched; and outputting the frequency modulation power instruction to the energy storage converter.

The invention relates to the technical field of electric power systems, and discloses a thermal storage combined frequency modulation control method, device and equipment and a medium, and the method comprises the steps: determining the working state of a heat storage device according to the load value of a thermal generator set when a frequency modulation control instruction is received; the working state comprises heat storage and heat release; based on the working state of the heat storage device and the difference value between the power of the thermal generator set and the automatic power generation control target, the opening degree value of a steam adjusting door and the first charging and discharging power value of a lithium battery energy storage system are calculated, or the opening degree value of a hot water adjusting door and the second charging and discharging power value of the lithium battery energy storage system are calculated; generating a coordination control instruction; and controlling the charging and discharging power of the lithium battery energy storage system according to the coordination control instruction, and controlling the opening degree of a steam adjusting door and the opening degree of a hot water adjusting door of the heat storage device so as to carry out peak regulation and frequency modulation on the thermal generator set. According to the technical scheme, the frequency modulation performance of the thermal power generating unit can be improved.

The invention discloses a hybrid energy storage configuration method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an automatic power generation control signal of a power grid in a preset time period of a target region, carrying out the decomposition processing of the automatic power generation control signal based on adaptive noise complete set empirical mode decomposition, so as to determine a high-frequency component and a low-frequency component, correspondingly distributing the high-frequency component and the low-frequency component to the energy storage battery to determine a power grid energy storage output demand, configuring a battery rate and a battery capacity of the energy storage battery based on the power grid energy storage output demand, and constructing an energy storage configuration constraint model based on a constraint condition of the energy storage battery, and establishing an energy storage battery life cycle cost efficiency model and a regional power grid frequency modulation policy model, and determining the capacity configuration of hybrid energy storage in the energy storage battery when the frequency modulation benefit of the energy storage battery life cycle cost efficiency model is optimal in combination with the battery rate, the battery capacity, the energy storage configuration constraint model and the regional power grid frequency modulation policy model. And the optimal capacity configuration can be accurately selected.

The invention discloses an AGC adjustment method and system based on multi-objective optimization, and the method comprises the steps: obtaining the output, load demands and new energy output information of each generator set in a real-time operation database of a power system, and obtaining the response capability and cost data of an adjustable load through a demand side management system, the input is used for constructing a multi-objective optimization model; aiming at the constructed high-dimensional nonlinear non-convex multi-objective optimization model, adopting an improved particle swarm optimization algorithm for solving, and improving the convergence speed and the global search capability of the algorithm by introducing an adaptive inertia weight and a diversity retention mechanism to obtain a Pareto optimal solution set; and selecting an optimal frequency modulation scheme from the obtained Pareto optimal solution set according to safety and stability constraints and frequency modulation performance requirements of the power system, determining output adjustment amount and adjustment time of each generator set, and generating a corresponding automatic power generation control instruction.

The invention discloses an automatic generation control (AGC) operation method based on a gradient equidirectional distribution strategy. The method comprises the steps of receiving a set value of a control center, measuring actual generation power, judging a distribution mode, executing gradient equidirectional distribution, issuing a distribution instruction, monitoring an operation state and the like. The set value needs verification and format conversion, and the actual generated power is obtained by collecting electrical parameters and calculating. And determining to execute small load distribution or gradient equidirectional distribution according to a comparison result of the difference value between the set value and the actual generated power and a preset threshold value. The gradient same-direction distribution algorithm comprises the steps of determining participating units, calculating distribution units, calculating a proportionality coefficient and distributing a load value. The distribution instruction needs to be coded and is transmitted to the generator set control system through a special communication line. The operation state monitoring comprises the steps of collecting operation parameters and judging a parameter range, and triggering an alarm and adjusting if the range is exceeded. According to the invention, the response speed and stability of the power system can be improved, and the reliability and safety of power supply are ensured.

The present application relates to the technical field of energy storage, and discloses an energy storage power control method, apparatus, and device, and a storage medium, which are used for carrying out energy storage power control taking into account the power requirements of inertial response, primary frequency control, and automatic generation control, so that conflicts among control functions are avoided. The method comprises: in response to an energy storage power control instruction, determining whether an inertial response requirement or a primary frequency control response requirement exists in an energy storage control system; if no inertial response requirement or primary frequency control response requirement exists, determining whether an automatic generation control function is in an enabled state; if the automatic generation control function is in the enabled state, determining a control power value corresponding to the automatic generation control function to be a target energy storage power value; and, according to the target energy storage power value, performing energy storage power control on the energy storage control system.

The invention relates to the technical field of energy storage assisted thermal power generating unit frequency modulation, in particular to an intelligent thermal power and energy storage combined frequency modulation control system and method based on multi-mode switching, and the system comprises a telecontrol device, an intelligent thermal power and energy storage cooperative control system, a thermal power generating unit and an energy storage system. The telecontrol device sends an automatic power generation control instruction to the intelligent fire-storage cooperative control system and the thermal power generating unit, and according to different mode selection modes, the intelligent fire-storage cooperative control system obtains an energy storage power instruction and adjusts the output of an energy storage system by using an internally designed functional module; the thermal power generating unit obtains a unit load instruction and adjusts the output of the thermal power generating unit by utilizing an internally designed functional module, the combined output of the energy storage system and the thermal power generating unit responds to an automatic power generation control instruction, deep coupling and efficient control of the thermal power storage system are achieved, the long-term frequent and rapid frequency modulation pressure of the thermal power generating unit is relieved, and the over-temperature risk of a boiler water cooling wall is reduced. The comprehensive economy and safety of the fire storage system are improved, and the combined frequency modulation capacity of the fire storage system is improved to the maximum extent.

The invention discloses a thermal power generating unit-flywheel energy storage interconnected power grid AGC control method, device and equipment, a medium and a product, and relates to the field of automatic power generation control. The method comprises the following steps: establishing a thermal power generating unit-flywheel energy storage interconnected regional power grid AGC control system; determining that a controller in the system comprises an outer loop fuzzy PID controller and an inner loop PD + 1 controller with a filter coefficient; establishing a fuzzy control rule table of PID control parameters in the outer loop fuzzy PID controller; optimizing parameters in an inner ring PD + 1 controller by adopting a particle swarm optimization algorithm to obtain optimal parameters; an ACE deviation signal is adjusted through an outer loop fuzzy PID controller by using a fuzzy control rule table, an outer loop control signal is obtained, and then an AGC adjustment instruction is obtained by using an inner loop PD + 1 controller with optimal parameters; and decomposing the AGC adjustment instruction into a thermal power generating unit control signal and a flywheel energy storage control signal, and responding. The frequency stabilization performance can be improved.

The invention relates to the technical field of power dispatching, in particular to a new energy active automatic power generation control parameter setting method and system, and the method comprises the steps: synchronizing the external conditions of a power grid, and completing AGC modeling and power grid modeling; setting a control parameter range, a setting step length and test verification time which need to be set to form a control parameter combination to be set, and starting a control closed-loop simulation test from the first group of control parameter combination; acquiring initial power flow and frequency, calculating regional control deviation, and decomposing the regional control deviation to form a control strategy; executing the control strategy, calculating the power flow and frequency of the power grid at the next moment when the strategy is executed, and carrying out alternate iteration until the test verification time is reached; calculating a control performance index in the verification time, and recording the performance of the current control parameter combination; selecting a next group of control parameter combinations, and repeating the closed-loop simulation test process until all the control parameter combinations are traversed; and selecting a control parameter combination meeting a set condition to generate a recommendation report.

The invention belongs to the technical field of automatic power generation control, and particularly relates to an automatic power generation control method, device and system based on an energy management system. The method comprises the following steps: S1, acquiring real-time operation data of a power grid; s2, according to the real-time operation data of the power grid, through a pre-trained load prediction model and a pre-trained generating capacity prediction model, obtaining a predicted load and a predicted generating capacity in a period of time in the future; s3, according to the predicted load, the predicted generating capacity, the power grid real-time operation data and preset strategy generation parameters, a control strategy is generated through a strategy generation model, and the control strategy comprises output of each power generation device and / or energy storage device; and S4, executing the control strategy, and correcting strategy generation parameters in the strategy generation model through an optimization algorithm according to an execution result of the control strategy. The technical problem that the stability of a power system is affected due to the lack of feedback of a control strategy execution result in the prior art is solved.

The application discloses a kind of offshore wind farm automatic power generation control flow field dynamic modeling methods, comprising the following steps: data sampling is carried out using CFD simulation, obtains data set;Data is collected and arranged;Eigen-orthogonal decomposition is used for order reduction processing;Offshore wind farm automatic power generation control flow field dynamic model based on yaw, variable pitch, speed regulation process and its disturbance process is constructed.The application can effectively overcome the shortcomings that the data set obtained by high-precision wind farm flow field dynamic simulation is large in structure and difficult to apply directly, and the dynamic reduced-order model of the wind farm flow field obtained can greatly compress the data structure, retain the main characteristics of the flow field, and has high wake prediction accuracy.

The invention relates to the technical field of photovoltaic power stations. The photovoltaic power station cluster power generation efficiency dynamic optimization intelligent scheduling device comprises an intelligent scheduling main cabinet, the front end of the intelligent scheduling main cabinet is movably connected with a gate, and the interior of the intelligent scheduling main cabinet is correspondingly connected with a communication module, a central controller and a data acquisition module. An automatic power generation control system and an emergency control function are connected to the center of the intelligent dispatching main cabinet, an adjusting device is fixedly connected to a top plate groove in the top of the intelligent dispatching main cabinet, the adjusting device comprises a rotating device, a driving device and an angle adjusting device, the driving device is a core power component, and the bottom of the driving device is fixedly connected with the top of the rotating device. When the monitoring angle needs to be adjusted, the rotating device rotates and adjusts at first, and then the driving device drives the angle adjusting device connected to one side of the driving device to rotate and adjust synchronously, so that the sensing assembly keeps the optimal sensing angle all the time, and the accuracy of environmental parameter acquisition is ensured.

The application discloses a wind-solar-thermal-storage automatic power generation control method based on closed-loop rolling optimization and belongs to the technical field of new energy grid connection and automatic power generation control. The method collects system frequency deviation, tie-line exchange power deviation and wind power, photovoltaic and thermal power station operation states in real time, establishes a wind-solar-thermal-storage coupling state space prediction model, takes the system frequency deviation and power increment of each power generation unit as a prediction output, takes a control increment as a decision variable, constructs a model prediction control objective function, and solves the control sequence under the constraints of active power balance, output boundary and thermal power unit climbing to realize closed-loop AGC control, improve the collaborative frequency modulation capability and operation stability of the multi-energy complementary system.

The invention relates to a method and device for determining the reserve capacity of a water-wind-light power generation system and electronic equipment, and the method comprises the steps: obtaining a target data set; inputting the meteorological data, the power grid state data and the water-wind-light regulation data into an output probability prediction model of the water-wind-light complementary power generation system to obtain probability distribution of water-wind-light power generation power; performing space-time correlation characteristic analysis on the automatic power generation control instruction to obtain an instruction space-time coupling relation matrix of the water-wind-light complementary power generation system; according to the probability distribution of the water-wind-light power generation power and the instruction space-time coupling relation matrix, determining a water-wind-light output fluctuation ratio; and determining the target reserve capacity according to the water-wind-light output fluctuation ratio, the water-wind-light adjustment margin and the power grid frequency deviation. According to the method, the demand of the standby capacity can be more accurately determined, and the problems of unstable power grid frequency or frequency modulation resource waste and the like caused by inaccurate calculation are effectively reduced.

The invention provides a control method of a sea wind flexible direct current power transmission project. After fault signals of the land connected transformers are received, the maximum transmittable power is determined according to the number of the remaining land connected transformers, working condition grades are divided according to overload conditions, and data support and decision basis are provided for follow-up control; the maximum transmittable power smaller than the actual power of the current land station is transmitted to an automatic power generation control system of the offshore station, limited power control is triggered, power input is reduced from the source, and the situation that the power continuously exceeds the bearing capacity of a land connection transformer is avoided; and cutting off the offshore connection transformer of the offshore station according to a cutting mechanism corresponding to the working condition grade, further dynamically adjusting the output of offshore power generation power, and reducing the overall power transmission load of the system. According to the scheme, grading and classification protection of transmission power of the land connection transformer is achieved in an all-around mode, system faults caused by overload are effectively prevented, safe and stable operation of a sea wind flexible direct current transmission project is guaranteed, and system operation reliability and stability are improved.

The invention discloses a wind storage automatic power generation control optimization method, and relates to the technical field of power system stability control, and the method comprises the steps: constructing an automatic power generation control model containing a wind turbine generator and an energy storage system, introducing a per-unit coefficient by the wind turbine generator through droop adjustment and a virtual inertia response strategy, and building an open-loop transfer function, the energy storage system adopts a first-order inertial model; constructing an improved MPC control model fused with the PIDN, connecting a feedforward control component of the MPC with a feedback control component of the PIDN in parallel, and generating a unified control signal to drive a wind turbine generator and an energy storage system to perform power adjustment; and carrying out global optimization on model predictive control MPC parameters by adopting an STOA algorithm and taking ITAE indexes of frequency deviation and tie line power deviation as optimization targets. According to the method, the system frequency stability and the power regulation precision are effectively improved, and the dynamic performance and the robustness of wind and storage combined participation in automatic power generation control are enhanced.

The present invention discloses a method and system for collaborative optimization of intelligent master control and frequency regulation of power systems, which relates to the technical field of automated control of power systems. The method comprises the following steps: constructing a deviation function based on the real-time collected grid frequency; determining the primary frequency regulation response power based on the frequency deviation and the unit regulation parameters; dynamically superimposing the primary frequency regulation response power with the power setting value of the automatic power generation control to form a comprehensive power instruction; and dynamically adjusting the weight ratio of the primary frequency regulation and the automatic power generation control. By collaboratively optimizing the regulation actions of the primary frequency regulation and the automatic power generation control, the present invention can provide a faster response when the frequency fluctuation is large, and optimize the unit power regulation when the frequency fluctuation is small, thereby avoiding the conflict and inefficiency caused by the inconsistent regulation time scales of the two in the traditional method. This not only improves the frequency regulation accuracy of the system, but also enhances the dynamic response capability of the system.

The invention relates to the technical field of automatic power generation control and frequency stabilization of a power system, in particular to a system economic frequency control method, system and equipment considering vibration area constraint, and the method comprises the steps: constructing a power dynamic model containing a variable speed pumped storage group VSPS; the method comprises the following steps: establishing an economic optimization model of vibration avoidance, taking minimization of the total adjustment cost of a system as a target, adopting quadratic form adjustment cost representation, introducing VSPS unit vibration area inequality constraints and an auxiliary variable gamma for relaxation power balance constraints, constructing a Lagrange function and designing a distributed primitive-dual solution algorithm for the economic optimization model, and solving the VSPS unit vibration area inequality constraints. According to the algorithm, non-negativity of dual variables is ensured by adopting adjustable positive step length parameters and utilizing a forward projection operator, and original variables and the dual variables are iteratively solved; by matching the power dynamic model with the steady-state condition of the algorithm, the anti-vibration economic AGC which can be directly embedded into the existing AGC structure is exported and realized, and the anti-vibration economic AGC is applied.

The invention discloses a hydropower station dynamic grid-connected performance self-evaluation method, system and device and a medium. The method comprises the steps of obtaining real-time operation data of a power grid; analyzing the obtained data, and evaluating the automatic voltage control performance to obtain a first dynamic grid-connected index; evaluating the performance of the excitation and power system stabilizer to obtain a second dynamic grid-connected index; evaluating the automatic power generation control performance to obtain a third dynamic grid-connected index; evaluating the primary frequency modulation performance to obtain a fourth dynamic grid-connected index; and based on the dynamic grid connection index, performing self-evaluation on the assessment index and the compensation index of the power plant, and generating early warning information. The safe and stable operation level of the hydropower station and good interaction with the power grid are improved.

The application provides a new energy station frequency control method and device considering power loss, determines an active power loss value of the new energy station and an active power instruction value that the new energy station should actually issue at a current time; determines an active power adjustment amount that the new energy station should actually issue; determines a frequency deviation of a grid connection point of the new energy station, and performs frequency control on the new energy station, thereby improving the accuracy and consistency of frequency control; the application considers the active power loss values of power generation units, power collection lines, step-up transformers and reactive power compensation devices and the like in the new energy station under different operating states, and optimizes technical indexes such as frequency modulation response time; the active power loss value of the new energy station determined by the technical scheme provided by the application is closer to the actual operating state of the new energy station, has higher reliability, and can be used in a new energy station containing multiple automatic generation control systems, and has good adaptability.

The invention discloses a power load prediction method and system based on a twin network, and belongs to the technical field of power system operation and control. The method comprises the following steps: collecting a dispatching side automatic power generation control instruction sequence, a unit side distributed control system output sequence and a cross-domain gateway timestamp, calculating a physical communication time delay sequence, constructing a physical constraint mask, and generating a training sample set according with a causal law; constructing a twin neural network containing physical constraints, and extracting an instruction expectation feature vector and a unit response feature vector; time delay fluctuation characteristic indexes are generated through time domain fluctuation analysis, dynamic alignment constraint topology is constructed, and sequence alignment is executed; and generating a global power prediction sequence based on physical residual compensation, and outputting a predicted value through consistency measurement and gating verification. The method solves the prediction problem of communication delay jitter and unit thermal inertia coupling, improves the prediction precision and the power grid stability, and is suitable for power load prediction in a complex network environment.

The invention discloses a hybrid energy storage configuration optimization method and device based on clustering analysis, equipment and a storage medium, and relates to the technical field of power systems, and the method comprises the steps: carrying out the feature extraction of a target automatic power generation control instruction, obtaining a target multi-dimensional feature vector, carrying out the standardization processing of the target multi-dimensional feature vector, and obtaining a target multi-dimensional feature vector; obtaining a standardized target multi-dimensional feature vector; determining an instruction mode type corresponding to the standardized target multi-dimensional feature vector based on the standardized target multi-dimensional feature vector and the obtained mapping relation; based on the instruction mode type, determining an initial hybrid energy storage configuration scheme; and based on the initial hybrid energy storage configuration scheme, the output of the thermal power generating unit and the target function, optimizing the initial hybrid energy storage configuration scheme to obtain a final hybrid energy storage configuration scheme. According to the method, feature extraction is performed on the target automatic power generation control instruction, so that the instruction mode type can be accurately determined, and the adjustment precision of the hybrid energy storage system is improved.

The application discloses a two-stage automatic power generation control active power distribution method and system, and belongs to the technical field of automatic control of power systems, and comprises the following steps: collecting current active power output, minimum active power output, maximum active power output of each generator set participating in automatic power generation control and active power interval endpoints representing vibration zones of each generator set, and constructing vibration zone sets and non-vibration operation sets of the generator sets; the sum of current active power outputs of all participating generator sets is calculated, a total active power deviation is calculated according to a total active power set value, and the total active power deviation is compared with a preset small load threshold value. The application introduces vibration zone intervals and vibration distance functions through mathematics, explicitly incorporates the vibration risk of the generator set into an AGC active power distribution optimization model, mathematically restricts the operation point of the generator set from the vibration zone, and improves mechanical safety and stability of operation of the generator set.

This invention proposes an adaptive speed-SOC limiting control method for magnetic levitation flywheels oriented towards AGC (Automatic Generation Control). The method includes: acquiring real-time speed and real-time SOC of the flywheel energy storage system; setting speed and SOC thresholds; and classifying the flywheel operating state into three categories based on the real-time speed and SOC, combined with the speed and SOC thresholds, and executing corresponding cooperative limiting control strategies. This invention implements differentiated cooperative limiting control strategies for different states: in normal conditions, it fully responds to AGC commands; when SOC exceeds the limit, it limits the maximum charging and discharging power in the corresponding direction; when both limits are exceeded, charging and discharging in the dangerous direction is prohibited, and only adjustment in the safe direction is allowed. This mechanism solves the problems of speed and SOC control being disconnected in existing technologies, and rigid cutoff upon reaching the threshold. It achieves cooperative judgment and intervention of speed and SOC, maximizing the continuity and response accuracy of AGC frequency regulation while ensuring the mechanical safety of the equipment, and avoiding unnecessary shutdowns or power surges caused by exceeding the limit of a single parameter.

The invention discloses a load control method and device for a coal-fired unit, and relates to the technical field of coal-fired unit control. The method comprises the steps that when it is detected that a difference value exists between a load instruction of an automatic power generation controller and the actual load of a current unit, the difference value is calculated to serve as a load instruction difference value, and whether the fused salt heat storage system participates in coordinated variable load control or not is determined; if it is determined that the fused salt heat storage system participates in coordinated variable load control, the operation mode of the fused salt heat storage system is judged based on the operation state of a cold salt pump and the operation state of a hot salt pump in the fused salt heat storage system; a main steam extraction valve and a reheating steam extraction valve are controlled according to the operation mode of the fused salt heat storage system, so that the variable load rate is increased; the main steam extraction valve is arranged between a boiler of the coal-fired unit and a high-pressure cylinder of the coal-fired unit; and the reheating steam extraction valve is arranged between a high-pressure cylinder of the coal-fired unit and a medium-pressure cylinder of the coal-fired unit. The method is used for realizing the load control function of the coal-fired unit.

The invention belongs to the technical field of source network coordination control, and particularly relates to a hydroelectric generating set source network coordination control parameter dynamic optimization method fusing historical context and an improved multi-target whale algorithm, a related system, equipment and a storage medium. Aiming at the problems of poor adaptability of control parameters, conflict of multi-target optimization, lack of historical working condition reference and the like in the process that a hydroelectric generating set participates in primary frequency modulation of a power grid and AGC (Automatic Gain Control), the method comprises the following steps: acquiring and preprocessing multi-source heterogeneous data, mining context information of historical working conditions to generate initial optimization parameters, and extracting real-time working condition characteristics and constraint conditions; and constructing a multi-objective optimization model fusing assessment of two detailed rules and unit performance, solving optimal control parameters by adopting an improved multi-objective whale algorithm, executing the optimal control parameters, and dynamically adjusting the parameters in combination with an online rolling optimization mechanism. According to the method, the source-network coordination response speed, the control precision and the operation economy of the hydroelectric generating set are effectively improved, the power grid assessment risk is reduced, and the method is adaptive to a novel power system under high-proportion new energy permeation.

The invention relates to the technical field of energy, in particular to a photo-thermal power station multi-energy automatic power generation control system based on model predictive control, and the system comprises a system division module which divides a multi-energy system into a plurality of subsystems; the data acquisition module is used for acquiring a power generation state feature set corresponding to each subsystem; the state evaluation module is used for obtaining the power generation state score of each subsystem; the score correction module is used for setting influence factors and correcting each power generation state score to obtain a real score; the queue construction module is used for constructing a priority calling queue by taking the real score as a sorting basis; the comparison and adjustment module is used for obtaining the current power generation regulation and control demand index and comparing the current power generation regulation and control demand index with a preset threshold; the power generation state of each subsystem can be accurately grasped by performing data acquisition, evaluation, scoring and correction on the multi-energy system according to energy types, and high-pertinence and high-efficiency power generation regulation and control can be realized by combining a priority calling queue and regulation and control demand index comparison.