Comprehensive energy management system and method for new energy station

Abstract

The invention relates to the technical field of new energy stations, and discloses a comprehensive energy management system and method for a new energy station, and the system is characterized in that an energy management module, an automatic voltage control module, an automatic power control module and a wind power prediction module are all integrated on one device, thereby reducing the number of devices in a control center of the new energy station, and improving the efficiency. The method has the advantages that the cost and the occupied area are reduced, multifunctional fusion of control and scheduling operation of the new energy station is realized, the communication delay is reduced, and the control efficiency is improved; and the energy management module performs comprehensive calculation based on the obtained power grid dispatching instruction, the operation data of each unit and the active power prediction curve, distributes active power and reactive power of each new energy unit, controls the centralized energy storage device to perform charging and discharging operation, and realizes comprehensive management of the new energy station.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy stations, and in particular to a comprehensive energy management system and method for new energy stations. Background Art

[0002] With the dual carbon goals and the proposal of "building a new power system with new energy as the main body", the power system with a high proportion of new energy is rapidly developing from local to national. The weaknesses of new energy power generation in terms of voltage, frequency and damping for power grid support are also rapidly exposed. The safe and stable operation of large power grids faces huge challenges, and therefore higher requirements are put forward for the energy management system of new energy sites.

[0003] However, the energy management systems for new energy stations currently under development have the following problems: 1. Low control efficiency. The control architecture of existing wind power and photovoltaic stations is complex, the data transmission efficiency is low, the ability to control multiple types of objects is weak, and the active support function for the power grid is missing, which can no longer meet the current and future development needs of new energy stations; 2. Single function. The energy management system for existing new energy stations only has a monitoring function and single functionality, which cannot meet more complex control and operation requirements; 3. Unable to meet the trading needs of the electricity market. Currently, new energy stations generally do not have the ability to predict the power of new energy stations, and cannot meet the growing trading needs of the new energy electricity market. Summary of the invention

[0004] In view of this, the present invention provides a new energy station comprehensive energy management system and method to solve the problem that the traditional new energy station management system has a single function and cannot meet the development needs of the energy station.

[0005] In a first aspect, the present invention provides a comprehensive energy management system for a new energy station, the system comprising an energy management module, a wind power prediction module, an automatic power control module, and an automatic voltage control module, wherein the wind power prediction module is used to predict a first active power prediction curve corresponding to a new energy substation and a second active power prediction curve corresponding to each unit, the new energy substation comprising all units in the new energy station; the energy management module obtains a power grid dispatching instruction, and is used to determine the active power adjustment target amount of the new energy substation and / or the energy storage substation respectively based on the active power demand in the target time period in the power grid dispatching instruction, the actual active power of the current new energy station, and the predicted active power corresponding to the target time period in the first active power prediction curve, control the energy storage substation to adjust the active power output based on the corresponding active power adjustment target amount, and send the active power adjustment target amount of the new energy substation to the automatic power control module, the energy storage substation Represents an energy storage power station in a new energy station; the energy management module is used to determine the reactive power regulation amount based on the target line voltage demand in the power grid dispatching instruction and the actual voltage value obtained, and determine the reactive power regulation target amount of the new energy substation based on the reactive power regulation amount, or determine the reactive power regulation target amounts of the new energy substation and the energy storage substation respectively, control the energy storage substation to perform reactive power regulation based on the corresponding reactive power regulation target amount, and send the reactive power regulation target amount corresponding to the new energy substation to the automatic voltage control module; the automatic power control module is used to determine the active power distribution amount of each unit based on the second active power prediction curve corresponding to each unit and the active power regulation target amount of the new energy substation, and control each unit to adjust according to its corresponding active power distribution amount; the automatic voltage control module is used to determine the reactive power regulation distribution amount of each unit based on the reactive power regulation amount corresponding to the new energy substation, and control each unit to adjust according to its corresponding reactive power regulation distribution amount.

[0006] The comprehensive energy management system of the new energy station provided by the present invention integrates the energy management module, the automatic voltage control module, the automatic power control module and the wind power prediction module into one device, thereby reducing the number of equipment in the new energy station control center, reducing the cost and the floor space, realizing the multifunctional integration of the new energy station control and dispatching operation, reducing the communication delay, and improving the control efficiency. The wind power prediction module predicts the active power prediction curve of the new energy substation, and the energy management module performs comprehensive calculation based on the acquired power grid dispatching instructions, the operating data of each unit and the active power prediction curve, allocates the active and reactive power of each new energy unit, controls the centralized energy storage device to perform charging and discharging operations, and realizes the comprehensive management of the new energy station.

[0007] In an optional embodiment, the system also includes a primary frequency regulation module, wherein the primary frequency regulation module is used to obtain the frequency deviation of the new energy substation, and when the frequency deviation is greater than a preset frequency regulation frequency threshold, calculate the required frequency regulation capacity of the new energy substation, and control the discharge output power of the energy storage substation based on the required frequency regulation capacity to perform frequency regulation operations.

[0008] In an optional embodiment, the automatic voltage control module includes a reactive setting unit and a reactive distribution unit, wherein the reactive setting unit is used to determine the reactive adjustment distribution amount of each group based on the reactive adjustment amount corresponding to the new energy substation and the adjustable amount of each unit, and send it to the reactive distribution unit; the reactive distribution unit distributes the reactive adjustment distribution amount of each group to each unit and performs reactive adjustment operations.

[0009] In a second aspect, the present invention provides a method for comprehensive energy management of a new energy station, which is applied to the comprehensive energy management system of a new energy station in the first aspect or any corresponding embodiment thereof, the method comprising: predicting a first active power prediction curve corresponding to a new energy substation and a second active power prediction curve corresponding to each unit, the new energy substation comprising all units in the new energy station; obtaining a power grid dispatching instruction, and determining active power adjustment target amounts of the new energy substation and / or energy storage substation respectively based on the active power demand in the target time period in the power grid dispatching instruction, the actual active power of the current new energy station, and the predicted active power corresponding to the target time period in the first active power prediction curve, and controlling the energy storage substation to adjust the active power output based on the corresponding active power adjustment target amount. The energy storage substation represents an energy storage power station in a new energy station; based on the target line voltage demand in the power grid dispatching instruction and the actual voltage value obtained, the reactive power regulation amount is determined, and the reactive power regulation target amount of the new energy substation is determined based on the reactive power regulation amount, or the reactive power regulation target amounts of the new energy substation and the energy storage substation are determined respectively, and the energy storage substation is controlled to perform reactive power regulation based on the corresponding reactive power regulation target amount; based on the second active power prediction curve corresponding to each unit and the active power regulation target amount of the new energy substation, the active power distribution amount of each unit is determined, and each unit is controlled to adjust according to its corresponding active power distribution amount; based on the reactive power regulation amount corresponding to the new energy substation, the reactive power regulation distribution amount of each unit is determined respectively, and each unit is controlled to adjust according to its corresponding reactive power regulation distribution amount.

[0010] In an optional embodiment, when determining that the active power demand is an active load increase scenario, the active power demand includes at least an active power increment, and the active power regulation target amounts of the new energy substation and / or the energy storage substation are determined based on the active power demand of the target time period in the power grid dispatching instruction, the actual active power of the current new energy station, and the predicted active power corresponding to the target time period in the first active power prediction curve, including: calculating the predicted active power corresponding to the target time period in the first active power prediction curve and the adjustment margin value of the actual active power, and judging whether the adjustment margin value is less than the active power increment; if the adjustment margin value is not less than the active power increment, determining the active power regulation target amount of the new energy substation to be the active power increment; if the adjustment margin value is less than the active power increment, calculating the active power difference between the active power increment and the adjustment margin value, determining the active power regulation target amount of the new energy substation to be the adjustment margin value, and determining the active power regulation target amount of the energy storage substation to be the active power difference.

[0011] In an optional embodiment, when it is determined that the active power demand is an active load reduction scenario, the active power demand includes at least an active power reduction amount, and the active power adjustment target amount of the new energy substation and / or the energy storage substation is determined based on the active power demand for the target time period in the power grid dispatching instruction, the actual active power of the current new energy station, and the predicted active power corresponding to the target time period in the first active power prediction curve, including: subtracting the active power reduction amount from the current storage capacity of the energy storage substation to obtain an adjusted storage capacity, and judging whether the adjusted storage capacity Reach the lower limit of the active power regulation of the energy storage substation; if the adjusted storage amount does not reach the lower limit of the active power regulation of the energy storage substation, determine the active power regulation target amount of the energy storage substation as the active power reduction amount; if the adjusted storage amount reaches the lower limit of the active power regulation of the energy storage substation, determine the active power regulation target amount of the energy storage substation as the first regulation target amount, and determine the active power regulation target amount of the new energy substation as the difference between the active power reduction amount and the first regulation target amount, wherein the first regulation target amount is the difference between the current storage amount of the energy storage substation and the lower limit of the active power regulation of the energy storage substation.

[0012] In an optional embodiment, the reactive regulation amount is a voltage regulation amount, and determining the reactive regulation target amount of the new energy substation based on the reactive regulation amount, or determining the reactive regulation target amounts of the new energy substation and the energy storage substation respectively, includes: calculating the sum of the current voltage of the new energy substation and the voltage regulation amount to obtain the adjusted voltage amount, and judging whether the adjusted voltage amount is within the normal voltage range of the new energy substation; if the adjusted voltage amount is within the normal voltage range of the new energy substation, determining the reactive regulation target amount of the new energy substation to be the voltage regulation amount; if the adjusted voltage amount is not within the normal voltage range of the new energy substation, determining the reactive regulation target amount of the new energy substation to be the first voltage regulation amount, and determining the reactive regulation target amount of the energy storage substation to be the difference between the voltage regulation amount and the first voltage regulation amount, wherein the first voltage regulation amount is the difference between the normal voltage threshold of the new energy substation and the adjusted voltage amount.

[0013] In an optional embodiment, the first active power prediction curve corresponding to the new energy substation and the second active power prediction curve corresponding to each unit are predicted by the following steps: obtaining the meteorological parameters of the current environment of the new energy substation, inputting the meteorological parameters of the current environment into the power prediction models corresponding to each unit that have been trained, to obtain the predicted first active power corresponding to each unit in the new energy substation, wherein different types of units correspond to different power prediction models; based on the predicted first active power corresponding to each unit, the first active power corresponding to the new energy substation is determined; wherein the power prediction model corresponding to the current unit is trained by the following steps: using the training data of different environmental meteorological parameters and corresponding active power to train the preset neural network model corresponding to the current unit, and using the particle swarm optimization algorithm to optimize the preset neural network model to obtain the power prediction model corresponding to the current unit.

[0014] In an optional embodiment, the preset neural network model is a BP neural network model, and the optimization processing of the preset neural network model using a particle swarm optimization algorithm includes: iteratively executing a particle optimal solution determination operation until an iteration termination condition is met, and using the updated position corresponding to the optimal particle in all particle sets after the iteration termination as the initial weight of the BP neural network, and the particle optimal solution determination operation includes: encoding the weights of each layer of the BP neural network into particles, and initializing the initial positions of the particles; training the BP neural network model using current environmental meteorological parameters to obtain predicted active power, and calculating deviations from the active power corresponding to the current meteorological parameters, and calculating the fitness value of each particle based on the deviations; comparing the fitness value of each particle with the fitness value of the optimal particle in all particle sets, updating the particle speed and position, and updating the optimal particle in all particle sets.

[0015] In an optional embodiment, the second active power prediction curve is updated according to the meteorological parameters of the environment, and the active power allocation of each unit is determined based on the second active power prediction curve corresponding to each unit and the active power regulation target of the new energy substation, including: determining the adjustable power of each unit based on the predicted active power corresponding to the target time period in the second active power prediction curve corresponding to each unit and the current actual active power of each unit; screening out a set of units whose adjustable power is greater than the active power regulation target of the new energy substation, and sorting the units in the set of units according to the order of the adjustable power of each unit from large to small and the evaluation index of each unit; selecting the unit with the highest ranking as the target unit, determining the active power allocation of the target unit to be the active power regulation target, and the active power allocation of any other unit except the target unit to be zero. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a schematic diagram of the structure of a new energy station integrated energy management system according to an embodiment of the present invention;

[0018] Figure 2 is a structural example diagram of a new energy station according to an embodiment of the present invention;

[0019] Figure 3 is a flow chart of a comprehensive energy management method for a new energy station according to an embodiment of the present invention;

[0020] Figure 4 is a structural example diagram of a BP neural network according to an embodiment of the present invention;

[0021] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] my country's power system reform has achieved remarkable results. With the promotion of green power trading, more and more new energy power generation companies have participated in power market transactions. In particular, in the process of new energy projects participating in spot trading, short-term and ultra-short-term power forecasts are an important basis and foundation for spot trading. However, the mainstream new energy power forecasting system in the market is configured based on the technical regulations of the power grid for the access of new energy sites and photovoltaic power stations to the power grid. Power forecasting systems of different manufacturers are configured at each new energy site level. The accuracy is uneven and the management is relatively decentralized. At the same time, the power grid is extremely strict in assessing the power forecasting data uploaded by new energy sites and photovoltaic power stations. There are clear requirements and penalties for the accuracy and stability of short-term and ultra-short-term reports. The main problems of wind and solar power forecasting systems on the market are: (1) The accuracy rate does not meet the standard; (2) The information obtained by power trading is scattered, and manual adjustments are entirely based on experience; (3) The coupling between power forecasting and power trading is insufficient, and strong support cannot be provided.

[0024] At present, the main application scenario of new energy power prediction is in power planning and dispatching. With the advancement of power reform and the gradual establishment of power trading market, power prediction technology will also play an important role in power trading. For new energy power stations, the current "reporting quantity without guaranteeing price" method that mainly participates in spot trading will gradually transition to the "reporting quantity and quoting price" method in the future. For "reporting quantity without quoting price", new energy stations only need to report the power generation, not the electricity price. Therefore, the key factor lies in the accuracy of the power generation capacity prediction. If the accuracy rate does not meet the standard, it will face market deviation assessment. Regional power prediction is an important factor affecting the trading electricity price. Therefore, power trading requires power prediction system to provide important technical support.

[0025] In order to ensure the safe and stable operation of the power grid and to accommodate wind power on a large scale as much as possible, it is necessary to add a new energy power prediction system suitable for the spot mode to the new energy station to accurately predict the processing change trend of the new energy station. At the same time, primary frequency regulation, automatic generation control (Automatic Generation Control, AGC), and automatic voltage control (Automatic Voltage Control, AVC) are added to the new energy station to realize the multifunctional integrated control of the new energy station from power forecasting, power market transactions to active and reactive power regulation.

[0026] However, in traditional renewable energy power stations, devices such as AGC, AVC, Wind Power Prediction (WPP) and Energy Management System (EMS) are all configured independently. Too many intermediate devices and communication levels lead to higher equipment costs, lower control efficiency and worse reliability for the entire power station.

[0027] In this embodiment, a new energy station integrated energy management system is provided. Figure 1 As shown, the system includes an energy management module, a wind power prediction module, an automatic power control module and an automatic voltage control module, wherein the wind power prediction module is used to predict a first active power prediction curve corresponding to a new energy substation and a second active power prediction curve corresponding to each unit, and the new energy substation includes all units in the new energy site; the energy management module obtains a power grid dispatching instruction, and is used to determine the active power adjustment target amount of the new energy substation and / or the energy storage substation respectively based on the active power demand in the target time period in the power grid dispatching instruction, the actual active power of the current new energy site and the predicted active power corresponding to the target time period in the first active power prediction curve, and send the active power adjustment target amount of the new energy substation to the automatic power control module, and the energy storage substation represents the energy storage power station in the new energy site; the energy management module The block is used to determine the reactive power regulation amount based on the target line voltage demand in the power grid dispatching instruction and the actual voltage value obtained, and to determine the reactive power regulation target amount of the energy storage substation based on the reactive power regulation amount, or to determine the reactive power regulation target amounts of the energy storage substation and the new energy substation respectively, and send the reactive power regulation target amount corresponding to the new energy substation to the automatic voltage control module; the automatic power control module is used to determine the active power distribution amount of each unit based on the second active power prediction curve corresponding to each unit and the active power regulation target amount of the new energy substation, and control each unit to adjust according to its corresponding active power distribution amount; the automatic voltage control module is used to determine the reactive power regulation distribution amount of the reactive generator in each unit based on the reactive power regulation amount corresponding to the new energy substation, and control each reactive generator to adjust according to its corresponding reactive power regulation distribution amount.

[0028] like Figure 2As shown, an embodiment of the present invention designs a multifunctional integrated energy management system for new energy stations, which integrates independent functional modules originally deployed in various new energy stations, including an energy management module, an automatic power control module, an automatic voltage control module, and a wind power prediction module. The integrated energy management system can monitor and collect the operating data of all units and lines in the new energy substation through a supervisory control system (SCADA), and obtain the operating data of the energy storage substation, wherein the operating data of the energy storage substation may include but is not limited to the output active power, voltage value, etc. For example only, the new energy substation includes all units in the new energy station, not limited to wind turbines and photovoltaic units, and the energy storage substation represents a centralized energy storage device.

[0029] The wind power prediction module (Wind Power Prediction, WPP) of the embodiment of the present invention can predict the first active power prediction curve of the new energy substation within a specific time in the future and the second active power prediction curve corresponding to each unit based on the meteorological information sent by the new energy substation, including but not limited to wind speed, wind direction, temperature and air pressure. There is no limitation on the method of predicting active power. For example, the corresponding relationship between meteorological parameters and active power prediction can be established through a mathematical module, which is only taken as an example; Figure 2 As shown, the energy management module can receive the grid dispatching instruction through 104 communication, wherein the grid dispatching instruction may include but is not limited to the active power demand in the target time period, which may be the active power adjustment amount or the active power demand amount, such as the need to increase the active power output by 10 watts, or the target active power demand is to output 100 watts, just as an example, and then the energy management module can obtain the predicted active power corresponding to the target time period based on the first active power prediction curve, and then determine the active power adjustment target amount of the new energy substation and / or the energy storage substation respectively with the actual active power and active power demand of the current new energy site, wherein, the determination There is no limitation on the method of adjusting the active power. Active power adjustment can be given priority to new energy substations. If it is detected that the adjustable active power of the new energy substation can cover the active power demand, only the active power adjustment target amount of the new energy substation is allocated as the active power demand, and the energy storage substation does not need to be allocated. If it is detected that the adjustable active power of the new energy substation cannot cover the active power demand, the remaining unregulated active power can be calculated and determined as the active power adjustment target amount of the energy storage substation. The active power adjustment target amount of the new energy substation is its adjustable active power. Active power adjustment can also be given priority to the energy storage substation. This is just an example.

[0030] After respectively determining the active power adjustment target amounts of the new energy substation and the energy storage substation, the energy management module of the embodiment of the present invention can control the energy storage substation to adjust the active power output based on the corresponding active power adjustment target amount, and can send the active power adjustment target amount of the new energy substation to the automatic power control module AGC. The AGC can determine the predicted active power of each unit in the target time period based on the second active power prediction curve corresponding to each unit, and can queue them in descending order of the predicted active power, and allocate the active power adjustment target amounts of the new energy substations to the corresponding units in sequence according to the queuing order, and send the unit control instructions to the units for execution, as an example only.

[0031] The grid dispatching instruction of the embodiment of the present invention also includes a target line voltage demand. The energy management module can receive the actual line voltage value sent by the electrical measuring device, and then calculate the deviation between the target line voltage demand and the actual line voltage value, and then multiply it with the preset voltage adjustment coefficient to determine the reactive power regulation amount, and then determine the reactive power regulation target amounts of the energy storage substation and the new energy substation respectively, wherein the reactive power regulation can be undertaken by the new energy substation first, and determine whether the reactive power regulation margin of the new energy substation meets the reactive power regulation amount. If the reactive power regulation amount is not met, the remaining reactive power regulation amount can be calculated, and the energy storage substation can be controlled to generate reactive power through the reactive generator or the reactive power generator. The reactive power compensator performs power compensation; determines the reactive power regulation target amount of the new energy substation as its reactive power regulation margin, and sends the reactive power regulation target amount of the new energy substation to the automatic voltage control module. The automatic voltage control module can determine the reactive power regulation allocation amount of each unit based on the reactive power regulation amount of the new energy substation, and control each unit to adjust according to its corresponding reactive power regulation allocation amount. Among them, the unit is generally a wind turbine unit for reactive power regulation, that is, after the energy management module completes the power distribution between substations, the automatic power control module performs active power distribution between units, and the automatic voltage control module performs reactive power distribution between units, just as an example.

[0032] The comprehensive energy management system of the new energy station provided by the present invention integrates the energy management module, the automatic voltage control module, the automatic power control module and the wind power prediction module into one device, thereby reducing the number of equipment in the new energy station control center, reducing the cost and the floor space, realizing the multifunctional integration of the new energy station control and dispatching operation, reducing the communication delay, and improving the control efficiency. The wind power prediction module predicts the active power prediction curve of the new energy substation, and the energy management module performs comprehensive calculation based on the acquired power grid dispatching instructions, the operating data of each unit and the active power prediction curve, allocates the active and reactive power of each new energy unit, controls the centralized energy storage device to perform charging and discharging operations, and realizes the comprehensive management of the new energy station.

[0033] In an optional embodiment, the system also includes a primary frequency regulation module, wherein the primary frequency regulation module is used to obtain the frequency deviation of the new energy substation, and when the frequency deviation is greater than a preset frequency regulation frequency threshold, calculate the required frequency regulation capacity of the new energy substation, and control the discharge output power of the energy storage substation based on the required frequency regulation capacity to perform frequency regulation operations.

[0034] like Figure 2 As shown, the integrated energy management system of the new energy station also integrates a primary frequency regulation module to control the energy storage substation to fully undertake the frequency regulation task of the new energy substation. The primary frequency regulation module can obtain the frequency deviation of the new energy substation and compare the frequency deviation with the preset frequency regulation threshold. When the frequency deviation is greater than the preset frequency regulation threshold, the required frequency regulation capacity of the new energy substation can be calculated, and the discharge output power of the energy storage substation can be controlled based on the required frequency regulation capacity of the new energy substation to complete the frequency regulation task, thereby improving the AGC control effect of the power station.

[0035] Specifically, the automatic voltage control module includes a reactive setting unit and a reactive distribution unit, wherein the reactive setting unit is used to determine the reactive regulation distribution amount of each group based on the reactive regulation amount corresponding to the new energy substation and the adjustable amount of each unit, and send it to the reactive distribution unit; the reactive distribution unit distributes the reactive regulation distribution amount of each group to each unit and performs reactive regulation operations.

[0036] The automatic voltage control module AVC of the embodiment of the present invention divides the reactive power control strategy into two layers, namely, the reactive setting unit and the reactive distribution unit. The reactive setting unit executes the reactive comprehensive optimization algorithm, and sends the reactive set value corresponding to each unit to the reactive distribution layer, wherein the reactive comprehensive optimization algorithm is not limited, and it can be a method proportional to capacity, an average distribution method, or a method proportional to the actual active power generated by the unit, etc. With the method proportional to capacity, the reactive adjustment component of each unit can be determined based on the reactive adjustment amount corresponding to the new energy substation and the adjustable amount of each unit. Just as an example, the reactive distribution unit distributes the reactive reference set value of the wind farm constrained by reactive power limitation to each wind turbine and wind farm reactive compensation device such as SVC, wherein SVC is a typical grid-connected compensation device in a flexible AC transmission system, and its basic function is to absorb or transmit continuously adjustable reactive power from the power grid to the power grid to maintain the voltage constant at the installation point.

[0037] According to an embodiment of the present invention, an embodiment of a comprehensive energy management method for a new energy station is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] In this embodiment, a new energy station integrated energy management method is provided, which is applied to the above-mentioned new energy station integrated energy management system. Figure 3 is a flow chart of a comprehensive energy management method for a new energy station according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0039] Step 301: predict the first active power prediction curve corresponding to the new energy substation and the second active power prediction curve corresponding to each unit. Please refer to the above embodiment for details, which will not be repeated here.

[0040] Among them, the new energy substation includes all units in the new energy station.

[0041] Specifically, the first active power prediction curve corresponding to the new energy substation and the second active power prediction curve corresponding to each unit are predicted through the following steps: obtaining the meteorological parameters of the current environment of the new energy substation, inputting the meteorological parameters of the current environment into the power prediction models corresponding to each unit that have been trained, and obtaining the predicted first active power corresponding to each unit in the new energy substation, wherein different types of units correspond to different power prediction models; based on the predicted first active power corresponding to each unit, determining the first active power corresponding to the new energy substation; wherein the power prediction model corresponding to the current unit is trained through the following steps: using the training data of different environmental meteorological parameters and corresponding active power to train the preset neural network model corresponding to the current unit, and using the particle swarm optimization algorithm to optimize the preset neural network model to obtain the power prediction model corresponding to the current unit.

[0042] The embodiment of the present invention takes into account the uncertainty of wind speed. The power of the new energy station has a strong randomness, and it is difficult to find an accurate mathematical model to describe it. However, the artificial neural network has a strong self-learning ability. By learning from historical data, it can find the rules contained therein very well. Meteorological parameters such as wind speed, wind direction, temperature and air pressure and power curves are used as the basis. Different power prediction models are used for different types of new energy units. For example, wind turbines are divided into two types: direct drive and double-fed. The corresponding power prediction models are definitely different. The same type of unit can basically use one model and a set of model parameters. Among them, the power prediction model can be put into operation synchronously with the new energy unit. In actual application, the meteorological parameters of the current environment of the new energy substation are obtained, and the meteorological parameters of the current environment are input into the power prediction models corresponding to each trained unit, respectively, to obtain the second active power prediction curve corresponding to each unit in the new energy substation, and then the second active power prediction curves corresponding to all units can be integrated to obtain the first active power curve corresponding to the new energy substation.

[0043] The power prediction model corresponding to the current unit of the embodiment of the present invention can use the training data of different environmental meteorological parameters and corresponding active power to train the preset neural network model, and can also use the particle swarm optimization algorithm to optimize the parameters such as the weights of the neural network model to obtain the optimal trained power prediction model.

[0044] Furthermore, the preset neural network model is a BP neural network model, and the preset neural network model is optimized using a particle swarm optimization algorithm, including: iteratively executing a particle optimal solution determination operation until an iteration termination condition is met, and using the updated position corresponding to the optimal particle in all particle sets after the iteration termination as the initial weight of the BP neural network. The particle optimal solution determination operation includes: encoding the weights of each layer of the BP neural network into particles, and initializing the initial position of the particles; training the BP neural network model using current environmental meteorological parameters to obtain predicted active power, and calculating the deviation from the active power corresponding to the current meteorological parameters, and calculating the fitness value of each particle based on the deviation; comparing the fitness value of each particle with the fitness value of the optimal particle in all particle sets, updating the particle speed and position, and updating the optimal particle in all particle sets.

[0045] The preset neural network model of the embodiment of the present invention is a BP neural network model (a multi-layer feedforward network trained by an error back propagation algorithm), such as Figure 4 As shown in the figure, taking the four meteorological parameters of wind speed, wind direction, temperature and air pressure as the input of the BP neural network, active power as the output of the BP neural network, and the hidden layer as 5 neurons as an example, the output of the hidden layer node is:

[0046]

[0047] The output layer node output is:

[0048]

[0049] The standard algorithm uses the mean square error function as the error function expression, where is the expected output of output node j, and p is the number of input samples.

[0050]

[0051] The output layer error variables and hidden layer error variables are defined as:

[0052]

[0053] The weight corrections of the output layer and hidden layer determined by the error variable are:

[0054]

[0055] The threshold correction amounts of the output layer and hidden layer determined by the error variable are:

[0056]

[0057] Therefore, the adjustment amount of each layer weight and threshold is determined by the above formula to obtain the adjustment formula of the BP network model:

[0058]

[0059] The embodiment of the present invention uses an improved example algorithm to optimize the BP neural network for prediction. First, the traditional particle swarm optimization algorithm (Particle swarm optimization, PSO) is an evolutionary computing technology. The algorithm is inspired by the regularity of bird flocking activities and then uses a simplified model established by swarm intelligence. Its mathematical expression is:

[0060]

[0061] In the formula and are the update speeds of particles at time k+1 and k respectively; ω is the particle inertia weight; c1 and c2 are the particle individual and global learning factors respectively; r1 and r2 are both random numbers in the range of [0, 1]; is the local optimal particle; is the global optimal particle; are the positions of particles at time k+1 and time k respectively.

[0062] In order to improve the global search ability, a dynamic learning factor is used. As the number of algorithm iterations increases, c1 gradually decreases, reducing the learning ability of individual particles, and c2 gradually increases, strengthening the global cognitive ability of particles. The specific implementation is as follows:

[0063]

[0064] Compared with the traditional BP neural network, which has the disadvantages of slow convergence, easy to fall into local minimum, and sensitive to the selection of initial weights and thresholds, the improved particle swarm optimization algorithm is used to optimize the connection weights of the BP neural network, and the weights of the neural network are encoded into particles. This method ensures the efficiency and accuracy of short-term new energy power forecasting. The use of the improved particle swarm optimization (IPSO) algorithm to optimize the BP neural network is to encode the weights of each layer of the neural network into particles. The optimization process is as follows:

[0065] 1. Clarify the structure of the BP neural network, including the number of nodes in the input layer, hidden layer, and output layer, and calculate the total number of weights.

[0066] 2. Encode particles and concatenate all values ​​into an array according to formula 13, where W ih1 Represents the weight from the input layer to the hidden layer, V ho1 Represents the weights from the hidden layer to the output layer.

[0067] p best =[W ih1 ,W ih2 ,…,W ih(n×m) ,V ho1 ,V ho2 ,…,V ho(m×p) ](13)

[0068] 3. Initialize particles. In the initialization stage of the IPSO algorithm, the initial position of the particles, i.e., the BP network weights, can be randomly generated.

[0069] 4. Calculate the fitness. For each particle in the particle swarm, calculate its fitness value according to formula 3 based on the weight and deviation.

[0070] 5. Update the speed and position of the particle according to its own optimal solution and the optimal solution in the group (that is, the fitness of the optimal particle in the set of all particles), as well as some weight coefficients.

[0071] Specifically, the new speed and position are calculated using Equation 14 and Equation 15.

[0072]

[0073] 6. Update the global optimal solution (i.e. the best particle in the set of all particles) and the individual optimal solution. After each iteration, update the global optimal solution and the individual optimal solution according to the fitness value. If the fitness of a particle exceeds the fitness of the global optimal solution, it will be used as the new global optimal solution; if the fitness of a particle exceeds the fitness of its individual optimal solution, it will be used as the new individual optimal solution.

[0074] 7. Repeat the iteration, and repeat step 4 and step 5 until the condition for stopping the iteration is reached. The condition for stopping the iteration can be set according to the actual situation (such as reaching the maximum number of iterations, the fitness value reaching a preset threshold, or the fitness value tending to be stable).

[0075] 8. Output the optimal result, use the optimal result as the value of the initial weight of the BP neural network model, and start training the BP neural network.

[0076] The present invention optimizes the preset neural network through the particle swarm optimization algorithm to obtain the optimal power prediction model, thereby ensuring the high efficiency and accuracy of short-term new energy power prediction.

[0077] Step S302, obtain the grid dispatch instruction, determine the active power adjustment target amount of the new energy substation and / or the energy storage substation respectively based on the active power demand in the target time period in the grid dispatch instruction, the actual active power of the current new energy station and the predicted active power corresponding to the target time period in the first active power prediction curve, and control the energy storage substation to adjust the active power output based on the corresponding active power adjustment target amount. Please refer to the above embodiment for details, which will not be repeated here.

[0078] Among them, the energy storage substation refers to the energy storage power station in the new energy station.

[0079] Specifically, when determining that the active power demand is an active load increase scenario, the active power demand includes at least an active power increment, and the adjustment margin value of the predicted active power and the actual active power corresponding to the target time period in the first active power prediction curve is calculated, and it is determined whether the adjustment margin value is less than the active power increment; if the adjustment margin value is not less than the active power increment, the active power adjustment target amount of the new energy substation is determined to be the active power increment; if the adjustment margin value is less than the active power increment, the active power difference between the active power increment and the adjustment margin value is calculated, and the active power adjustment target amount of the new energy substation is determined to be the adjustment margin value, and the active power adjustment target amount of the energy storage substation is determined to be the active power difference.

[0080] When the energy management module of the embodiment of the present invention receives the grid dispatching instruction and determines that the active power demand in the grid dispatching instruction at least includes the active power increment, it is determined that the current is an active load increase scenario, and the total active power given by the new energy substation can be increased preferentially, and the adjustment margin value of the predicted active power and the actual active power corresponding to the target time period in the first active power prediction curve is calculated, and it is determined whether the adjustment margin value can cover the active power increment. When the adjustment margin value can cover the active power increment (that is, the adjustment margin value is not less than the active power increment), the adjustment margin value is increased. The target amount of active power regulation of the new energy substation is determined to be the active power increment, that is, it is only increased by the new energy substation; when the increase margin value cannot cover the active power increment (that is, the increase margin value is less than the active power increment), the energy storage substation is controlled to output electric energy to compensate the active power, and the active power difference between the active power increment and the increase margin value is calculated. Then, the active power regulation target amount of the new energy substation can be determined to be the increase margin value, and the active power regulation target amount of the energy storage substation can be determined to be the active power difference. This is just an example.

[0081] In the active load increase scenario, the present invention gives priority to increasing the total active power of the new energy substation. When the active power increase margin of the new energy substation cannot cover the active power increment, the energy storage substation is controlled to output electric energy to compensate for the active power, thereby ensuring accurate and effective scheduling of the new energy station.

[0082] In an optional implementation, when it is determined that the active power demand is an active load reduction scenario, the active power demand includes at least an active power reduction amount, the current storage amount of the energy storage substation is subtracted from the active power reduction amount to obtain an adjusted storage amount, and it is determined whether the adjusted storage amount reaches the lower limit of the active power regulation of the energy storage substation; if the adjusted storage amount does not reach the lower limit of the active power regulation of the energy storage substation, the active power regulation target amount of the energy storage substation is determined to be the active power reduction amount; if the adjusted storage amount reaches the lower limit of the active power regulation of the energy storage substation, the active power regulation target amount of the energy storage substation is determined to be a first regulation target amount, and the active power regulation target amount of the new energy substation is determined to be the difference between the active power reduction amount and the first regulation target amount, and the first regulation target amount is the difference between the current storage amount of the energy storage substation and the lower limit of the active power regulation of the energy storage substation.

[0083] When the energy management module of the embodiment of the present invention receives a power grid dispatching instruction and determines that the active power demand in the power grid dispatching instruction at least includes an active power reduction, it is determined to be an active load reduction scenario, and the active power output of the energy storage substation can be preferentially reduced. The current storage amount of the energy storage substation is first subtracted from the active power reduction amount to obtain the adjusted storage amount, and it is determined whether the adjusted storage amount reaches the lower limit of the active power regulation of the energy storage substation (to ensure the normal operation of the energy storage substation). If the adjusted storage amount does not reach the lower limit of the active power regulation of the energy storage substation, it can be determined that only the energy storage substation performs the charging operation to complete the active power reduction task; if the adjusted storage amount reaches the lower limit of the active power regulation of the energy storage substation, it can be determined that the active power regulation target amount of the energy storage substation is the first regulation target amount, and the difference between the active power reduction amount and the first regulation target amount is calculated as the active power regulation target amount of the new energy substation.

[0084] Step S303, based on the target line voltage demand in the grid dispatching instruction and the actual voltage value obtained, determine the reactive adjustment amount, and determine the reactive adjustment target amount of the new energy substation based on the reactive adjustment amount, or determine the reactive adjustment target amounts of the new energy substation and the energy storage substation respectively, and control the energy storage substation to perform reactive adjustment based on the corresponding reactive adjustment target amount. Please refer to the above embodiment for details, which will not be repeated here.

[0085] Step S304: Based on the second active power prediction curves corresponding to each unit and the active power adjustment target of the new energy substation, determine the active power allocation of each unit, and control each unit to adjust according to its corresponding active power allocation. Please refer to the above embodiment for details, which will not be repeated here.

[0086] Specifically, the second active power prediction curve is updated according to the meteorological parameters of the environment, and the adjustable power of each unit is determined based on the predicted active power corresponding to the target time period in the second active power prediction curve corresponding to each unit and the current actual active power of each unit; a set of units whose adjustable power is greater than the active power adjustment target of the new energy substation is screened out, and the units in the set are sorted in descending order of the adjustable power of each unit and the evaluation index of each unit; the unit with the highest ranking is selected as the target unit, and the active power allocation of the target unit is determined to be the active power adjustment target, and the active power allocation of any unit other than the target unit is zero.

[0087] The second active power prediction curve of the embodiment of the present invention is affected by the current meteorological parameters such as wind speed, wind direction, temperature and air pressure, so it changes in real time according to the changes in the meteorological parameters of the environment. The automatic power control module AGC can determine the adjustable power of each unit based on the predicted active power corresponding to the target time period in the second active power prediction curve corresponding to each unit and the current actual active power of each unit. The set of units whose adjustable power is greater than the active power adjustment target amount of the new energy substation can be pre-screened, that is, when the adjustable power in the target time period is less than the active power adjustment target amount of the new energy substation, the unit does not participate in the active power distribution, and the active power distribution is performed only when the adjustable power is greater than the active power adjustment target amount; Then, based on the planned queuing method of power generation prediction provided by the wind power prediction module, all units in the unit set can be sorted in the order of the adjustable power of each unit from large to small and comprehensive indicators such as the unit's cumulative power limit, technical level and assessment status, and then the unit with the highest ranking is selected as the target unit according to the sorting result, and the active power allocation of the target unit is determined to be the active power adjustment target amount, and the active power allocation of any unit except the target unit is zero. Among them, because the predicted active power of the unit is affected by various meteorological parameters, the predicted active power of the unit may change in real time, and then the ranking of the unit is also changing, so the units can be sorted in real time and power allocation can be carried out in turn to ensure the accuracy and flexibility of active power adjustment.

[0088] The present invention sorts the units according to factors such as the adjustable power and comprehensive indicators, and then preferentially allocates active power based on the sorting results to enhance system stability. Reasonable power allocation helps to maintain the stability of system frequency and power, thereby enhancing the stability of the entire new energy station.

[0089] Step S305: based on the reactive power regulation amount corresponding to the new energy substation, determine the reactive power regulation allocation amount of each unit, and control each unit to adjust according to its corresponding reactive power regulation allocation amount. Please refer to the above embodiment for details, which will not be repeated here.

[0090] The present invention provides a comprehensive energy management method for a new energy station, in which an energy management module, an automatic voltage control module, an automatic power control module and a wind power prediction module are all integrated into one device, thereby reducing the number of equipment in the new energy station control center, reducing both the cost and the floor area, with the floor area reduced by 30% and the cost reduced by 40%, realizing the multifunctional integration of the control and dispatching operation of the new energy station, reducing communication delay, improving control efficiency, and increasing the annual power generation of the new energy station by more than 2%, bringing significant economic benefits. The wind power prediction module predicts the active power prediction curve of the new energy substation, and the energy management module performs comprehensive calculation based on the acquired power grid dispatching instructions, the operating data of each unit and the active power prediction curve, allocates the active and reactive power of each new energy unit, controls the centralized energy storage device to perform charging and discharging operations, and realizes the comprehensive management of the new energy station.

[0091] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0092] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0093] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0094] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0095] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0096] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0097] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0098] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0099] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A new energy station integrated energy management system, characterized in that: The system includes an energy management module, a wind power prediction module, an automatic power control module, and an automatic voltage control module, wherein: The wind power prediction module is used to predict the first active power prediction curve corresponding to the new energy substation and the second active power prediction curve corresponding to each unit, wherein the new energy substation includes all units in the new energy station; The energy management module obtains a power grid dispatching instruction, and is used to determine the active power adjustment target amount of the new energy substation and / or the energy storage substation respectively based on the active power demand of the target time period in the power grid dispatching instruction, the actual active power of the current new energy site and the predicted active power corresponding to the target time period in the first active power prediction curve, control the energy storage substation to adjust the active power output based on the corresponding active power adjustment target amount, and send the active power adjustment target amount of the new energy substation to the automatic power control module, wherein the energy storage substation represents the energy storage power station in the new energy site; The energy management module is used to determine the reactive power regulation amount based on the target line voltage demand in the power grid dispatching instruction and the actual voltage value obtained, and determine the reactive power regulation target amount of the new energy substation based on the reactive power regulation amount, or determine the reactive power regulation target amounts of the new energy substation and the energy storage substation respectively, control the energy storage substation to perform reactive power regulation based on the corresponding reactive power regulation target amount, and send the reactive power regulation target amount corresponding to the new energy substation to the automatic voltage control module; The automatic power control module is used to determine the active power allocation of each unit based on the second active power prediction curve corresponding to each unit and the active power adjustment target amount of the new energy substation, and control each unit to adjust according to its corresponding active power allocation; The automatic voltage control module is used to determine the reactive power regulation allocation of each unit based on the reactive power regulation amount corresponding to the new energy substation, and control each unit to adjust according to its corresponding reactive power regulation allocation amount.

2. The system according to claim 1, characterized in that The system also includes a primary frequency modulation module, wherein: The primary frequency regulation module is used to obtain the frequency deviation of the new energy substation, and when the frequency deviation is greater than the preset frequency regulation frequency threshold, calculate the required frequency regulation capacity of the new energy substation, and control the discharge output power of the energy storage substation to perform frequency regulation based on the required frequency regulation capacity.

3. The system according to claim 1, characterized in that The automatic voltage control module includes a reactive power setting unit and a reactive power distribution unit, wherein: The reactive power setting unit is used to determine the reactive power adjustment allocation of each unit based on the reactive power adjustment amount corresponding to the new energy substation and the adjustable amount of each unit, and send it to the reactive power allocation unit; The reactive power distribution unit distributes the reactive power regulation distribution amount of each unit to each unit and performs reactive power regulation operation.

4. A comprehensive energy management method for a new energy station, characterized in that: Applied to the new energy station integrated energy management system according to any one of claims 1 to 3, the method comprising: Predicting a first active power prediction curve corresponding to a new energy substation and a second active power prediction curve corresponding to each unit, wherein the new energy substation includes all units in the new energy station; Obtaining a power grid dispatching instruction, determining active power adjustment target amounts of the new energy substation and / or the energy storage substation respectively based on the active power demand in the target time period in the power grid dispatching instruction, the actual active power of the current new energy site, and the predicted active power corresponding to the target time period in the first active power prediction curve, and controlling the energy storage substation to adjust the active power output based on the corresponding active power adjustment target amount, wherein the energy storage substation represents an energy storage power station in the new energy site; Based on the target line voltage demand in the grid dispatching instruction and the actual voltage value obtained, determine the reactive power regulation amount, and determine the reactive power regulation target amount of the new energy substation based on the reactive power regulation amount, or determine the reactive power regulation target amounts of the new energy substation and the energy storage substation respectively, and control the energy storage substation to perform reactive power regulation based on the corresponding reactive power regulation target amount; Based on the second active power prediction curves corresponding to each unit and the active power adjustment target amount of the new energy substation, the active power allocation amount of each unit is determined, and each unit is controlled to adjust according to its corresponding active power allocation amount; Based on the reactive power regulation amount corresponding to the new energy substation, the reactive power regulation allocation amount of each unit is determined, and each unit is controlled to adjust according to its corresponding reactive power regulation allocation amount.

5. The method according to claim 4, characterized in that When it is determined that the active power demand is an active load increase scenario, the active power demand includes at least an active power increment, and the active power demand for the target time period in the power grid dispatching instruction, the actual active power of the current new energy station, and the predicted active power corresponding to the target time period in the first active power prediction curve are determined to adjust the active power target amounts of the new energy substation and / or the energy storage substation respectively, including: Calculating the increase margin value of the predicted active power corresponding to the target time period in the first active power prediction curve and the actual active power, and determining whether the increase margin value is less than the active power increment; If the increase margin value is not less than the active power increment, determining the active power adjustment target amount of the new energy substation to be the active power increment; If the adjustment margin value is less than the active power increment, the active power difference between the active power increment and the adjustment margin value is calculated, the active power adjustment target of the new energy substation is determined to be the adjustment margin value, and the active power adjustment target of the energy storage substation is determined to be the active power difference.

6. The method according to claim 4, characterized in that When it is determined that the active power demand is an active load reduction scenario, the active power demand includes at least an active power reduction amount, and the active power demand for the target time period in the power grid dispatching instruction, the actual active power of the current new energy station, and the predicted active power corresponding to the target time period in the first active power prediction curve are determined to determine the active power adjustment target amounts of the new energy substation and / or the energy storage substation, respectively, including: Subtract the active power reduction amount from the current storage amount of the energy storage substation to obtain the adjusted storage amount, and determine whether the adjusted storage amount reaches the lower limit of the active power regulation of the energy storage substation; If the adjusted storage energy does not reach the lower limit of the active power regulation of the energy storage substation, the active power regulation target amount of the energy storage substation is determined to be the active power reduction amount; If the adjusted energy storage amount reaches the lower limit of the active power regulation of the energy storage substation, the active power regulation target amount of the energy storage substation is determined to be the first regulation target amount, and the active power regulation target amount of the new energy substation is determined to be the difference between the active power reduction amount and the first regulation target amount, and the first regulation target amount is the difference between the current energy storage amount of the energy storage substation and the lower limit of the active power regulation of the energy storage substation.

7. The method according to claim 4, characterized in that The reactive adjustment amount is a voltage adjustment amount, and determining the reactive adjustment target amount of the new energy substation based on the reactive adjustment amount, or determining the reactive adjustment target amounts of the new energy substation and the energy storage substation respectively, includes: Calculate the sum of the current voltage of the new energy substation and the voltage regulation amount to obtain the adjusted voltage amount, and determine whether the adjusted voltage amount is within the normal voltage range of the new energy substation; If the adjusted voltage is within the normal voltage range of the new energy substation, determining the reactive power regulation target of the new energy substation as the voltage regulation amount; If the adjusted voltage is not within the normal voltage range of the new energy substation, the reactive power regulation target of the new energy substation is determined to be the first voltage regulation amount, and the reactive power regulation target of the energy storage substation is determined to be the difference between the voltage regulation amount and the first voltage regulation amount, wherein the first voltage regulation amount is the difference between the normal voltage threshold of the new energy substation and the adjusted voltage.

8. The method according to claim 4, characterized in that The first active power prediction curve corresponding to the new energy substation and the second active power prediction curve corresponding to each unit are predicted through the following steps: Obtain the meteorological parameters of the current environment of the new energy substation, input the meteorological parameters of the current environment into the power prediction models corresponding to the trained units, and obtain the predicted first active power corresponding to the units in the new energy substation, wherein different types of units correspond to different power prediction models; Determine the first active power corresponding to the new energy substation based on the predicted first active power corresponding to each of the units; Among them, the power prediction model corresponding to the current unit is trained through the following steps: The preset neural network model corresponding to the current unit is trained using the training data of different environmental meteorological parameters and the corresponding active power, and the preset neural network model is optimized using the particle swarm optimization algorithm to obtain the power prediction model corresponding to the current unit.

9. The method according to claim 8, characterized in that The preset neural network model is a BP neural network model, and the optimization process of the preset neural network model by using a particle swarm optimization algorithm includes: The particle optimal solution determination operation is iteratively performed until the iteration termination condition is met, and the updated position corresponding to the optimal particle in all particle sets after the iteration termination is used as the initial weight of the BP neural network. The particle optimal solution determination operation includes: Encoding the weights of each layer of the BP neural network into particles, and initializing the initial positions of the particles; The BP neural network model is trained using the current environmental meteorological parameters to obtain the predicted active power, and the deviation is calculated from the active power corresponding to the current meteorological parameters, and the fitness value of each particle is calculated based on the deviation; The fitness value of each particle is compared with the fitness value of the best particle in the set of all particles, the particle speed and position are updated, and the best particle in the set of all particles is updated.

10. The method according to claim 4, characterized in that The second active power prediction curve is updated according to the meteorological parameters of the environment, and the active power allocation amount of each unit is determined based on the second active power prediction curve corresponding to each unit and the active power adjustment target amount of the new energy substation, including: Determine the adjustable power of each unit based on the predicted active power corresponding to the target time period in the second active power prediction curve corresponding to each unit and the current actual active power of each unit; Filter out the set of units whose adjustable power is greater than the active power adjustment target of the new energy substation, Sorting the units in the set of units according to the order of the adjustable power of each unit from large to small and the evaluation index of each unit; The unit with the highest ranking is selected as the target unit, the active power distribution amount of the target unit is determined to be the active power regulation target amount, and the active power distribution amount of any unit other than the target unit is zero.

Images