Method, device and equipment for predicting increment of generating capacity, storage medium and product

Abstract

The invention relates to the technical field of electric energy storage, in particular to a prediction method, device and equipment for generating capacity increment, a storage medium and a product. The method comprises the steps of predicting a wind power generation increment of a wind power station after a future time period based on wind power generation parameter information, predicting a photovoltaic power generation increment of a photovoltaic power station based on photovoltaic power generation parameter information, and predicting a load increment of a virtual power station based on load parameter information, predicting charge and discharge increments of charge and discharge of the clustered resources based on the charge and discharge parameter information; and on the basis of a random partial differential equation, according to the wind power generation increment, the photovoltaic power generation increment, the load increment, the charging and discharging increment, the wind power generation parameter information, the photovoltaic power generation parameter information, the load parameter information and the charging and discharging parameter information, predicting the power generation increment of the virtual power plant to obtain the total power generation increment of the virtual power plant. According to the invention, the problems of poor real-time performance and poor accuracy of prediction of the power generation increment of the virtual power plant can be solved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of electric energy storage, and particularly relates to a method and device for predicting power generation increment, equipment, storage medium and product. BACKGROUND

[0002] A virtual power plant integrates various distributed energy resources, adjustable loads and energy storage systems, and the like distributed energy resources to participate in spot trading in the form of bidding every day. For example, the virtual power plant trades in the market with a trading frequency of 15 minutes / once and runs uninterruptedly by day. Therefore, the virtual power plant can improve its trading decision by predicting the spot trading (power generation increment), so as to obtain greater benefits.

[0003] In the related art, big data analysis and artificial intelligence and the like information technology are usually used to predict the power generation increment on a daily basis, so that the real-time performance of the power generation increment prediction is poor, and it is difficult to meet the requirements of spot trading with a trading frequency of 15 minutes / once. Moreover, since each energy resource in the virtual power plant has randomness, the prediction of the power generation increment of the virtual power plant is also inaccurate. SUMMARY

[0004] In order to solve the above technical problems, the present disclosure provides a method and device for predicting power generation increment, equipment, storage medium and product to solve the problems of poor real-time performance and poor accuracy of the prediction of the power generation increment of the virtual power plant.

[0005] In a first aspect, the present disclosure provides a method for predicting power generation increment, the method comprising: obtaining wind power generation parameter information of each wind power generator in a plurality of wind power generators of each wind power station corresponding to a virtual power plant, photovoltaic power generation parameter information of each photovoltaic cell in a plurality of photovoltaic cells of each photovoltaic power station, load parameter information of a power distribution network, and charge-discharge parameter information of a clonable resource charge-discharge; predicting wind power generation increment of the wind power station after a future time period based on the wind power generation parameter information, predicting photovoltaic power generation increment of the photovoltaic power station after the future time period based on the photovoltaic power generation parameter information, predicting load increment of the virtual power plant after the future time period based on the load parameter information, and predicting charge-discharge increment of the clonable resource charge-discharge after the future time period based on the charge-discharge parameter information; based on a stochastic partial differential equation, predicting power generation increment of the virtual power plant according to the wind power generation increment, the photovoltaic power generation increment, the load increment and the charge-discharge increment, the wind power generation parameter information, the photovoltaic power generation parameter information, the load parameter information and the charge-discharge parameter information, to obtain total power generation increment of the virtual power plant.

[0006] Based on the above method, the random partial differential equation can be constructed based on the wind power increment, the photovoltaic power increment, the load increment and the charge-discharge increment of the virtual power plant. Since the random correction quantity is defined as the product of the mean value of the power generation of the virtual power plant clusterable resources and the mean value of the number of participants, the superimposed influence of the two types of core random factors on the system can be comprehensively reflected. The introduction of the mean value avoids the interference of extreme values of single random sampling, and improves the accuracy of the correction term. The first-order differential can essentially represent the instantaneous change rate of the variable with time or space. By taking the first-order differential of the wind power, the photovoltaic power, the supercapacitor energy storage and other types of resources and the conventional load, the running state of each type of resource can be accurately and dynamically captured. Compared with other forms of energy storage, the compressed air energy storage has the characteristics of large capacity, relatively slow response speed and pressure in the running process. The state change not only has an instantaneous rate, but also has a sustained fluctuation of the change rate. By taking the second-order partial differential, the trend of the change rate can be effectively captured. Therefore, by constructing the random partial differential equation for prediction, the real-time performance of the power generation increment prediction and the accuracy of the power generation increment prediction of the virtual power plant can be improved.

[0007] In a second aspect, the present application provides a power generation increment prediction device, the power generation increment prediction device comprising: an acquisition module configured to acquire wind power generation parameter information of each wind power generator in a plurality of wind power generators of each wind power station to which a virtual power plant belongs, photovoltaic power generation parameter information of each photovoltaic cell in a plurality of photovoltaic cells of each photovoltaic power station to which the virtual power plant belongs, load parameter information of a power distribution network, and charge-discharge parameter information of charge-discharge of clusterable resources.

[0008] The prediction module is configured to predict, based on the wind power generation parameter information, a wind power generation increment of the wind power station after a future time period, predict, based on the photovoltaic power generation parameter information, a photovoltaic power generation increment of the photovoltaic power station after the future time period, predict, based on the load parameter information, a load increment of the virtual power plant after the future time period, and predict, based on the charge-discharge parameter information, a charge-discharge increment of the charge-discharge of the clusterable resources after the future time period; and predict, based on the random partial differential equation, the power generation increment of the virtual power plant according to the wind power generation increment, the photovoltaic power generation increment, the load increment and the charge-discharge increment, the wind power generation parameter information, the photovoltaic power generation parameter information, the load parameter information and the charge-discharge parameter information, to obtain a total power generation increment of the virtual power plant.

[0009] In a third aspect, the present application provides a computer device, comprising a memory and a processor, the memory and the processor being in communication connection with each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the power generation increment prediction method of the first aspect or any of the corresponding embodiments thereof.

[0010] In a fourth aspect, the present application provides a computer readable storage medium, having stored thereon computer instructions for causing a computer to execute the power generation increment prediction method of the first aspect or any of the corresponding embodiments thereof.

[0011] In a fifth aspect, the present application provides a computer program product comprising computer instructions for causing a computer to execute the power generation increment prediction method of the first aspect or any of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0012] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure or the prior art, the drawings required to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative labor.

[0014] Figure 1 is a flow chart of the power generation increment prediction method according to the embodiment of the present application; Figure 2 is a flow chart of the wind power generation increment prediction according to the embodiment of the present application; Figure 3 is a flow chart of the photovoltaic power generation increment prediction according to the embodiment of the present application; Figure 4 is a flow chart of the power distribution network load increment prediction of a virtual power plant according to the embodiment of the present application; Figure 5 is a flow chart of the charge-discharge increment prediction of a clonable resource charge-discharge according to the embodiment of the present application; Figure 6 is a structural block diagram of the power generation increment prediction device according to the embodiment of the present application; Figure 7 is a hardware structure schematic diagram of the computer device of the embodiment of the present application. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure or the prior art, the drawings required to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative labor.

[0016] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0017] The embodiments of this application are applied to the scenario of predicting the increase in power generation of a virtual power plant.

[0018] In related technologies, research on the randomness and intermittency of various distributed generation resources within virtual power plants currently focuses on information technologies such as big data analysis and artificial intelligence. Research on loads, especially the charging and discharging of electric vehicles, also utilizes probabilistic simulation techniques in addition to information technology. This method of predicting day-ahead generation increases on a daily basis results in poor real-time performance, making it difficult to meet the requirements of spot trading with a frequency of 15 minutes per transaction. Furthermore, due to the randomness of the various energy resources within a virtual power plant, the prediction of generation increases is also inaccurate.

[0019] To address the aforementioned technical problems, this application provides a method for predicting the increase in power generation. This method calculates the change in power generation of each component of a virtual power plant within a unit of time, establishes a stochastic partial differential equation (KPZ equation) for the increase in power generation of the virtual power plant, and predicts the increase in power generation of the virtual power plant within the next unit of time based on this KPZ equation.

[0020] The method for predicting the increase in power generation provided in this embodiment is executed by a device for predicting the increase in power generation. This device can be any device with computing and communication capabilities. For example, it can be a server or a cloud server.

[0021] Figure 1 This is a flowchart of a method for predicting the increase in power generation according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: S101, obtain the wind power generation parameter information of each wind turbine in each wind power station corresponding to the virtual power plant at time t, the photovoltaic power generation parameter information of each photovoltaic cell in each photovoltaic power station, the load parameter information of the distribution network, and the charging and discharging parameter information of the clusterable resources.

[0022] The wind power generation parameter information includes the number of wind power stations, and further includes the wind power parameters for each wind turbine, including the current rotor speed and current wind speed. The wind power parameter information also includes the wind energy utilization coefficient, air density, effective swept area of ​​the wind turbine, and the grid's rated power.

[0023] Photovoltaic power generation parameter information includes the number of photovoltaic power stations, the cell parameters of each photovoltaic cell in the power station, the current solar radiation intensity and current cell temperature, as well as the predicted solar radiation intensity and predicted ambient temperature in the future, and the circuit parameters of the photovoltaic array corresponding to the multiple photovoltaic cells. Among these, the cell parameter information includes conversion efficiency, effective cell area, cell temperature coefficient, and cell reference temperature.

[0024] Load parameter information includes the number of supercapacitor energy storage stations, the number of flywheel energy storage stations, the number of compressed air energy storage stations, the active and reactive power of the entire network load, the output active and reactive power of the equivalent generators in the entire network, the equivalent impedance of the distribution network, and the system bus voltage.

[0025] The charging and discharging parameter information includes the average number of vehicles arriving at the charging station per unit time, the probability density function of the remaining battery power of the electric vehicle, the probability density function of the starting charging time, and the charging and discharging power of a single electric vehicle at time t.

[0026] S102, based on wind power generation parameter information, predicts the wind power generation increment of wind power stations in the future time period, based on photovoltaic power generation parameter information, predicts the photovoltaic power generation increment of photovoltaic power stations in the future time period, based on load parameter information, predicts the load increment of virtual power plants in the future time period, and based on charging and discharging parameter information, predicts the charging and discharging increment of clusterable resources in the future time period.

[0027] The load increment includes the distribution network load increment, supercapacitor energy storage increment, flywheel energy storage increment, and compressed air energy storage increment.

[0028] The future time period can be determined based on the actual trading situation of the virtual power plant and is not restricted. For example, the future time period could be 15 minutes.

[0029] Specifically, the calculation process for the incremental wind power generation, incremental photovoltaic power generation, incremental distribution network load, incremental supercapacitor energy storage, incremental flywheel energy storage, incremental compressed air energy storage, and incremental charge and discharge of clusterable resources will be described in detail below.

[0030] like Figure 2 As shown, Figure 2 This is a schematic flowchart illustrating the incremental prediction of wind power generation according to an embodiment of the present invention; Figure 2 In this process, the power generation increment prediction device can perform the following steps: S201 inputs the current rotor speed and current wind speed into the preset prediction model, and outputs the wind speed change and rotor speed change rate for each wind turbine in the future time period.

[0031] The preset prediction model is used to predict the wind speed change and rotor speed change rate for each wind turbine in the future time period. The predicted wind speed change and rotor speed change rate for each wind turbine in the future time period are shown below.

[0032] S202 determines the mechanical power increment of each wind turbine in the future time period based on wind speed changes and wind force parameter information.

[0033] In wind turbines, the increase in mechanical power for:

[0034] Among them, C P Where ρ is the wind energy utilization coefficient, A1 is the air density, and V is the effective swept area of ​​the wind turbine. W P represents the change in wind speed. N This is the rated power of the power grid.

[0035] S203, based on the rotor speed change rate and the current rotor speed, determines the inertial potential energy increment of each wind turbine in the future time period.

[0036] Because the inertial potential energy of a wind turbine is related to the change in generator speed, for example, for a doubly-fed induction generator (DFIG), when the rotor speed of the DFIG is... At that time, the kinetic energy stored in its rotor for:

[0037] In the above formula, J is the moment of inertia, ω r This represents the rotor speed.

[0038] When all the rotor's kinetic energy is converted into electrical energy, the electromagnetic power that can be provided when the generator's speed changes is:

[0039] Specifically, the inertial potential energy released by the fan is directly proportional to the rate of change of the rotor speed. This refers to the output active power of a doubly-fed wind turbine. For the mechanical power captured by the wind turbine, the doubly-fed induction generator (DFIG) exhibits the following characteristics during its dynamic response:

[0040] in, The instantaneous active power provided for the rotor inertial kinetic energy of the doubly fed wind turbine.

[0041] S204 calculates the sum of the mechanical power increment and the inertial potential energy increment to obtain the power generation increment of the wind power station in the future time period.

[0042] In one example, the incremental power generation of a wind power station after a future time period. for:

[0043] like Figure 3 As shown, Figure 3 This is a schematic diagram of a process for predicting incremental photovoltaic power generation according to an embodiment of the present invention; in Figure 3 In this process, the power generation increment prediction device can perform the following steps: S301 determines the predicted cell temperature of each photovoltaic cell in the future time period based on the predicted solar radiation intensity and predicted ambient temperature.

[0044] The predicted ambient temperature refers to the ambient temperature predicted in the weather forecast.

[0045] Understandably, a photovoltaic panel is composed of multiple photovoltaic cells, which are devices that convert solar energy into electrical energy.

[0046] S302 determines the maximum output power of the photovoltaic power station in the future time period based on battery parameter information and predicted battery temperature.

[0047] The maximum output power of the photovoltaic power station after the future time period is: P = η × A × G × (1 + α ×(T - T0)).

[0048] Where P is the maximum output power of the photovoltaic power station after a future time period; η is the conversion efficiency; A is the effective area of ​​the cell; α is the cell temperature coefficient; T0 is the cell reference temperature; and T is the predicted cell temperature.

[0049] Understandably, the intensity of solar radiation is affected by various external factors, including atmospheric properties, atmospheric transparency, the angle of solar incidence, soil reflectivity, and the latitude of solar radiation. Solar energy radiating to the Earth's surface consists of two parts: direct radiation intensity received directly by the Earth, and diffused radiation intensity. By considering both external interference factors affecting radiation and the types of solar radiation, a mathematical model for computer simulation of solar photovoltaic power generation can be established. A photovoltaic cell is a device that converts solar energy into electrical energy. The output power of a photovoltaic cell is related to various factors, including solar radiation intensity, temperature, and spectral distribution.

[0050] S303, based on the photovoltaic array equation, determines the changing current corresponding to the photovoltaic power station according to circuit parameters, current solar radiation intensity, predicted solar radiation intensity, predicted battery temperature, and current battery temperature.

[0051] In a photovoltaic power station, multiple photovoltaic cells can form a photovoltaic panel, and multiple photovoltaic panels can form a photovoltaic array. A photovoltaic array can be represented by a diode, a capacitor, and a resistor. The photovoltaic effect of this photovoltaic array generates a current Iph, the current flowing into the diode is Id, the photovoltaic array capacitance is C, the photovoltaic parallel resistance is Rsh, and the photovoltaic series resistance is Rs.

[0052] The photovoltaic array equation can be expressed by the following expression:

[0053] in, S is the difference between the current solar radiation intensity and the predicted solar radiation intensity; T is the difference between the predicted battery temperature and the current battery temperature; S1 is the current solar radiation intensity, S is the predicted solar radiation intensity, and I... SCl U is the short-circuit current before the change. SCl This represents the open-circuit voltage before the change. α is taken as 1.2 × 10⁻⁶. -3 β is taken as 5 × 10 -3 I m1 U is the maximum power point current before the change. m1 This is the voltage at the maximum power point before the change.

[0054] S304: Based on the changing current, maximum output power, and the maximum current corresponding to the maximum output power, the incremental power generation of the photovoltaic power station in the future time period is obtained.

[0055] Among them, the increase in power generation from photovoltaic power stations in the future time period. for:

[0056] P represents the incremental power generation of a photovoltaic power station after a future time period. map Maximum output power; I map This refers to the maximum current corresponding to the maximum output power. I represents the changing current.

[0057] Optionally, photovoltaic power plants are current-driven renewable energy generation devices and have a certain reserve active power. Therefore, the reserve active power ratio is defined as r*%, which represents the proportion of the active power actually generated by the photovoltaic power plant to the maximum available power. The reserve active power ratio is:

[0058] In the formula, P map This represents the maximum power output of a photovoltaic power station, and its magnitude is affected by external irradiance and temperature. r*% This represents the actual power output after the photovoltaic system is unloaded.

[0059] like Figure 4 As shown, Figure 4 This is a schematic diagram of a distribution network load increment prediction process using a virtual power plant according to an embodiment of the present invention; Figure 4 In this process, the power generation increment prediction device can perform the following steps: S401, based on the system bus voltage, the equivalent impedance of the distribution network, the active power of the load, and the reactive power of the load, determine the active power loss and reactive power loss of the equivalent impedance of the distribution network.

[0060] The active power loss and reactive power loss of the equivalent impedance of the distribution network can be expressed by the following expressions:

[0061] P D0 The active power loss of the distribution network is represented by the equivalent impedance; Q D0 The reactive power loss is the equivalent impedance of the distribution network. Equivalent impedance of the distribution network; U S0 System bus voltage; P0 is the active power of the load and Q0 is the reactive power of the load.

[0062] S402, based on active power loss, reactive power loss, load active power, load reactive power, output active power, and output reactive power, determine the initial active power and initial reactive power of the load of the virtual power plant.

[0063] The initial active power and initial reactive power of the load in a virtual power plant can be represented by the following expressions:

[0064] Among them, P L Q represents the initial active power of the load in the virtual power plant. L This represents the initial active power of the load in the virtual power plant.

[0065] S403 determines the power factor angle change of the virtual power plant based on the initial active power, initial reactive power, and reactive power loss.

[0066] Power factor angle change of virtual power plant for:

[0067] S404 predicts the increase in distribution network load of the virtual power plant in the future time period based on the power factor angle and active power loss.

[0068] The increase in the distribution network load of the virtual power plant after a future time period can be represented by the following expression: .

[0069] in, This represents the increase in the distribution network load of the virtual power plant in the future time period.

[0070] In addition, when the virtual power plant also includes a supercapacitor energy storage station, a flywheel energy storage station, and a compressed air energy storage station, the power generation increment prediction device can also predict the supercapacitor energy storage increment, flywheel energy storage increment, and compressed air energy storage increment of the virtual power plant in the future time period.

[0071] For predicting the incremental power generation from supercapacitor energy storage, the capacity can exceed several hundred megawatts. Supercapacitor energy storage has a very fast discharge rate, typically charging to over 85% of its rated capacity within tens of seconds to minutes. Supercapacitor energy storage mainly consists of various energy storage units, bidirectional DC / DC circuits, and DC / AC converters. The charging and discharging power of the energy storage power station is:

[0072] in, The rated power of the energy storage; This represents the rated charge / discharge power of the energy storage unit. Simultaneously, the state of charge of the i-th energy storage power station... (The percentage of remaining battery power) is:

[0073] This refers to the rated capacity of the energy storage power station.

[0074] The incremental power generation from supercapacitor energy storage in the future time period will be:

[0075] in, This is to increase the amount of electricity generated by supercapacitor energy storage in the future.

[0076] For predicting the incremental power generation from flywheel energy storage, the capacity typically ranges from tens to hundreds of kilowatts. Flywheel energy storage stores and releases energy through a high-speed rotating flywheel, achieving frequency regulation speeds at the millisecond level. This rapid response time makes flywheel energy storage particularly suitable for frequency regulation in power systems. The power generation capacity of flywheel energy storage primarily depends on the flywheel's rotational speed and moment of inertia. The formula for calculating the total releaseable energy E of flywheel energy storage is:

[0077] Where J is the moment of inertia of the flywheel, ω is the angular velocity of the flywheel, and ωmin and ωmax are the minimum and maximum angular velocities, respectively. The state of charge S (the percentage of remaining charge) of the flywheel's energy storage is:

[0078] The flywheel energy storage control method is virtual droop control, with a 0.033 Hz dead zone set to limit flywheel operation and prevent frequent charging and discharging of the flywheel system, based on the energy storage's participation in grid frequency regulation. Therefore, the incremental power generation from flywheel energy storage in the future time period is:

[0079] in, This is to increase the amount of electricity generated by flywheel energy storage in the future.

[0080] For predicting the incremental power generation from compressed air energy storage, the capacity can exceed several hundred megawatts. Compressed air energy storage discharges very quickly; from receiving the command to the efficient operation of the power generation equipment, it only takes 6 to 8 minutes. A compressed air energy storage system consists of a compression system, an air storage system, and a turbine expander system. The outlet air temperature and pressure of the i-th stage expander are:

[0081] in, This indicates the temperature of the air entering the expander inlet (which can be controlled by the compressor and is used as a monitoring and uploading quantity). This represents the rated expansion ratio of the i-th stage expander. Let represent the rated isentropic efficiency of the i-th stage expander, and k be the air adiabatic index (the adiabatic index is the index of an ideal gas in a reversible adiabatic process, with a value of 1.4).

[0082] The output power of the i-th stage expander is:

[0083] in: The mass flow rate of the expander. This refers to the specific heat capacity of air at constant pressure.

[0084] The total output power of each stage of the expander is:

[0085] Where Ne represents the number of stages in the expander.

[0086] Compressed air energy storage requires frequency regulation devices to operate under varying conditions, and the actual pressure ratio of the compressor... Actual isentropic efficiency Let and me represent the actual air mass flow rate of the i-th stage expander, which will change with its partial load operation. Using these quantities as monitored parameters, the output power of compressed air energy storage can be calculated. Therefore, the predicted power generation of compressed air energy storage is:

[0087] in, The mass flow rate of the expander. Let be the specific heat capacity of air at constant pressure, and Ne be the number of stages in the expander. This represents the temperature of the air entering the expander at stage i. This represents the rated expansion ratio of the i-th stage expander. Let represent the rated isentropic efficiency of the i-th stage expander, and k be the air adiabatic index.

[0088] like Figure 5 As shown, Figure 5 This is a schematic flowchart illustrating the prediction of charge / discharge increments for clusterable resources according to an embodiment of the present invention; Figure 5 In this process, the power generation increment prediction device can perform the following steps: S501 determines the number of electric vehicles participating in charging and discharging in the future time period based on the Poisson distribution algorithm, the average number of vehicles arriving at the charging station per unit time, and the length of the future time period.

[0089] The Poisson distribution algorithm can be expressed by the following expression:

[0090] Where N(t) represents the number of vehicles arriving at the charging station per unit time, e represents the natural constant 2.71828…, and λ represents the average number of vehicles arriving at the charging station per unit time. The Poisson distribution algorithm is used to predict the probability distribution of the number of vehicles arriving at the charging station in the future time period.

[0091] Understandably, the clusterable resources in a virtual power plant are primarily electric vehicles, each capable of charging and discharging. The charging and discharging of each electric vehicle, much like energy storage, includes factors such as the remaining battery capacity and the battery's charging curve. Therefore, predicting the charging and discharging of clusterable resources in a virtual power plant mainly considers how many electric vehicles join the charging and discharging sequence within 15 minutes. The probability of an electric vehicle arriving is closely related to user behavior and the distribution of charging stations; a Poisson distribution can be used as the probability model for an electric vehicle reaching a charging station.

[0092] S502, based on the probability density function of the remaining power of the electric vehicle, the probability density function at the start of charging, and the charging and discharging power of a single electric vehicle at time t, determine the average charging and discharging power of a single electric vehicle.

[0093] In one example, let P be the power of the electric vehicle at any given time. jAnd if the electric vehicle starts charging at time k (k≤t), without considering whether the charging is aimed at full load, then the power at time k is P. j-(t-k) And at this time, SOC is E j-(t-k) The probability density function for obtaining the remaining battery power of the electric vehicle is:

[0094] in, The probability density function of the remaining battery power of an electric vehicle and Let be the probability density function at the initial charging moment.

[0095] The average charging and discharging power of a single electric vehicle is:

[0096] in, This represents the average charge / discharge power.

[0097] S503 calculates the product between the number of electric vehicles and the average charging and discharging power to determine the charging and discharging increment of clusterable resources in the future time period.

[0098] Understandably, by calculating the power generation and consumption of each entity within the virtual power plant within the above-mentioned time period, the incremental power consumption of each entity in the future time period can be calculated.

[0099] S103, based on stochastic partial differential equations, predicts the power generation increment of the virtual power plant based on the increments of wind power generation, photovoltaic power generation, load, and charging / discharging, as well as wind power generation parameter information, photovoltaic power generation parameter information, load parameter information, and charging / discharging parameter information, and obtains the total power generation increment of the virtual power plant.

[0100] The stochastic partial differential equations are expressed in the following formula:

[0101] in, Nw represents the total increase in power generation from the virtual power plant; Nw represents the number of wind power stations. s represents the increase in wind power generation; s represents the number of photovoltaic power stations. c represents the increase in photovoltaic power generation; c represents the number of supercapacitor energy storage stations. l represents the incremental energy storage capacity of supercapacitors; l represents the number of flywheel energy storage stations. represents the incremental energy storage capacity of the flywheel; m represents the number of compressed air energy storage stations. Increased energy storage capacity for compressed air; For the increase in distribution network load; Let be the charge / discharge increment of the electric vehicle at time t.

[0102] Understandably, treating the virtual power plant's trading volume over 15 minutes as a random variable, fluctuating between its minimum and maximum values, can be viewed as the fluctuation of the boundary between the virtual power plant's power generation and its power consumption. Specifically, at time t, this boundary fluctuates to a height of h (output power). The relationship between h and t can be expressed using stochastic partial differential equations (Kardar–Parisi–Zhang, KPZ equations). The KPZ equations are as follows:

[0103] Where λ is proportional to the average growth rate. The effects of time-space noise, including its nonlinear terms, can describe many similar natural phenomena. To obtain the first-order differential of the output power of the wind power plant in the virtual power plant as a function of time; To obtain the first-order differential of the output power of the photovoltaic power station in the virtual power plant as a function of time; To obtain the first-order differential of the output power of the supercapacitor energy storage station in the virtual power plant as a function of time; To obtain the first-order differential of the output power of the flywheel energy storage in the virtual power plant as a function of time; To obtain the first-order differential of the output power of the virtual power plant load as a function of time; To obtain the second-order differential of the output power of compressed air energy storage in a virtual power plant as a function of time, the KPZ equation can be derived. This leads to the total increase in power generation from the virtual power plant.

[0104] The stochastic correction ξ(t,x) in the KPZ equations is the product of the means of two stochastic distributions: the mean of the stochastic distribution of power generation from clusterable resources within the virtual power plant parameters, and the mean of the stochastic distribution of the number of dynamically participating clusterable resources within the virtual power plant parameters. In the KPZ equations, the first-order differential can be obtained for the virtual power plant, wind power station, photovoltaic power station, supercapacitor energy storage station, flywheel energy storage station, compressed air energy storage station, and conventional load. The second-order partial differential is obtained for the compressed air energy storage station within the virtual power plant.

[0105] based on Figure 1The method shown can construct stochastic partial differential equations based on the incremental wind power generation, photovoltaic power generation, load increase, and charge / discharge increments of a virtual power plant. Since the stochastic correction is defined as the product of the mean power generation of clusterable resources in the virtual power plant and the mean number of participants, it can comprehensively reflect the superimposed influence of two types of core stochastic factors on the system. The introduction of the mean avoids the interference of extreme values ​​from single random sampling, improving the accuracy of the correction term. The first-order differential essentially characterizes the instantaneous rate of change of a variable with time or space. Taking the first-order differential for various resources such as wind power, photovoltaics, and supercapacitor energy storage, as well as conventional loads, enables accurate dynamic capture of the operating states of various resources. Compressed air energy storage, compared to other energy storage forms, has the characteristics of large capacity, relatively slow response speed, and pressure during operation. Its state changes not only have instantaneous rates but also continuous fluctuations in the rate of change. Taking the second-order partial differential can effectively capture the changing trends of these rates of change. Therefore, by constructing stochastic partial differential equations for prediction, the real-time performance of power generation increment prediction and the accuracy of power generation increment prediction for virtual power plants can be improved.

[0106] This embodiment also provides a device for predicting the increase in power generation, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0107] This embodiment provides a device for predicting the increase in power generation, such as... Figure 6 As shown, Figure 6 This is a structural block diagram of a power generation increment prediction device according to an embodiment of the present invention; the power generation increment prediction device includes: The acquisition module 601 is used to acquire the wind power generation parameter information of each wind turbine in each wind power station corresponding to the virtual power plant at time t, the photovoltaic power generation parameter information of each photovoltaic cell in each photovoltaic power station, the load parameter information of the distribution network, and the charging and discharging parameter information of the clusterable resources.

[0108] The prediction module 602 is used to predict the increase in wind power generation of a wind power station in the future time period based on wind power generation parameter information, the increase in photovoltaic power generation of a photovoltaic power station in the future time period based on photovoltaic power generation parameter information, the increase in load of a virtual power plant in the future time period based on load parameter information, and the increase in charging and discharging of clusterable resources in the future time period based on charging and discharging parameter information. Based on stochastic partial differential equations, the module predicts the increase in power generation of the virtual power plant according to the increase in wind power generation, the increase in photovoltaic power generation, the increase in load, the increase in charging and discharging, and the information on wind power generation parameters, photovoltaic power generation parameters, load parameters, and charging and discharging parameters, and obtains the total increase in power generation of the virtual power plant.

[0109] In some optional implementations, wind power generation parameter information includes the number of wind power stations; photovoltaic power generation parameter information includes the number of photovoltaic power stations; load parameter information includes the number of supercapacitor energy storage stations, flywheel energy storage stations, and compressed air energy storage stations; load increments include distribution network load increments, supercapacitor energy storage increments, flywheel energy storage increments, and compressed air energy storage increments; the clusterable resource is electric vehicles; the expression of the stochastic partial differential equation is shown in the following formula:

[0110] in, Nw represents the total increase in power generation from the virtual power plant; Nw represents the number of wind power stations. s represents the increase in wind power generation; s represents the number of photovoltaic power stations. c represents the increase in photovoltaic power generation; c represents the number of supercapacitor energy storage stations. l represents the incremental energy storage capacity of supercapacitors; l represents the number of flywheel energy storage stations. represents the incremental energy storage capacity of the flywheel; m represents the number of compressed air energy storage stations. Increased energy storage capacity for compressed air; For the increase in distribution network load; Let be the charge / discharge increment of the electric vehicle at time t.

[0111] In some optional implementations, the wind power generation parameter information also includes wind power parameter information, current rotor speed, and current wind speed for each wind turbine; the prediction module 602 is specifically used to input the current rotor speed and current wind speed into a preset prediction model, and output the wind speed change and rotor speed change rate for each wind turbine after a future time period; determine the mechanical power increment of each wind turbine after a future time period based on the wind speed change and wind power parameter information; determine the inertial potential energy increment of each wind turbine after a future time period based on the rotor speed change rate and current rotor speed; and calculate the sum of the mechanical power increment and the inertial potential energy increment to obtain the power generation increment of the wind power station after a future time period.

[0112] In some optional implementations, the photovoltaic power generation parameter information also includes the battery parameter information of each photovoltaic cell in the multiple photovoltaic cells of the photovoltaic power station, the current solar radiation intensity and the current battery temperature, as well as the predicted solar radiation intensity and predicted ambient temperature after a future time period, and the circuit parameters corresponding to the photovoltaic array corresponding to the multiple photovoltaic cells; based on the predicted solar radiation intensity and predicted ambient temperature, the predicted battery temperature of each photovoltaic cell after the future time period is determined; the prediction module 602 is specifically used to determine the maximum output power of the photovoltaic power station after the future time period based on the battery parameter information and the predicted battery temperature; based on the photovoltaic array equation, according to the circuit parameters, the current solar radiation intensity, the predicted solar radiation intensity, the predicted battery temperature, and the current battery temperature, the changing current corresponding to the photovoltaic power station is determined; based on the changing current, the maximum output power, and the maximum current corresponding to the maximum output power, the power generation increment of the photovoltaic power station after the future time period is obtained.

[0113] In some optional implementations, the load parameter information includes the active and reactive power of the entire network load, the output active and reactive power of the equivalent generators of the entire network, the equivalent impedance of the distribution network, and the system bus voltage. The prediction module 602 is specifically used to predict the distribution network load increment of the virtual power plant after a future time period based on the load parameter information; determine the active and reactive power losses of the equivalent impedance of the distribution network based on the system bus voltage, the equivalent impedance of the distribution network, the active and reactive power of the load; determine the initial active and initial reactive power of the virtual power plant load based on the active and reactive power losses, the load active and reactive power, the output active and output reactive power; determine the power factor angle change of the virtual power plant based on the initial active power, the initial reactive power, and the reactive power loss; and predict the distribution network load increment of the virtual power plant after a future time period based on the power factor angle and the active power loss.

[0114] In some optional implementations, the charging and discharging parameter information includes the average number of vehicles arriving at the charging pile per unit time, the probability density function of the remaining battery power of the electric vehicle, the probability density function of the starting charging time, and the charging and discharging power of a single electric vehicle at time t. The prediction module 602 is specifically used to determine the number of electric vehicles participating in charging and discharging in the future time period based on the Poisson distribution algorithm, the average number of vehicles arriving at the charging pile per unit time, and the length of the future time period; to determine the average charging and discharging power of a single electric vehicle based on the probability density function of the remaining battery power of the electric vehicle, the probability density function of the starting charging time, and the charging and discharging power of a single electric vehicle at time t; and to calculate the product between the number of electric vehicles and the average charging and discharging power to determine the charging and discharging increment of clusterable resources after the future time period.

[0115] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0116] In this embodiment, the power generation increment prediction device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0117] This invention also provides a computer device having the above-described features. Figure 6 The device shown is for predicting the increase in power generation.

[0118] Please see Figure 7 , Figure 7 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention, such as... Figure 7 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 7 Take a processor 10 as an example.

[0119] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GPA), or any combination thereof.

[0120] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0121] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0122] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0123] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0124] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0125] This invention provides a computer program product, which includes computer instructions for causing a computer to execute the method of any embodiment of this invention.

[0126] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0127] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of predicting an energy production increment, characterized by, The method comprises: acquiring wind power generation parameter information of each wind turbine in a plurality of wind turbines of each wind power station corresponding to the virtual power plant, photovoltaic generation parameter information of each photovoltaic cell in a plurality of photovoltaic cells of each photovoltaic power station, load parameter information of the power distribution network, and charge-discharge parameter information of the clusterable resource charge-discharge; predicting, based on the wind power generation parameter information, a wind power generation increment of the wind power station after a future time period, predicting, based on the photovoltaic generation parameter information, a photovoltaic power generation increment of the photovoltaic power station after the future time period, predicting, based on the load parameter information, a load increment of the virtual power plant after the future time period, and predicting, based on the charge-discharge parameter information, a charge-discharge increment of the clusterable resource charge-discharge after the future time period; based on a stochastic partial differential equation, predicting, according to the wind power generation increment, the photovoltaic power generation increment, the load increment, and the charge-discharge increment, the wind power generation parameter information, the photovoltaic generation parameter information, the load parameter information, and the charge-discharge parameter information, a power generation increment of the virtual power plant, to obtain a total power generation increment of the virtual power plant.

2. The method of claim 1, wherein, The wind power generation parameter information comprises a number of the wind power stations; the photovoltaic generation parameter information comprises a number of the photovoltaic power stations; the load parameter information comprises a number of super capacitor energy storage stations, a number of flywheel energy storage stations, and a number of compressed air energy storage stations; the load increment comprises a power distribution network load increment, a super capacitor energy storage increment, a flywheel energy storage increment, and a compressed air energy storage increment; the clusterable resource is an electric vehicle; and the expression form of the stochastic partial differential equation is shown in the following formula: wherein, is the total power generation increment of the virtual power plant; Nw is the number of wind power stations; is the wind power generation increment; s is the number of photovoltaic power stations, is the photovoltaic power generation increment; c is the number of super capacitor energy storage stations, is the super capacitor energy storage increment; l is the number of flywheel energy storage stations, is the flywheel energy storage increment; m is the number of compressed air energy storage stations, is the compressed air energy storage increment; is the power distribution network load increment; is the charging and discharging increment of the electric vehicle at time t.

3. The method of claim 2, wherein, The wind power generation parameter information further comprises wind parameter information of each wind turbine, a current rotor speed, and a current wind speed; and the prediction of the wind power generation increment of the wind power station after the future time period based on the wind power generation parameter information comprises: inputting the current rotor speed and the current wind speed into a preset prediction model to output a wind speed change amount and a rotor speed change rate of each wind turbine after the future time period; determining, according to the wind speed change amount and the wind parameter information, a mechanical power increment of each wind turbine after the future time period; determining, according to the rotor speed change rate and the current rotor speed, an inertial potential energy increment of each wind turbine after the future time period; calculating a sum of the mechanical power increment and the inertial potential energy increment to obtain the power generation increment of the wind power station after the future time period.

4. The method of claim 2, wherein, The photovoltaic generation parameter information further comprises cell parameter information of each photovoltaic cell in a plurality of photovoltaic cells of the photovoltaic power station, a current solar radiation intensity and a current cell temperature, a predicted solar radiation intensity and a predicted ambient temperature after the future time period, and circuit parameters of a photovoltaic array corresponding to the plurality of photovoltaic cells; and the prediction of the photovoltaic power generation increment of the photovoltaic power station after the future time period based on the photovoltaic generation parameter information comprises: determining a predicted cell temperature of each of the photovoltaic cells after the future time period according to the predicted solar radiation intensity and the predicted ambient temperature; determining a maximum output power of the photovoltaic power plant after the future time period according to the cell parameter information and the predicted cell temperature; determining a change current corresponding to the photovoltaic power plant according to the circuit parameter, the current solar radiation intensity, the predicted solar radiation intensity, the predicted cell temperature, and the current cell temperature based on a photovoltaic array equation; obtaining an electricity generation increment of the photovoltaic power plant after the future time period according to the change current, the maximum output power, and a maximum current corresponding to the maximum output power.

5. The method of claim 2, wherein, The load parameter information includes load active power and load reactive power of a whole network, output active power and output reactive power of an equivalent generator of the whole network, equivalent impedance of a distribution network, and system bus voltage. The prediction of the load increment of the virtual power plant after the future time period based on the load parameter information includes: The prediction of the distribution network load increment of the virtual power plant after the future time period based on the load parameter information includes: determining active power loss and reactive power loss of the equivalent impedance of the distribution network according to the system bus voltage, the equivalent impedance of the distribution network, the load active power, and the load reactive power; determining initial active power and initial reactive power of the load of the virtual power plant according to the active power loss, the reactive power loss, the load active power, the load reactive power, the output active power, and the output reactive power; determining a power factor angle change amount of the virtual power plant according to the initial active power, the initial reactive power, and the reactive power loss; predicting the distribution network load increment of the virtual power plant after the future time period according to the power factor angle and the active power loss. The charging and discharging parameter information includes average number of vehicles arriving at a charging pile per unit time, probability density function of residual power of an electric vehicle, probability density function of starting charging time, and charging and discharging power of a single electric vehicle at t time; 6. The method of claim 2, wherein, The prediction of the charging and discharging increment of the clusterable resource charging and discharging after the future time period based on the charging and discharging parameter information includes: determining a number of electric vehicles participating in charging and discharging in the future time period based on a Poisson distribution algorithm, average number of vehicles arriving at a charging pile per unit time, and time length of the future time period; determining average charging and discharging power of a single electric vehicle based on the probability density function of residual power of the electric vehicle, the probability density function of starting charging time, and the charging and discharging power of the single electric vehicle at t time; calculating a product between the number of electric vehicles and the average charging and discharging power to determine the charging and discharging increment of the clusterable resource charging and discharging after the future time period. The electricity generation increment prediction device includes:

7. An electric power generation increment amount prediction device characterized by comprising: ​ acquire wind power generation parameter information of each wind power generator in a plurality of wind power generators of each wind power station to which the virtual power plant belongs, photovoltaic power generation parameter information of each photovoltaic cell in a plurality of photovoltaic cells of each photovoltaic power station, load parameter information of the power distribution network, and charge-discharge parameter information of the clusterable resource charge-discharge; predict, based on the wind power generation parameter information, a wind power generation increment of the wind power station after a future time period, predict, based on the photovoltaic power generation parameter information, a photovoltaic power generation increment of the photovoltaic power station after the future time period, predict, based on the load parameter information, a load increment of the virtual power plant after the future time period, and predict, based on the charge-discharge parameter information, a charge-discharge increment of the clusterable resource charge-discharge after the future time period; based on a stochastic partial differential equation, predict, according to the wind power generation increment, the photovoltaic power generation increment, the load increment, and the charge-discharge increment, the wind power generation parameter information, the photovoltaic power generation parameter information, the load parameter information, and the charge-discharge parameter information, a power generation increment of the virtual power plant, and obtain a total power generation increment of the virtual power plant.

8. A computer device, comprising: comprise: a memory and a processor, which are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the power generation increment prediction method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing a computer to execute the power generation increment prediction method in any one of claims 1 to 6.

10. A computer program product, characterised in that, comprise computer instructions for causing a computer to execute the power generation increment prediction method in any one of claims 1 to 6.

Images