Power grid load forecasting method and device

Abstract

The present invention discloses a method and device for predicting the load of a power grid. The method includes: predicting the spatial load of the power grid; predicting the load of various load devices in the power grid and the input power of various power supply devices to the power grid, the load includes electric vehicle load and demand side load; the input power includes photovoltaic input power, wind turbine input power, and energy storage input power; based on the spatial load, determining the load prediction result of the power grid. The device includes: a first prediction module for predicting the spatial load of the power grid; a second prediction module for predicting the electric vehicle load, demand side load, photovoltaic input power, wind turbine input power, and energy storage input power in the power grid; and a determination module for determining the load prediction result of the power grid. The present invention solves the technical problem that the power grid load prediction method in the related art cannot meet the power grid's requirements for load prediction accuracy due to fewer considerations through the above method and device.

Description

Technical Field

[0001] The present invention relates to the field of electric power, and in particular to a method and device for predicting power grid load. Background Art

[0002] The distribution system is an important part of the power system and an important intermediate link between the transmission network and the user. In the traditional distribution network planning, the distribution network and the user side play a stable supply and demand relationship. However, in recent years, with the continuous development of the economy and the growth of social electricity demand, the maximum load utilization hours of the power grid have continued to decline, and the peak load problem has become increasingly prominent. In this process, the emergence of new loads has also put forward new requirements for the operation and control of the distribution network, such as electric vehicles and electric heating. On the other hand, the increasing penetration rate of new energy sources such as distributed power sources and energy storage is also the current development trend of the distribution network. Compared with traditional power generation methods, distributed power sources have the characteristics of large randomness, strong volatility, and uncontrollable input power. In power planning, they cannot be treated the same as conventional units, and the original distribution system needs to introduce active coordination and control capabilities for distributed power sources. All these have prompted the original distribution system to change, that is, to develop towards an active distribution system.

[0003] Related technologies usually use the following methods to predict power grid load:

[0004] 1. Spatial load forecasting method: This method is based on the division of regional plots, gives the load density index of each type of land use, completes the load forecast of each plot, and then summarizes the load forecast results of the entire region.

[0005] 2. Mathematical model method: This method is usually based on historical data and uses mathematical models such as regression analysis, trend extrapolation, polynomials, etc. for prediction.

[0006] 3. Load classification-based prediction method: First, the load is divided into uncontrollable load, controllable load, and adjustable load, and then further divided into friendly load and unfriendly load; then the concept of load response coefficient (λ) is introduced, and mathematical models are established respectively, and then the typical distribution network load prediction method of far first and near later is used for prediction.

[0007] At present, the research on load forecasting methods has been very in-depth, and different methods are used to predict future regional loads. However, with the development and utilization of comprehensive energy and the emergence of new loads, the traditional forecasting method has a low accuracy in grid load forecasting due to the relatively few factors considered, and can no longer meet current needs.

[0008] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0009] The embodiments of the present invention provide a method and device for predicting power grid load, so as to at least solve the technical problem that the power grid load prediction method in the related art cannot meet the demand for power grid load prediction due to fewer considerations.

[0010] According to one aspect of an embodiment of the present invention, a method for predicting the load of a power grid is provided, comprising: predicting the spatial load of the power grid, as well as the loads of various load devices in the power grid and the input power of various power supply devices to the power grid, wherein the various loads include at least one of the following: electric vehicle load, demand side load; the various input powers include at least one of the following: photovoltaic input power, wind turbine input power, energy storage input power; and according to the various loads and the various input powers and based on the spatial load, determining the load prediction result of the power grid.

[0011] Optionally, determining the load prediction result of the power grid based on the spatial load according to the multiple loads and the multiple input powers includes: determining the load prediction result according to a load prediction formula, and the load prediction formula is as follows:

[0012] F a =F0-F p -F w +F e +F d -F q

[0013] In the formula, F a is the load forecast result under the active distribution network; F0 is the spatial load, F p is the photovoltaic input power, F w is the fan input power, F e is the electric vehicle load, F d is the demand side load, F q Input power for energy storage.

[0014] Optionally, predicting multiple loads in the power grid includes: predicting spatial load; in the case of predicting the spatial load of a prospect year, predicting the spatial load of the prospect year by a prospect year formula, wherein the prospect year formula is:

[0015]

[0016] Where F0′ is the forecast result of the space load in the future year; m is the number of land uses in the grid of the space; D i is the floor space-load characteristic curve of the unit building of the i-th type of building; S i is the floor area of ​​the i-th type of building;

[0017] Alternatively, in the case of predicting the space load of an intermediate year, the space load of the intermediate year is predicted by the intermediate year formula, wherein the intermediate year is the year between the current year and the prospect year, and the intermediate year formula is:

[0018] F0″=Y(t)·F0′

[0019] Where Y is the percentage of the spatial load in the intermediate year to the spatial load in the prospective year; t is the number of years from the current year;

[0020]

[0021] Where A is the growth coefficient of the load in the middle year, and e is the natural constant.

[0022] Optionally, predicting multiple loads in the power grid includes: predicting the photovoltaic input power when the photovoltaic input power exists in the power grid; determining the photovoltaic input power according to a photovoltaic power formula, where the photovoltaic power formula is:

[0023]

[0024] In the formula, F p is the photovoltaic input power, S is the measured solar intensity; T is the measured solar panel temperature; S ref is the light intensity under standard conditions, P ref is the output power under standard conditions; T ref is the panel temperature under standard conditions; γ is the preset maximum power temperature coefficient of the photovoltaic device.

[0025] Optionally, predicting multiple loads in the power grid includes: predicting the wind turbine input power when the wind turbine input power exists in the power grid; determining the wind turbine input power according to a wind turbine power formula, wherein the wind turbine power formula is:

[0026] F w =min(N e , P max )

[0027] Where N e is the optimal installed capacity of the wind turbine, P max The generation load without considering the wind turbine capacity;

[0028]

[0029] Where K is the wind turbine power conversion factor; C a C is the air altitude density conversion factor; t is the air temperature density correction factor; S is the swept area of ​​the wind turbine blade; is the average wind speed in the forecast year; η is the overall efficiency of the wind turbine,

[0030] P max =K×C a ×C t ×S×v t 3 ×η

[0031] In the formula, v t The real-time wind speed.

[0032] Optionally, predicting multiple loads in the power grid includes: predicting the electric vehicle load when the electric vehicle load exists in the power grid; determining the electric vehicle load according to an electric vehicle load formula, wherein the electric vehicle load formula is:

[0033] F e =N·q·D1·k1+N·(1-q)·D2·k2

[0034] In the formula, F e is the electric vehicle load; N is the number of electric vehicle positions; q is the slow charging ratio; D1 is the slow charging pile load index; k1 is the slow charging pile simultaneous rate; D2 is the fast charging pile load index; k2 is the fast charging pile simultaneous rate.

[0035] Optionally, predicting multiple loads in the power grid includes: predicting the demand side load when the demand side load exists in the power grid; determining a first single demand side load according to a first single demand side load formula when the consumption reduction rate of the demand side resource of user i′ is determined, and the first single demand side load formula is:

[0036]

[0037] In the formula, ΔP max，i′ represents the consumption reduction load under the action of i′ type demand side resources; α EE，i′ represents the consumption reduction rate of the demand-side resources of user i′; t represents the number of hours during the forecast period; β LD，i′ represents the load rate of the user under the action of load resources; Q 0，pre Indicates the electricity consumption of the user in the forecast year without considering the demand-side resources;

[0038] Q 0，pre =P 0，pre ·T max

[0039] Where P 0，pre is the maximum load of the user without considering the demand-side resources; T max The maximum load utilization hours for the user;

[0040] Alternatively, when the i′-type demand-side resource of the user is adjustable, the second single demand-side load of the i′-type demand-side resource is determined according to a second single demand-side load formula, and the second single demand-side load formula is:

[0041] ΔP max，i＇ =P 0，pre ·μ i＇ ·σ i＇ ·ρ i′，j

[0042] In the formula, μ i′ is the total controllable load ratio of i′ type demand side resources, σ i′ is the proportion of available demand-side resources of type i′ demand-side resources, ρ i′，j is the impact coefficient of response measure j on type i′ demand side resources; the demand side load is determined according to the demand side load formula, and the demand side load formula is:

[0043]

[0044] Where n represents the number of demand-side resources owned by the user; ξ is the preset demand-side load coefficient.

[0045] Optionally, predicting multiple loads in the power grid includes: predicting energy storage input power; when the energy storage device is charged, predicting the energy storage input power according to a charging energy storage input power formula, the charging energy storage input power formula is:

[0046] F q =-P1(t)

[0047] Wherein, P1(t) is the charging power of the energy storage device; P1(t) satisfies the following formula:

[0048] E(t)=(1-τ)E(t-1)+P1(t)η1Δt

[0049] Wherein, E(t) is the amount of electricity of the energy storage device in time period t; E(t-1) is the amount of electricity of the energy storage device in time period t-1 before time period t; η1 is the charge and discharge efficiency of the energy storage device; τ is the self-discharge rate of the energy storage device;

[0050] When the energy storage device is discharged, the energy storage input power is predicted according to the discharge energy storage input power formula, and the discharge energy storage input power formula is:

[0051] F q =P2(t)

[0052] Wherein, P2(t) is the discharge power of the energy storage device; P2(t) satisfies the following formula:

[0053]

[0054] According to another aspect of an embodiment of the present invention, a power grid load prediction device is also provided, including: a prediction module, used to predict the spatial load of the power grid, as well as the loads of various load devices in the power grid and the input power of various power supply devices to the power grid, wherein the various loads include at least one of the following: electric vehicle load, demand side load; the various input powers include at least one of the following: photovoltaic input power, wind turbine input power, energy storage input power; a determination module, used to determine the load prediction result of the power grid based on the spatial load according to the various loads and the various input powers.

[0055] Optionally, the determination module includes: a determination unit, configured to determine the load prediction result according to a load prediction formula, wherein the load prediction formula is as follows:

[0056] F a =F0-F p -F w +F e +F d -F q

[0057] In the formula, F a is the load forecast result under the active distribution network; F0 is the spatial load, F p is the photovoltaic input power, F w is the fan input power, F e is the electric vehicle load, F d is the demand side load, F q Input power for energy storage.

[0058] Optionally, the prediction module includes: a first prediction unit, the first prediction unit being used to predict the space load;

[0059] The first prediction unit is used to predict the space load of the prospect year by using a prospect year formula when predicting the space load of the prospect year, wherein the prospect year formula is:

[0060]

[0061] Where F0′ is the forecast result of the space load in the future year; m is the number of land uses in the grid of the space; D i is the floor space-load characteristic curve of the unit building of the i-th type of building; S i is the floor area of ​​the i-th type of building;

[0062] The first prediction unit is further used to predict the space load of the intermediate year by using the intermediate year formula when predicting the space load of the intermediate year, wherein the intermediate year is the year between the current year and the prospect year, and the intermediate year formula is:

[0063] F0″=Y(t)·F0′

[0064] Where Y is the percentage of the spatial load in the intermediate year to the spatial load in the prospective year; t is the number of years from the current year;

[0065]

[0066] Where A is the growth coefficient of the load in the middle year, and e is the natural constant.

[0067] Optionally, the prediction module includes: a second prediction unit, the second prediction unit is used to predict the photovoltaic input power when the photovoltaic input power exists in the power grid; determine the photovoltaic input power according to the photovoltaic power formula, and the photovoltaic power formula is:

[0068]

[0069] In the formula, F p is the photovoltaic input power, S is the measured solar intensity; T is the measured solar panel temperature; S ref is the light intensity under standard conditions, P ref is the output power under standard conditions; T ref is the panel temperature under standard conditions; γ is the preset maximum power temperature coefficient of the photovoltaic device.

[0070] Optionally, the prediction module includes: a third prediction unit, the third prediction unit is used to predict the wind turbine input power when the wind turbine input power exists in the power grid; determine the wind turbine input power according to the wind turbine power formula, the wind turbine power formula is:

[0071] F w =min(N e , P max )

[0072] Where N e is the optimal installed capacity of the wind turbine, P max The generation load without considering the wind turbine capacity;

[0073]

[0074] Where K is the wind turbine power conversion factor; C a C is the air altitude density conversion factor; tis the air temperature density correction factor; S is the swept area of ​​the wind turbine blade; is the average wind speed in the forecast year; η is the overall efficiency of the wind turbine,

[0075] P max =K×C a ×C t ×S×v t 3 ×η

[0076] In the formula, v t The real-time wind speed.

[0077] Optionally, the prediction module includes: a fourth prediction unit, the fourth prediction unit being used to predict the electric vehicle load when the electric vehicle load exists in the power grid;

[0078] The fourth prediction unit is used to determine the electric vehicle load according to the electric vehicle load formula, and the electric vehicle load formula is:

[0079] F e =N·q·D1·k1+N·(1-q)·D2·k2

[0080] In the formula, F e is the electric vehicle load; N is the number of electric vehicle positions; q is the slow charging ratio; D1 is the slow charging pile load index; k1 is the slow charging pile simultaneous rate; D2 is the fast charging pile load index; k2 is the fast charging pile simultaneous rate.

[0081] Optionally, the prediction module includes: a fifth prediction unit, the fifth prediction unit being used to predict the demand side load when the demand side load exists in the power grid;

[0082] The fifth prediction unit is used to determine the first single demand side load according to the first single demand side load formula when determining the consumption reduction rate of the demand side resource of user i′, and the first single demand side load formula is:

[0083]

[0084] In the formula, ΔP max，i′ represents the consumption reduction load under the action of i′ type demand side resources; α EE，i′ represents the consumption reduction rate of the demand-side resources of user i′; t represents the number of hours during the forecast period; β LD，i′ represents the load rate of the user under the action of load resources; Q 0，pre Indicates the electricity consumption of the user in the forecast year without considering the demand-side resources;

[0085] Q 0，pre =P 0，pre ·Tmax

[0086] Where P 0，pre is the maximum load of the user without considering the demand-side resources; T max The maximum load utilization hours for the user;

[0087] The fifth prediction unit is further configured to determine, when the i′-type demand side resource of the user is controllable, a second single demand side load of the i′-type demand side resource according to a second single demand side load formula, wherein the second single demand side load formula is:

[0088] ΔP max，i′ =P 0，pre ·μ i′ ·σ i＇ ·ρ i′，j

[0089] In the formula, μ i′ is the total controllable load ratio of i′ type demand side resources, σ i′ is the proportion of available demand-side resources of type i′ demand-side resources, ρ i′，j is the impact coefficient of response measure j on type i′ demand side resources; the demand side load is determined according to the demand side load formula, and the demand side load formula is:

[0090]

[0091] Where n represents the number of demand-side resources owned by the user; ξ is the preset demand-side load coefficient.

[0092] Optionally, the prediction module includes: a sixth prediction unit, the sixth prediction unit being used to predict the energy storage input power when the energy storage input power exists in the power grid;

[0093] The sixth prediction unit is used to predict the energy storage input power according to the charging energy storage input power formula when the energy storage device is charged. The charging energy storage input power formula is:

[0094] F q =-P1(t)

[0095] Wherein, P1(t) is the charging power of the energy storage device; P1(t) satisfies the following formula:

[0096] E(t)=(1-τ)E(t-1)+P1(t)η1Δt

[0097] Wherein, E(t) is the amount of electricity of the energy storage device in time period t; E(t-1) is the amount of electricity of the energy storage device in time period t-1 before time period t; η1 is the charge and discharge efficiency of the energy storage device; τ is the self-discharge rate of the energy storage device;

[0098] The sixth prediction unit is further configured to predict the energy storage input power according to a discharge energy storage input power formula when the energy storage device is discharged. The discharge energy storage input power formula is:

[0099] F q =P2(t)

[0100] Wherein, P2(t) is the discharge power of the energy storage device; P2(t) satisfies the following formula:

[0101]

[0102] According to another aspect of an embodiment of the present invention, a storage medium is further provided, wherein the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the above-mentioned power grid load forecasting methods.

[0103] According to another aspect of an embodiment of the present invention, a processor is further provided, wherein the processor is used to run a program, wherein the program executes any one of the above-mentioned power grid load forecasting methods when running.

[0104] In an embodiment of the present invention, a method is adopted to predict the spatial load of a power grid; predict the loads of various load devices in the power grid and the input power of various power supply devices to the power grid, wherein the various loads include at least one of the following: electric vehicle load, demand side load; the various input powers include at least one of the following: photovoltaic input power, wind turbine input power, energy storage input power; according to the various loads and the various input powers, based on the spatial load, a method of determining the load prediction result of the power grid is adopted, by rechecking and predicting the various loads in the power grid, and predicting the input power of various power supply devices, so that the predicted spatial load of the power grid is corrected by considering more factors through the various loads and the various power supply devices, thereby achieving the purpose of accurately determining the load prediction result of the power grid, thereby realizing the technical effect of improving the accuracy of the power grid load prediction, and further solving the technical problem that the power grid load prediction method in the related technology cannot meet the demand of power grid load prediction due to fewer considerations. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0106] Figure 1 is a flow chart of a power grid load forecasting method according to an embodiment of the present invention;

[0107] Figure 2 is a flow chart of a space load calculation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0108] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0109] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0110] According to an embodiment of the present invention, a method embodiment of a power grid load forecasting method 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 a 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.

[0111] Figure 1 is a flow chart of a power grid load forecasting method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0112] Step S102, predicting the spatial load of the power grid, as well as the loads of various load devices in the power grid and the input power of various power devices to the power grid, wherein the various loads include at least one of the following: electric vehicle load, demand side load; the various input powers include at least one of the following: photovoltaic input power, wind turbine input power, energy storage input power;

[0113] Step S104, determining a load prediction result of the power grid according to the multiple loads and the multiple input powers based on the spatial load.

[0114] Through the above steps, the spatial load of the power grid and the loads of various load devices in the power grid and the input power of various power supply devices to the power grid are predicted, wherein the various loads include at least one of the following: electric vehicle load, demand side load; the various input powers include at least one of the following: photovoltaic input power, wind turbine input power, energy storage input power; according to the various loads and various input powers, based on the spatial load, the load prediction result of the power grid is determined, by reviewing and predicting the various loads in the power grid, and predicting the input power of various power supply devices, so that the predicted spatial load of the power grid is corrected by considering more factors through various loads and various power supply devices, so as to achieve the purpose of accurately determining the load prediction result of the power grid, thereby realizing the technical effect of improving the accuracy of power grid load prediction, and then solving the technical problem that the power grid load prediction method in the related technology cannot meet the demand of power grid load prediction due to fewer considerations.

[0115] As the load of the power grid changes more and more dramatically and the peak load increases, the prediction of the power grid load can improve the power grid's ability to cope with the drastic changes in the power grid load to a certain extent, thereby improving the stability and reliability of the power grid. The power grid load prediction methods in the relevant technology, including the spatial load prediction method, the mathematical model method, and the load classification prediction method, all predict the power grid load from one area. With the development and utilization of comprehensive energy in the power grid and the emergence of various new loads, the changes in the power grid load have intensified, resulting in the inability of traditional power grid load prediction methods to make comprehensive and effective predictions, resulting in low accuracy in the prediction of the outgoing power grid load.

[0116] The present application combines the spatial load prediction method, the mathematical model method, and the load classification prediction method to predict various loads including spatial loads, electric vehicle loads, and demand-side loads, as well as various input powers including photovoltaic input power, wind turbine input power, and energy storage input power, and predicts the load of the power grid through the above-mentioned various loads and various input powers.

[0117] The above-mentioned spatial load is the traditional load in the power grid predicted by the spatial load prediction method. The above-mentioned spatial load prediction method is a method for predicting the traditional load of the power grid. The above-mentioned spatial load prediction method can predict the traditional load in the power grid, and then special predictions are made for new loads, such as electric vehicle loads, demand side loads, etc. As new loads, they can be predicted by other methods, such as mathematical model methods. The above-mentioned new loads can also include other loads that may appear different from traditional loads, such as the load of high-speed rail after the rise of high-speed rail, the load of electric vehicles after the rise of electric vehicles, and so on.

[0118] Different from the traditional power grid, the rise of new energy has increased the types of power sources in the power grid, and the proportion is increasing. Therefore, the input power of new energy power sources to the power grid is predicted. The above new energy sources can include photovoltaic power generation, wind power generation, hydropower generation, tidal power, biomass power generation, etc. When the types of traditional power sources in the power grid are different and exceed a certain proportion, it is necessary to consider the input power prediction of the new energy to the power grid, so as to improve the accuracy of the power grid load prediction.

[0119] The above-mentioned load forecasting result of the power grid is determined based on the input power of various power grid loads and various power sources in the power grid. It can be the spatial load obtained by predicting the traditional load through spatial prediction, superimposing the new load and reducing the new energy. Since both the traditional load and the new load cause power output to the power grid, they are the load of the power grid, and they are superimposed. The above-mentioned traditional load is the power output of the power grid, and the new energy is the power input to the power grid. Therefore, when predicting the power grid load, it is necessary to subtract the input power of various new energy sources.

[0120] In this embodiment, the multiple loads include at least one of the following: electric vehicle load, demand side load, and the multiple input powers include at least one of the following: photovoltaic input power, wind turbine input power, and energy storage input power. Determining the load forecast result of the power grid according to the multiple loads and the multiple input powers includes: determining the load forecast result according to the load forecast formula, and the load forecast formula is as follows:

[0121] F a =F0-F p -F w +F e +F d -F q

[0122] In the formula, F a is the load forecast result under the active distribution network; F0 is the spatial load, F p is the photovoltaic input power, F w is the fan input power, F e is the electric vehicle load, Fd is the demand side load, F q Input power for energy storage.

[0123] The order of the various loads and various input powers can be determined according to the specific needs of the power grid. In this embodiment, the various loads and various input powers can be determined according to the load prediction formula, F a =F0-F p -F w +F e +F d -F q The prediction is determined in the order of priority, that is, the spatial load F0 is predicted first, and based on the above spatial load, the photovoltaic input power F is predicted when there is photovoltaic input power in the power grid. p , when there is wind turbine input power in the power grid, predict the wind turbine input power F w , when there is electric vehicle load in the power grid, the electric vehicle load F is predicted e , when there is demand side load in the power grid, the demand side load F is predicted d , when there is energy storage input power in the power grid, the predicted energy storage input power F q The above-mentioned compliance prediction is based on the traditional spatial load F0, and the spatial load F0 is corrected by considering various influencing factors. Therefore, the spatial load F0 is calculated first, and then various loads and various input powers are predicted when they exist in the power grid. The above-mentioned various loads and various input powers are ranked according to the degree of influence on the power grid load. The higher the ranking, the greater the influence on the power grid load.

[0124] The above-mentioned degree of influence on the grid load can be determined according to the ratio of the load or input power to the spatial load. The larger the ratio, the greater the influence. The above-mentioned types of loads have different degrees of influence on the grid in different grid systems. In some grid systems, wind power generation may be more developed than photovoltaic power generation. Therefore, it can be considered to predict the wind turbine input power first, and then predict the photovoltaic input power. Other loads and input powers can also be adjusted in sequence. In the case where there are new loads or new energy in the grid system and the proportion exceeds a certain threshold, they can also be included in the load prediction formula. For example, the grid system in the coastal area may rely more on tidal energy. Therefore, in the process of grid load prediction, tidal energy input power can be added. The specific order can also be determined according to the tidal energy input power and various loads and the degree of influence of various input powers on the grid system. Through the above sequence, the importance of various loads and various input powers in the grid load prediction can be more fully considered, so as to predict the grid load more reasonably and accurately.

[0125] Optionally, predicting multiple loads in the power grid includes: predicting spatial load; in the case of predicting spatial load in a prospective year, predicting spatial load in the prospective year by a prospective year formula, wherein the prospective year formula is:

[0126]

[0127] Where F0′ is the prediction result of spatial load in the future year; m is the number of land uses in the spatial grid; D i is the floor space-load characteristic curve of the unit building of the i-th type of building; S i is the floor area of ​​the i-th type of building; the above-mentioned vision year is a year that is farther away from the current status quo year, usually the vision year can be from the eleventh to fifteenth year, or from the fifteenth to the twentieth year, or from the eleventh to the twentieth year, from the current status quo year.

[0128] The above spatial load is based on the division of regional plots. The plots in the prediction area are divided into multiple grids, and the load density index of each type of land use is given to complete the load prediction of each grid plot, and then the load prediction results of the entire region are summarized. The types of the above buildings have different classification results according to different classification principles. For example, they can be divided according to their use, including civil buildings and industrial buildings. Civil buildings also include residential buildings and public relations buildings. Residential buildings include urban residences, apartments, dormitories, villas, rural residences, etc. Public relations buildings include office buildings, educational buildings, scientific research and experimental buildings, memorial buildings, medical buildings, commercial buildings, financial and insurance buildings, transportation buildings, postal and telecommunications buildings, and other buildings. Among industrial buildings, they can be divided according to the nature of production, including ferrous metallurgical buildings, textile industry buildings, machinery industry buildings, chemical industry buildings, building materials industry buildings, power industry buildings, light industry buildings, and other buildings. They can also be classified according to the use of the factory building, including main production plants, auxiliary production plants, power plants, and ancillary storage buildings. They can also be classified according to the number of floors of the factory building, including single-story factories, multi-story factories, mixed factories, etc. It can also be classified according to the internal production conditions of the production workshop, including hot workshop, cold workshop, constant temperature and humidity workshop, etc. Different types of buildings have different floor area and load characteristic curves. According to the floor area-load characteristic curve of each type of building, The area of ​​the building is used to predict the load characteristics of the building, thereby determining the load of the building and thus the load of each grid plot, thereby determining the spatial load.

[0129] Alternatively, in the case of predicting the spatial load of the intermediate year, the spatial load of the intermediate year is predicted by the intermediate year formula, wherein the intermediate year is the year between the current year and the vision year, and the above intermediate year is usually the first to fifth year, or the fifth to tenth year, or the first to tenth year from the current year.

[0130] The formula for the middle year is:

[0131] F0″=Y(t)·F0′

[0132] Where Y is the percentage of the spatial load in the intermediate year to the spatial load in the prospective year; t is the number of years from the current year;

[0133]

[0134] Where A is the growth coefficient of the intermediate year load, and e is a natural constant. The growth coefficient of the intermediate year load needs to be calculated based on the load data of the specific year.

[0135] Optionally, predicting multiple loads in the power grid includes: predicting the photovoltaic input power when there is photovoltaic input power in the power grid; determining the photovoltaic input power according to a photovoltaic power formula, where the photovoltaic power formula is:

[0136]

[0137] In the formula, F p is the photovoltaic input power, S is the measured solar intensity; T is the measured solar panel temperature; S ref is the light intensity under standard conditions, P ref is the output power under standard conditions; T ref is the panel temperature under standard conditions; γ is the preset maximum power temperature coefficient of the photovoltaic device.

[0138] Optionally, predicting multiple loads in the power grid includes: predicting the wind turbine input power when there is wind turbine input power in the power grid; determining the wind turbine input power according to a wind turbine power formula, the wind turbine power formula being:

[0139] F w =min(N e , P max )

[0140] Where N e is the optimal installed capacity of the wind turbine, P max The generation load without considering the wind turbine capacity;

[0141]

[0142] Where K is the wind turbine power conversion factor; C a C is the air altitude density conversion factor; t is the air temperature density correction factor; S is the swept area of ​​the wind turbine blade; is the average wind speed in the forecast year; η is the overall efficiency of the wind turbine,

[0143] P max =K×C a ×C t ×S×v t 3 ×η

[0144] In the formula, v t The real-time wind speed.

[0145] The above wind turbine input power and photovoltaic input power are predicted by mathematical model method to their respective input power to the grid.

[0146] Optionally, predicting multiple loads in the power grid includes: predicting the electric vehicle load when there is an electric vehicle load in the power grid; determining the electric vehicle load according to an electric vehicle load formula, the electric vehicle load formula is:

[0147] F e =N·q·D1·k1+N·(1-q)·D2·k2

[0148] In the formula, F e is the electric vehicle load; N is the number of electric vehicle positions; q is the slow charging ratio; D1 is the slow charging pile load index; k1 is the slow charging pile simultaneous rate; D2 is the fast charging pile load index; k2 is the fast charging pile simultaneous rate. The above slow charging pile can be a charging pile that does not use fast charging technology for charging, and the above fast charging pile can be a charging pile that uses fast charging technology for charging.

[0149] Optionally, predicting multiple loads in the power grid includes: predicting the demand side load when there is a demand side load in the power grid; determining a first single demand side load according to a first single demand side load formula when determining a consumption reduction rate of a user i′ type demand side resource, the first single demand side load formula being:

[0150]

[0151] In the formula, ΔP max，i′ represents the consumption reduction load under the action of i′ type demand side resources; α EE，i′ represents the consumption reduction rate of the demand-side resources of user i′; t represents the number of hours during the forecast period; β LD，i′ It indicates the load rate of the user under the action of load resources; Q 0，pre It indicates the electricity consumption of users in the forecast year without considering the demand-side resources;

[0152] Q 0，pre =P 0，pre ·T max

[0153] Where P 0，preThe maximum load of the user without considering the demand-side resources; T max The maximum load utilization hours for users;

[0154] Alternatively, when the user's i'-type demand side resources are adjustable, the second single demand side load of the i'-type demand side resources is determined according to the second single demand side load formula, and the second single demand side load formula is:

[0155] ΔP max，i′ =P 0，pre ·μ i′ ·σ i′ ·ρ i′，j

[0156] In the formula, μ i′ is the total controllable load ratio of i' type demand side resources, σ i′ is the proportion of available demand-side resources of type i’, ρ i′，j is the impact coefficient of response measure j on i' type demand side resources; the demand side load is determined according to the demand side load formula, and the demand side load formula is:

[0157]

[0158] Where n represents the number of demand-side resources owned by the user; ξ is the preset demand-side load coefficient.

[0159] The load classification prediction method is used to predict the above demand side load. The above first single demand side load is the load for determining the consumption reduction rate of the user's i' type demand side resources. The above second single demand side load is the load that can be adjusted by the user's i' type demand side resources.

[0160] The above-mentioned measures for demand-side resources may include improving the efficiency of electricity use of lighting, air conditioning, motors, electric heating, refrigeration and other equipment; changing the way of electricity use by storing cold, virtual heat, and energy; energy substitution, surplus energy recovery; contractually agreed interruptible loads; improving electricity use by insulation of buildings; changing consumption behavior of customers; and self-owned power plants. Correspondingly, the above-mentioned demand-side resources refer to the demand side of the power grid, that is, the node resources of the client, mainly including: electricity and power saved by improving the efficiency of electricity use of lighting, air conditioning, motors, electric heating, refrigeration and other equipment; electricity saved by changing the way of electricity use by storing cold, virtual heat, and energy; electricity and power reduced and saved by energy substitution and surplus energy recovery; electricity and power saved by contractually agreed interruptible loads; electricity and power saved by improving electricity use by insulation of buildings; electricity and power saved by customers changing their consumption behavior to reduce electricity use; electricity and power reduced by the power grid after the participation of self-owned power plants in dispatching, etc.

[0161] Optionally, predicting multiple loads in the power grid includes: predicting the energy storage input power when there is energy storage input power in the power grid; predicting the energy storage input power according to the charging energy storage input power formula when the energy storage device is charging, and the charging energy storage input power formula is:

[0162] F q =-P1(t)

[0163] Where P1(t) is the charging power of the energy storage device; P1(t) satisfies the following formula:

[0164] E(t)=(1-τ)E(t-1)+P1(t)η1Δt

[0165] Where, E(t) is the amount of electricity in the energy storage device in period t; E(t-1) is the amount of electricity in the energy storage device in period t-1 before period t; η1 is the charge and discharge efficiency of the energy storage device; τ is the self-discharge rate of the energy storage device;

[0166] When the energy storage device is discharged, the energy storage input power is predicted according to the discharge energy storage input power formula. The discharge energy storage input power formula is:

[0167] F q =P2(t)

[0168] Where P2(t) is the discharge power of the energy storage device; P2(t) satisfies the following formula:

[0169]

[0170] In addition, for energy storage devices, considering the hardware characteristics of energy storage devices and the charging and discharging power limitations, there are the following charging and discharging constraints:

[0171] 0≤P2, P1≤P2

[0172] In the formula, P1 represents the minimum charging and discharging power of the energy storage device, and P2 represents the maximum charging and discharging power of the energy storage device;

[0173] At the same time, in order to provide emergency backup for active distribution networks, the state of charge constraints of energy storage are set as follows:

[0174] E1≤E≤E2

[0175] In the formula, E1 and E2 represent the maximum and minimum capacity of the battery, and E represents the power of the energy storage device. This constrains the power and charge / discharge power of the energy storage device, making the calculation result more accurate.

[0176] It should be noted that this embodiment also provides an optional implementation, which is described in detail below.

[0177] This implementation will complete the load forecasting under the active distribution network by analyzing the input power of distributed power sources to the grid, future energy storage layout, small power sources, electric vehicles, demand-side response, etc. The load forecasting results completed by this model can directly guide the planning of the regional distribution network framework to achieve the level of accurate load prediction and grid planning. The specific steps are as follows:

[0178] Step 1: Build the model

[0179] This embodiment provides a source measurement calculation model for photovoltaic, wind energy, and energy storage.

[0180] 1) Photovoltaic model: The power of solar power generation is mainly determined by irradiance and temperature. The output power of photovoltaic cell modules at different times is approximately linearly related to environmental factors. The power estimation formula is as follows:

[0181]

[0182] S is the measured solar intensity; T is the measured solar panel temperature; S ref is the light intensity under standard conditions, taking 800W / m2, T ref is the panel temperature under standard conditions; P ref is the output power under standard conditions, which is 3.5kW; γ is the maximum power temperature coefficient of the preset photovoltaic device.

[0183] 2) Wind turbine model: The optimal installed capacity of the wind turbine is calculated using the following formula:

[0184]

[0185] Without considering the capacity of the wind turbine, its hourly power generation load is calculated by the following formula:

[0186] P max =K×C a ×C t ×S×v t 5 ×η

[0187] The actual input power of the wind turbine is calculated by the following formula:

[0188] F w =min(N e , P max )

[0189] Where K is the wind turbine power conversion factor, with a default value of 0.6127; Ca is the air altitude density conversion factor, which refers to the correction value of air density at different altitudes, which can be found based on the altitude; Ct is the air temperature density correction factor, and the air density varies at different temperatures, which can be found based on the average temperature; S is the swept area of ​​the wind turbine blades; is the average wind speed; v t is the real-time wind speed; η is the overall efficiency of the wind turbine, and its value is related to the type of wind turbine, and is generally between 25% and 50%.

[0190] 3) Energy storage model: The amount of electricity stored in an energy storage device is a cumulative amount that changes over time. It is related to the charge and discharge power and charge and discharge efficiency of the energy storage element, and the self-discharge loss must also be considered. Its mathematical model is:

[0191] Charging: E(t)=(1-τ)E(t-1)+P1(t)η1Δt

[0192] Discharge:

[0193] E(t) is the amount of electricity in the energy storage device in period t; E(t-1) is the amount of electricity in the energy storage device in period t-1 before period t; P1(t) and P2(t) are the charging power and discharging power respectively; η1 is the charging and discharging efficiency of the energy storage device; τ is the self-discharge rate of the energy storage element.

[0194] Considering the hardware characteristics of energy storage equipment and the charging and discharging power limit, there are the following charging and discharging constraints:

[0195] 0≤P2, P1≤P2

[0196] In the formula, P1 represents the minimum charging and discharging power of the energy storage device, and P2 represents the maximum charging and discharging power of the energy storage device;

[0197] At the same time, in order to provide emergency backup for active distribution networks, the state of charge constraints of energy storage are set as follows:

[0198] E1≤E≤E2

[0199] Where E1 and E2 represent the maximum and minimum capacity of the battery.

[0200] 4) Electric vehicle model: The grid electric vehicle charging load can be calculated by the following formula:

[0201] F e =N·q·D1·k1+N·(1-q)·D2·k2

[0202] In the formula, F eis the charging pile load, unit, W; N is the number of electric parking spaces; q is the slow charging ratio; D1 is the slow charging pile load index; k1 is the slow charging pile simultaneous rate; D2 is the fast charging pile load index; k2 is the fast charging pile simultaneous rate.

[0203] 5) Demand-side load model: First, the maximum load forecasting model of a single demand-side resource in the grid is studied and calculated in two cases:

[0204] When the power saving and consumption reduction rate of a certain type of demand-side resource is known, the maximum load prediction formula for a certain type of user considering a single demand-side resource is as follows:

[0205]

[0206] Where ΔP max，i′ Represents the consumption reduction load under the action of demand-side resources, unit, kW; α EE，i′ represents the consumption reduction rate of this type of user under the action of energy efficiency resources; t represents the number of hours in the forecast period, unit, hour; β LD，i′ It indicates the load rate of this type of user under the action of load resources; Q 0，pre Indicates the electricity consumption of this type of user in the forecast year without considering the demand-side resources, unit, kWh; P 0，pre The maximum load of this type of user without considering the demand-side resources, unit, kW; T max The maximum load utilization hours for this type of user, unit: hours.

[0207] When the controllable conditions of a certain type of demand-side resources are known, the calculation formula is as follows:

[0208] ΔP max，i′ =P 0，pre ·μ i′ ·σ i′ ·ρ i′，j

[0209] Where P 0，pre is the maximum load of this type of user without considering demand-side resources, kW; μ i′ is the total controllable load ratio, σ i′ is the proportion of demand-side resources that can be called during this time period, ρ i′，j The impact of demand-side response measures on the demand-side resources.

[0210] When there are multiple load resources in the grid, the maximum load reduction is:

[0211]

[0212] Where n represents the number of load resources owned by the user; ξ is the preset demand-side load coefficient.

[0213] Step 2: Space load calculation

[0214] Figure 2 is a flow chart of a method for calculating space load according to an embodiment of the present invention. Figure 2 As shown, the steps are as follows:

[0215] 1) Long-term forecast:

[0216] The planned land use classification building area or land area, the following formula is used to calculate the grid hourly load:

[0217]

[0218] Where: F0′ is the hourly load of the grid;

[0219] m is the number of land uses in the grid;

[0220] D i is the unit building / floor area load characteristic curve of the i-th type of building;

[0221] S i It is the i-th type of building / land area.

[0222] 2) Mid-year forecast

[0223] According to the grid saturation load and the development sequence of the plots, the S-curve method is used to predict the load in the middle year.

[0224] The load growth of each development plot in the middle year is predicted based on the load growth curve model. The mathematical model of the S-curve method is as follows:

[0225] S-curve mathematical model:

[0226]

[0227] in:

[0228] Y is the percentage of the annual maximum load in year t to the prospective saturation load.

[0229] t is the number of years from the status quo year;

[0230] A is the growth coefficient of the S-curve;

[0231] e is a natural constant.

[0232] Step 3: Load forecasting based on active distribution network

[0233] After completing the basic spatial load forecast, add the active load model to complete a more accurate forecast.

[0234] F a =F0-F p-F w +F e +F d -F q

[0235] F a is the load forecast result under the active distribution network, F0 is the traditional load based on space, F p is the photovoltaic input power, F w is the fan input power, F e is the electric vehicle load, F d is the demand side load, F q Input power for energy storage.

[0236] This embodiment provides an active distribution network load forecasting method based on a comprehensive energy background. This embodiment establishes a calculation model on the energy side during the load forecasting process, and establishes a calculation model for user load measurement. The load forecast is completed by superimposing the two ends, providing a basis for grid planning.

[0237] According to another aspect of an embodiment of the present invention, a power grid load prediction device is provided, including: a prediction module and a determination module. The device is described in detail below.

[0238] The prediction module is used to predict the load of various load devices in the power grid and the input power of various power supply devices to the power grid, among which the various loads include space loads, electric vehicle loads, and demand-side loads; the various input powers include photovoltaic input power, wind turbine input power, and energy storage input power; the determination module is connected to the above prediction module and is used to determine the load prediction results of the power grid based on the various loads and various input powers.

[0239] Through the above-mentioned device, a prediction module is used to predict the spatial load of the power grid, as well as the loads of various load devices in the power grid and the input power of various power supply devices to the power grid, wherein the various loads include at least one of the following: electric vehicle load, demand side load; the various input powers include at least one of the following: photovoltaic input power, wind turbine input power, energy storage input power; the determination module determines the load prediction result of the power grid based on the various loads and various input powers and based on the spatial load, by reviewing and predicting the various loads in the power grid and predicting the input power of various power supply devices, thereby correcting the spatial load of the power grid predicted by considering more factors through various loads and various power supply devices, thereby achieving the purpose of accurately determining the load prediction result of the power grid, thereby achieving the technical effect of improving the accuracy of power grid load prediction, and further solving the technical problem that the power grid load prediction method in the related technology cannot meet the needs of power grid load prediction due to fewer considerations.

[0240] Optionally, the determination module includes: a determination unit, configured to determine a load prediction result according to a load prediction formula, the load prediction formula being as follows:

[0241] F a =F0-F p -F w +F e +F d -F q

[0242] In the formula, F a is the load forecast result under the active distribution network; F0 is the spatial load, F p is the photovoltaic input power, F w is the fan input power, F e is the electric vehicle load, F d is the demand side load, F q Input power for energy storage.

[0243] Optionally, the prediction module includes: a first prediction unit, the first prediction unit is used to predict the space load; in the case of predicting the space load of the prospect year, the space load of the prospect year is predicted by the prospect year formula, wherein the prospect year formula is:

[0244]

[0245] Where F0′ is the prediction result of spatial load in the future year; m is the number of land uses in the spatial grid; D i is the floor space-load characteristic curve of the unit building of the i-th type of building; S i is the floor area of ​​the i-th type of building;

[0246] The first prediction unit is also used to predict the space load of the intermediate year by using the intermediate year formula when predicting the space load of the intermediate year, wherein the intermediate year is the year between the current year and the prospect year, and the intermediate year formula is:

[0247] F0″=Y(t)·F0′

[0248] Where Y is the percentage of the spatial load in the intermediate year to the spatial load in the prospective year; t is the number of years from the current year;

[0249]

[0250] Where A is the growth coefficient of the load in the middle year, and e is the natural constant.

[0251] Optionally, the prediction module includes: a second prediction unit, the second prediction unit is used to predict the photovoltaic input power when there is photovoltaic input power in the power grid; determine the photovoltaic input power according to the photovoltaic power formula, the photovoltaic power formula is:

[0252]

[0253] In the formula, F p is the photovoltaic input power, S is the measured solar intensity; T is the measured solar panel temperature; S ref is the light intensity under standard conditions, P ref is the output power under standard conditions; T ref is the panel temperature under standard conditions; γ is the preset maximum power temperature coefficient of the photovoltaic device.

[0254] Optionally, the prediction module includes: a third prediction unit, the third prediction unit is used to predict the wind turbine input power when there is wind turbine input power in the power grid; determine the wind turbine input power according to the wind turbine power formula, the wind turbine power formula is:

[0255] F w =min(N e , P max )

[0256] Where N e is the optimal installed capacity of the wind turbine, P max The generation load without considering the wind turbine capacity;

[0257]

[0258] Where K is the wind turbine power conversion factor; C a C is the air altitude density conversion factor; t is the air temperature density correction factor; S is the swept area of ​​the wind turbine blade; is the average wind speed in the forecast year; η is the overall efficiency of the wind turbine,

[0259] P max =K×C a ×C t ×S×v t 3 ×η

[0260] In the formula, v t The real-time wind speed.

[0261] Optionally, the prediction module includes: a fourth prediction unit, the fourth prediction unit being used to predict the electric vehicle load when there is an electric vehicle load in the power grid;

[0262] The fourth prediction unit is used to determine the electric vehicle load according to the electric vehicle load formula, and the electric vehicle load formula is:

[0263] F e =N·q·D1·k1+N·(1-q)·D2·k2

[0264] In the formula, F e is the electric vehicle load; N is the number of electric vehicle positions; q is the slow charging ratio; D1 is the slow charging pile load index; k1 is the slow charging pile simultaneous rate; D2 is the fast charging pile load index; k2 is the fast charging pile simultaneous rate.

[0265] Optionally, the prediction module includes: a fifth prediction unit, the fifth prediction unit being used to predict the demand side load when there is a demand side load in the power grid;

[0266] The fifth prediction unit is used to determine the first single demand side load according to the first single demand side load formula when determining the consumption reduction rate of the demand side resource of user i′, and the first single demand side load formula is:

[0267]

[0268] Where ΔP max，i′ represents the consumption reduction load under the action of i′ type demand side resources; α EE，i′ represents the consumption reduction rate of the demand-side resources of user i′; t represents the number of hours during the forecast period; β LD，i′ It indicates the load rate of the user under the action of load resources; Q 0，pre It indicates the electricity consumption of the user in the forecast year without considering the demand-side resources;

[0269] Q 0，pre =P 0，pre ·T max

[0270] Where P 0，pre The maximum load of the user without considering the demand-side resources; T max Maximum load utilization hours for users:

[0271] The fifth prediction unit is further used to determine the second single demand side load of the i′ type demand side resource according to the second single demand side load formula when the i′ type demand side resource of the user is adjustable. The second single demand side load formula is:

[0272] ΔP max，i′ =P 0，pre ·μ i′ ·σ i′ ·ρ i′，j

[0273] In the formula, μ i′is the total controllable load ratio of i′ type demand side resources, σ i′ is the proportion of available demand-side resources of type i′ demand-side resources, ρ i′，j is the impact coefficient of response measure j on type i′ demand-side resources; the demand-side load is determined according to the demand-side load formula, which is:

[0274]

[0275] Where n represents the number of demand-side resources owned by the user; ξ is the preset demand-side load coefficient.

[0276] Optionally, the prediction module includes: a sixth prediction unit, the sixth prediction unit being used to predict the energy storage input power when there is energy storage input power in the power grid;

[0277] The sixth prediction unit is used to predict the energy storage input power according to the charging energy storage input power formula when the energy storage device is charged. The charging energy storage input power formula is:

[0278] F q =-P1(t)

[0279] Where P1(t) is the charging power of the energy storage device; P1(t) satisfies the following formula:

[0280] E(t)=(1-τ)E(t-1)+P1(t)η1Δt

[0281] Where, E(t) is the amount of electricity in the energy storage device in period t; E(t-1) is the amount of electricity in the energy storage device in period t-1 before period t; η1 is the charge and discharge efficiency of the energy storage device; τ is the self-discharge rate of the energy storage device;

[0282] The sixth prediction unit is also used to predict the energy storage input power according to the discharge energy storage input power formula when the energy storage device is discharged. The discharge energy storage input power formula is:

[0283] F q =P2(t)

[0284] Where P2(t) is the discharge power of the energy storage device; P2(t) satisfies the following formula:

[0285]

[0286] According to another aspect of an embodiment of the present invention, a storage medium is further provided, the storage medium including a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the above-mentioned power grid load forecasting methods.

[0287] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned power grid load forecasting methods is executed.

[0288] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0289] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0290] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0291] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0292] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0293] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0294] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for predicting power grid load, characterized in that: include: Predicting the spatial load of the power grid, as well as the loads of various load devices in the power grid and the input power of various power supply devices to the power grid, wherein the various loads include at least one of the following: electric vehicle load, demand side load; the various input powers include at least one of the following: photovoltaic input power, wind turbine input power, energy storage input power, wherein predicting the spatial load of the power grid includes: in the case of predicting the spatial load of the prospect year, predicting the spatial load of the prospect year by the prospect year formula, wherein the prospect year formula is: Where F0′ is the forecast result of the space load in the future year; m is the number of land uses in the grid of the space; D i is the floor space-load characteristic curve of the unit building of the i-th type of building; S i is the floor area of ​​the i-th type of building; In the case of predicting the space load of the intermediate year, the space load of the intermediate year is predicted by the intermediate year formula, wherein the intermediate year is the year between the current year and the prospect year, and the intermediate year formula is: F0″=Y(t)·F0′ Where Y is the percentage of the spatial load in the intermediate year to the spatial load in the prospective year; t is the number of years from the current year; Where A is the growth coefficient of the load in the middle year, and e is the natural constant; According to the multiple loads and the multiple input powers, based on the spatial load, a load prediction result of the power grid is determined.

2. The method according to claim 1, characterized in that Determining the load prediction result of the power grid according to the multiple loads and the multiple input powers based on the spatial load includes: determining the load prediction result according to a load prediction formula, and the load prediction formula is as follows: F a =F0-F p -F w +F e +F d -F q In the formula, F a is the load forecast result under the active distribution network; F0 is the spatial load, F p is the photovoltaic input power, F w is the fan input power, F e is the electric vehicle load, F d is the demand side load, F q Input power for energy storage.

3. The method according to claim 1, characterized in that Predicting multiple loads in the power grid further includes: predicting photovoltaic input power in the event that the photovoltaic input power exists in the power grid; The photovoltaic input power is determined according to the photovoltaic power formula, which is: In the formula, F p is the photovoltaic input power, S is the measured solar intensity; T is the measured solar panel temperature; S ref is the light intensity under standard conditions, P ref is the output power under standard conditions; T ref is the panel temperature under standard conditions; γ is the preset maximum power temperature coefficient of the photovoltaic device.

4. The method according to claim 1, characterized in that: Predicting multiple loads in the power grid further includes: predicting the wind turbine input power if the wind turbine input power exists in the power grid; The fan input power is determined according to the fan power formula, which is: F w =min(N e ,P max ) Where N e is the optimal installed capacity of the wind turbine, P max The generation load without considering the wind turbine capacity; Where K is the wind turbine power conversion factor; C a C is the air altitude density conversion factor; t is the air temperature density correction factor; S is the swept area of ​​the wind turbine blade; is the average wind speed in the forecast year; η is the overall efficiency of the wind turbine, P max =K×C a ×C t ×S×v t 3 ×η In the formula, v t The real-time wind speed.

5. The method according to claim 1, characterized in that Predicting the multiple loads in the power grid further includes: predicting the electric vehicle load if the electric vehicle load exists in the power grid; The electric vehicle load is determined according to the electric vehicle load formula, which is: F e =N·q·D1·k1+N·(1-q)·D2·k2 In the formula, F e is the electric vehicle load; N is the number of electric vehicle positions; q is the slow charging ratio; D1 is the slow charging pile load index; k1 is the slow charging pile simultaneous rate; D2 is the fast charging pile load index; k2 is the fast charging pile simultaneous rate.

6. The method according to claim 1, characterized in that Predicting multiple loads in the power grid includes: predicting the demand side load if the demand side load exists in the power grid; When the consumption reduction rate of the demand side resource of user i′ is determined, the first single demand side load is determined according to the first single demand side load formula, and the first single demand side load formula is: In the formula, ΔP max,i′ represents the consumption reduction load under the action of i′ type demand side resources; α EE，i′ represents the consumption reduction rate of the demand-side resources of user i′; t represents the number of hours during the forecast period; β LD,i′ represents the load rate of the user under the action of load resources; Q 0,pre Indicates the electricity consumption of the user in the forecast year without considering the demand-side resources; Q 0,pre =P 0,pre ·T max Where P 0,pre is the maximum load of the user without considering the demand-side resources; T max The maximum load utilization hours for the user; or, In the case where the i′ type demand side resource of the user is adjustable, the second single demand side load of the i′ type demand side resource is determined according to the second single demand side load formula, and the second single demand side load formula is: ΔP max,i′ =P 0,pre ·m i′ ·s i′ ·r i′,j In the formula, μ i′ is the total controllable load ratio of i′ type demand side resources, σ i′ is the proportion of available demand-side resources of type i′ demand-side resources, ρ i′,j is the impact coefficient of response measure j on type i′ demand-side resources; The demand side load is determined according to the demand side load formula, and the demand side load formula is: Where n represents the number of demand-side resources owned by the user; ξ is the preset demand-side load coefficient.

7. The method according to claim 1, characterized in that Predicting multiple loads in the power grid includes: predicting energy storage input power when the energy storage input power exists in the power grid; When the energy storage device is charged, the energy storage input power is predicted according to the charging energy storage input power formula, which is: F q =-P1(t) Wherein, P1(t) is the charging power of the energy storage device; P1(t) satisfies the following formula: E(t)=(1-τ)E(t-1)+P1(t)η1Δt Wherein, E(t) is the amount of electricity of the energy storage device in time period t; E(t-1) is the amount of electricity of the energy storage device in time period t-1 before time period t; η1 is the charge and discharge efficiency of the energy storage device; τ is the self-discharge rate of the energy storage device; When the energy storage device is discharged, the energy storage input power is predicted according to the discharge energy storage input power formula, and the discharge energy storage input power formula is: F q =P2(t) Wherein, P2(t) is the discharge power of the energy storage device; P2(t) satisfies the following formula:

8. A power grid load prediction device, characterized in that: include: The prediction module is used to predict the spatial load of the power grid, as well as the loads of various load devices in the power grid and the input power of various power supply devices to the power grid, wherein the various loads include at least one of the following: electric vehicle load, demand side load; the various input powers include at least one of the following: photovoltaic input power, wind turbine input power, energy storage input power, and the prediction module includes: a first prediction unit, the first prediction unit is used to predict the spatial load; in the case of predicting the spatial load of the prospect year, the spatial load of the prospect year is predicted by the prospect year formula, wherein the prospect year formula is: Where F0′ is the prediction result of spatial load in the future year; m is the number of land uses in the spatial grid; D i is the floor space-load characteristic curve of the unit building of the i-th type of building; S i is the floor area of ​​the i-th type of building; The first prediction unit is also used to predict the space load of the intermediate year by using the intermediate year formula when predicting the space load of the intermediate year, wherein the intermediate year is the year between the current year and the prospect year, and the intermediate year formula is: F0″=Y(t)·F0′ Where Y is the percentage of the spatial load in the intermediate year to the spatial load in the prospective year; t is the number of years from the current year; Where A is the growth coefficient of the load in the middle year, and e is the natural constant; A determination module is used to determine the load prediction result of the power grid based on the spatial load according to the multiple loads and the multiple input powers.

9. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the power grid load forecasting method described in any one of claims 1 to 7.

Images