Source network load storage resource integrated cooperative control method

Abstract

The invention discloses a source-grid-load-storage-resource integrated cooperative control method, and belongs to the technical field of power grid management, and the method comprises the steps: carrying out the butt joint of a photovoltaic power generation system of a user, and determining a power generation module, an energy storage module and a power utilization module according to the photovoltaic power generation system; performing predictive analysis on the power generation module and the power consumption module to obtain a power generation predictive curve and a power consumption predictive curve, and generating an energy storage predictive curve according to the power generation predictive curve and the power consumption predictive curve; generating a grid-connected prediction curve according to the energy storage prediction curve and the energy storage information of the energy storage module; marking corresponding absolute grid-connected points in the grid-connected prediction curve in real time according to the energy storage information; acquiring grid-connected information in real time, and performing grid-connected management according to the grid-connected prediction curve and the grid-connected information; according to the invention, a finer and more intelligent optimal scheduling and control strategy is formulated and executed, and the output fluctuation of a photovoltaic power generation system is effectively stabilized, so that the overall stability and reliability of a power system are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid management, and specifically is a method for integrated collaborative control of source, grid, load and storage resources. Background Art

[0002] With the transformation of energy structure and the pursuit of sustainable development, the development and utilization of renewable energy has become the focus of current attention; photovoltaic power generation, as an important part of renewable energy, is widely used in power systems due to its clean, pollution-free and renewable characteristics. However, the output of photovoltaic power generation systems is affected by many factors such as weather and light intensity, and is intermittent and unstable, which poses a challenge to the stable operation of power systems. In order to meet this challenge, the power system needs to achieve coordinated control of source, grid, load and storage resources, that is, comprehensively consider the operating status of power sources (such as photovoltaic power generation), power grids, loads and energy storage systems, and ensure the stable operation and efficient utilization of the power system by optimizing scheduling and control strategies.

[0003] However, for private enterprises or individuals who use their own rooftops or open spaces to install photovoltaic power generation systems, differences in capabilities and experience lead to deficiencies in achieving integrated and coordinated control of source, grid, load and storage resources.

[0004] Based on this, in order to solve the above problems, the present invention provides an integrated collaborative control method for source, grid, load and storage resources. Summary of the invention

[0005] In order to solve the problems existing in the above scheme, the present invention provides an integrated collaborative control method for source, grid, load and storage resources.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A source-grid-load-storage resource integrated collaborative control method, the method comprising:

[0008] Step 1: Connecting to the user's photovoltaic power generation system, and determining the power generation module, energy storage module and power consumption module according to the photovoltaic power generation system;

[0009] Step 2: Perform forecast analysis on the power generation module and the power consumption module to obtain a power generation forecast curve and a power consumption forecast curve, wherein the horizontal axis of the power generation forecast curve is time and the vertical axis is the power generation forecast amount; the horizontal axis of the power consumption forecast curve is time and the vertical axis is the power consumption forecast amount; generate an energy storage forecast curve according to the power generation forecast curve and the power consumption forecast curve, wherein the horizontal axis of the energy storage forecast curve is time and the vertical axis is the energy storage forecast amount;

[0010] Furthermore, the method for predicting and analyzing the power generation module includes:

[0011] Acquire historical power generation data of the power generation module; determine variable factors that have an impact on power generation of the power generation module based on the historical power generation data, collect data on the historical power generation data based on the variable factors, obtain power generation condition data of the power generation module, and identify historical power generation corresponding to the power generation condition data based on the historical power generation data;

[0012] Set training data based on power generation condition data and historical power generation, and establish a power generation prediction model based on the training data;

[0013] Real-time data collection is performed according to variable factors to obtain power generation analysis data; the power generation analysis data is analyzed through the power generation prediction model to obtain the power generation prediction amount at the corresponding time, and the power generation prediction curve is generated according to the power generation prediction amount and the corresponding time.

[0014] Furthermore, the method for predicting and analyzing the power consumption module includes:

[0015] Establishing an electricity consumption prediction model, performing real-time analysis through the electricity consumption prediction model to obtain a predicted amount of electricity consumption at a corresponding time, marking corresponding electricity consumption prediction detailed data for the predicted amount of electricity consumption; generating an electricity consumption prediction curve according to the predicted amount of electricity consumption and the corresponding time;

[0016] The power consumption forecast detail data is visualized to obtain forecast power consumption visualization data; the forecast power consumption visualization data is displayed to the user, the user adjusts the forecast power consumption visualization data, and the power consumption forecast curve is adjusted according to the adjusted forecast power consumption visualization data.

[0017] Furthermore, the method for generating an energy storage prediction curve according to the power generation prediction curve and the power consumption prediction curve includes:

[0018] The power generation prediction curve and the power consumption prediction curve are fitted respectively to obtain the power generation prediction function and the power consumption prediction function, which are marked as FD(t) and YD(t), respectively, where t is time;

[0019] The energy storage prediction curve is calculated based on the power generation prediction function and the power consumption prediction function. The calculation formula of the energy storage prediction curve is:

[0020] CW(t)=FD(t)-YD(t);

[0021] Where: CW(t) is the energy storage prediction curve;

[0022] Generate an energy storage prediction function based on the energy storage prediction curve.

[0023] Step 3: Real-time identification of energy storage information of the energy storage module, wherein the energy storage information includes stored power, storage upper limit, and storage lower limit; generating a grid connection prediction curve according to the energy storage prediction curve and the energy storage information, wherein the horizontal axis of the grid connection prediction curve is time and the vertical axis is the grid connection prediction amount; marking the corresponding absolute grid connection point in the grid connection prediction curve in real time according to the energy storage information;

[0024] Furthermore, the method for generating a grid connection prediction curve based on the energy storage prediction curve and the energy storage information includes:

[0025] Obtain a preset energy storage plan, analyze the energy storage prediction curve and energy storage information according to the energy storage plan, and obtain the grid connection prediction amount at the corresponding time; and generate a grid connection prediction curve according to the grid connection prediction amount.

[0026] Furthermore, the method for marking the absolute grid connection point in real time in the grid connection prediction curve according to the energy storage information includes:

[0027] Identify the grid-connection prediction quantity of the grid-connection prediction curve at the corresponding time in real time, and mark the grid-connection prediction quantity as BWt, where t is time;

[0028] Identify the storage capacity and storage upper limit corresponding to the energy storage information, and mark the storage capacity and storage upper limit as CA and CX respectively;

[0029] The energy storage forecast for the corresponding time is calculated in real time according to the energy storage formula. The energy storage formula is:

[0030] CYt=BWt+CA;

[0031] Where: CYt is the predicted amount of energy storage;

[0032] An energy storage judgment model is established, and the expression of the energy storage judgment model is:

[0033]

[0034] Where: (CYt, CX) is the input data, the output data is the energy storage judgment value CP (CYt, CX), and the energy storage judgment value is 1 or 0;

[0035] The energy storage prediction value at the corresponding time is analyzed in chronological order through the energy storage judgment model to obtain the energy storage judgment value at the corresponding time;

[0036] When the energy storage judgment value is 0, continue to analyze the energy storage forecast at the corresponding time;

[0037] When the energy storage judgment value is 1, the analysis is stopped, and the corresponding absolute grid connection point is marked in the grid connection prediction curve according to the time corresponding to the energy storage judgment value.

[0038] Step 4: Obtain grid-connected information in real time, including grid-connected time period and grid-connected requirements, and perform grid-connected management based on the grid-connected prediction curve and grid-connected information.

[0039] Furthermore, the method for collecting grid-connected information includes:

[0040] The platform obtains information of each user, including user location and photovoltaic power generation system information; sets a user map according to the user information, and marks each power management area in the user map according to the corresponding power management department;

[0041] The expected grid connection data corresponding to the power management area is obtained in real time, the expected grid connection data is marked in the user map, and the grid connection information of the corresponding user is obtained by analyzing the user map through a preset information conversion model, and the grid connection information is sent to the corresponding user in real time.

[0042] Furthermore, the method for performing grid connection management according to the grid connection prediction curve and the grid connection information includes:

[0043] Mark the corresponding grid-connected time period in the grid-connected prediction curve according to the grid-connected information, and obtain the electricity price curve in real time; identify the absolute grid-connected point in the grid-connected prediction curve; mark the time corresponding to the highest price of the electricity price curve in the grid-connected time period as the maximum benefit time;

[0044] When the absolute grid connection point is not before the maximum benefit time, the grid connection process shall be carried out according to the maximum benefit time and grid connection requirements;

[0045] When the absolute grid-connected point is before the maximum benefit time, the initial grid-connected time and initial grid-connected capacity are determined according to the absolute grid-connected point and the electricity price curve, and the grid-connected processing is carried out according to the initial grid-connected time, initial grid-connected capacity and grid-connected requirements.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] By comprehensively considering the operating status of power sources (such as photovoltaic power generation), power grids, loads and energy storage systems, the present invention can formulate and implement more refined and intelligent optimization scheduling and control strategies, effectively smooth out the output fluctuations of photovoltaic power generation systems, and thus significantly improve the overall stability and reliability of the power system. At the same time, it enables power management departments to more accurately manage the power of individuals and enterprises, and reduce the adverse effects of grid connection on the power grid caused by individuals and enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. 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 are within the scope of protection of the present invention.

[0051] like Figure 1 As shown, a source-grid-load-storage resource integrated collaborative control method comprises:

[0052] Step 1: Connect to the user's photovoltaic power generation system, mark the power generation part and energy storage part in the photovoltaic power generation system as power generation module and energy storage module respectively; integrate the power consumption part of the user carried by the photovoltaic power generation system and mark it as a power consumption module.

[0053] Step 2: Perform forecast analysis on the power generation module and the power consumption module to obtain the power generation forecast curve and the power consumption forecast curve. The horizontal axis of the power generation forecast curve is time, and the vertical axis is the power generation forecast amount; the horizontal axis of the power consumption forecast curve is time, and the vertical axis is the power consumption forecast amount; determine the energy storage forecast curve based on the power generation forecast curve and the power consumption forecast curve, and the horizontal axis of the energy storage forecast curve is time, and the vertical axis is the energy storage forecast amount.

[0054] In one embodiment, the power generation forecast and power consumption forecast can be made based on the power forecast technology provided by the existing power grid department. Since the current power grid department has accumulated a large number of forecasting technologies for power generation forecast and power consumption forecast, the corresponding power generation forecast model and power consumption forecast model can be established through the corresponding technical support for forecasting; the platform can also directly establish the power generation forecast model and power consumption forecast model based on the user's historical power generation data and historical power consumption data.

[0055] In one embodiment, a method for obtaining a power generation prediction curve includes:

[0056] Obtain the historical power generation data of the power generation module, including power generation and corresponding environmental information, such as light, photovoltaic panel installation status, etc.; determine the variable factors that affect the power generation of the power generation module based on the historical power generation data, collect data on the historical power generation data based on the variable factors, obtain the power generation condition data of the power generation module, and identify the historical power generation corresponding to the power generation condition data;

[0057] Set training data based on power generation condition data and corresponding historical power generation, establish a power generation prediction model based on the training data, and then make learning adjustments based on actual power generation; for example, establish a power generation prediction model based on a neural network such as a CNN network or a DNN network, and perform training, adjustment, and verification through training data;

[0058] Real-time data collection is performed based on variable factors to obtain power generation analysis data, which is the corresponding power generation condition data; the power generation analysis data is analyzed through the power generation prediction model to obtain the power generation prediction amount at the corresponding time, and the power generation prediction curve is generated based on the power generation prediction amount and the corresponding time.

[0059] In one embodiment, a method for obtaining a power consumption forecast curve includes:

[0060] Establish an electricity consumption prediction model, conduct real-time analysis through the electricity consumption prediction model, obtain the predicted electricity consumption at the corresponding time, and generate an electricity consumption prediction curve based on the predicted electricity consumption and the corresponding time.

[0061] In one embodiment, in order to improve the accuracy of power consumption prediction, the obtained power consumption prediction amount is marked with corresponding power consumption prediction detail data, and the power consumption prediction detail data includes the power consumption of each power consumption part at the user, so as to facilitate the intuitive explanation of power consumption details to the user;

[0062] The electricity consumption forecast details data is visualized, such as displaying the predicted electricity consumption equipment, the electricity consumption of each equipment, etc. in the form of tables, graphs, etc., to obtain the predicted electricity consumption visualization data; the predicted electricity consumption visualization data is displayed to the user, and the user adjusts the predicted electricity consumption visualization data according to the actual situation, and adjusts the electricity consumption forecast curve according to the adjusted predicted electricity consumption visualization data.

[0063] In one embodiment, a method for generating an energy storage prediction curve based on a power generation prediction curve and a power consumption prediction curve includes:

[0064] The power generation prediction curve and the power consumption prediction curve are fitted respectively to obtain the power generation prediction function and the power consumption prediction function, which are marked as FD(t) and YD(t), respectively, where t is time;

[0065] The energy storage prediction curve is calculated based on the power generation prediction function and the power consumption prediction function. The calculation formula of the energy storage prediction curve is:

[0066] CW(t)=FD(t)-YD(t);

[0067] Where: CW(t) is the energy storage prediction curve;

[0068] Generate an energy storage prediction function based on the energy storage prediction curve.

[0069] Step 3: Identify the energy storage information corresponding to the energy storage module in real time. The energy storage information includes relevant information such as storage capacity, storage upper limit, storage lower limit, etc. The storage upper limit and storage lower limit represent the maximum storage capacity and minimum storage capacity allowed by the energy storage module, which can be adjusted by the user based on the benchmark set by the platform; generate a grid connection prediction curve based on the energy storage prediction curve and the energy storage information, the horizontal axis of the grid connection prediction curve is time, and the vertical axis is the grid connection prediction amount that can be provided at the corresponding time; mark the corresponding absolute grid connection point in the grid connection prediction curve in real time based on the energy storage information.

[0070] In one embodiment, a grid connection prediction curve is generated according to the energy storage prediction curve and the energy storage information, and an analysis is performed based on the energy storage scheme currently preset for the energy storage module. The energy storage scheme is the energy storage management method for power generation, energy storage, discharge, and grid connection corresponding to the user's photovoltaic power generation system. Generally, the platform optimizes and adjusts the user's original energy storage management method to obtain the energy storage scheme;

[0071] The energy storage prediction curve and energy storage information are analyzed according to the energy storage plan to obtain the storage power available for grid connection at the corresponding time, marked as the grid connection prediction amount, and then generate the grid connection prediction curve; if the expected storage power at the corresponding time is determined according to the energy storage plan, the grid connection prediction amount is subsequently determined based on the expected storage power.

[0072] In one embodiment, a grid-connected prediction curve is generated based on the energy storage prediction curve and the energy storage information. A grid-connected analysis model can be established based on a CNN network or a DNN network, and a corresponding training set is manually established for training. The training set includes input data and output data. The input data is the energy storage prediction curve and the energy storage information, and the output data is the grid-connected prediction curve. After successful training, the grid-connected analysis model is used for analysis.

[0073] In one embodiment, a method for marking an absolute grid connection point in real time in a grid connection prediction curve according to energy storage information includes:

[0074] Real-time identification of the grid-connected forecast quantity corresponding to the grid-connected forecast curve at the corresponding time, and marking the obtained grid-connected forecast quantity as BWt, where t is time;

[0075] Identify the storage capacity and storage upper limit corresponding to the energy storage information, and mark the storage capacity and storage upper limit as CA and CX respectively;

[0076] The energy storage forecast for the corresponding time is calculated in real time according to the energy storage formula. The energy storage formula is:

[0077] CYt=BWt+CA;

[0078] Where: CYt is the predicted amount of energy storage;

[0079] An energy storage judgment model is established, and the expression of the energy storage judgment model is:

[0080]

[0081] Where: (CYt, CX) is the input data, the output data is the energy storage judgment value CP (CYt, CX), and the energy storage judgment value is 1 or 0;

[0082] The energy storage prediction value at the corresponding time is analyzed in chronological order through the energy storage judgment model to obtain the energy storage judgment value at the corresponding time;

[0083] When the energy storage judgment value is 0, continue to analyze the energy storage forecast at the corresponding time;

[0084] When the energy storage judgment value is 1, the analysis is stopped, and the corresponding absolute grid connection point is marked in the grid connection prediction curve according to the time corresponding to the energy storage judgment value, that is, the curve point corresponding to the time.

[0085] Step 4: Obtain grid-connected information in real time, including grid-connected time period and grid-connected requirements, and perform grid-connected management based on the grid-connected prediction curve and grid-connected information.

[0086] In one embodiment, the method for collecting grid-connected information includes:

[0087] The platform obtains information about each user, including user location, photovoltaic power generation system information and other related data; sets up a user map based on the user information, which is used to display the location of each user, photovoltaic power generation system grid-connected related information, jurisdiction of the power department to which they belong and other related data; and marks each power management area in the user map, which is set according to the jurisdiction of the corresponding power management department;

[0088] The platform establishes an information conversion model, which is used to convert the grid-connected expectations of the power management department in the corresponding jurisdiction into grid-connected information for the corresponding users in the jurisdiction. For example, in order to improve the power quality in the jurisdiction, the power management department expects individuals, enterprises, etc. to connect to the grid in a way with less impact during the corresponding period of time. The platform converts the grid-connected expectations according to the specific user information. The information conversion model is established based on existing technologies, such as establishing an information conversion model based on a CNN network or a DNN network, and manually establishing a corresponding training set for training. The training set includes input data and output data. The input data is the grid-connected expectation data and user information of the power management department, and the output data is the grid-connected information of the corresponding user. The information conversion model is analyzed after successful training.

[0089] Obtain the expected grid-connected data corresponding to each power management area in real time, mark the obtained expected grid-connected data in the user map, and generally add it to the user information to facilitate the subsequent direct information conversion of the user; analyze the user map through the information conversion model, obtain the grid-connected information of the corresponding user, and send the grid-connected information to the corresponding user in real time.

[0090] In one embodiment, grid connection management is performed according to the grid connection prediction curve and the grid connection information. Grid connection management is performed according to the existing method according to the grid connection prediction curve and the grid connection information. For example, after waiting for the grid connection time period to be reached, grid connection is performed according to the grid connection requirements. When the grid connection time period has not been reached but the absolute grid connection point has been reached, a portion of the electricity is connected to the grid according to a preset ratio.

[0091] In one embodiment, the user conducts grid connection for economic benefits, so the maximum benefit time can be determined under the requirements of grid connection information, and the grid connection process is performed according to the maximum benefit time. That is, the difference between this embodiment and the previous embodiment is that when the grid connection period is reached, a benefit analysis is performed, the maximum benefit time is determined, and the grid connection is performed according to the maximum benefit time.

[0092] In one embodiment, the maximum benefit time can be determined by combining the current electricity price information and benefit analysis technology, such as obtaining the electricity price curve during the grid-connected period and taking the time corresponding to the highest electricity price as the maximum benefit time; based on this, the power management department can encourage users to connect to the grid during the grid-connected period by adjusting the electricity prices in different time periods.

[0093] Exemplarily, the corresponding grid-connected period is marked in the grid-connected prediction curve according to the grid-connected information, and the electricity price curve is obtained in real time. The horizontal axis of the electricity price curve is time, and the vertical axis is price. The electricity price curve is generally collected and provided by the platform. The price prediction can also be combined with the prediction technology to perform price prediction; identify the absolute grid-connected point in the grid-connected prediction curve; mark the time corresponding to the highest price of the electricity price curve in the grid-connected period as the maximum benefit time;

[0094] When the absolute grid connection point is not before the maximum benefit time, the grid connection process shall be carried out according to the maximum benefit time and grid connection requirements;

[0095] When the absolute grid-connected point is before the maximum benefit time, the initial grid-connected time and initial grid-connected quantity are determined according to the absolute grid-connected point and the electricity price curve. That is, on the premise of being no later than the absolute grid-connected point, a highest price that can last until the maximum benefit time is selected as the initial grid-connected time. It can be inferred according to the maximum benefit principle and the grid-connected prediction curve, such as inferring that the maximum benefit time and the absolute grid-connected point are the same; the grid-connected processing is carried out according to the initial grid-connected time, the initial grid-connected quantity and the grid-connected requirements; at this time, the absolute grid-connected point is not before the maximum benefit time.

[0096] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0097] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for integrated collaborative control of source, grid, load and storage resources, characterized in that: include: Step 1: Connecting to the user's photovoltaic power generation system, and determining the power generation module, energy storage module and power consumption module according to the photovoltaic power generation system; Step 2: Perform forecast analysis on the power generation module and the power consumption module to obtain a power generation forecast curve and a power consumption forecast curve, wherein the horizontal axis of the power generation forecast curve is time and the vertical axis is the power generation forecast amount; the horizontal axis of the power consumption forecast curve is time and the vertical axis is the power consumption forecast amount; generate an energy storage forecast curve according to the power generation forecast curve and the power consumption forecast curve, wherein the horizontal axis of the energy storage forecast curve is time and the vertical axis is the energy storage forecast amount; Step 3: Real-time identification of energy storage information of the energy storage module, wherein the energy storage information includes stored power, storage upper limit, and storage lower limit; generating a grid connection prediction curve according to the energy storage prediction curve and the energy storage information, wherein the horizontal axis of the grid connection prediction curve is time and the vertical axis is the grid connection prediction amount; marking the corresponding absolute grid connection point in the grid connection prediction curve in real time according to the energy storage information; Step 4: Obtain grid connection information in real time, including grid connection period and grid connection requirements, and perform grid connection management according to the grid connection prediction curve and grid connection information.

2. The integrated collaborative control method of source, grid, load and storage resources according to claim 1 is characterized in that: Methods for predictive analysis of power generation modules include: Acquire historical power generation data of the power generation module; determine variable factors that have an impact on power generation of the power generation module based on the historical power generation data, collect data on the historical power generation data based on the variable factors, obtain power generation condition data of the power generation module, and identify historical power generation corresponding to the power generation condition data based on the historical power generation data; Set training data based on power generation condition data and historical power generation, and establish a power generation prediction model based on the training data; Real-time data collection is performed according to variable factors to obtain power generation analysis data; the power generation analysis data is analyzed through the power generation prediction model to obtain the power generation prediction amount at the corresponding time, and the power generation prediction curve is generated according to the power generation prediction amount and the corresponding time.

3. The integrated collaborative control method of source, grid, load and storage resources according to claim 1 is characterized in that: Methods for predictive analysis of power consumption modules include: Establishing an electricity consumption prediction model, performing real-time analysis through the electricity consumption prediction model to obtain a predicted amount of electricity consumption at a corresponding time, marking corresponding electricity consumption prediction detailed data for the predicted amount of electricity consumption; generating an electricity consumption prediction curve according to the predicted amount of electricity consumption and the corresponding time; The power consumption forecast detail data is visualized to obtain forecast power consumption visualization data; the forecast power consumption visualization data is displayed to the user, the user adjusts the forecast power consumption visualization data, and the power consumption forecast curve is adjusted according to the adjusted forecast power consumption visualization data.

4. The integrated collaborative control method of source, grid, load and storage resources according to claim 1 is characterized in that: The method for generating an energy storage prediction curve according to a power generation prediction curve and a power consumption prediction curve includes: The power generation prediction curve and the power consumption prediction curve are fitted respectively to obtain the power generation prediction function and the power consumption prediction function, which are marked as FD(t) and YD(t), respectively, where t is time; The energy storage prediction curve is calculated based on the power generation prediction function and the power consumption prediction function. The calculation formula of the energy storage prediction curve is: CW(t)=FD(t)-YD(t); Where: CW(t) is the energy storage prediction curve; Generate an energy storage prediction function based on the energy storage prediction curve.

5. The integrated collaborative control method of source, grid, load and storage resources according to claim 1 is characterized in that: The method for generating a grid connection prediction curve based on the energy storage prediction curve and the energy storage information includes: Obtain a preset energy storage plan, analyze the energy storage prediction curve and energy storage information according to the energy storage plan, and obtain the grid connection prediction amount at the corresponding time; and generate a grid connection prediction curve according to the grid connection prediction amount.

6. The integrated collaborative control method of source, grid, load and storage resources according to claim 1 is characterized in that: Methods for marking the absolute grid connection point in real time in the grid connection prediction curve according to energy storage information include: Identify the grid-connection prediction quantity of the grid-connection prediction curve at the corresponding time in real time, and mark the grid-connection prediction quantity as BWt, where t is time; Identify the storage capacity and storage upper limit corresponding to the energy storage information, and mark the storage capacity and storage upper limit as CA and CX respectively; The energy storage forecast for the corresponding time is calculated in real time according to the energy storage formula. The energy storage formula is: CYt=BWt+CA; Where: CYt is the predicted amount of energy storage; An energy storage judgment model is established, and the expression of the energy storage judgment model is: Where: (CYt, CX) is the input data, the output data is the energy storage judgment value CP (CYt, CX), and the energy storage judgment value is 1 or 0; The energy storage prediction value at the corresponding time is analyzed in chronological order through the energy storage judgment model to obtain the energy storage judgment value at the corresponding time; When the energy storage judgment value is 0, continue to analyze the energy storage forecast at the corresponding time; When the energy storage judgment value is 1, the analysis is stopped, and the corresponding absolute grid connection point is marked in the grid connection prediction curve according to the time corresponding to the energy storage judgment value.

7. The integrated collaborative control method of source, grid, load and storage resources according to claim 1 is characterized in that: The methods for collecting grid-connected information include: The platform obtains information of each user, including user location and photovoltaic power generation system information; sets a user map according to the user information, and marks each power management area in the user map according to the corresponding power management department; The expected grid connection data corresponding to the power management area is obtained in real time, the expected grid connection data is marked in the user map, and the grid connection information of the corresponding user is obtained by analyzing the user map through a preset information conversion model, and the grid connection information is sent to the corresponding user in real time.

8. The integrated collaborative control method of source, grid, load and storage resources according to claim 1 is characterized in that: The methods for grid connection management based on grid connection prediction curve and grid connection information include: Mark the corresponding grid-connected time period in the grid-connected prediction curve according to the grid-connected information, and obtain the electricity price curve in real time; identify the absolute grid-connected point in the grid-connected prediction curve; mark the time corresponding to the highest price of the electricity price curve in the grid-connected time period as the maximum benefit time; When the absolute grid connection point is not before the maximum benefit time, the grid connection process shall be carried out according to the maximum benefit time and grid connection requirements; When the absolute grid-connected point is before the maximum benefit time, the initial grid-connected time and initial grid-connected capacity are determined according to the absolute grid-connected point and the electricity price curve, and the grid-connected processing is carried out according to the initial grid-connected time, initial grid-connected capacity and grid-connected requirements.

Images