Intelligent scheduling method and device for wind-solar complementary energy storage power station based on time sequence analysis

Abstract

The invention relates to the technical field of wind-solar hybrid power generation, and discloses a wind-solar complementary energy storage power station intelligent scheduling method and device based on time sequence analysis, and the method comprises the steps: judging whether a target wind-solar complementary energy storage power station is in a free power generation mode or not based on the operation state of the wind-solar complementary energy storage power station; if the target wind-solar complementary energy storage power station is in the free power generation mode, collecting wind energy output data and photovoltaic output data in a plurality of period windows; performing time sequence analysis on the wind energy output data and the photovoltaic output data in the plurality of period windows, and determining the time sequence similarity of the output data in the adjacent period windows; dynamically adjusting the power generation power of the power station based on the time sequence similarity of the output data in the adjacent period windows to obtain the maximum power generation capacity of the power station; and obtaining a preset adjustment factor, and carrying out generation power allocation on the target wind-solar complementary energy storage power station based on the maximum power generation amount and the preset adjustment factor. According to the invention, efficient power generation of the target wind-solar complementary energy storage power station in different operation states is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of wind-solar hybrid power generation, and in particular to an intelligent scheduling method and device for a wind-solar complementary energy storage power station based on time series analysis. Background Art

[0002] Wind-solar hybrid energy storage power stations combine wind and solar energy systems, resulting in significant power generation instability. Because wind and solar power generation is affected by factors such as climate and weather, efficiently utilizing power generation capacity and ensuring maximum power consumption under varying power station operating conditions is a critical issue. Especially in free power generation mode, there can be a lag or mismatch between the power station's power generation instructions and the actual power generation capacity of the power generation equipment, leading to power losses or inappropriate scheduling. Summary of the Invention

[0003] In view of this, the present invention provides an intelligent scheduling method and device for a wind-solar complementary energy storage power station based on time series analysis to solve the problem that a wind-solar complementary energy storage power station cannot generate electricity efficiently under different operating conditions.

[0004] In a first aspect, the present invention provides a method for intelligent scheduling of a wind-solar complementary energy storage power station based on time series analysis, the method comprising:

[0005] Obtaining the operating status of the target wind-solar complementary energy storage power station, and judging whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station;

[0006] If the target wind-solar hybrid energy storage power station is in free power generation mode, wind power output data and photovoltaic power output data within multiple cycle windows are collected;

[0007] Perform time series analysis on wind power output data and photovoltaic power output data within multiple cycle windows to determine the time series similarity of output data within adjacent cycle windows;

[0008] Based on the time series similarity of output data in adjacent cycle windows, the power generation of the power station is dynamically adjusted to obtain the maximum power generation of the power station;

[0009] Obtain the preset adjustment factor and allocate the power generation capacity of the target wind-solar complementary energy storage power station based on the maximum power generation and the preset adjustment factor.

[0010] The intelligent scheduling method for wind-solar hybrid energy storage power stations based on time series analysis provided in this embodiment monitors the operating status of a target wind-solar hybrid energy storage power station in real time to accurately determine whether the target wind-solar hybrid energy storage power station is in free power generation mode, ensuring that the wind power generation and photovoltaic power generation systems can maximize their power generation capacity based on natural conditions. In free power generation mode, the power station is not affected by external grid scheduling or load control, effectively improving power generation efficiency and resource utilization. Furthermore, by calculating the time series similarity of output data within adjacent cycle windows, the relationship between the power station's current operating status and historical power generation patterns can be accurately determined. The power station can accurately adjust its maximum power generation, helping it adjust its power generation mode to achieve optimal power generation under different environmental and load conditions. Furthermore, the scheduling strategy for wind turbines and photovoltaic generators is optimized through preset adjustment factors, ensuring optimal wind and photovoltaic power generation output under different operating conditions. The preset adjustment factors, combined with changes in wind and solar resources and the capabilities of the generators, can intelligently adjust the generated power, reducing energy waste and improving the overall power generation stability of the power station, ensuring efficient power generation by the target wind-solar hybrid energy storage power station under different operating conditions.

[0011] In an optional embodiment, obtaining the operating status of the target wind-solar complementary energy storage power station, and determining whether the target wind-solar complementary energy storage power station is in the free power generation mode based on the operating status of the wind-solar complementary energy storage power station includes:

[0012] Obtain the communication status of the communication data path between the target wind-solar hybrid energy storage power station and the power control center;

[0013] If the communication status of the communication data path is normal, the power generation command issued by the power control center is received;

[0014] Obtain the maximum power output value of the target wind-solar hybrid energy storage power station, and compare the maximum power output value with the target power value in the power generation power instruction;

[0015] If the maximum power output value is equal to the target power value, the target wind-solar complementary energy storage power station is in free power generation mode.

[0016] The intelligent dispatching method for wind-solar complementary energy storage power stations based on time series analysis provided in this embodiment determines whether the power station is in free power generation mode by real-time monitoring of the operating status of the target wind-solar complementary energy storage power station. Unlike the method that relies on external dispatching instructions, this method can autonomously adjust the power generation according to the wind and solar resource status of the power station. In particular, in the absence of external grid dispatching instructions, the power station can still maximize power generation based on natural conditions. The autonomous judgment and dispatching method reduces the response lag, enabling the power station to make rapid adjustments in real time according to environmental changes and grid demand, ensuring more accurate power generation.

[0017] In an optional embodiment, obtaining the operating status of the target wind-solar complementary energy storage power station, and judging whether the target wind-solar complementary energy storage power station is in the free power generation mode based on the operating status of the wind-solar complementary energy storage power station further includes:

[0018] If the power generation instruction issued by the power control center is not received, a power generation prediction model is constructed, and the prediction results of the power generation prediction model are used to dynamically determine whether the target wind-solar complementary energy storage power station is in free power generation mode.

[0019] The intelligent scheduling method for wind-solar complementary energy storage power stations based on time series analysis provided in this embodiment uses the prediction results of the power generation prediction model to dynamically determine whether the target wind-solar complementary energy storage power station is in the free power generation mode, which can significantly improve the system's automation level and response speed and reduce dependence on external instructions.

[0020] In an optional embodiment, performing time series analysis on wind power output data and photovoltaic power output data within multiple period windows to determine time series similarity of output data within adjacent period windows includes:

[0021] Preprocessing the wind power output data and photovoltaic power output data within multiple period windows to obtain a preprocessed multidimensional data matrix;

[0022] Based on the preprocessed multidimensional data matrix, the Fourier transform algorithm is used to calculate the cross-correlation of wind power output data and photovoltaic output data in adjacent period windows.

[0023] The temporal similarity of output data in adjacent period windows is determined based on the cross-correlation coefficients of wind power output data and photovoltaic output data.

[0024] The intelligent scheduling method for wind-solar complementary energy storage power stations based on time series analysis provided in this embodiment is based on the time series characteristics of wind power output data and photovoltaic power output data, uses methods such as Fourier transform to conduct in-depth analysis of wind power and photovoltaic data, calculates the time series similarity of output data in adjacent cycle windows, and accurately predicts the trend of power generation changes by analyzing the periodic characteristics of wind and photovoltaic power generation, thereby optimizing scheduling decisions. Compared with simple prediction models, the use of time series analysis can effectively identify the relationship and regularity between wind power and photovoltaic output, improve the accuracy of prediction and the flexibility of power generation scheduling, especially for situations where wind and photovoltaic resources fluctuate greatly, and can effectively balance the power generation of the two and reduce resource waste.

[0025] In an optional embodiment, the wind power output data and photovoltaic power output data within multiple period windows are preprocessed to obtain a preprocessed multidimensional data matrix, including:

[0026] The wind power output data and photovoltaic power output data in multiple period windows are aligned according to the time series, and a preprocessed multidimensional data matrix is ​​constructed based on the aligned wind power output data and photovoltaic output data.

[0027] In an optional embodiment, the power generation capacity of the power station is dynamically adjusted based on the time series similarity of the output data in adjacent period windows to obtain the maximum power generation capacity of the power station, including:

[0028] Compare the time series similarity of the output data in adjacent cycle windows with the time series similarity threshold;

[0029] If the time series similarity of the output data in adjacent cycle windows is less than or equal to the time series similarity threshold, the maximum power generation state flag of the current cycle window is updated;

[0030] Based on the updated maximum power generation state identifier of the current cycle window, the power generation power instruction of the target wind-solar hybrid energy storage power station is updated;

[0031] The maximum power generation capacity of the power station is determined based on the updated target power generation power instruction of the wind-solar complementary energy storage power station.

[0032] The intelligent scheduling method for wind-solar-hybrid energy storage power stations based on time series analysis provided in this embodiment dynamically adjusts the power generation instructions of the target wind-solar-hybrid energy storage power stations based on the comparison results of the time series similarity of output data in adjacent cycle windows and the time series similarity threshold. This not only meets the needs of the power grid, but also maximizes the output of renewable energy, thereby reducing the waste of wind and photovoltaic power generation and improving energy utilization efficiency.

[0033] In a second aspect, the present invention provides an intelligent dispatching device for a wind-solar hybrid energy storage power station based on time series analysis, the device comprising:

[0034] A judgment module is used to obtain the operating status of the target wind-solar complementary energy storage power station, and judge whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station;

[0035] A collection module is used to collect wind power output data and photovoltaic power output data within multiple cycle windows if the target wind-solar hybrid energy storage power station is in free power generation mode;

[0036] The time series analysis module is used to perform time series analysis on wind power output data and photovoltaic power output data in multiple cycle windows and determine the time series similarity of output data in adjacent cycle windows;

[0037] An adjustment module is used to dynamically adjust the power generation of the power station based on the time series similarity of the output data in adjacent cycle windows to obtain the maximum power generation of the power station;

[0038] The allocation module is used to obtain a preset adjustment factor and allocate the power generation power of the target wind-solar complementary energy storage power station based on the maximum power generation and the preset adjustment factor.

[0039] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the intelligent scheduling method for wind-solar complementary energy storage power stations based on timing analysis of the above-mentioned first aspect or any corresponding embodiment thereof.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the intelligent scheduling method for a wind-solar complementary energy storage power station based on timing analysis of the above-mentioned first aspect or any corresponding embodiment thereof.

[0041] In a fifth aspect, the present invention provides a computer program product comprising computer instructions, the computer instructions being used to enable a computer to execute the intelligent scheduling method for a wind-solar complementary energy storage power station based on timing analysis of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 1 is a flow chart of an intelligent dispatching method for a wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention;

[0044] Figure 2 1 is a flow chart of another method for intelligent scheduling of a wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention;

[0045] Figure 3 1 is a flow chart of another method for intelligent scheduling of a wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention;

[0046] Figure 4 1 is a flow chart of another method for intelligent scheduling of a wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention;

[0047] Figure 5 1 is a flow chart of an intelligent dispatching method for a wind-solar hybrid energy storage power station according to an embodiment of the present invention;

[0048] Figure 6 This is a structural block diagram of an intelligent dispatching device for a wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention;

[0049] Figure 7 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0051] The following problems exist in the scheduling methods of related wind-solar hybrid energy storage power stations:

[0052] 1) The dispatching of wind-solar hybrid power stations often relies on instructions from external grid dispatching, or is based on fixed power generation forecast models. This may lead to a lag in power generation response, especially in the case of dynamic weather changes or large fluctuations in grid load. This lag may lead to excessive fluctuations in grid load, or even failure to fully utilize wind and solar resources, resulting in energy waste.

[0053] 2) Most wind-solar-combined energy storage power station dispatching technologies rely on simple linear models or empirical data for power forecasting, and lack in-depth analysis of the time series characteristics of wind and photovoltaic output data. This makes the power station less adaptable to external conditions (such as weather, load changes, etc.). Without effective time series characteristic analysis and prediction, it may be impossible to accurately grasp future power generation capacity, thereby affecting the accuracy of grid dispatching and failing to maximize the utilization of wind and solar resources.

[0054] 3) There is a lack of a dynamic feedback mechanism in the communication and interaction with the power control center. Even if the power plant is in free power generation mode, it cannot flexibly respond to grid demand or adaptively adjust the maximum power generation. This lack of dynamic interaction may result in the power plant's power generation being unable to be adjusted in a timely manner according to the actual needs of the grid, resulting in waste of resources or uneven load on the grid.

[0055] 4) Most of them rely on the instructions of the grid dispatching center for dispatching. When the grid load is low, the system often does not have the ability to independently determine whether to enter the free power generation mode. This results in the wind, solar and storage power stations failing to fully utilize their potential, especially when the grid load is low or the power demand is insufficient. They still need to wait for external instructions and cannot enter the efficient power generation state in time.

[0056] The embodiment of the present invention provides a method for intelligent scheduling of a wind-solar complementary energy storage power station based on timing analysis. It should be noted that the embodiment of the present invention provides a method for intelligent scheduling of a wind-solar complementary energy storage power station based on timing analysis, and its execution subject can be an intelligent scheduling device of a wind-solar complementary energy storage power station based on timing analysis. The intelligent scheduling device of a wind-solar complementary energy storage power station based on timing analysis can be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware, wherein the electronic device can be a server or a terminal, wherein the server in the embodiment of the present application can be a single server or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application can be a smart phone, a personal computer, a tablet computer, a wearable device, an intelligent robot, and other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0057] According to an embodiment of the present invention, an embodiment of intelligent scheduling of a wind-solar complementary energy storage power station based on timing analysis 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.

[0058] In this embodiment, a method for intelligent dispatching of a wind-solar hybrid energy storage power station based on time series analysis is provided, which can be used for the above-mentioned electronic equipment. Figure 1 Flowchart of the intelligent dispatching method of wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0059] Step S101: Acquire the operating status of a target wind-solar complementary energy storage power station, and determine whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station.

[0060] Specifically, the target wind-solar complementary energy storage power station is usually connected to the power control center through a communication system and receives power generation instructions issued by the power control center. Under normal circumstances, the power control center will issue specific power generation instructions to the target wind-solar complementary energy storage power station based on factors such as grid load demand, renewable energy power generation, and the status of the energy storage system. These instructions stipulate the power that the power station should output within a certain period of time and are usually used to balance the load demand of the grid.

[0061] Furthermore, the free power generation mode means that under specific circumstances, the target wind-solar-complementary energy storage power station is no longer constrained by the power generation power instructions issued by the power control center, but generates electricity entirely in accordance with its own natural power generation capacity (i.e., the maximum power generation value); among them, the maximum power generation value refers to the maximum output power that the wind energy and photovoltaic system can achieve under the environmental conditions where the target wind-solar-complementary energy storage power station is located. This value is based on the dynamic changes of wind speed, light intensity and other climatic factors.

[0062] Furthermore, the free power generation mode means that the actual power generation capacity of the target wind-solar-combined energy storage power station is completely determined by natural conditions and is not affected by the power generation power instructions issued by the power control center. Under this operating state, the wind-solar-combined energy storage power station will make the best use of its power generation resources to maximize its output power.

[0063] Step S102: If the target wind-solar hybrid energy storage power station is in the free power generation mode, wind power output data and photovoltaic power output data within multiple cycle windows are collected.

[0064] Specifically, if the actual power generation of the target wind-solar complementary energy storage power station is equal to its maximum power generation value (that is, the power generation capacity of the wind-solar complementary energy storage power station is completely determined by natural conditions and is not restricted by grid dispatch instructions), it can be determined that the power station has entered the free power generation mode.

[0065] Step S103 , performing time series analysis on the wind power output data and the photovoltaic power output data in a plurality of period windows, and determining the time series similarity of the output data in adjacent period windows.

[0066] Step S104 : dynamically adjusting the power generation capacity of the power station based on the time series similarity of the output data in adjacent period windows to obtain the maximum power generation capacity of the power station.

[0067] Specifically, before dynamically adjusting the power generation capacity of the power station based on the temporal similarity of the output data in adjacent cycle windows, it is necessary to determine whether the time-related characteristics of the output data in adjacent cycle windows have a peak-valley span or a seasonal span; if so, directly update and adjust the maximum power generation status identifier of the power station to obtain the maximum power generation of the power station in the current cycle window, without paying attention to the temporal similarity between the wind power and photovoltaic output data of two adjacent cycle windows.

[0068] For example, in some areas, the peak period is from 8:00 to 22:00, and the valley period is from 22:00 to 8:00 the next day. Therefore, the previous cycle period is 21:45-22:00, and the next cycle period is 22:00-22:15, which is a cross-peak and valley cycle period. The maximum power generation status indicator of the power station is directly updated and adjusted.

[0069] Furthermore, if the time-related characteristics of the output data in adjacent period windows are the same peak or the same valley or season, the time series similarity between the wind power and photovoltaic output data in two adjacent period windows is calculated.

[0070] Step S105: Obtain a preset adjustment factor, and adjust the power generation of the target wind-solar complementary energy storage power station based on the maximum power generation and the preset adjustment factor.

[0071] Specifically, in extreme weather conditions such as extremely high wind speeds and excessive solar radiation, the power generation capacity of wind-solar complementary energy storage may exceed the grid's acceptance capacity, especially in the generation of reactive power, which may cause the voltage at the grid connection point to be too high, and may even cause grid breakdown or the wind-solar complementary energy storage power station to be disconnected from the grid.

[0072] Furthermore, the preset adjustment factor is set to 1.2, that is, the power generation instruction based on 1.2 times the maximum power generation is issued to the wind power generator set and the photovoltaic power generator set, so that the wind power generator set and the photovoltaic power generator set generate electricity based on 1.2 times the maximum power generation. In order to achieve this goal, the preset multiple of the maximum power generation value is used as the adjustment factor to ensure that the power generation of the wind-solar complementary energy storage power station will not burden the power grid in extreme weather.

[0073] The intelligent scheduling method for wind-solar hybrid energy storage power stations based on time series analysis provided in this embodiment monitors the operating status of the target wind-solar hybrid energy storage power station in real time to accurately determine whether the target wind-solar hybrid energy storage power station is in free power generation mode, ensuring that the wind power generation and photovoltaic power generation systems can maximize their power generation capacity according to natural conditions. In free power generation mode, the power station is not affected by external grid scheduling or load control, which can effectively improve power generation efficiency and resource utilization. Moreover, by calculating the time series similarity of output data within adjacent cycle windows, the relationship between the current operating status of the power station and the historical power generation mode can be accurately determined. The power station can accurately adjust the maximum power generation, which helps the power station adjust the power generation mode under different environmental and load conditions to achieve the optimal power generation state. Furthermore, by presetting adjustment factors, combining time series characteristics with real-time analysis of maximum power generation, the power station's power generation can be intelligently adjusted in the absence of external grid scheduling instructions. Dynamic feedback and communication with the power control center ensure that the power generation of the power station matches the grid demand. This dynamic feedback mechanism ensures that the power station can flexibly respond to grid demand, optimize the power generation and resource scheduling of the power station, and avoid the scheduling and communication lag problems of traditional methods. The power station can not only adjust itself according to current demand, but also coordinate with the grid dispatching center through real-time feedback to ensure a stable supply of energy.

[0074] In this embodiment, a method for intelligent dispatching of a wind-solar hybrid energy storage power station based on time series analysis is provided, which can be used for the above-mentioned electronic equipment. Figure 2 Flowchart of the intelligent dispatching method of wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0075] Step S201: Acquire the operating status of the target wind-solar complementary energy storage power station, and determine whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station.

[0076] Specifically, the above step S201 includes:

[0077] Step S2011: Acquire the communication status of the communication data path between the target wind-solar hybrid energy storage power station and the power control center.

[0078] Specifically, if there is a problem with the communication data path, the target wind-solar hybrid energy storage power station will enter emergency mode and adopt a preset emergency strategy. Emergency modes include power reduction mode, temporary power generation suspension mode, and autonomous energy storage regulation mode.

[0079] Furthermore, the operating state of the target wind-solar complementary energy storage power station enters emergency mode and cannot rely entirely on external dispatching instructions. A preset emergency strategy needs to be adopted. When in power reduction mode, the wind-solar complementary energy storage power station can automatically reduce the power generation to avoid excessive power supply, and the power grid cannot be dispatched or adjusted in time. By reducing the power generation, the burden on the power grid can be reduced, and the power grid can be avoided from being overloaded due to the loss of dispatching instructions. When the power generation mode is temporarily stopped, if the communication link is disconnected for a long time and the power grid load does not allow excessive fluctuations, the system can choose to temporarily stop power generation, and the target wind-solar complementary energy storage power station enters shutdown or standby mode until communication is restored. When in autonomous energy storage adjustment mode, if the target wind-solar complementary energy storage power station has energy storage equipment, part of the power generation can be stored to reduce the direct output to the power grid until normal power generation is restored after communication is restored.

[0080] Step S2012: If the communication status of the communication data path is normal, the power generation instruction issued by the power control center is received.

[0081] Specifically, it is necessary to continuously monitor the recovery status of the communication link (i.e., the communication data path). If the link is found to be restored to normal, the emergency mode will be automatically exited to resume normal power generation scheduling. Once the communication link is restored, it is necessary to re-evaluate the instructions of the power grid dispatching center, and quickly adjust the power generation power to restore normal power output, and restore to the optimal state in time according to the real-time load and dispatching instructions.

[0082] Furthermore, the condition that the communication data path is in a normal communication state is to avoid the wind-solar complementary energy storage power station from misjudging whether it has received instructions due to communication failures, network broadband speed, etc., and it is necessary to ensure that the communication link between the wind-solar complementary energy storage power station and the power control center is normal; only when the communication data path is working normally and no scheduling instructions are received, can it be considered that the target wind-solar complementary energy storage power station enters the free power generation mode. In this case, the power generation of the target wind-solar complementary energy storage power station will no longer be restricted by the power generation power instructions of the power control center, but will autonomously adjust the power generation power according to its actual power generation capacity (such as wind speed, light, energy storage status, etc.).

[0083] Furthermore, if a communication data path detects a fault, the system should be able to trigger an alarm and record specific information about the communication data path fault for subsequent troubleshooting. An alternative communication data path can be enabled or maintenance personnel can be notified to perform a manual inspection.

[0084] Step S2013: Acquire the maximum power output value of the target wind-solar hybrid energy storage power station, and compare the maximum power output value with the target power value in the power generation power instruction.

[0085] Specifically, the maximum power output value of the target wind-solar complementary energy storage power station refers to the total rated power of all wind power generators and photovoltaic power generators in the power station. It represents the maximum electric power that the power station can provide at a certain point in time and can be obtained through the real-time monitoring system.

[0086] Furthermore, the target wind-solar-hybrid energy storage power station needs to receive a power generation instruction from the superior power control center, which is sent and received through a communication protocol (such as MODBUS, IEC61850, etc.); wherein, the power generation instruction includes a target power value, which is the power that the power control center requires the wind-solar-hybrid energy storage power station to output during the current period.

[0087] Furthermore, if the power generation instruction issued by the power control center is not received, a power generation prediction model is constructed, and the prediction results of the power generation prediction model are used to dynamically determine whether the target wind-solar complementary energy storage power station is in the free power generation mode.

[0088] Furthermore, when the target wind-solar hybrid energy storage power station does not receive a power generation instruction, indicating that the power control center has not issued a clear power dispatch requirement, and the communication data path is normal, the wind-solar hybrid energy storage power station can freely generate electricity according to its own power generation situation and dispatch requirements. Therefore, it is necessary to collect real-time data to build a power generation prediction model and dynamically determine in advance whether to enter the free power generation mode based on the prediction results; among them, real-time data includes grid load, weather, wind speed, sunlight, the real-time power generation capacity and energy storage status of the wind-solar hybrid energy storage power station. The grid load refers to the current load situation and short-term forecast of the grid, such as whether the grid load is low or whether the load is close to maximum capacity. Weather data refers to real-time meteorological data including wind speed, solar radiation and temperature, which helps predict the power generation capacity of wind and solar power. Wind speed and sunlight intensity refer to wind speed and sunlight intensity, which are key factors determining the power generation capacity of the wind-solar hybrid energy storage power station and directly affect the power generation. The energy storage status refers to the current charging state of the energy storage system and the discharge capacity and efficiency of the battery. The real-time power generation capacity of the wind-solar hybrid energy storage power station includes the output power of the wind turbine and the power generation power of the photovoltaic cell.

[0089] Furthermore, building a power generation prediction model specifically includes: acquiring meteorological data and grid load data in real time, collecting the power and charge and discharge status of energy storage batteries, and cleaning and standardizing the data to avoid noise, omissions or anomalies in the collected data; extracting time series features from meteorological data such as wind speed and light intensity, combining historical power generation data of wind-solar complementary energy storage power stations to analyze the relationship between weather conditions and power generation capacity, obtaining current load information from the grid load monitoring system, combining weather and power generation forecasts to predict grid demand; using regression analysis combined with multiple input variables including wind speed, light intensity, grid load and temperature to predict power generation capacity, and training the power generation prediction model through historical data.

[0090] Furthermore, based on real-time data, a preset logic is used to dynamically determine whether to enter the free power generation mode, the steps of which include:

[0091] 1) Monitor the load of the power grid in real time and compare it with the set threshold. If the power grid load is lower than the preset threshold, it is considered that the power grid demand is low, providing the load basis conditions for the wind-solar hybrid energy storage power station to enter the free power generation mode.

[0092] Among them, the grid load threshold is 70%. When the grid load is lower than 70%, it is determined that the grid's demand for electricity is low, and the possibility of the target wind-solar complementary energy storage power station entering the free power generation mode becomes higher. This condition will provide preliminary conditions for the wind-solar complementary energy storage power station to enter the free power generation mode.

[0093] 2) Real-time monitoring of wind speed and light intensity is used to obtain the maximum power generation capacity of the wind-solar hybrid energy storage power station through the power generation prediction model and compare it with the current grid load demand. If the obtained power generation capacity is greater than the grid load demand and the power demand of the grid is low as determined in 1), the wind-solar hybrid energy storage power station enters the free power generation mode.

[0094] 3) Real-time weather data and weather forecast data for the next few hours are obtained through the meteorological platform. The power generation prediction model is used to determine future power generation capacity. If it is determined that the future power generation capacity will significantly exceed the grid load and the low power demand condition determined in 1) is met, the decision is made to enter free power generation mode.

[0095] Among them, weather data and meteorological forecasts provide predictions of future power generation potential. Wind speed and light intensity are factors that directly affect the power generation capacity of wind-solar hybrid energy storage power stations. If the forecast shows that the wind speed will be high or the light intensity will be strong in the future, the increase in power generation capacity can be predicted and a decision on free power generation can be made in advance. For example, if the wind speed and light intensity increase significantly in the next few hours, it can be judged that the power generation capacity of the wind-solar hybrid energy storage power station will increase, thereby deciding whether to enter the free power generation mode in advance. If the forecast results show that the wind speed or light intensity can provide higher power generation, while the grid load is still low, the corresponding free power generation strategy will be adopted.

[0096] When the grid load is low and the power generation capacity of the wind-solar-storage complementary power station is greater than the grid load, the prediction model is used to determine whether to enter the free power generation mode; if the prediction shows that the grid load is insufficient to absorb the full power generation capacity of the wind-solar-storage power station, and the grid load is low, the wind-solar-storage power station can autonomously enter the free power generation mode, otherwise it will continue to wait for grid dispatch instructions.

[0097] The above judgment logic ensures that the system enters the free power generation mode not only when the grid load is low, but also combines the prediction of power generation capacity and the status of energy storage batteries through multiple conditional judgments. When judging whether to enter the free power generation mode, the system will first determine whether the grid load is low, and then compare the power generation capacity calculated by the power generation prediction model based on the real-time wind speed and light intensity, and use meteorological forecast data to predict future power generation capacity. This multi-level, multi-conditional logical judgment greatly improves the system's intelligent decision-making ability, that is, the above-mentioned free power generation mode judgment method has dynamic adjustment and online learning capabilities. When meteorological conditions or grid load changes, the system can update the model and adjust the prediction strategy in real time. For example, based on future meteorological forecast data such as wind speed and light intensity, it can predict the increase in future power generation capacity and make the decision to enter the free power generation state in advance. This adaptive capability can significantly improve the system's automation level and response speed, and reduce dependence on external instructions.

[0098] Step S2014: If the maximum power output value is equal to the target power value, the target wind-solar complementary energy storage power station is in the free power generation mode.

[0099] Step S202: If the target wind-solar hybrid energy storage power station is in free power generation mode, wind power output data and photovoltaic power output data within multiple cycle windows are collected. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0100] Step S203: Perform time series analysis on wind power output data and photovoltaic power output data in multiple cycle windows to determine the time series similarity of output data in adjacent cycle windows. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0101] Step S204: Dynamically adjust the power generation of the power station based on the time series similarity of the output data in adjacent cycle windows to obtain the maximum power generation of the power station. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0102] Step S205: Obtain a preset adjustment factor, and adjust the power generation of the target wind-solar hybrid energy storage power station based on the maximum power generation and the preset adjustment factor. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0103] The intelligent dispatching method for wind-solar complementary energy storage power stations based on time series analysis provided in this embodiment determines whether the power station is in free power generation mode by real-time monitoring of the operating status of the target wind-solar complementary energy storage power station. Unlike the method that relies on external dispatching instructions, this method can autonomously adjust the power generation according to the wind and solar resource status of the power station. In particular, in the absence of external grid dispatching instructions, the power station can still maximize power generation based on natural conditions. The autonomous judgment and dispatching method reduces the response lag, enabling the power station to make rapid adjustments in real time according to environmental changes and grid demand, ensuring more accurate power generation.

[0104] In this embodiment, a method for intelligent dispatching of a wind-solar hybrid energy storage power station based on time series analysis is provided, which can be used for the above-mentioned electronic equipment. Figure 3 Flowchart of the intelligent dispatching method of wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0105] Step S301: Obtain the operating status of the target wind-solar complementary energy storage power station, and determine whether the target wind-solar complementary energy storage power station is in free power generation mode based on the operating status of the wind-solar complementary energy storage power station. Figure 2Step S201 of the illustrated embodiment will not be described in detail here.

[0106] Step S302: If the target wind-solar hybrid energy storage power station is in free power generation mode, wind power output data and photovoltaic power output data within multiple cycle windows are collected. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0107] Step S303 : performing time series analysis on the wind power output data and the photovoltaic power output data in a plurality of period windows to determine the time series similarity of the output data in adjacent period windows.

[0108] Specifically, the above step S303 includes:

[0109] Step S3031 , preprocessing the wind power output data and photovoltaic power output data in multiple period windows to obtain a preprocessed multi-dimensional data matrix.

[0110] Specifically, the wind power output data and the photovoltaic power output data in multiple period windows are aligned according to the time series, and a pre-processed multi-dimensional data matrix is ​​constructed based on the aligned wind power output data and photovoltaic output data.

[0111] Furthermore, wind power output data and photovoltaic power output data within a certain time period are collected, and the wind power output data and photovoltaic power output data are aligned according to the time series, that is, wind power output data and photovoltaic power output data within multiple period windows are obtained, each period window contains multiple data collection sample points, and a multidimensional matrix is ​​constructed. The multidimensional matrix includes the number of data collection samples, wind power output characteristics, photovoltaic output characteristics, and time series characteristic information.

[0112] Furthermore, ensure data format consistency: Data samples are usually collected by sensors and transmitted through a real-time data acquisition system. Ensure that the timestamps of these data are unified, and that the timestamp correspondence between wind and photovoltaic data is consistent. The time series length and time interval of wind power output data and photovoltaic output data should be consistent. If there is missing data or mismatched timestamps, use interpolation or imputation methods to fill in the missing data.

[0113] Furthermore, synchronize data: If the sampling times of wind power output and photovoltaic power output are not completely consistent, that is, the sampling frequencies are different, the sampling frequencies can be unified through the resampling method, and then the data can be synchronized through the interpolation method to ensure that wind power and photovoltaic power output data are available at each time point.

[0114] Furthermore, the multidimensional data matrix E corresponding to the i-th period window i Expressed as:

[0115]

[0116] Among them, TimeP represents the interval length of the period window; TimeF represents the time-related characteristics, which specifically include TimeF_1 whether the current period window is a peak period (yes / no), TimeF_2 seasonal factors (such as spring, summer, autumn and winter, etc.); Fw1 represents the wind power output characteristics, which specifically include wind speed Fw 1- 1. Wind direction Fw 1- 2 and wind power generation Fw 1- 3; Fl2 represents the photovoltaic output characteristics, which specifically include the sunshine intensity Fl 2- 1. Photovoltaic panel temperature Fl 2- 2. Photovoltaic power generation Fl 2- 3, etc.; Tp1 represents the first data sampling time point in the cycle window, TP2 represents the second data sampling time point after Tp1 with a fixed interval; TP n Indicates the last sampling time point in the cycle window; n indicates the number of samples taken at fixed intervals in the cycle window; data indicates wind power and photovoltaic power output data.

[0117] For example, the multidimensional data matrix E corresponding to the i-th period window i , take i as 1, take 12:00-12:05 as a period window, the period window interval of TimeP is within 5 minutes, and collect data samples corresponding to wind power output data and photovoltaic output data every 3 seconds in the period window, specifically including the corresponding wind power output characteristics and photovoltaic output characteristics. A total of 50 data are collected, and the value of n is 50. There will be data at 50 time points (sampling moments), which can describe in detail the changes in wind power and photovoltaic output in the period window of 12:00-12:05.

[0118] Step S3032 : Based on the pre-processed multidimensional data matrix, a Fourier transform algorithm is used to calculate the cross-correlation coefficients of the wind power output data and the photovoltaic power output data in adjacent period windows.

[0119] Specifically, the calculation formula for the cross-correlation coefficient of wind power output data and the cross-correlation coefficient of photovoltaic power output data in adjacent period windows is as follows:

[0120]

[0121] in, represents the cross-correlation coefficient between the i-th cycle window and its adjacent j-th cycle window regarding the wind energy output feature Fw1; represents the cross-correlation coefficient between the ith cycle window and its adjacent jth cycle window with respect to the photovoltaic output feature Fl2; E i(Fw1) represents the multidimensional data matrix E in the i-th period window i Wind power output data in E j (Fw1) represents the multidimensional data matrix E in the jth period window j PV output data in .

[0122] Step S3033 : determining the time series similarity of the output data in adjacent period windows based on the cross-correlation coefficients of the wind power output data and the cross-correlation coefficients of the photovoltaic power output data.

[0123] Specifically, the calculation formula for the time series similarity of output data in adjacent cycle windows is as follows:

[0124]

[0125] Among them, α represents the weight coefficient; S i,j Indicates the temporal similarity between the output data of the i-th cycle window and its adjacent j-th cycle window output data.

[0126] Step S304: Dynamically adjust the power generation of the power station based on the time series similarity of the output data in adjacent cycle windows to obtain the maximum power generation of the power station. Figure 2 Step S204 of the illustrated embodiment will not be described in detail here.

[0127] Step S305: Obtain a preset adjustment factor, and adjust the power generation of the target wind-solar hybrid energy storage power station based on the maximum power generation and the preset adjustment factor. Figure 2 Step S205 of the illustrated embodiment will not be described in detail here.

[0128] The intelligent scheduling method for wind-solar complementary energy storage power stations based on time series analysis provided in this embodiment is based on the time series characteristics of wind power output data and photovoltaic power output data, uses methods such as Fourier transform to conduct in-depth analysis of wind power and photovoltaic data, calculates the time series similarity of output data in adjacent cycle windows, and accurately predicts the trend of power generation changes by analyzing the periodic characteristics of wind and photovoltaic power generation, thereby optimizing scheduling decisions. Compared with simple prediction models, the use of time series analysis can effectively identify the relationship and regularity between wind power and photovoltaic output, improve the accuracy of prediction and the flexibility of power generation scheduling, especially for situations where wind and photovoltaic resources fluctuate greatly, and can effectively balance the power generation of the two and reduce resource waste.

[0129] In this embodiment, a method for intelligent dispatching of a wind-solar hybrid energy storage power station based on time series analysis is provided, which can be used for the above-mentioned electronic equipment. Figure 4 Flowchart of the intelligent dispatching method of wind-solar hybrid energy storage power station based on time series analysis according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0130] Step S401: Obtain the operating status of the target wind-solar complementary energy storage power station, and determine whether the target wind-solar complementary energy storage power station is in free power generation mode based on the operating status of the wind-solar complementary energy storage power station. Figure 3 Step S301 of the illustrated embodiment will not be described in detail here.

[0131] Step S402: If the target wind-solar hybrid energy storage power station is in free power generation mode, wind power output data and photovoltaic power output data within multiple cycle windows are collected. Figure 3 Step S302 of the illustrated embodiment will not be described in detail here.

[0132] Step S403: Perform time series analysis on wind power output data and photovoltaic power output data in multiple cycle windows to determine the time series similarity of output data in adjacent cycle windows. Figure 3 Step S303 of the illustrated embodiment will not be described in detail here.

[0133] Step S404 : dynamically adjusting the power generation capacity of the power station based on the time series similarity of the output data in adjacent period windows to obtain the maximum power generation capacity of the power station.

[0134] Specifically, the above step S404 includes:

[0135] Step S4041 : Compare the time series similarity of the output data in adjacent period windows with the time series similarity threshold.

[0136] Step S4042: If the time series similarity of the output data in adjacent cycle windows is less than or equal to the time series similarity threshold, the maximum power generation state flag of the current cycle window is updated.

[0137] Specifically, the temporal similarity between the wind and photovoltaic output data in the current cycle window and the wind and photovoltaic output data in the previous cycle window is used to determine whether the maximum power generation state identification needs to be adjusted. A temporal similarity threshold θ is set. When the similarity is lower than the threshold, it is considered that the current wind and photovoltaic power generation modes have changed significantly and maximum power generation state identification scheduling is required.

[0138] Furthermore, if S i,j >θ, the power generation modes between two adjacent cycle windows are relatively consistent, and no maximum power generation state identification adjustment is required; if S i,j ≤θ, the power generation mode between two adjacent cycle windows has changed significantly, and it is necessary to adjust the maximum power generation state flag once and obtain the maximum power generation of the power station in the current cycle window. The maximum power generation includes the maximum wind power generation and the maximum photovoltaic power generation.

[0139] For example, the maximum power generation state flag of the previous update cycle window 12:00-12:05 is 0. If the time series similarity between the wind energy and photovoltaic output data of the current cycle window 12:05-12:10 and the wind energy and photovoltaic output data of the previous adjacent cycle window 12:00-12:05 is greater than the time series similarity threshold, the maximum power generation state flag of the current update cycle window is still 0; if the time series similarity between the wind energy and photovoltaic output data of the current cycle window 12:05-12:10 and the wind energy and photovoltaic output data of the previous adjacent cycle window 12:00-12:05 does not exceed the threshold, the maximum power generation state flag of the current update cycle window is adjusted from 0 to 1, and the maximum power generation of the power station in the cycle window is obtained.

[0140] Step S4043: Based on the updated maximum power generation state identifier of the current cycle window, update the power generation instruction of the target wind-solar hybrid energy storage power station.

[0141] Specifically, the power generation instruction of the target wind-solar complementary energy storage power station includes a wind power generation instruction and a photovoltaic power generation instruction.

[0142] Step S4044: determining the maximum power generation capacity of the power station based on the updated target power generation power instruction of the wind-solar complementary energy storage power station.

[0143] Specifically, when the wind and solar controller receives the maximum power generation state flag, it sends a wind power generation power instruction to the wind generator set and a photovoltaic power generation power instruction to the photovoltaic generator set, and determines the maximum power generation of the power station according to the wind power generation power instruction and the photovoltaic power generation power instruction, including the maximum wind power generation W max and the maximum photovoltaic power generation L max .

[0144] For example, the time series similarity between the wind and photovoltaic output data of the current cycle window 12:05-12:10 and the wind and photovoltaic output data of the previous cycle window 12:00-12:05 is less than the time series similarity threshold, and the maximum power generation state flag of the current updated cycle window is adjusted from 0 to 1, and the maximum wind power generation W of the power station in the cycle window is obtained. max and the maximum photovoltaic power generation L max At 12:10, the wind power generation power instruction and photovoltaic power generation power instruction of the wind-solar hybrid energy storage station are updated to determine the maximum power generation of the station at 12:10, including the maximum wind power generation W. max and the maximum photovoltaic power generation L max , from the next cycle window, take 12:10 as the window and 12:10-12:15 as the new cycle window to calculate the similarity again and update the maximum power generation state identifier.

[0145] Step S405: Obtain a preset adjustment factor, and adjust the power generation of the target wind-solar hybrid energy storage power station based on the maximum power generation and the preset adjustment factor. Figure 3 Step S305 of the illustrated embodiment will not be described in detail here.

[0146] The intelligent scheduling method for wind-solar-hybrid energy storage power stations based on time series analysis provided in this embodiment dynamically adjusts the power generation instructions of the target wind-solar-hybrid energy storage power stations based on the comparison results of the time series similarity of output data in adjacent cycle windows and the time series similarity threshold. This not only meets the needs of the power grid, but also maximizes the output of renewable energy, thereby reducing the waste of wind and photovoltaic power generation and improving energy utilization efficiency.

[0147] The following is a specific example to illustrate the specific steps of the intelligent scheduling method of a wind-solar complementary energy storage power station based on time series analysis.

[0148] Example 1:

[0149] like Figure 5 As shown in FIG, the specific steps of the intelligent dispatching method of the wind-solar hybrid energy storage power station based on time series analysis include:

[0150] S1: By real-time monitoring of the operating status of the wind-solar complementary energy storage power station, it is determined whether the current power station status is in free power generation mode. In free power generation mode, the power generation of wind and photovoltaic power generation systems is not affected by external grid scheduling or load control. The power station can autonomously generate electricity to the maximum extent according to natural conditions.

[0151] S1-1: Use remote monitoring tools to conduct real-time diagnosis and check whether the communication data path between the power plant and the power control center is in a normal communication state. If there is a problem with the communication data path, the current power plant operation state enters emergency mode and the preset emergency strategy needs to be implemented.

[0152] S1-2: If the communication data path between the power station and the power control center is in normal communication status, determine whether the power station has received the power generation instruction issued by the power control center. When the power generation instruction is received and the maximum power output value of the wind-solar complementary energy storage power station is compared with the target power value in the power generation instruction and they are consistent, the current power station operation status is free power generation mode.

[0153] S1-3: If the power generation command issued by the power control center is not received, real-time data is collected to build a power generation prediction model, and a dynamic judgment is made in advance on whether to enter the free power generation mode based on the prediction results.

[0154] S2: Based on step S1, it is determined that the current wind-solar hybrid energy storage station is in free power generation mode, and wind power output data and photovoltaic power output data in multiple cycle windows are collected. After preprocessing the wind power and photovoltaic power output data, the cross-correlation coefficient of the wind power data in adjacent cycle windows is calculated to determine the time series similarity between the wind power and photovoltaic power output data in two adjacent cycle windows.

[0155] S2-1: Collect wind power output data and photovoltaic power output data within a certain period of time and align them in time series. That is, obtain wind power output data and photovoltaic power output data within multiple period windows. Each period window contains multiple data collection sample points. Construct a multidimensional matrix. The multidimensional matrix includes the number of data collection samples, wind power output characteristics, photovoltaic output characteristics, and time series characteristic information.

[0156] S2-2: Preprocess the wind energy and photovoltaic output data collected in step S2-1 to obtain a preprocessed multidimensional data matrix.

[0157] S2-3: Based on the multiple pre-processed period window data obtained in step S2-2, a Fourier transform algorithm is used to calculate the cross-correlation coefficient of the data of adjacent period windows, and the time series similarity between the wind energy and photovoltaic output data of two adjacent period windows is determined.

[0158] S3: Based on the time-related characteristic relationship between the two adjacent cycle windows in step S2 and the preset threshold relationship of the temporal similarity between the wind power and photovoltaic output data, a judgment is made to obtain the maximum power generation of the power station in the cycle window and update and adjust the maximum power generation status indicator of the power station accordingly.

[0159] S4: Based on the maximum power generation state identifier and the corresponding maximum power generation obtained in step S3, the power generation power instruction of the wind-solar hybrid energy storage station is updated, and the maximum power generation of the power station is determined by the updated power generation power instruction.

[0160] S5: The maximum power generation based on the preset adjustment factor is used to allocate the power generation of the wind-solar complementary energy storage station, so that the wind power generator set and the photovoltaic generator set are allocated with the maximum power generation of the preset adjustment factor.

[0161] The above embodiment 1 has the following advantages:

[0162] 1) By real-time monitoring of the power station's operating status, it is accurately determined whether the power station has entered the free power generation mode, ensuring that the wind power generation and photovoltaic power generation systems can maximize their power generation capacity according to natural conditions. In the free power generation mode, the power station is not affected by external grid scheduling or load control, which can effectively improve power generation efficiency and resource utilization.

[0163] 2) By collecting and processing wind and photovoltaic output data within multiple cycle windows, constructing a multidimensional data matrix, and calculating the time series similarity of adjacent cycle windows through mathematical tools such as Fourier transform, the periodic characteristics and mutual relationships of wind and solar power generation data can be accurately captured. This time series analysis method helps to accurately predict and dispatch power generation and efficiently identify the similarities between power generation patterns and grid demand.

[0164] 3) By calculating the timing similarity between adjacent cycle windows, the relationship between the power plant’s current operating status and historical power generation patterns can be accurately determined. The power plant can precisely adjust the maximum power generation and update the status indicator in real time. This helps the power plant adjust the power generation mode under different environmental and load conditions to achieve the optimal power generation state.

[0165] 4) Combining the preset time series similarity threshold with the power generation status of the power station, the system can dynamically adjust the power generation capacity of the power station. This adjustment not only meets the needs of the power grid, but also maximizes the output of renewable energy, thereby reducing the waste of wind and photovoltaic power generation and improving energy utilization efficiency.

[0166] 5) By setting adjustment factors to optimize the deployment strategy of wind turbines and photovoltaic generators, the system can ensure that the output of wind and photovoltaic power generation can reach the optimal level under different operating conditions. The preset adjustment factors are combined with the changes in wind and solar resources and the capabilities of the generators to intelligently adjust the power generation, reduce energy waste and improve the overall power generation stability of the power station.

[0167] 6) Multiple conditional judgments ensure that the system not only enters free power generation mode when the grid load is low, but also combines the prediction of power generation capacity and the status of energy storage batteries. When determining whether to enter free power generation mode, the system will first determine whether the grid load is low, and then compare the power generation capacity calculated by the power generation prediction model based on real-time wind speed and light intensity. It also uses meteorological forecast data to predict future power generation capacity. This multi-level, multi-conditional logical judgment greatly improves the system's intelligent decision-making ability.

[0168] In this embodiment, a wind-solar hybrid energy storage power station intelligent dispatching device based on timing analysis is also provided. The device is used to implement the above-mentioned embodiments and preferred implementation methods. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0169] This embodiment provides an intelligent dispatching device for a wind-solar hybrid energy storage power station based on time series analysis. Figure 6 Shown, including:

[0170] The judgment module 601 is used to obtain the operating status of the target wind-solar complementary energy storage power station and determine whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station;

[0171] The collection module 602 is configured to collect wind power output data and photovoltaic power output data within multiple period windows if the target wind-solar hybrid energy storage power station is in a free power generation mode;

[0172] The time series analysis module 603 is used to perform time series analysis on the wind power output data and the photovoltaic power output data in multiple period windows to determine the time series similarity of the output data in adjacent period windows;

[0173] An adjustment module 604 is configured to dynamically adjust the power generation of the power station based on the time series similarity of the output data in adjacent period windows to obtain the maximum power generation of the power station;

[0174] The allocation module 605 is used to obtain a preset adjustment factor and allocate the power generation of the target wind-solar complementary energy storage power station based on the maximum power generation and the preset adjustment factor.

[0175] In some optional implementations, the determination module 601 includes:

[0176] An acquisition unit, configured to acquire the communication status of the communication data path between the target wind-solar hybrid energy storage power station and the power control center;

[0177] A receiving unit, configured to receive a power generation instruction issued by the power control center if the communication status of the communication data path is normal;

[0178] A first comparing unit is used to obtain a maximum power output value of a target wind-solar complementary energy storage power station, and compare the maximum power output value with a target power value in a power generation power instruction;

[0179] The judgment unit is used to determine whether the target wind-solar complementary energy storage power station is in a free power generation mode if the maximum power output value is equal to the target power value.

[0180] In some optional implementations, the determination module 601 further includes:

[0181] The prediction unit is used to build a power generation prediction model if it does not receive the power generation power instruction issued by the power control center, and use the prediction results of the power generation prediction model to dynamically determine whether the target wind-solar complementary energy storage power station is in the free power generation mode.

[0182] In some optional implementations, the timing analysis module 603 includes:

[0183] A preprocessing unit, configured to preprocess the wind power output data and the photovoltaic power output data within a plurality of period windows to obtain a preprocessed multidimensional data matrix;

[0184] a calculation unit, configured to calculate, based on the preprocessed multidimensional data matrix, a cross-correlation number of wind power output data and a cross-correlation number of photovoltaic power output data within adjacent period windows using a Fourier transform algorithm;

[0185] The first determining unit is configured to determine the time series similarity of the output data in adjacent period windows based on the cross-correlation coefficients of the wind power output data and the cross-correlation coefficients of the photovoltaic power output data.

[0186] In some optional embodiments, the preprocessing unit is specifically used to align the wind power output data and photovoltaic power output data in multiple period windows according to the time series, and construct a preprocessed multidimensional data matrix based on the aligned wind power output data and photovoltaic output data.

[0187] In some optional implementations, the adjustment module 604 includes:

[0188] A second comparing unit, configured to compare the time series similarity of the output data in adjacent period windows with a time series similarity threshold;

[0189] A first updating unit is configured to update the maximum power generation state identifier of the current cycle window if the time series similarity of the output data in adjacent cycle windows is less than or equal to the time series similarity threshold;

[0190] A second updating unit is configured to update a power generation instruction of a target wind-solar hybrid energy storage power station based on the updated maximum power generation state identifier of the current cycle window;

[0191] The second determining unit is used to determine the maximum power generation of the power station based on the updated target power generation power instruction of the wind-solar complementary energy storage power station.

[0192] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0193] The wind-solar complementary energy storage power station intelligent dispatching device based on timing analysis in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0194] The embodiment of the present invention also provides a computer device having the above Figure 6 The figure shows an intelligent dispatching device for a wind-solar complementary energy storage power station based on time series analysis.

[0195] See also Figure 7 , Figure 7 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of a GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0196] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0197] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0198] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0199] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0200] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0201] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0202] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0203] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. An intelligent dispatching method for a wind-solar hybrid energy storage power station based on time series analysis, characterized in that: The method comprises: Acquire the operating status of the target wind-solar complementary energy storage power station, and determine whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station; If the target wind-solar complementary energy storage power station is in the free power generation mode, collecting wind power output data and photovoltaic power output data within multiple cycle windows; Performing time series analysis on the wind power output data and the photovoltaic power output data in a plurality of periodic windows to determine time series similarity of output data in adjacent periodic windows; Dynamically adjusting the power generation of the power station based on the time series similarity of the output data in the adjacent cycle windows to obtain the maximum power generation of the power station; A preset adjustment factor is obtained, and power generation power of the target wind-solar complementary energy storage power station is allocated based on the maximum power generation and the preset adjustment factor.

2. The method according to claim 1, characterized in that The obtaining of the operating status of the target wind-solar complementary energy storage power station and determining whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station include: Obtain the communication status of the communication data path between the target wind-solar hybrid energy storage power station and the power control center; If the communication status of the communication data path is normal, receiving the power generation instruction issued by the power control center; Obtaining a maximum power output value of a target wind-solar hybrid energy storage power station, and comparing the maximum power output value with a target power value in the power generation instruction; If the maximum power output value is equal to the target power value, the target wind-solar complementary energy storage power station is in the free power generation mode.

3. The method according to claim 2, characterized in that The step of obtaining the operating status of the target wind-solar complementary energy storage power station and determining whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station further includes: If the power generation instruction issued by the power control center is not received, a power generation prediction model is constructed, and the prediction result of the power generation prediction model is used to dynamically determine whether the target wind-solar complementary energy storage power station is in the free power generation mode.

4. The method according to claim 1, wherein The performing time series analysis on the wind power output data and the photovoltaic power output data in a plurality of period windows to determine the time series similarity of the output data in adjacent period windows includes: Preprocessing the wind power output data and the photovoltaic power output data within a plurality of period windows to obtain a preprocessed multidimensional data matrix; Based on the pre-processed multidimensional data matrix, using a Fourier transform algorithm to calculate the cross-correlation coefficients of wind power output data and photovoltaic power output data in adjacent period windows; The temporal similarity of the output data in the adjacent period windows is determined based on the cross-correlation coefficient of the wind power output data and the cross-correlation coefficient of the photovoltaic power output data.

5. The method according to claim 4, characterized in that The preprocessing of the wind power output data and the photovoltaic power output data in the plurality of period windows to obtain a preprocessed multidimensional data matrix includes: The wind energy output data and the photovoltaic output data in a plurality of periodic windows are aligned in time series, and the pre-processed multi-dimensional data matrix is ​​constructed based on the aligned wind energy output data and photovoltaic output data.

6. The method according to claim 1, wherein The dynamically adjusting the power generation of the power station based on the time series similarity of the output data in the adjacent period windows to obtain the maximum power generation of the power station includes: Comparing the time series similarity of the output data in the adjacent period windows with a time series similarity threshold; If the time series similarity of the output data in the adjacent cycle windows is less than or equal to the time series similarity threshold, updating the maximum power generation state identifier of the current cycle window; Based on the updated maximum power generation state identifier of the current cycle window, the power generation power instruction of the target wind-solar hybrid energy storage power station is updated; The maximum power generation capacity of the power station is determined based on the updated target power generation power instruction of the wind-solar complementary energy storage power station.

7. An intelligent dispatching device for wind-solar hybrid energy storage power station based on time series analysis, characterized in that: The device comprises: A judgment module is used to obtain the operating status of the target wind-solar complementary energy storage power station, and judge whether the target wind-solar complementary energy storage power station is in a free power generation mode based on the operating status of the wind-solar complementary energy storage power station; a collection module, configured to collect wind power output data and photovoltaic power output data within a plurality of period windows if the target wind-solar complementary energy storage power station is in the free power generation mode; a time series analysis module, configured to perform time series analysis on the wind power output data and the photovoltaic power output data within a plurality of periodic windows, and determine time series similarity of output data within adjacent periodic windows; An adjustment module, configured to dynamically adjust the power generation capacity of the power station based on the time series similarity of the output data in the adjacent period windows to obtain the maximum power generation capacity of the power station; The allocation module is used to obtain a preset adjustment factor and allocate the power generation power of the target wind-solar complementary energy storage power station based on the maximum power generation and the preset adjustment factor.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the intelligent scheduling method for a wind-solar complementary energy storage power station based on timing analysis according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the intelligent scheduling method for a wind-solar complementary energy storage power station based on time series analysis according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the intelligent dispatching method for a wind-solar complementary energy storage power station based on time series analysis according to any one of claims 1 to 6.

Images