An AI-based power grid data management system

Abstract

This invention relates to the field of power grid data analysis and management technology, and in particular to a power grid data management system based on artificial intelligence. The invention uses a feature aggregation module to plot dynamic tracking curves for each energy storage device, a dynamic analysis module to extract dynamic parameters from these curves, and a comparison of these dynamic parameters with preset thresholds to determine the dynamic fatigue state of each energy storage device, thereby constructing a device dispatch cluster. The device management module determines the energy coordination estimate for the next operational evaluation period and, based on this estimate, determines the dispatch strategy for the device dispatch cluster. This achieves accurate capture of the dynamic operating status of energy storage devices and, based on performance changes during charging and discharging switching and multi-dimensional factors, formulates an intelligent dispatch strategy for the device cluster, improving the economy and reliability of power grid operation.

Description

Technical Field

[0001] This invention relates to the field of power grid data analysis and management technology, and in particular to a power grid data management system based on artificial intelligence. Background Technology

[0002] With the continuous improvement of the requirements for power supply security and reliability due to high-quality economic and social development, a large number of new energy sources with volatility, randomness, and intermittency are being connected to the grid. Distributed photovoltaic power, new energy storage systems, virtual power plants, and other new types of power operators are also being integrated into the power system. The power grid is transforming from a traditional, single-function grid into a smart and green modern grid. Traditional distribution network systems often cannot accurately capture the changing power demand of users, resulting in excessive and ineffective power consumption. Artificial intelligence technology can extract key features and patterns from massive amounts of data, efficiently characterize complex power grid systems, and improve the economic efficiency of grid operation.

[0003] For example, Chinese Patent Publication No. CN113258606A discloses an artificial intelligence-based intelligent microgrid energy management system. This system includes: a parameter acquisition module for acquiring droop control parameters of each distributed energy source; an energy selection module for selecting a first optimized energy source at the initial moment of a preset time period and selecting a second optimized energy source from the first optimized energy source at a non-initial moment of the preset time period; a parameter optimization module for optimizing the droop control parameters of the selected optimized energy source based on the state data of the distributed energy source and obtaining the microgrid stability after parameter optimization; and an energy determination module for determining the centrally controlled energy source based on the utilization rate of the channel between the control center and the first optimized energy source and the stability of the microgrid within a preset time period.

[0004] The following problems still exist in the existing technology:

[0005] Existing technologies are unable to accurately capture the dynamic operating status of energy storage devices and cannot reflect performance changes during the charging and discharging process in real time. Existing technologies cannot formulate intelligent dispatching strategies for device clusters based on performance changes during the charging and discharging process and multiple factors, which affects the economy and reliability of power grid operation. Summary of the Invention

[0006] To address this, the present invention provides an artificial intelligence-based power grid data management system to overcome the problem that existing technologies cannot formulate intelligent dispatch strategies for equipment clusters based on performance changes during equipment charging and discharging switching processes and multi-dimensional factors.

[0007] To achieve the above objectives, the present invention provides an artificial intelligence-based power grid data management system, comprising:

[0008] The power grid equipment includes power conversion equipment, power storage equipment, and power consumption equipment connected in sequence.

[0009] The feature aggregation module is connected to the power grid equipment terminal to obtain the operating status and operating power of each energy storage device during the preset current operating evaluation period, and to draw the dynamic tracking curve of each energy storage device based on the operating status and operating power.

[0010] A dynamic analysis module, which is connected to the feature aggregation module, is used to extract dynamic parameters from the dynamic following curve, determine the dynamic fatigue state of each energy storage device based on the comparison result of the dynamic parameters and the preset threshold, and construct a device call cluster based on the dynamic fatigue state.

[0011] The equipment management module is connected to the power grid equipment terminal and the dynamic analysis module, respectively. It includes an estimation unit for determining the power coordination estimate for the next operation evaluation period based on the historical data of the power conversion equipment and the power consumption equipment, and an intelligent dispatching unit for determining the dispatching strategy of the equipment call cluster based on the power coordination estimate.

[0012] The intelligent allocation unit is also used to determine the equipment operating parameters under different allocation strategies.

[0013] Furthermore, the feature aggregation module is used to construct dynamic tracking curves for each energy storage device, and the feature aggregation module includes:

[0014] The division unit is used to obtain the key time nodes for the switching of the charging and discharging states of the energy storage device within the preset current operation evaluation period, and to divide the current operation evaluation period into several first-class state sub-periods and several second-class state sub-periods based on the key time nodes.

[0015] A plotting unit, connected to the division unit, is used to plot power curve segments for each type I state sub-period and each type II state sub-period based on real-time operating power, and to determine the curve composed of the type I state sub-period and the type II state sub-period as the dynamic following curve of the energy storage device.

[0016] Among them, the power curve segment of the first-class state sub-period and the power curve segment of the second-class state sub-period increase in opposite directions on the vertical axis of the coordinate system, where the vertical axis represents the operating power and the horizontal axis represents time.

[0017] Furthermore, the dynamic parameters extracted by the dynamic analysis module from the dynamic following curve include the number of nodes at key time points within the preset current operation evaluation period and the dynamic power change of each characteristic representative time period.

[0018] The characteristic representing the time period includes a Class I state sub-time period and a Class II state sub-time period at both ends of each key time node. The dynamic change in power is determined based on the absolute value of the maximum power of the Class I state sub-time period and the absolute value of the maximum power of the Class II state sub-time period.

[0019] Furthermore, the dynamic analysis module is used to determine the dynamic fatigue state of each energy storage device, wherein,

[0020] If the number of nodes does not exceed a preset node number threshold, or the dynamic power change does not exceed a preset dynamic power change threshold, then the dynamic analysis module determines that the dynamic fatigue state of the energy storage device during the current operation evaluation period is a weak dynamic fatigue state.

[0021] If the number of nodes exceeds a preset node number threshold and the dynamic power change exceeds a preset dynamic power change threshold, then the dynamic analysis module determines that the dynamic fatigue state of the energy storage device during the current operation evaluation period is a state of strong dynamic fatigue performance.

[0022] Furthermore, the dynamic analysis module is used to construct a device call cluster, wherein,

[0023] The dynamic analysis module is used to classify several energy storage devices in a state of weak dynamic fatigue into a first device call cluster.

[0024] The dynamic analysis module is used to classify several energy storage devices exhibiting strong dynamic fatigue performance into a second device call cluster.

[0025] Furthermore, the estimation unit is used to determine the estimated amount of power coordination in the next operation evaluation period after the current operation evaluation period, wherein,

[0026] The estimation unit is used to determine the estimated amount of power conversion of the power conversion equipment in the next operation evaluation period based on historical meteorological data that meets preset reference conditions, and to determine the estimated amount of power consumption of the power consuming equipment in the next operation evaluation period based on historical meteorological data that meets preset reference conditions. The difference between the estimated amount of power conversion and the estimated amount of power consumption is determined as the estimated amount of power coordination in the next operation evaluation period.

[0027] The duration of each evaluation period is the same.

[0028] Furthermore, the preset reference conditions are determined based on meteorological data for the next operational evaluation period, including light intensity, cloud cover, and wind speed.

[0029] Furthermore, the intelligent dispatching unit is used to determine the dispatching strategy for device call clusters, wherein,

[0030] If the absolute value of the power coordination estimate does not exceed the preset coordination estimate threshold, the intelligent allocation unit determines the allocation strategy as to only call the power storage device in the first device cluster during the next operation evaluation period;

[0031] If the absolute value of the power coordination estimate exceeds the preset coordination estimate threshold, the intelligent allocation unit determines the allocation strategy as to call the power storage devices in the first device call cluster and the second device call cluster in the next operation evaluation period.

[0032] Furthermore, the intelligent dispatching unit is used to determine the device operating parameters under the condition that only the energy storage devices within the cluster are called upon for the first device, wherein,

[0033] The intelligent allocation unit is used to adjust the charging rate of the energy storage devices in the first device call cluster during the next operation evaluation period based on the positive or negative status of the energy coordination estimate.

[0034] Furthermore, the intelligent dispatching unit is used to determine the operating parameters of the energy storage devices within the first and second device dispatching clusters, wherein...

[0035] The intelligent dispatching unit is used to determine the number of junction points for the second device to call the energy storage devices in the cluster to output energy in the next operation evaluation period based on the energy coordination estimate.

[0036] The number of junction points is positively correlated with the estimated amount of electrical energy coordination.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention draws the dynamic following curve of each energy storage device through the feature aggregation module, extracts dynamic parameters from the dynamic following curve through the dynamic analysis module, determines the dynamic fatigue state of each energy storage device based on the comparison results of the dynamic parameters and preset thresholds, so as to construct a device call cluster, and determines the energy coordination estimate for the next operation evaluation period through the device management module, and determines the allocation strategy of the device call cluster based on the energy coordination estimate. Thus, it realizes the accurate capture of the dynamic operating status of energy storage devices, and formulates an intelligent allocation strategy for the device cluster based on the performance changes during the charging and discharging switching process of the devices and multi-dimensional factors, thereby improving the economy and reliability of power grid operation.

[0038] Furthermore, this invention accurately obtains the key time nodes for the switching of charging and discharging states of energy storage devices by dividing the unit, and based on this, the current operation evaluation period is meticulously divided into Class I and Class II state sub-periods, so that the charging and discharging process of the device is clearly defined in the time dimension. The drawing unit draws the power curve segments of each sub-period based on the real-time operating power and combines them into a dynamic following curve. Moreover, the power curve segments of the two types of sub-periods are opposite in direction on the vertical axis. The visual curve shape comprehensively reflects the operating status of the device, thereby realizing the accurate capture of the dynamic operating status of energy storage devices and the intelligentization of the entire process from device operating status monitoring to management decision-making.

[0039] Furthermore, this invention characterizes the number of charge-discharge cycles of the energy storage device by the number of nodes and reflects the power difference in a single state switch by the dynamic power change. When both the number of charge-discharge cycles and the power difference exceed the threshold, the combined material damage leads to poor operating conditions of the energy storage device. By constructing a group of devices in different fatigue states, the system can achieve differentiated scheduling. The weakly fatigued energy storage devices undertake more regulation, while the strongly fatigued devices undertake high-power demand scenarios on the demand side, ultimately achieving balanced management of the device group's lifespan. In turn, it enables differentiated distinction of performance changes during the charging and discharging switching process of the devices.

[0040] Furthermore, this invention combines meteorological data with historical data that meets preset reference conditions to estimate the energy conversion of power conversion equipment and the energy consumption of power consumption equipment. The difference between the two is used to determine the estimated energy coordination for the next operational evaluation period. Based on the dynamic correlation of meteorological data, this invention uses samples from historical data that are similar to the meteorological conditions of future periods for prediction. This significantly improves the adaptability of the estimation model to the actual operating environment, avoids estimation deviations caused by meteorological changes, and makes the prediction of energy conversion and consumption more in line with the actual scenario. It accurately captures the dynamic change patterns of the generation side and the load side, providing more refined data support for the supply and demand balance analysis of the power grid, thereby improving the operating efficiency and reliability of the power system.

[0041] Furthermore, this invention divides equipment clusters into dynamic fatigue states and formulates differentiated dispatch strategies based on power coordination estimates. When the power coordination estimate is small, dispatching only the first cluster of equipment is sufficient to meet the regulation requirements. However, when the estimated values ​​differ significantly, both types of cluster equipment are dispatched simultaneously. This allows for rapid response to grid supply and demand fluctuations and enhances the system's ability to cope with large-scale energy regulation. Through state classification and strategy linkage, equipment dispatch is matched with actual energy regulation needs. This avoids over-deployment of fatigued equipment in low-load scenarios while ensuring multi-cluster collaborative operation in high-load scenarios. Consequently, it achieves intelligent dispatch strategies for equipment clusters based on performance changes during equipment charging and discharging switching, combined with multi-dimensional factors, thereby improving the overall utilization efficiency of the energy storage system.

[0042] Furthermore, this invention prioritizes the use of equipment clusters in a weak dynamic fatigue state, avoiding the overuse of equipment in a strong fatigue state. This effectively reduces aging and damage caused by frequent charging and discharging or high current surges, lowering equipment operation and maintenance costs. Dynamically adjusting the charging rate based on an estimated amount of electrical energy coordination, which characterizes the degree of energy imbalance between supply and demand, enables precise energy scheduling. When there is an energy shortage, increasing the charging rate accelerates energy storage, ensuring power supply in subsequent periods. If there is energy redundancy, the charging rate is reduced to prevent safety hazards and energy loss caused by overcharging. This adaptive adjustment mechanism of the charging rate enhances the grid's ability to cope with supply and demand fluctuations, ensuring stable power system operation while also improving the flexibility of energy storage resource utilization. It enables intelligent allocation strategies for equipment clusters, improving the economy and reliability of grid operation.

[0043] Furthermore, this invention increases the number of junction points based on the estimated amount of power coordination. When energy demand is high, increasing the number of junction points can achieve distributed current transmission, reduce the current density at a single point, reduce line resistance loss and overheating risk, improve energy transmission efficiency, realize intelligent dispatching strategies for equipment clusters, and improve the economy and reliability of power grid operation. Attached Figure Description

[0044] Figure 1 This is a system block diagram of an artificial intelligence-based power grid data management system according to an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of the dynamic following curve in an embodiment of the present invention;

[0046] Figure 3 A flowchart illustrating the logic of the dynamic analysis module determining the dynamic fatigue state of each energy storage device in an embodiment of the present invention.

[0047] Figure 4 This is a flowchart illustrating the logic of how the intelligent dispatching unit determines the dispatching strategy for the device call cluster in an embodiment of the present invention. Detailed Implementation

[0048] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0049] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0050] It should be noted that in the description of this invention, the terms "upper," "lower," "inner," "outer," etc., which indicate the direction or positional relationship, are based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0051] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation" and "connection" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0052] Please see Figure 1 The diagram shown is a system block diagram of an artificial intelligence-based power grid data management system according to an embodiment of the present invention. The artificial intelligence-based power grid data management system of the present invention includes:

[0053] The power grid equipment includes power conversion equipment, power storage equipment, and power consumption equipment connected in sequence.

[0054] Specifically, in this invention, the power conversion device can be a photovoltaic power generation device, a wind power generation device, etc., the power storage device can be an energy storage battery, and the power consumption device can be an electrical building and industrial equipment, etc. It is well known to those skilled in the art that the power conversion device, the power storage device, and the power consumption device are connected in sequence by cables to realize the storage of electrical energy output by the power conversion device into the power storage device, and the transmission of electrical energy stored in the power storage device to the power consumption device for utilization as needed.

[0055] The feature aggregation module is connected to the power grid equipment terminal to obtain the operating status and operating power of each energy storage device during the preset current operating evaluation period, and to draw the dynamic tracking curve of each energy storage device based on the operating status and operating power.

[0056] Specifically, each preset operation evaluation period can be manually set by those skilled in the art according to the needs of power grid data monitoring. The duration of each operation evaluation period is in the range of [1, 3], with the unit of interval being h. Preferably, the duration of the operation evaluation period is 2h to ensure that there is enough power grid sample data for each operation evaluation period to participate in analysis and decision-making.

[0057] A dynamic analysis module, which is connected to the feature aggregation module, is used to extract dynamic parameters from the dynamic following curve, determine the dynamic fatigue state of each energy storage device based on the comparison result of the dynamic parameters and the preset threshold, and construct a device call cluster based on the dynamic fatigue state.

[0058] Specifically, the dynamic analysis module in this invention can be a CPU that supports the operation of complex algorithms, used to extract and analyze dynamic parameters of curves. This is existing technology and will not be described in detail here.

[0059] The equipment management module is connected to the power grid equipment terminal and the dynamic analysis module, respectively. It includes an estimation unit for determining the power coordination estimate for the next operation evaluation period based on the historical data of the power conversion equipment and the power consumption equipment, and an intelligent dispatching unit for determining the dispatching strategy of the equipment call cluster based on the power coordination estimate.

[0060] The intelligent allocation unit is also used to determine the equipment operating parameters under different allocation strategies.

[0061] Specifically, the device management module of the present invention, or its units, may be constructed using logic components, such as field-programmable logic components, microprocessors, processors used in computers, etc., which will not be elaborated here.

[0062] Specifically, the feature aggregation module is used to construct dynamic tracking curves for each energy storage device, and the feature aggregation module includes:

[0063] The division unit is used to obtain the key time nodes for the switching of the charging and discharging states of the energy storage device within the preset current operation evaluation period, and to divide the current operation evaluation period into several first-class state sub-periods and several second-class state sub-periods based on the key time nodes.

[0064] A plotting unit, connected to the division unit, is used to plot power curve segments for each type I state sub-period and each type II state sub-period based on real-time operating power, and to determine the curve composed of the type I state sub-period and the type II state sub-period as the dynamic following curve of the energy storage device.

[0065] Among them, the power curve segment of the first-class state sub-period and the power curve segment of the second-class state sub-period increase in opposite directions on the vertical axis of the coordinate system, where the vertical axis represents the operating power and the horizontal axis represents time.

[0066] Specifically, the present invention does not limit the way in which the charging state and the discharging state of the energy storage device are distinguished. In the present invention, the charging state and the discharging state of the energy storage device can be distinguished by the change of the current direction. The moment when the current direction of the energy storage device changes is determined as the key time node for the switching of the charging and discharging state. This is well known to those skilled in the art and will not be elaborated here.

[0067] Please see Figure 2 As shown, this is a schematic diagram of the dynamic following curve in an embodiment of the present invention. The division unit divides the current operation evaluation period into first-class state sub-periods a1, a3 and a5 and second-class state sub-periods a2, a4 and a6 based on the key time nodes of the switching of the charging and discharging state of the energy storage device within the current operation evaluation period. Among them, the power curve segments in the first-class state sub-periods a1, a3 and a5 are above the horizontal axis of the coordinate system, and the power curve segments in the second-class state sub-periods a2, a4 and a6 are below the horizontal axis of the coordinate system.

[0068] Specifically, the present invention does not limit the method of obtaining the real-time operating power of the energy storage device. The real-time power data of the device can be obtained from the battery management system (BMS) equipped inside the energy storage device. Based on the real-time operating power at several moments, the real-time operating power at each moment is fitted to generate a power curve segment in various state sub-periods. This is the prior art and will not be described in detail here.

[0069] Specifically, the present invention does not limit the division unit, which can be a data processor; the present invention does not limit the drawing unit, which can be a computer with graphics processing capabilities, and will not be elaborated here.

[0070] It is understood that the division unit of this invention identifies key time nodes by monitoring the switching of charging and discharging states. Its essence is to capture the physical turning point of energy flow and divide the time period into charging and discharging periods, which conforms to the energy conversion cycle law of energy storage devices. The plotting unit uses the positive and negative directions of the vertical axis to distinguish charging and discharging power, which is a mathematical expression based on the law of conservation of energy. Charging power is positive and discharging power is negative, so that the curve forms a mirror structure about the horizontal axis in the coordinate system. This design unifies the state switching in the time domain and the power fluctuation in the frequency domain, so that the nonlinear changes in the device's operating state are transformed into a quantifiable and analyzable curve shape.

[0071] Specifically, this invention accurately obtains the key time nodes for the switching of charging and discharging states of energy storage devices by dividing the unit, and based on this, the current operation evaluation period is meticulously divided into Class I and Class II state sub-periods, so that the charging and discharging process of the device is clearly defined in the time dimension. The drawing unit draws the power curve segments of each sub-period based on the real-time operating power and combines them into a dynamic following curve. The power curve segments of the two types of sub-periods are opposite in direction on the vertical axis. The visual curve shape comprehensively reflects the operating status of the device, thereby realizing the accurate capture of the dynamic operating status of energy storage devices and the intelligentization of the entire process from device operating status monitoring to management decision-making.

[0072] Specifically, the dynamic parameters extracted by the dynamic analysis module from the dynamic following curve include the number of nodes at key time points within the preset current operation evaluation period and the dynamic power change of each characteristic representing the time period.

[0073] The characteristic representing the time period includes a Class I state sub-time period and a Class II state sub-time period at both ends of each key time node. The dynamic change in power is determined based on the absolute value of the maximum power of the Class I state sub-time period and the absolute value of the maximum power of the Class II state sub-time period.

[0074] For example, the dynamic power change is determined as follows: the dynamic analysis module obtains a Class I state sub-period and a Class II state sub-period at both ends of any key time node, determines the absolute value of the maximum power of the Class I state sub-period and the absolute value of the maximum power of the Class II state sub-period, and determines the sum of the absolute values ​​of the maximum power of the Class I state sub-period and the absolute values ​​of the maximum power of the Class II state sub-period as the dynamic power change of the characteristic representative time period. The characteristic representative time period includes a Class I state sub-period and a Class II state sub-period at both ends of the key time node.

[0075] As will be understood by those skilled in the art, from an electrochemical perspective, the switching of charge and discharge states will trigger a cycle of phase change stress inside the battery. For example, during the charging and discharging process of a lithium-ion battery, the electrode material will undergo expansion or contraction. The higher the switching frequency, the faster the material structure damage accumulates. The dynamic change in power reflects the power fluctuation during the charging and discharging process. High fluctuations will lead to an increase in the local overpotential at the electrode and electrolyte interface, accelerating side reactions and thus increasing the battery's internal resistance.

[0076] Specifically, please refer to Figure 3 The diagram shown is a logic flowchart of the dynamic analysis module determining the dynamic fatigue state of each energy storage device according to an embodiment of the present invention. The dynamic analysis module is used to determine the dynamic fatigue state of each energy storage device.

[0077] If the number of nodes does not exceed a preset node number threshold, or the dynamic power change does not exceed a preset dynamic power change threshold, then the dynamic analysis module determines that the dynamic fatigue state of the energy storage device during the current operation evaluation period is a weak dynamic fatigue state.

[0078] If the number of nodes exceeds a preset node number threshold and the dynamic power change exceeds a preset dynamic power change threshold, then the dynamic analysis module determines that the dynamic fatigue state of the energy storage device during the current operation evaluation period is a state of strong dynamic fatigue performance.

[0079] In implementation, the preset node number threshold is determined based on the historical node number. The number of nodes of key time nodes in several operation evaluation periods with the same duration is obtained in advance, and the average number of nodes of key time nodes in several operation evaluation periods is determined as the preset node number threshold. Preferably, for an operation evaluation period with a duration of 2 hours, the preset node number threshold is 4.

[0080] In implementation, the preset power dynamic change threshold is determined based on the rated operating power of the energy storage device. The preset power dynamic change threshold is determined by multiplying the rated operating power of the energy storage device by the power dynamic change value factor. The value range of the power dynamic change value factor is [0.15, 0.2]. Preferably, the power dynamic change value factor is set to 0.18 to screen out energy storage devices with large power differences between adjacent Class I state sub-periods and a Class II state sub-period.

[0081] Specifically, this invention characterizes the number of charge-discharge cycles of an energy storage device by the number of nodes and reflects the power difference in a single state switch by the dynamic power change. When both the number of charge-discharge cycles and the power difference exceed the threshold, the combined material damage leads to poor operating conditions of the energy storage device. By constructing a group of devices in different fatigue states, the system can achieve differentiated scheduling. The weakly fatigued energy storage devices undertake more regulation, while the strongly fatigued devices undertake high-power demand scenarios on the demand side, ultimately achieving balanced management of the device group's lifespan. Furthermore, it enables differentiated distinction of performance changes during the charge-discharge switching process of the devices.

[0082] Specifically, the dynamic analysis module is used to build a device call cluster, wherein,

[0083] The dynamic analysis module is used to classify several energy storage devices in a state of weak dynamic fatigue into a first device call cluster.

[0084] The dynamic analysis module is used to classify several energy storage devices exhibiting strong dynamic fatigue performance into a second device call cluster.

[0085] Specifically, the estimation unit is used to determine the estimated amount of power coordination in the next operation evaluation period after the current operation evaluation period, wherein,

[0086] The estimation unit is used to determine the estimated amount of power conversion of the power conversion equipment in the next operation evaluation period based on historical meteorological data that meets preset reference conditions, and to determine the estimated amount of power consumption of the power consuming equipment in the next operation evaluation period based on historical meteorological data that meets preset reference conditions. The difference between the estimated amount of power conversion and the estimated amount of power consumption is determined as the estimated amount of power coordination in the next operation evaluation period.

[0087] The duration of each evaluation period is the same.

[0088] Specifically, the preset reference conditions are determined based on meteorological data for the next operational evaluation period, including light intensity, cloud cover, and wind speed.

[0089] For example, in this invention, meteorological data for the next operational evaluation period, including light intensity, cloud cover, and wind speed, can be obtained in advance. Operational evaluation sample periods that meet preset reference conditions are determined from historical meteorological data. The preset reference conditions include that the difference between the average light intensity of the next operational evaluation period and the average light intensity of the operational evaluation sample period does not exceed 10% of the average light intensity of the operational evaluation sample period, the difference between the average cloud cover of the next operational evaluation period and the average cloud cover of the operational evaluation sample period does not exceed 10% of the average cloud cover of the operational evaluation sample period, and the difference between the average wind speed of the next operational evaluation period and the average wind speed of the operational evaluation sample period does not exceed 10% of the average wind speed of the operational evaluation sample period.

[0090] Specifically, in this invention, the estimated amount of power conversion of the power conversion equipment in the next operation evaluation period can be determined based on the amount of power conversion in the operation evaluation sample period that meets the preset reference conditions. The estimated amount of power conversion is the product of the amount of power conversion in the operation evaluation sample period and the conversion fluctuation factor. The conversion fluctuation factor is set by those skilled in the art. Preferably, the value of the conversion fluctuation factor is 0.95, so that the estimated amount of power conversion has a redundancy relative to the amount of power conversion in the operation evaluation sample period, so as to avoid the problem of energy imbalance on the supply and demand side caused by the estimated amount of power conversion not meeting expectations.

[0091] Specifically, in this invention, the estimated energy consumption of the power conversion equipment in the next operation evaluation period can be determined based on the energy consumption in the operation evaluation sample period that meets the preset reference conditions. The estimated energy consumption is the product of the energy consumption in the operation evaluation sample period and the consumption fluctuation factor. The consumption fluctuation factor is set by those skilled in the art. Preferably, the value of the conversion fluctuation factor is 1.05, so that the estimated energy consumption has a redundancy relative to the energy consumption in the operation evaluation sample period, so as to avoid the problem of energy imbalance on the supply and demand side caused by the estimated energy consumption exceeding the expectation.

[0092] Specifically, the estimated power conversion, the power conversion amount, the estimated power consumption, and the power consumption are all products of power and time, and their units are all kilowatt-hours. In practice, they can be calculated based on the integration of the power curve and time, which is existing technology and will not be elaborated here.

[0093] Specifically, irradiance, cloud cover, and wind speed are key factors affecting the efficiency of photovoltaic and wind power generation. This invention combines meteorological data with historical data that meets preset reference conditions to estimate the energy conversion output of power conversion equipment and the energy consumption output of energy consumption equipment. The difference between the two is used to determine the estimated energy coordination output for the next operational evaluation period. Based on the dynamic correlation of meteorological data, this invention uses samples from historical data with similar meteorological conditions to future periods for prediction, which can significantly improve the adaptability of the estimation model to the actual operating environment, avoid estimation deviations caused by meteorological changes, and make the prediction of energy conversion and consumption more in line with the actual scenario. It accurately captures the dynamic change patterns of the generation side and the load side, providing more refined data support for the supply and demand balance analysis of the power grid, thereby improving the operating efficiency and reliability of the power system.

[0094] Specifically, please refer to Figure 4 The diagram shown is a logical flowchart illustrating how the intelligent allocation unit determines the allocation strategy for device calling the cluster according to an embodiment of the present invention. The intelligent allocation unit is used to determine the allocation strategy for device calling the cluster.

[0095] If the absolute value of the power coordination estimate does not exceed the preset coordination estimate threshold, the intelligent allocation unit determines the allocation strategy as to only call the power storage device in the first device cluster during the next operation evaluation period;

[0096] If the absolute value of the power coordination estimate exceeds the preset coordination estimate threshold, the intelligent allocation unit determines the allocation strategy as to call the power storage devices in the first device call cluster and the second device call cluster in the next operation evaluation period.

[0097] Specifically, the preset coordination estimation threshold is determined based on the average rated capacity of the energy storage device. The preset coordination estimation threshold can be the product of the average rated capacity and the preset coordination threshold factor. The preset coordination threshold factor has a value range of [0.1, 0.2]. One possible value for the coordination threshold factor is 0.15.

[0098] Specifically, this invention divides equipment clusters into dynamic fatigue states and formulates differentiated dispatch strategies based on power coordination estimates. When the power coordination estimate is small, dispatching only the first cluster of equipment is sufficient to meet the regulation requirements. However, when the estimated values ​​differ significantly, both types of cluster equipment are dispatched simultaneously. This allows for rapid response to grid supply and demand fluctuations and enhances the system's ability to cope with large-scale energy regulation. Through state classification and strategy linkage, equipment dispatch is matched with actual energy regulation needs. This avoids over-deployment of fatigued equipment in low-load scenarios while ensuring multi-cluster collaborative operation in high-load scenarios. Consequently, it achieves intelligent dispatch strategies for equipment clusters based on performance changes during equipment charging and discharging switching, combined with multi-dimensional factors, thereby improving the overall utilization efficiency of the energy storage system.

[0099] Specifically, the intelligent dispatching unit is used to determine the device operating parameters under the condition that only the energy storage devices within the cluster are called upon for the first device, wherein,

[0100] The intelligent allocation unit is used to adjust the charging rate of the energy storage devices in the first device call cluster during the next operation evaluation period based on the positive or negative status of the energy coordination estimate.

[0101] Specifically, when the energy coordination estimate is positive, it indicates that there is energy redundancy. The intelligent allocation unit can reduce the charging rate to avoid overcharging of the equipment. When the energy coordination estimate is negative, it indicates that there is energy shortage. In this case, increasing the charging rate can accelerate the energy storage process of the equipment and meet the load demand in subsequent periods.

[0102] Understandably, when the system determines that only the first device is called to call the cluster, it indicates that the current power coordination estimate is at a low level. The system prioritizes devices with better performance and lower risk of lifespan loss to participate in operation, in order to reduce the overall equipment aging rate. The positive or negative sign of the power coordination estimate directly reflects the direction of energy imbalance between power grid supply and demand: if the estimate is positive, it means that there is energy redundancy, and reducing the charging rate can prevent overcharging of the equipment. If the estimate is negative, it means that there is an energy gap, and increasing the charging rate can accelerate the energy storage process of the equipment, enabling it to quickly replenish power in subsequent periods to meet load demand. By converting the positive or negative information of the power coordination estimate into charging rate adjustment commands, the system achieves refined control of equipment with low fatigue, effectively balancing the power grid supply and demand relationship while ensuring the healthy operation of the equipment.

[0103] Specifically, this invention prioritizes the use of equipment clusters in a weak dynamic fatigue state, avoiding the overuse of equipment in a strong fatigue state. This effectively reduces aging and damage caused by frequent charging and discharging or high current surges, lowering equipment operation and maintenance costs. Furthermore, by dynamically adjusting the charging rate based on an estimated amount of electrical energy coordination that characterizes the degree of energy imbalance between supply and demand, precise energy scheduling can be achieved. When there is an energy shortage, increasing the charging rate accelerates energy storage, ensuring power supply for subsequent periods. If there is energy redundancy, the charging rate is reduced to prevent safety hazards and energy loss caused by overcharging. This adaptive adjustment mechanism of the charging rate enhances the grid's ability to cope with supply and demand fluctuations, ensuring stable operation of the power system while also improving the flexibility of energy storage resource utilization. This enables intelligent allocation strategies for equipment clusters, improving the economy and reliability of grid operation.

[0104] Specifically, the intelligent dispatching unit is used to determine the operating parameters of the energy storage devices within the first and second device dispatching clusters, wherein...

[0105] The intelligent dispatching unit is used to determine the number of junction points for the second device to call the energy storage devices within the cluster to output energy in the next operation evaluation period, based on the energy coordination estimate.

[0106] The number of junction points is positively correlated with the estimated amount of electrical energy coordination.

[0107] Those skilled in the art will understand that the output of the energy storage device is connected to the junction point of the junction box via a wire, and the combined energy is then used to power energy-consuming devices in different areas. This is existing technology and will not be described in detail here.

[0108] For example, the number of junction points can be determined by: using the ratio of the absolute value of the power coordination estimate to a preset coordination estimate threshold as the expansion index of the number of junction points, and multiplying the expansion index by the current value of the number of junction points to determine the new number of junction points.

[0109] Understandably, by dynamically linking the power coordination estimate with the number of junction points, energy transmission loss can be minimized. When both weak and strong dynamic fatigue equipment groups are called simultaneously, it means that the system faces a large power regulation demand. At this time, the strong dynamic fatigue equipment group needs to bear part of the output power. Distributing the current transmission can avoid local overheating at the junction point and reduce energy loss caused by overheating. The larger the power coordination estimate, the more junction points are added to avoid local overheating at the junction point. The mechanism of adaptively adjusting the number of junction points can ensure the efficient operation of the system.

[0110] Specifically, this invention increases the number of junction points based on the estimated amount of power coordination. When energy demand is high, the increased number of junction points can achieve distributed current transmission, reduce the current density at a single point, reduce line resistance loss and overheating risk, improve energy transmission efficiency, realize intelligent dispatching strategies for equipment clusters, and improve the economy and reliability of power grid operation.

[0111] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0112] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An artificial intelligence-based power grid data management system, characterized in that, include: The power grid equipment includes power conversion equipment, power storage equipment, and power consumption equipment connected in sequence. The feature aggregation module is connected to the power grid equipment terminal to obtain the operating status and operating power of each energy storage device during the preset current operating evaluation period, and to draw the dynamic tracking curve of each energy storage device based on the operating status and operating power. A dynamic analysis module, which is connected to the feature aggregation module, is used to extract dynamic parameters from the dynamic following curve, determine the dynamic fatigue state of each energy storage device based on the comparison result of the dynamic parameters and the preset threshold, and construct a device call cluster based on the dynamic fatigue state. The equipment management module is connected to the power grid equipment terminal and the dynamic analysis module, respectively. It includes an estimation unit for determining the power coordination estimate for the next operation evaluation period based on the historical data of the power conversion equipment and the power consumption equipment, and an intelligent dispatching unit for determining the dispatching strategy of the equipment call cluster based on the power coordination estimate. The intelligent allocation unit is also used to determine the equipment operating parameters under different allocation strategies; The feature aggregation module is used to construct the dynamic tracking curves of each energy storage device. The feature aggregation module includes: The division unit is used to obtain the key time nodes for the switching of the charging and discharging states of the energy storage device within the preset current operation evaluation period, and to divide the current operation evaluation period into several first-class state sub-periods and several second-class state sub-periods based on the key time nodes. A plotting unit, connected to the division unit, is used to plot power curve segments for each type I state sub-period and each type II state sub-period based on real-time operating power, and to determine the curve composed of the type I state sub-period and the type II state sub-period as the dynamic following curve of the energy storage device. Among them, the power curve segment of the first-class state sub-period and the power curve segment of the second-class state sub-period increase in opposite directions on the vertical axis of the coordinate system, where the vertical axis of the coordinate system is the operating power and the horizontal axis is time. The dynamic parameters extracted by the dynamic analysis module from the dynamic following curve include the number of nodes at key time points within the preset current operation evaluation period and the dynamic power change of each characteristic representing the time period. The characteristic representing the time period includes a Class I state sub-time period and a Class II state sub-time period at both ends of each key time node. The dynamic power change is determined based on the absolute value of the maximum power of the Class I state sub-time period and the absolute value of the maximum power of the Class II state sub-time period. The dynamic analysis module is used to determine the dynamic fatigue state of each energy storage device, wherein... If the number of nodes does not exceed a preset node number threshold, or the dynamic power change does not exceed a preset dynamic power change threshold, then the dynamic analysis module determines that the dynamic fatigue state of the energy storage device during the current operation evaluation period is a weak dynamic fatigue state. If the number of nodes exceeds a preset node number threshold and the dynamic power change exceeds a preset dynamic power change threshold, then the dynamic analysis module determines that the dynamic fatigue state of the energy storage device during the current operation evaluation period is a state of strong dynamic fatigue performance.

2. The power grid data management system based on artificial intelligence according to claim 1, characterized in that, The dynamic analysis module is used to build a device call cluster, wherein, The dynamic analysis module is used to classify several energy storage devices in a state of weak dynamic fatigue into a first device call cluster. The dynamic analysis module is used to classify several energy storage devices exhibiting strong dynamic fatigue performance into a second device call cluster.

3. The power grid data management system based on artificial intelligence according to claim 2, characterized in that, The estimation unit is used to determine the estimated amount of power coordination for the next operating evaluation period within the current operating evaluation period, wherein, The estimation unit is used to determine the estimated amount of power conversion of the power conversion equipment in the next operation evaluation period based on historical meteorological data that meets preset reference conditions, and to determine the estimated amount of power consumption of the power consuming equipment in the next operation evaluation period based on historical meteorological data that meets preset reference conditions. The difference between the estimated amount of power conversion and the estimated amount of power consumption is determined as the estimated amount of power coordination in the next operation evaluation period. The duration of each evaluation period is the same.

4. The artificial intelligence-based power grid data management system according to claim 3, characterized in that, The preset reference conditions are determined based on meteorological data for the next operational evaluation period, including light intensity, cloud cover, and wind speed.

5. The power grid data management system based on artificial intelligence according to claim 3, characterized in that, The intelligent dispatching unit is used to determine the dispatching strategy for devices calling the cluster, wherein, If the absolute value of the power coordination estimate does not exceed the preset coordination estimate threshold, the intelligent allocation unit determines the allocation strategy as to only call the power storage device in the first device cluster during the next operation evaluation period; If the absolute value of the power coordination estimate exceeds the preset coordination estimate threshold, the intelligent allocation unit determines the allocation strategy as to call the power storage devices in the first device call cluster and the second device call cluster in the next operation evaluation period.

6. The artificial intelligence-based power grid data management system according to claim 5, characterized in that, The intelligent dispatching unit is used to determine the device operating parameters under the condition that only the energy storage devices within the cluster are called upon for the first device, wherein, The intelligent allocation unit is used to adjust the charging rate of the energy storage devices in the first device call cluster during the next operation evaluation period based on the positive or negative status of the energy coordination estimate.

7. The artificial intelligence-based power grid data management system according to claim 5, characterized in that, The intelligent dispatching unit is used to determine the operating parameters of the energy storage devices within the first and second device dispatching clusters for dispatching, wherein... The intelligent dispatching unit is used to determine the number of junction points for the second device to call the energy storage devices in the cluster to output energy in the next operation evaluation period based on the energy coordination estimate. The number of junction points is positively correlated with the estimated amount of electrical energy coordination.

Images