Method and terminal for automatic execution of optical storage charging inspection station under demand side response

Abstract

The invention discloses a method and terminal for automatic execution of an optical storage charging inspection station under demand side response, a virtual power plant operation platform generates a corresponding execution strategy based on a pre-trained AI model and a time period electricity price according to preset invitation content, and the AI model comprises a user charging prediction model and a photovoltaic prediction model; an equipment end energy management system EMS generates a standby strategy according to the invitation content issued by the virtual power plant operation platform, and the standby strategy controls a power grid power value to be a difference value between an operation baseline and response capacity: if the execution strategy normally takes effect, equipment control is automatically performed according to the execution strategy in an invitation time period; the equipment end energy management system EMS executes the standby strategy to control the equipment, two sets of automatic control strategies are generated according to the data analysis and AI technology, the equipment control strategy is intelligently adjusted according to the equipment data collected in the execution process, and the safety and stability in the invitation execution process are improved.

Description

[0001] This is a divisional application of the invention patent with the application date of November 29, 2024, the application number of 202411730608.X, and the title of "A Method and Terminal for Automated Execution of a Photovoltaic Energy Storage Charging and Detection Station". Technical Field

[0002] The present invention relates to the technical field of energy storage charge and discharge regulation, and particularly to a method and terminal for automated execution of a photovoltaic energy storage charging and detection station under demand response. Background Art

[0003] A virtual power plant is a concept that centrally manages and schedules dispersed energy resources (such as solar photovoltaic power, wind power generation, energy storage systems, etc.) through software and intelligent technologies. It can optimize energy production, storage, and consumption, improve energy efficiency and grid stability; demand response service is that the power grid guides users to reduce electricity consumption during peak grid demand or increase electricity consumption during off-peak periods through additional subsidies and incentives to balance the grid load, which is one of the main operating revenue sources of virtual power plants; a photovoltaic energy storage charging and detection station integrates multiple functions such as photovoltaic power generation, energy storage, charging, and battery detection, and such a station can be used as part of a virtual power plant to provide flexible energy supply and demand response for the power grid.

[0004] Currently, most demand responses are invitation-based and executed offline without system participation, resulting in slow response speed, low efficiency, and difficulty in quickly adapting to changes in grid load demand; at the same time, the method of using manual adjustment of equipment strategies has poor accuracy, cannot fully utilize the advantages of equipment to achieve maximum benefits, and fails to fully utilize historical data and real-time data for prediction and optimal decision-making.

[0005] Therefore, how to optimize demand response strategies, implement a reliable and stable automated solution, and ensure that demand response services can be executed quickly and accurately; at the same time, how to ensure the safety and stability of the system during the automated execution process is the problem to be solved currently. Summary of the Invention

[0006] The technical problems to be solved by the present invention are: to provide a method and terminal for automated execution of a photovoltaic energy storage charging and detection station under demand response, to achieve multi-strategy automated response to invitations and intelligent adjustment of equipment control strategies, to improve the revenue of the station, and to ensure the safety and stability of the system during the automated execution process.

[0007] To solve the above technical problems, the technical solution adopted by the present invention is: A method for automated execution of a photovoltaic energy storage charging and detection station under demand response, including the steps: S1. The virtual power plant operation platform generates corresponding execution strategies based on the preset invitation content, pre-trained AI models, and time-of-use electricity prices. The AI models include a user charging prediction model and a photovoltaic prediction model; S2. The device-side energy management system EMS generates a backup strategy according to the invitation content sent by the virtual power plant operation platform. The backup strategy controls the grid power value to be the difference between the operating baseline and the response capacity; S3. If the execution strategy takes effect normally, device control is automatically performed according to the execution strategy during the invitation period. Among them, the device control according to the execution strategy includes: Controlling the device according to the demand-side response demand during the invitation period. If the demand-side response is a peak shaving demand, the energy storage device is charged in advance during the valley electricity period. When in the invitation period, power is stopped from being taken from the grid, the photovoltaic system and the energy storage device are controlled to supply power, and the charging power of the charging pile is reduced; If the demand-side response is a valley filling demand, the energy storage device is discharged in advance, and during the invitation period, the energy storage device is charged at the maximum required power and users are guided to charge; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

[0008] To solve the above technical problems, the technical solution adopted by the present invention is: A method for automatic execution of a photovoltaic energy storage charging and inspection station, including the steps of: S1. The virtual power plant operation platform generates corresponding execution strategies based on the preset invitation content, pre-trained AI models, and time-of-use electricity prices. The AI models include a user charging prediction model and a photovoltaic prediction model; S2. The device-side energy management system EMS generates a backup strategy according to the invitation content sent by the virtual power plant operation platform. The backup strategy controls the grid power value to be the difference between the operating baseline and the response capacity; S3. If the execution strategy takes effect normally, device control is automatically performed according to the execution strategy during the invitation period; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

[0009] To solve the above technical problems, another technical solution adopted by the present invention is: A terminal for automatic execution of a photovoltaic energy storage charging and inspection station under demand-side response, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S1. The virtual power plant operation platform generates corresponding execution strategies based on the preset invitation content, the pre-trained AI model, and the time-of-use electricity price. The AI model includes a user charging prediction model and a photovoltaic prediction model; S2. The device-side energy management system EMS generates a backup strategy according to the invitation content sent by the virtual power plant operation platform. The backup strategy controls the grid power value to be the difference between the operating baseline and the response capacity; S3. If the execution strategy takes effect normally, device control is automatically performed according to the execution strategy during the invitation period. Among them, the device control according to the execution strategy includes: Controlling the device according to the demand response demand during the invitation period. If the demand response is a peak shaving demand, the energy storage device is charged in advance during the valley electricity period. When in the invitation period, power intake from the grid is stopped, the photovoltaic system and the energy storage device are controlled to supply power, and the charging power of the charging pile is reduced; If the demand response is a valley filling demand, the electricity in the energy storage device is emptied in advance. During the invitation period, the energy storage device is charged at the maximum required power and users are guided to charge; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

[0010] To solve the above technical problems, another technical solution adopted by the present invention is: A terminal for automatic execution of a photovoltaic energy storage charging and inspection station includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S1. The virtual power plant operation platform generates corresponding execution strategies based on the preset invitation content, the pre-trained AI model, and the time-of-use electricity price. The AI model includes a user charging prediction model and a photovoltaic prediction model; S2. The device-side energy management system EMS generates a backup strategy according to the invitation content sent by the virtual power plant operation platform. The backup strategy controls the grid power value to be the difference between the operating baseline and the response capacity; S3. If the execution strategy takes effect normally, device control is automatically performed according to the execution strategy during the invitation period; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

[0011] The beneficial effects of the present invention are as follows: It provides a method and a terminal for automatic execution of a photovoltaic energy storage charging and inspection station under demand-side response. By using data analysis and AI technology, an execution strategy and a backup strategy are generated according to the invitation content. During the invitation period, the execution strategy is preferentially used to control the equipment and the execution strategy can be automatically adjusted. When the execution strategy fails, the backup strategy is used to control the equipment. On the one hand, it realizes the automatic execution of the invitation and the intelligent adjustment of the equipment control strategy, improving the site revenue; on the other hand, two sets of equipment control strategies are generated, ensuring the safety and stability of the automatic execution process. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flowchart of a method for automatic execution of a photovoltaic energy storage charging and inspection station according to an embodiment of the present invention; Figure 2 It is a schematic flowchart of a method for automatic execution of a photovoltaic energy storage charging and inspection station according to an embodiment of the present invention; Figure 3 It is an architecture diagram of a method for automatic execution of a photovoltaic energy storage charging and inspection station according to an embodiment of the present invention; Figure 4 It is a structural diagram of a terminal for automatic execution of a photovoltaic energy storage charging and inspection station according to an embodiment of the present invention; Reference Numeral Explanation: 1. A terminal for automatic execution of a photovoltaic energy storage charging and inspection station; 2. A processor; 3. A memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] To describe in detail the technical content, the achieved objectives and the effects of the present invention, the following is described in conjunction with the embodiments and with reference to the accompanying drawings.

[0014] Please refer to Figure 1 , a method for automatic execution of a photovoltaic energy storage charging and inspection station, including the steps of: S1. The virtual power plant operation platform generates a corresponding execution strategy based on the preset invitation content, the pre-trained AI model and the time-of-use electricity price. The AI model includes a user charging prediction model and a photovoltaic prediction model; S2. The equipment-side energy management system EMS generates a backup strategy according to the invitation content issued by the virtual power plant operation platform. The backup strategy controls the grid power value to be the difference between the operation baseline and the response capacity; S3. If the execution strategy takes effect normally, the equipment is automatically controlled according to the execution strategy during the invitation period; Otherwise, the equipment-side energy management system EMS executes the backup strategy to control the equipment.

[0015] As can be seen from the above description, the beneficial effects of the present invention are as follows: A method for automatic execution of a photovoltaic energy storage charging and inspection station is provided. By using data analysis and AI technology, an execution strategy and a backup strategy are generated according to the invitation content. During the invitation period, the execution strategy is preferentially used to control the equipment and the execution strategy can be automatically adjusted. When the execution strategy fails, the backup strategy is used to control the equipment. On the one hand, it realizes the automatic execution of invitations and the intelligent adjustment of equipment control strategies, improving the site revenue; on the other hand, two sets of equipment control strategies are generated, ensuring the safety and stability of the automatic execution process.

[0016] Further, before step S1, there is also a step: S01. The power grid platform sends a demand response invitation to the virtual power plant operation platform and triggers a notification reminder to notify the invited users; S02. The invited user independently selects whether to accept the invitation. If the invitation is accepted, the invited user determines the invitation content through the virtual power plant operation platform and gives an invitation feedback. The power grid platform receives and feeds back the invitation content fed back by the invited user to the virtual power plant operation platform for invitation execution confirmation; Otherwise, end this demand response invitation.

[0017] As can be seen from the above description, the power grid platform sends a demand response invitation to the virtual power plant operation platform and notifies the users. The invited users can independently select whether to accept the invitation, making the demand response more in line with the needs and capabilities of the users; at the same time, the power grid platform sends an invitation to the virtual power plant operation platform and then the platform notifies the users. This way broadens the participation channels of the demand response, and more users can receive the invitation information, thus having the opportunity to participate in the demand response, promoting the optimal allocation of power resources, and improving the flexibility and adaptability of the entire power system.

[0018] Further, after step S02, there is also a step: S03. The virtual power plant operation platform monitors the execution process of the invitation in real time. When a key node anomaly is triggered, a notification is sent to remind the invited user; The key node anomalies include the failure to generate the execution strategy or the backup strategy, the failure to issue the execution strategy or the backup strategy, the equipment adjustment accuracy not meeting the invitation requirements, and the failure to collect data due to the equipment being offline or abnormal.

[0019] As can be seen from the above description, by monitoring the key nodes in real time and timely notifying and reminding the invited customers, the users can timely understand the system status, reduce the execution deviation caused by abnormal situations, and improve the stability and reliability of the system.

[0020] Further, the invitation content includes the invitation period, the response capacity, and the subsidy electricity price; In step S1, based on the pre-trained AI model and time-of-use electricity price, corresponding execution strategies are generated, including: Adjust the charging and discharging power magnitude and execution time period of the devices in the execution strategy according to the user charging prediction model, the photovoltaic prediction model, the invitation time period, and the response capacity; The photovoltaic prediction model is established based on historical weather data and historical operation data of the photovoltaic system of the optical storage charging and inspection station, and the user charging prediction model is established based on historical charging data of the charging piles of the optical storage charging and inspection station; According to the subsidy electricity price, compare the grid electricity price and the user charging cost to adjust the charging capacity of the devices in the execution strategy.

[0021] As can be seen from the above description, targeted adjustments are made according to different invitation contents and relevant models, and execution strategies are generated by comprehensively considering various factors, improving the rationality and adaptability of the strategies; at the same time, the electricity price difference and subsidy policies can be better utilized to improve the economic benefits of the station in demand response services.

[0022] Further, step S3 is specifically as follows: If the execution strategy takes effect normally, the energy storage device is automatically controlled according to the execution strategy during the invitation time period, the device status is monitored in real time through the virtual power plant operation platform, and the execution strategy is adjusted according to the pre-trained AI model and the collected device data, and the execution strategy is reissued at a preset interval; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

[0023] As can be seen from the above description, the pre-trained AI model combines the collected device data to adjust the execution strategy, which can continuously optimize the control strategy according to the actual situation, make the system more adaptable to different operating environments, and enhance the stability of the system; reissuing the execution strategy at a preset interval ensures that the system is always in the optimal control state and improves the reliability of the system.

[0024] Please refer to Figure 4 , a terminal for automatic execution of an optical storage charging and inspection station, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S1. The virtual power plant operation platform generates corresponding execution strategies based on the preset invitation content, the pre-trained AI model, and the time-of-use electricity price. The AI model includes a user charging prediction model and a photovoltaic prediction model; S2. The device-side energy management system EMS generates a backup strategy according to the invitation content issued by the virtual power plant operation platform, and the backup strategy controls the power value of the power grid to be the difference between the operating baseline and the response capacity; S3. If the execution strategy is in effect normally, the device is automatically controlled according to the execution strategy during the invitation period; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

[0025] From the above description, it can be seen that the beneficial effects of the present invention are: providing a terminal for automated execution of an optical storage and charging inspection station, using data analysis and AI technology to generate execution strategies and backup strategies based on the invitation content, giving priority to using execution strategies to control the equipment during the invitation period and automatically adjusting the execution strategies, and using backup strategies to control the equipment when the execution strategies fail. On the one hand, it realizes automated execution of invitations and intelligent adjustment of equipment control strategies, thereby increasing site revenue; on the other hand, it generates two sets of equipment control strategies, ensuring the safety and stability of the automated execution process.

[0026] Furthermore, before step S1, the following steps are also included: S01. The power grid platform initiates a demand-side response invitation to the virtual power plant operation platform and triggers a notification reminder to notify the invited user; S02, the inviting user independently chooses whether to accept the invitation. If the invitation is accepted, the inviting user determines the invitation content through the virtual power plant operation platform and provides invitation feedback. The power grid platform receives and provides feedback of the invitation content provided by the inviting user to the virtual power plant operation platform to confirm the invitation execution. Otherwise, end this demand-side response invitation.

[0027] From the above description, it can be seen that the power grid platform initiates a demand-side response invitation to the virtual power plant operation platform and notifies the user. The invited user can choose whether to accept the invitation, making the demand-side response more in line with the user's needs and capabilities; at the same time, the power grid platform initiates an invitation to the virtual power plant operation platform, and the platform notifies the user. This method broadens the participation channels for demand-side response. More users can receive invitation information and have the opportunity to participate in demand-side response, which promotes the optimal allocation of power resources and improves the flexibility and adaptability of the entire power system.

[0028] Furthermore, after step S02, the following steps are also included: S03, monitoring the execution process of the invitation in real time through the virtual power plant operation platform, and sending a notification to remind the inviting user when an abnormality of a key node is triggered; The key node anomalies include failures in generating the execution strategy or the backup strategy, failures in distributing the execution strategy or the backup strategy, the device adjustment accuracy not meeting the invitation requirements, and data collection failures caused by the device being offline or abnormal.

[0029] As can be seen from the above description, by monitoring key nodes in real time and promptly notifying and reminding the invited customers, users can timely understand the system status, reduce execution deviations caused by abnormal situations, and improve the stability and reliability of the system.

[0030] Furthermore, the invitation content includes the invitation time period, response capacity, and subsidy electricity price; In step S1, based on the pre-trained AI model and the time-of-use electricity price, the corresponding execution strategy is generated, including: Adjusting the charging and discharging power magnitudes and execution time periods of the devices in the execution strategy according to the user charging prediction model, the photovoltaic prediction model, the invitation time period, and the response capacity; The photovoltaic prediction model is established based on historical weather data and the historical operation data of the photovoltaic system of the integrated energy storage, charging, and inspection station, and the user charging prediction model is established based on the historical charging data of the charging piles of the integrated energy storage, charging, and inspection station; Adjusting the charging capacity of the devices in the execution strategy according to the subsidy electricity price, comparing the grid electricity price and the user charging cost.

[0031] As can be seen from the above description, targeted adjustments are made according to different invitation contents and relevant models, and multiple factors are comprehensively considered to generate the execution strategy, improving the rationality and adaptability of the strategy; at the same time, the electricity price difference and subsidy policies can be better utilized to improve the economic benefits of the station in the demand-side response service.

[0032] Furthermore, step S3 is specifically as follows: If the execution strategy takes effect normally, the energy storage device is automatically controlled according to the execution strategy during the invitation time period, the device status is monitored in real time through the virtual power plant operation platform, and the execution strategy is adjusted according to the pre-trained AI model and the collected device data, and the execution strategy is re-distributed at a preset interval; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

[0033] As can be seen from the above description, the pre-trained AI model adjusts the execution strategy in combination with the collected device data, can continuously optimize the control strategy according to the actual situation, makes the system more adaptable to different operating environments, and enhances the stability of the system; re-distributing the execution strategy at a preset interval ensures that the system is always in the optimal control state and improves the reliability of the system.

[0034] A method and a terminal for automatic execution of a photovoltaic energy storage charging and inspection station, which are applicable to the automatic execution of demand-side response by the photovoltaic energy storage charging and inspection station based on a virtual power plant operation platform.

[0035] Please refer to Figures 1 to 3 , the first embodiment of the present invention is: A method for automatic execution of a photovoltaic energy storage charging and inspection station, including the steps of: S01. The power grid platform sends a demand-side response invitation to the virtual power plant operation platform and triggers a notification reminder to notify the invited users.

[0036] In this embodiment, data transmission between the power grid platform and the virtual power plant operation platform is carried out through MQTT (in other equivalent embodiments, it is not limited to the MQTT communication protocol), and the invitation request and execution process data are synchronized.

[0037] Such as Figure 3 , the virtual power plant platform performs device scheduling and control through a cloud-edge-end architecture, where the cloud is the virtual power plant operation platform, which undertakes functions such as invitation demand filling, execution data monitoring, and AI strategy operation; the edge is the EMS energy management system deployed on the on-site industrial control computer, which undertakes functions such as device control, device data processing, and data reporting; the device side is devices such as photovoltaic, energy storage, and charging piles in the photovoltaic energy storage charging and inspection station, which accept scheduling and control and complete device actions and data reporting.

[0038] In this embodiment, the power grid platform sends an invitation to the virtual power plant operation platform through the MQTT protocol, and the content includes the invited users, demand types, execution time periods, execution capacities, etc. The platform triggers a notification reminder and notifies the users by means of text messages, in-station messages, emails, etc.

[0039] Among them, the invited users are power users registered in the power grid. The virtual power plant operation platform establishes user files and device files for each invited user, and the file information is synchronized by the virtual power plant to the power grid system for the power grid to perform scheduling.

[0040] S02. The invited user independently selects whether to accept the invitation. If the invitation is accepted, the invited user determines the invitation content through the virtual power plant operation platform and gives an invitation feedback. The power grid platform receives and feeds back the invitation content fed back by the invited user to the virtual power plant operation platform for invitation execution confirmation; Otherwise, end this demand-side response invitation.

[0041] In this embodiment, the invited user gives an invitation feedback on the virtual power plant operation platform. The feedback content includes whether to participate in this demand invitation and fills in the response capacity. The operation platform transmits the information to the power grid platform through the MQTT protocol. After the power grid platform receives the invitation filling information, it feeds back to the virtual power plant operation platform, and both parties confirm the execution of the invitation.

[0042] S03. The virtual power plant operation platform monitors the execution process of the invitation in real time, and when a key node anomaly is triggered, it sends a notification to remind the invited user. The key node anomalies include the failure to generate the execution strategy or the backup strategy, the failure to issue the execution strategy or the backup strategy, the equipment adjustment accuracy not meeting the invitation requirements, and the failure to collect data due to the equipment being offline or abnormal.

[0043] In this embodiment, the virtual power plant operation platform monitors the entire invitation process in real time, detects and alarms at each key node of the invitation response. When a key node is abnormal or manual processing is required, the system will send reminder content to the corresponding user in the form of in-station messages, text messages, emails, etc.

[0044] S1. The virtual power plant operation platform generates a corresponding execution strategy based on the preset invitation content, the pre-trained AI model, and the time-of-use electricity price. The AI model includes a user charging prediction model and a photovoltaic prediction model; the invitation content includes the invitation time period, the response capacity, and the subsidy electricity price. Among them, generating a corresponding execution strategy based on the pre-trained AI model and the time-of-use electricity price includes: Adjusting the charging and discharging power magnitude and execution time period of the equipment in the execution strategy according to the user charging prediction model, the photovoltaic prediction model, the invitation time period, and the response capacity. The photovoltaic prediction model is established based on historical weather data and the historical operation data of the photovoltaic system of the optical storage charging and inspection station, and the user charging prediction model is established based on the historical charging data of the charging piles of the optical storage charging and inspection station. Adjusting the charging capacity of the equipment in the execution strategy according to the subsidy electricity price, comparing the grid electricity price and the user charging cost.

[0045] In this embodiment, a photovoltaic prediction model is established according to historical weather data and the historical photovoltaic power generation data of the station, and combined with weather prediction data to obtain the predicted photovoltaic power generation; a prediction model is established according to the historical charging situation of the charging piles of the station combined with periodic changes (weekdays, holidays, seasons) to predict user charging data, which is used to plan the energy storage power supply and discharge strategy. The two are combined. When charging the energy storage, a certain margin is reserved to absorb the photovoltaic power generation and reduce the light curtailment rate; among them, the invitation time period and the response capacity affect the charging and discharging power magnitude and execution time period of the AI strategy control equipment; the subsidy electricity price affects the AI to weigh when charging the energy storage, and it is necessary to compare the grid electricity price and the user charging cost to ensure that the revenue from executing this invitation can reach the maximum.

[0046] Among them, when generating the strategy, at least the following requirements should be met: ensure that photovoltaic power generation gives priority to charging the charging pile, and then charges the energy storage to avoid the situation of photovoltaic power abandonment; the electricity price is distinguished according to peak, valley, and normal periods. The energy storage battery should be charged as much as possible during the valley period of the electricity price, discharged during the peak period, and charged or discharged or standby will be selected according to the consumption situation predicted by the model during the normal period of electricity to ensure the maximum peak shaving and valley filling benefits; when the invitation demand of the virtual power plant intervenes, the subsidy electricity price is generally greater than the peak-valley price difference, so the strategy required by the virtual power plant is given priority to execute.

[0047] In this embodiment, by combining the charging power prediction, photovoltaic power generation prediction, and invitation content, etc., the electric quantity of the energy storage is controlled within a certain range at the appropriate time.

[0048] Specifically, if the demand-side response is a peak shaving demand, at an appropriate time when the electricity price is low, a certain amount of electricity is charged into the energy storage in advance before the response period, and at the same time, the remaining photovoltaic power consumption is taken into account. During the peak shaving response period, power is no longer taken from the grid, but is supplied by photovoltaic and energy storage, and the charging power of the charging pile is appropriately reduced to ensure the normal power consumption of users during the response period, achieving the best power supply effect during peak shaving and maximizing the benefits of users; If the demand-side response is a valley filling demand, the energy storage is emptied in advance. During the execution of the invitation, the energy storage is charged at the required maximum power, and at the same time, users can be guided to charge in an orderly manner to ensure the best valley filling effect.

[0049] In this implementation, the generated execution strategy will be sent by the virtual power plant operation platform to the device side for preferential execution during the invitation period to control the device to automatically execute the demand-side response.

[0050] S2. The energy management system EMS on the device side generates a standby strategy according to the invitation content sent by the virtual power plant operation platform, and the standby strategy controls the grid power value to be the difference between the operation baseline and the response capacity.

[0051] S3. If the execution strategy takes effect normally, the energy storage device will be automatically controlled according to the execution strategy during the invitation period. The device status is monitored in real time through the virtual power plant operation platform, and the execution strategy is adjusted according to the pre-trained AI model and the collected device data, and the execution strategy is re-sent at a preset interval. Otherwise, the energy management system EMS on the device side executes the standby strategy to control the device.

[0052] In this embodiment, the content of the strategy includes the execution period, target SOC, execution power, battery protection parameters, etc. Devices such as photovoltaic, energy storage, and charging piles in the integrated energy station will perform device operations such as charging and discharging, limiting power usage, and adjusting grid power intake to ensure meeting the requirements of the invitation response. During the execution of the strategy, the platform will collect device operation parameters in real time, import the data results into the AI model for calculation. When there is a power deviation or the result does not match the expected effect, according to factors such as grid electricity price, charging cost, weather and photovoltaic prediction, user charging prediction, and invitation execution requirements, a device scheduling strategy will be generated, and the strategy will be adjusted and reissued to the device within a certain period to ensure normal device control. Among them, the minimum granularity of strategy control is half an hour, and a day is divided into 48 periods by half an hour to issue the strategy.

[0053] In this implementation, the judgment of whether the execution strategy takes effect normally mainly depends on the various performances of the device during operation. The following scenarios can be specifically referred to: The adjustment accuracy of the device fails to meet the invitation requirements: During the execution of the invitation, the adjustment accuracy of the device fails to meet the requirements specified in the invitation. For example, if the invitation requires the power to be controlled within a certain range during a specific period, but the actual operating power of the device deviates from this range, this indicates that the device does not perform precise control according to the predetermined strategy, and the execution strategy may have problems and does not take effect normally; The device is offline or abnormal: If the device is in an offline state and cannot normally receive or execute the execution strategy instruction, at this time, the execution strategy cannot be normally implemented on the device, and it can be determined that the execution strategy does not take effect normally; Data collection fails: During the operation of the device, problems occur in the data collection link, and the operating data of the device, such as power and electricity parameters, cannot be accurately obtained. Due to the lack of accurate data feedback, the virtual power plant operation platform cannot effectively monitor the device operation situation and cannot adjust the strategy according to the actual situation, which means that the execution strategy cannot play its normal role and can be determined as not taking effect normally.

[0054] In this embodiment, only when the execution strategy fails abnormally, a backup strategy will be adopted, and the device-side energy management system EMS will control the device according to the backup strategy; EMS will strictly control the grid power value to be the difference between the operation baseline and the response capacity according to the requirements of the invitation response. Although this strategy can ensure the completion of the invitation, it cannot intelligently adjust the energy storage power to maximize the benefits.

[0055] Please refer to Figure 4 , Embodiment 2 of the present invention is: An automation - executing terminal 1 for a photovoltaic - storage - charging - inspection station, comprising a processor 2, a memory 3, and a computer program stored in the memory 3 and operable on the processor 2. When the processor 2 executes the computer program, it implements the steps in the method for automating the execution of a photovoltaic - storage - charging - inspection station described in the first embodiment above.

[0056] In summary, the method and terminal for automating the execution of a photovoltaic - storage - charging - inspection station provided by the present invention solve the integration problem among the power grid, the virtual power plant operation platform, and the equipment systems, ensuring the efficient collaborative operation of the systems. At the same time, by using data analysis and AI technology, an execution strategy and a backup strategy are generated according to the invitation content. During the invitation period, the execution strategy is preferentially used to control the equipment and the execution strategy can be automatically adjusted. When the execution strategy fails, the backup strategy is used to control the equipment. On the one hand, it realizes the automated execution of invitations and the intelligent adjustment of equipment control strategies, improving the site revenue. On the other hand, two sets of equipment control strategies are generated, ensuring the safety and stability of the automated execution process.

[0057] The above are only the embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in the relevant technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for automated execution of a solar-storage-charging inspection station under demand-side response, characterized in that: Includes steps: S1. The virtual power plant operation platform generates a corresponding execution strategy according to the preset invitation content, based on the pre-trained AI model and the time-slot electricity price, wherein the AI ​​model includes a user charging prediction model and a photovoltaic prediction model; S2. The device-side energy management system EMS generates a backup strategy according to the invitation content issued by the virtual power plant operation platform, and the backup strategy controls the power value of the power grid to be the difference between the operating baseline and the response capacity; S3. If the execution strategy is in effect normally, the device is automatically controlled according to the execution strategy during the invitation period, wherein the device control according to the execution strategy includes: Control the device according to the demand-side response requirements during the invitation period. If the demand-side response is a peak-shaving requirement, the energy storage device is charged in advance during the valley period. When in the invitation period, the power grid is stopped, the photovoltaic system and the energy storage device are controlled to supply power, and the charging power of the charging pile is reduced; If the demand-side response is a valley-filling demand, the energy storage device is discharged in advance, and during the invitation period, the energy storage device is charged at the maximum required power and guides the user to charge; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

2. The method for automated execution of a photovoltaic storage and charging inspection station under demand-side response according to claim 1 is characterized in that: Before step S1, the method further includes the following steps: S01. The power grid platform initiates a demand-side response invitation to the virtual power plant operation platform and triggers a notification reminder to notify the invited user; S02, the inviting user independently chooses whether to accept the invitation. If the invitation is accepted, the inviting user determines the invitation content through the virtual power plant operation platform and provides invitation feedback. The power grid platform receives and provides feedback of the invitation content provided by the inviting user to the virtual power plant operation platform to confirm the invitation execution. Otherwise, end this demand-side response invitation.

3. The method for automated execution of a solar-storage-charging inspection station under demand-side response according to claim 2 is characterized in that: The step S02 further includes the following steps: S03, monitoring the execution process of the invitation in real time through the virtual power plant operation platform, and sending a notification to remind the inviting user when an abnormality of a key node is triggered; The key node anomalies include failure to generate the execution strategy or the backup strategy, failure to issue the execution strategy or the backup strategy, device adjustment accuracy not meeting the invitation requirements, and device offline or abnormality leading to data collection failure.

4. The method for automated execution of a photovoltaic storage and charging inspection station under demand-side response according to claim 1 is characterized in that: Step S3 is specifically as follows: If the execution strategy is effective normally, the energy storage equipment is automatically controlled according to the execution strategy during the invitation period, the equipment status is monitored in real time through the virtual power plant operation platform, and the execution strategy is adjusted according to the pre-trained AI model and the collected equipment data, and the execution strategy is re-issued at a preset interval; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

5. The method for automated execution of a solar-storage-charging inspection station under demand-side response according to claim 1 is characterized in that: The invitation content includes the invitation period, response capacity and subsidized electricity price; In step S1, based on the pre-trained AI model and the electricity price during the time period, a corresponding execution strategy is generated, including: Adjusting the device charging and discharging power and the execution period in the execution strategy according to the user charging prediction model, the photovoltaic prediction model, the invitation period and the response capacity; The photovoltaic prediction model is established based on historical weather data and historical operation data of the photovoltaic system of the photovoltaic storage and charging inspection station, and the user charging prediction model is established based on historical charging data of the charging piles of the photovoltaic storage and charging inspection station; According to the subsidized electricity price, the charging capacity of the equipment in the execution strategy is adjusted by comparing the grid electricity price and the user charging fee.

6. A terminal for automatically executing a photovoltaic storage and charging inspection station under demand-side response, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the following steps are implemented: S1. The virtual power plant operation platform generates a corresponding execution strategy according to the preset invitation content, based on the pre-trained AI model and the time-slot electricity price, wherein the AI ​​model includes a user charging prediction model and a photovoltaic prediction model; S2. The device-side energy management system EMS generates a backup strategy according to the invitation content issued by the virtual power plant operation platform, and the backup strategy controls the power value of the power grid to be the difference between the operating baseline and the response capacity; S3. If the execution strategy is in effect normally, the device is automatically controlled according to the execution strategy during the invitation period, wherein the device control according to the execution strategy includes: Control the device according to the demand-side response requirements during the invitation period. If the demand-side response is a peak-shaving requirement, the energy storage device is charged in advance during the valley period. When in the invitation period, the power grid is stopped, the photovoltaic system and the energy storage device are controlled to supply power, and the charging power of the charging pile is reduced; If the demand-side response is a valley-filling demand, the energy storage device is discharged in advance, and during the invitation period, the energy storage device is charged at the maximum required power and guides the user to charge; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

7. A terminal for automated execution of a photovoltaic storage and charging inspection station under demand-side response according to claim 6, characterized in that: Before step S1, the method further includes the following steps: S01. The power grid platform initiates a demand-side response invitation to the virtual power plant operation platform and triggers a notification reminder to notify the invited user; S02, the inviting user independently chooses whether to accept the invitation. If the invitation is accepted, the inviting user determines the invitation content through the virtual power plant operation platform and provides invitation feedback. The power grid platform receives and provides feedback of the invitation content provided by the inviting user to the virtual power plant operation platform to confirm the invitation execution. Otherwise, end this demand-side response invitation.

8. A terminal for automated execution of a photovoltaic storage and charging inspection station under demand-side response according to claim 7, characterized in that: The step S02 further includes the following steps: S03, monitoring the execution process of the invitation in real time through the virtual power plant operation platform, and sending a notification to remind the inviting user when an abnormality of a key node is triggered; The key node anomalies include failure to generate the execution strategy or the backup strategy, failure to issue the execution strategy or the backup strategy, device adjustment accuracy not meeting the invitation requirements, and device offline or abnormality leading to data collection failure.

9. A terminal for automated execution of a photovoltaic storage and charging inspection station under demand-side response according to claim 6, characterized in that: Step S3 is specifically as follows: If the execution strategy is effective normally, the energy storage equipment is automatically controlled according to the execution strategy during the invitation period, the equipment status is monitored in real time through the virtual power plant operation platform, and the execution strategy is adjusted according to the pre-trained AI model and the collected equipment data, and the execution strategy is re-issued at a preset interval; Otherwise, the device-side energy management system EMS executes the backup strategy to control the device.

10. A terminal for automated execution of a photovoltaic storage and charging inspection station under demand-side response according to claim 6, characterized in that: The invitation content includes the invitation period, response capacity and subsidized electricity price; In step S1, based on the pre-trained AI model and the electricity price during the time period, a corresponding execution strategy is generated, including: Adjusting the device charging and discharging power and the execution period in the execution strategy according to the user charging prediction model, the photovoltaic prediction model, the invitation period and the response capacity; The photovoltaic prediction model is established based on historical weather data and historical operation data of the photovoltaic system of the photovoltaic storage and charging inspection station, and the user charging prediction model is established based on historical charging data of the charging piles of the photovoltaic storage and charging inspection station; According to the subsidized electricity price, the charging capacity of the equipment in the execution strategy is adjusted by comparing the grid electricity price and the user charging fee.

Images