An electric energy output control method and device, computer equipment and storage medium

Abstract

The application relates to an electric energy output control method and device, computer equipment and a storage medium. The method comprises the following steps: analyzing an electricity acquisition request, determining a total amount of electric energy to be supplied to an electric entity by an electric energy output device; determining a pre-supply risk score of the electric entity and determining a pre-supply amount; supplying electric energy to the electric entity based on a first supply power curve, and determining a second supply power curve to continue supplying electric energy to the electric entity when the cumulative delivered electric energy reaches a preset first supply amount; when the cumulative delivered electric energy reaches the pre-supply amount, generating a virtual resource conversion request according to the cumulative delivered electric energy; in response to receiving a virtual resource corresponding to the cumulative delivered electric energy, determining a third supply power curve, and supplying electric energy to the electric entity based on the third supply power curve until the supply of electric energy to the electric entity is completed. The method can meet the electric energy demand, improve the controllability of electric energy output, and reduce the waste of electric energy caused by power supply interruption or subsequent resource conversion failure.

Description

Technical Field

[0001] This application relates to the field of power output control technology, and in particular to a power output control method, device, computer equipment and storage medium. Background Technology

[0002] In the process of power output devices providing power to power-consuming entities, the power supply is usually not completed in one go, but rather gradually occurs along with the interactive operations of the power-consuming entities, changes in equipment operating status, and dynamic fluctuations in scene conditions. In existing technologies, power output control is usually based on the total amount of power to be supplied or the immediate power demand of the power-consuming entities, and continuously outputs power according to a single power control strategy. However, in the actual power supply process, unstable usage behavior of the power-consuming entities, abnormal equipment operating status, or changes in the scene environment may all lead to interruptions or unsustainable power supply, thus preventing the delivered power from being utilized as expected, resulting in ineffective power delivery or waste.

[0003] On the other hand, in some power supply scenarios, the completion of power supply does not mean that the power has been effectively confirmed or settled. It is still necessary to convert the delivered power into corresponding virtual resources, control credentials or other verifiable resource forms during or after the power supply process. This conversion process itself has the risk of failure, and existing technologies generally lack a control mechanism to quantitatively assess this risk during the power supply process and adjust the power supply rhythm accordingly. Once the conversion fails in the later stage of power supply, it is difficult to compensate for the power output in the early stage through power rollback or process correction, which further amplifies the power loss and system operation risk. Summary of the Invention

[0004] Based on this, it is necessary to provide a power output control method, device, computer equipment, and storage medium that assesses the pre-supply risk of power-consuming entities at the start and during the power supply process, and performs segmented regulation of power supply in conjunction with phased power supply targets, thereby improving the controllability of power output and reducing power waste caused by power outages or subsequent resource conversion failures while meeting power demand.

[0005] On the one hand, a method for controlling electrical energy output is provided, the method comprising: In response to receiving a power request from an electricity-consuming entity, the power request is parsed to determine the total amount of power to be supplied by the power output device to the electricity-consuming entity; Based on the interaction data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scene data corresponding to the region where the power output device is located, a pre-supply risk score is determined for the power-consuming entity, and the pre-supply amount is determined based on the pre-supply risk score and the total amount of power to be supplied. Power is supplied to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, a second power supply curve is determined based on the preset power supply amount, so as to continue to supply power to the power-consuming entity based on the second power supply curve. When the cumulative delivered electricity reaches the pre-supplied amount, a virtual resource conversion request is generated based on the cumulative delivered electricity and sent to the electricity-consuming entity; In response to receiving virtual resources corresponding to the cumulative delivered electricity, a third power supply curve is determined based on the total amount of electricity to be supplied, and power is supplied to the electricity-consuming entity based on the third power supply curve until the power supply to the electricity-consuming entity is completed.

[0006] In one embodiment, parsing the power request and determining the total amount of power to be supplied by the power output device to the power-consuming entity includes: Parsing the power request yields a session identifier, a power-consuming entity identifier, and entity energy demand information. The entity energy demand information includes at least one or more of the following: entity target power quantity and entity target state of charge. Obtain the current state of charge of the power-consuming entity, and determine the power demand of the power-consuming entity based on the entity's target power, the entity's target state of charge, and the current state of charge. The initial total amount of power to be supplied by the power output device to the power-consuming entity is determined based on the required power consumption. Based on the electricity-consuming entity identifier, the charging database is retrieved to obtain the historical charging records of the electricity-consuming entity; Based on the historical charging records and the device output parameters of the power output device, a power output loss factor is generated. Based on the power output loss factor, the initial total amount of power to be supplied is corrected, a corrected total amount of power to be supplied to the power-consuming entity is generated, and the corrected total amount of power to be supplied is determined as the total amount of power to be supplied by the power output device to the power-consuming entity.

[0007] In one embodiment, determining the pre-supply risk score for the electricity-consuming entity based on the interaction data between the electricity-consuming entity and the power output device, the device operation data of the power output device, and the scene data corresponding to the location of the power output device includes: The interaction behavior data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scene data corresponding to the region where the power output device is located are obtained respectively. The interaction behavior data is analyzed to obtain a set of behavior feature parameters. The stability of the interaction behavior between the power-consuming entity and the power output device is determined based on the set of behavior feature parameters. The behavior risk index is determined based on the stability of the interaction behavior. The equipment operation data is analyzed to obtain a set of equipment characteristic parameters. The operating stability of the power output equipment is determined based on the set of equipment characteristic parameters, and the equipment risk index is determined based on the operating stability. The scene data is analyzed to obtain a scene feature parameter set. The scene risk level of the region where the power output device is located is determined based on the scene feature parameter set, and the scene risk index is determined based on the scene risk level. Based on the electricity-consuming entities, the power output devices, and the geographical region, a multi-entity association graph is constructed. In the multi-entity association graph, a set of neighboring nodes associated with the device node corresponding to the power output device is determined, and the historical anomaly records corresponding to the set of neighboring nodes are parsed to obtain a set of neighboring anomaly feature parameters. The degree of domain risk propagation is determined based on the set of neighboring anomaly feature parameters. Determine the domain risk propagation index based on the domain risk propagation degree; A comprehensive risk value is determined based on the behavioral risk index, the equipment risk index, the scenario risk index, and the domain risk propagation index, and the pre-power supply risk score is determined based on the mapping of the comprehensive risk value.

[0008] In one embodiment, the step of parsing the historical anomaly records corresponding to the neighborhood node set to obtain a neighborhood anomaly feature parameter set, and determining the domain risk propagation degree based on the neighborhood anomaly feature parameter set, includes: The historical anomaly records are parsed to obtain an anomaly event set, and a neighborhood anomaly feature parameter set is determined based on the anomaly event set. The neighborhood anomaly feature parameter set includes at least one or more of the following: anomaly event occurrence frequency parameter, anomaly event severity parameter, and anomaly event time decay parameter. The intensity of a neighborhood anomaly is determined based on the frequency parameter of the anomaly event and the severity parameter of the anomaly event, and the intensity of the neighborhood anomaly is attenuated based on the time decay parameter of the anomaly event to obtain the attenuated anomaly intensity. Based on the association between multiple neighboring nodes in the neighboring node set and the device node, the attenuation anomaly intensity is weighted and aggregated to obtain the neighborhood propagation risk value; The risk propagation degree of the neighborhood is determined based on the neighborhood propagation risk value, so as to at least characterize the risk contribution of the neighborhood node anomaly to the target interactive session through multi-entity association relationship.

[0009] In one embodiment, determining the pre-supply quantity based on the pre-supply risk score and the total amount of power to be supplied includes: Based on a preset pre-power supply ratio mapping function, the pre-power supply risk score is mapped to obtain a pre-power supply ratio coefficient, so that the pre-power supply ratio coefficient decreases as the pre-power supply risk score increases; The initial pre-powered quantity is obtained by calculating the total amount of power to be supplied based on the pre-powered quantity ratio coefficient. Based on preset minimum and maximum pre-supply thresholds, the initial pre-supply is limited to obtain the pre-supply amount.

[0010] In one embodiment, before supplying power to the power-consuming entity based on a preset first power supply curve, the method further includes: Based on the device operating parameters of the power output device and the total amount of power to be supplied, a first power supply curve is generated; The first power supply curve is determined in the following way: Analyze the operating parameters of the equipment to determine the upper limit of the output power and the equipment temperature of the power output equipment; Based on the device temperature, the upper limit of the output power is derating to obtain the maximum allowable power supply, and power variation constraints are determined based on the maximum allowable power supply. The power variation constraints include at least the upper limit of power ramp-up speed and the upper limit of power step. Based on the total amount of power to be supplied and the first power supply, a preset first power supply cycle is planned, and the power supply process is divided into at least an initial stage, a ramp-up stage and a steady-state stage within the first power supply cycle. Based on the first power supply and the maximum allowable power supply, the target power supply for the steady-state stage is determined, and the target power supply for the steady-state stage does not exceed the maximum allowable power supply. Based on the power ramp-up speed limit and the power step limit, the power update rule for the ramp-up stage is determined so that the power supply power gradually ramps up to the target power supply power while satisfying the constraints of the power ramp-up speed limit and the power step limit. Based on the initial power supply in the initial stage, the power update rule in the ramp-up stage, and the target power supply in the steady-state stage, a piecewise curve of power supply changing over time is constructed, and the execution of the first power supply curve is terminated when the cumulative delivered power reaches the first power supply amount.

[0011] In one embodiment, determining a second power supply curve based on the pre-supply amount, and continuing to supply power to the power-consuming entity based on the second power supply curve, includes: Obtain the power supply amount of the first cycle at the end of the first power supply cycle, the current power supply power, and the current device temperature; Based on the pre-supply amount and the first cycle supply amount, determine the target supply amount for the second cycle; Based on the current device temperature, the upper limit of the output power is corrected by a second temperature derating to obtain the maximum allowable power supply power for the second cycle. The execution result of the first power supply curve is obtained and parsed to obtain at least the power response deviation within the first power supply cycle and at least the power reachable characteristic quantity characterizing the device's power tracking capability. Based on the power response deviation, a power correction factor is determined, and the maximum allowable power supply power of the second cycle is corrected based on the power correction factor to obtain the peak target power supply power of the second cycle, so that the peak target power supply power of the second cycle does not exceed the maximum allowable power supply power of the second cycle, and is higher than the steady-state target power supply power of the first power supply cycle. The second-cycle power change constraint parameters are determined based on the power response deviation and the power achievable characteristic to limit the allowable range of power regulation in the second power supply curve; Based on the peak target power and target power supply of the second cycle, the second power supply cycle is divided into at least a two-stage ramp-up phase, a high-power phase, and a power drop-off phase. Based on the second cycle peak target power supply, the target power supply for the high power phase is determined, and the target power supply for the high power phase is made not to exceed the second cycle peak target power supply. Based on the second cycle power change constraint parameters, the power update rules for the second ramp-up stage are determined so that the power supply power can be gradually increased from the current power supply power to the target power supply power of the high power stage, provided that the adjustment rate threshold and / or adjustment amplitude threshold defined by the second cycle power change constraint parameters are met. Based on the second cycle power change constraint parameters, the power update rules for the power fall-off phase are determined so that the power supply gradually falls off under the condition that the adjustment rate threshold and / or adjustment amplitude threshold defined by the second cycle power change constraint parameters are met, and the cumulative power supply ends the second power supply cycle when the pre-supply amount is reached. Based on the initial power supply of the second ramp-up phase, the power update rule of the second ramp-up phase, the target power supply of the high-power phase, and the power update rule of the power fall-down phase, a piecewise curve of power supply changing with time is constructed and determined as the second power supply curve.

[0012] On the other hand, a power output control device is provided, the device comprising: The request receiving module is used to, in response to receiving a power request from an electricity-consuming entity, parse the power request and determine the total amount of power to be supplied by the power output device to the electricity-consuming entity; The risk assessment module is used to determine the pre-supply risk score for the power-consuming entity based on the interaction behavior data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scenario data corresponding to the region where the power output device is located, and to determine the pre-supply amount based on the pre-supply risk score and the total amount of power to be supplied. The pre-supply module is used to supply power to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, to determine a second power supply curve based on the pre-supply amount, so as to continue supplying power to the power-consuming entity based on the second power supply curve. The resource conversion module is used to generate a virtual resource conversion request based on the cumulative delivered electricity and send it to the electricity-consuming entity when the cumulative delivered electricity reaches the pre-supply amount. The power supply module is used to respond to receiving virtual resources corresponding to the cumulative delivered power, determine a third power supply curve based on the total amount of power to be supplied, and supply power to the power-consuming entity based on the third power supply curve until the power supply to the power-consuming entity is completed.

[0013] In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: In response to receiving a power request from an electricity-consuming entity, the power request is parsed to determine the total amount of power to be supplied by the power output device to the electricity-consuming entity; Based on the interaction data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scene data corresponding to the region where the power output device is located, a pre-supply risk score is determined for the power-consuming entity, and the pre-supply amount is determined based on the pre-supply risk score and the total amount of power to be supplied. Power is supplied to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, a second power supply curve is determined based on the preset power supply amount, so as to continue to supply power to the power-consuming entity based on the second power supply curve. When the cumulative delivered electricity reaches the pre-supplied amount, a virtual resource conversion request is generated based on the cumulative delivered electricity and sent to the electricity-consuming entity; In response to receiving virtual resources corresponding to the cumulative delivered electricity, a third power supply curve is determined based on the total amount of electricity to be supplied, and power is supplied to the electricity-consuming entity based on the third power supply curve until the power supply to the electricity-consuming entity is completed.

[0014] In another aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps: In response to receiving a power request from an electricity-consuming entity, the power request is parsed to determine the total amount of power to be supplied by the power output device to the electricity-consuming entity; Based on the interaction data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scene data corresponding to the region where the power output device is located, a pre-supply risk score is determined for the power-consuming entity, and the pre-supply amount is determined based on the pre-supply risk score and the total amount of power to be supplied. Power is supplied to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, a second power supply curve is determined based on the preset power supply amount, so as to continue to supply power to the power-consuming entity based on the second power supply curve. When the cumulative delivered electricity reaches the pre-supplied amount, a virtual resource conversion request is generated based on the cumulative delivered electricity and sent to the electricity-consuming entity; In response to receiving virtual resources corresponding to the cumulative delivered electricity, a third power supply curve is determined based on the total amount of electricity to be supplied, and power is supplied to the electricity-consuming entity based on the third power supply curve until the power supply to the electricity-consuming entity is completed.

[0015] The aforementioned power output control method, apparatus, computer equipment, and storage medium, by introducing an assessment mechanism for the pre-supply risk of power-consuming entities at the start of power supply, and establishing a constraint relationship between the risk assessment result and the current phased deliverable power limit, ensure that the power delivery of the power output device is naturally within a controllable risk exposure before resources are fully confirmed. Furthermore, since the power supply control does not use a single power strategy throughout the entire process, but rather triggers segmented switching of the power supply strategy around the phased power supply target when the accumulated delivered power reaches a specific node, the initial stage can quickly establish power supply according to a preset strategy, and subsequent stages continue to output power under the aforementioned risk limit constraint and reach the target. When the upper limit is reached, resource conversion confirmation is initiated in a timely manner. This ensures that in the event of interaction anomalies, equipment status fluctuations, power outages, or resource conversion failures, previously delivered power that may not be effectively confirmed is limited to the predetermined upper limit, thereby reducing invalid delivery and power waste. Simultaneously, after successful resource confirmation, the control logic further switches to subsequent power supply regulation oriented towards the remaining power supply target. This allows the power supply process to converge to the power supply target under a closed-loop sequence of first controlling risks and then confirming completion. This improves the controllability and stability of the power output process while meeting power demand, and reduces repeated power supply, power fluctuations, and metering and settlement deviations caused by inconsistent confirmation sequences. Attached Figure Description

[0016] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is an application environment diagram of the power output control method in one embodiment; Figure 2 This is a flowchart illustrating a power output control method in one embodiment; Figure 3 This is a structural block diagram of the power output control device in one embodiment; Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] The power output control method provided in this application can be applied to, for example... Figure 1In the application environment shown, the power-consuming entity 101 is connected to the power output device 102 via a transmission cable; the power output device 102 is communicatively connected to the power supply control terminal 103, which can also be located within the power output device 102. The power-consuming entity 101 can be an electric vehicle, a battery swapping / storage battery pack, or other loads with power receiving and status feedback capabilities. It may contain a battery system and a battery management unit (such as a BMS) to generate power requests, report state of charge / demand parameters, and conduct handshake negotiations and operational interactions with external systems during power supply. The power output device 102 can be a DC charging pile, an AC charging pile, a mobile power supply terminal, or a power module with metering and power regulation capabilities. Structurally, it may include a power conversion unit, a metering unit, a communication unit, and a control execution unit. It can output power to the power-consuming entity 101 via a transmission cable and collect operating parameters such as output voltage / current / power, cumulative delivered power, and temperature in real time. The power supply control terminal 103 can be a station controller, an edge gateway, an operation platform server, or a cloud control module. It may also be integrated into the power output device 102. It may include a processor, a memory, and a communication interface for strategic decision-making, risk assessment, and resource confirmation management of the power supply session. In this application environment, the power-consuming entity 101 initiates a power request, carrying session and demand information; the power output device 102 reports session-related data (including at least device operating status, metering data, and interaction logs) to the power supply control terminal 103 via a communication interface; when the power supply control terminal 103 is integrated within the power output device 102, the session-related data is directly read by the local acquisition module of the power supply control terminal 103 via inter-process communication or a bus interface; scenario-related data is provided by the station control system / operation platform / third-party data source, and is input to the power supply control terminal 103 after being associated with the power output device 102 through a station identifier or regional identifier; the power supply control terminal 103 executes a risk assessment model based on the above inputs and generates a model that matches the phased power supply target. The power supply is controlled by a segmented power supply control strategy, and the power output device 102 implements power output and stage switching according to the strategy. When the power supply progresses to the predetermined stage boundary, the power output device 102 or the power supply control terminal 103 triggers the resource confirmation or virtual resource conversion process corresponding to the delivered power, and adjusts the subsequent power supply strategy after the confirmation result is returned to complete the remaining power supply target. At the same time, during the power supply process, the power output device 102 continuously transmits execution feedback and metering data, and the power consumption entity 101 continuously transmits demand and status changes, so that the power supply control terminal 103 can make necessary dynamic corrections to risk assessment and power control, thereby realizing the overall closed-loop interaction of assessable risk, segmented power control, resource confirmation and coordinated power supply process at the start of power supply and during the power supply process.

[0020] In one embodiment, such as Figure 2 As shown, a power output control method is provided, which is applied to... Figure 1 Taking the power supply control terminal 103 as an example, the explanation includes the following steps: Step 201: In response to receiving a power request from an electricity-consuming entity, the power request is parsed to determine the total amount of power to be supplied by the power output device to the electricity-consuming entity. The power request is a request message initiated by the power-consuming entity to start this power supply session. It can be sent by the power-consuming entity's BMS (Battery Management System) to the power output device through the charging communication link, and then forwarded by the power output device to the power supply control terminal; or it can be sent directly to the power supply control terminal by the client / vehicle-mounted device bound to the power-consuming entity via the network. The power request includes at least a session identifier, a power-consuming entity identifier, and energy demand information, and may carry constraint parameters such as the current SOC (State of Charge), the allowed charging flag, and the maximum allowed voltage / current. Step 202: Based on the interaction data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scenario data corresponding to the region where the power output device is located, determine the pre-supply risk score for the power-consuming entity, and determine the pre-supply amount based on the pre-supply risk score and the total amount of power to be supplied. Interactive behavior data is preferably recorded and reported by the power output device or collected by the power supply control terminal on the session link; equipment operation data is preferably collected in real time by the power output device and sent according to the preset reporting cycle; scenario data is preferably obtained by the station control system, operation platform or third-party data source and associated with the station / region identifier; the preset reporting cycle / sampling cycle is a configurable parameter, preferably configured by default by the device and allowed to be updated by the station policy; for example, equipment operation data can be sampled at a second-level cycle or a sub-second-level cycle and reported once in the range of a few tenths of a second to several seconds, and interactive behavior data can be reported according to event triggers and supplemented by periodic summary reporting, and the specific cycle value is not limited; Step 203: Power is supplied to the power-consuming entity based on the preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, a second power supply curve is determined based on the pre-supply amount, so as to continue to supply power to the power-consuming entity based on the second power supply curve. Among them, the power curve refers to the control strategy for the power supply control target power to change over time. It can be generated by the power supply control terminal and then sent to the power output device for execution, or it can be generated and executed locally by the power output device based on the key parameters sent by the power supply control terminal. The cumulative delivered power refers to the power output of the power output device in this session. It is preferably obtained by the metering unit based on voltage / current sampling and accumulated according to the metering procedure. The first power supply is the power boundary of the first stage. It is preferably configured as a fixed small power or a small part of the total power to be supplied for the purpose of quickly establishing power supply and verifying stability. The specific value can be configured by the operation strategy or equipment level. Step 204: When the cumulative delivered electricity reaches the pre-supplied electricity, generate a virtual resource conversion request based on the cumulative delivered electricity and send it to the electricity-consuming entity; Among them, the virtual resource conversion request refers to the request message used to trigger the mapping of delivered electricity to verifiable rights. It preferably carries at least the session identifier, the cumulative delivered electricity, the device identifier, and the metering consistency verification information (such as serial number, signature digest, or hash digest, etc.) so that the electricity user or its account system can perform consistency verification and confirmation accordingly. Step 205: In response to receiving virtual resources corresponding to the cumulative delivered electricity, a third power supply curve is determined based on the total amount of electricity to be supplied, and power is supplied to the power-consuming entity based on the third power supply curve until the power supply to the power-consuming entity is completed. The virtual resource refers to a verifiable rights certificate corresponding to the cumulative delivered electricity, preferably a payment authorization token, pre-deduction certificate, frozen amount certificate, points amount certificate, or other digital certificate that can be used for settlement confirmation. When the power supply control terminal receives the virtual resource, it indicates that the electricity delivered in the pre-supply stage has been verifiable, thereby allowing the control strategy to switch to the subsequent power supply stage to complete the remaining power supply target.

[0021] In the aforementioned power output control method, by introducing an assessment mechanism for the pre-supply risk of power-consuming entities at the beginning of power supply, and establishing a constraint relationship between the risk assessment result and the upper limit of the deliverable power volume for this phase, the power delivery of the power output equipment is naturally within a controllable risk exposure before the resources are fully confirmed. Furthermore, since the power supply control does not use a single power strategy throughout the entire process, but rather triggers a segmented switching of the power supply strategy around the phased power supply target when the accumulated delivered power volume reaches a specific node, the power supply can be quickly established according to the preset strategy in the initial stage, and in subsequent stages, it continues to output under the constraint of the risk upper limit and promptly releases power when the upper limit is reached. Resource conversion confirmation is initiated so that when interaction anomalies, equipment status fluctuations, power outages, or resource conversion failures occur, the previously delivered but potentially unconfirmed electrical energy is limited to a predetermined upper limit, thereby reducing invalid deliveries and energy waste. Simultaneously, once resource confirmation is successful, the control logic further switches to subsequent power supply regulation oriented towards the remaining power supply target. This allows the power supply process to converge to the power supply target under a closed-loop sequence of first controlling risks and then confirming completion. This improves the controllability and stability of the power output process while meeting electricity demand, and reduces repeated power supply, power fluctuations, and metering and settlement deviations caused by inconsistent confirmation sequences.

[0022] In one embodiment, parsing the power request to determine the total amount of power to be supplied by the power output device to the power-consuming entity includes: Parsing the power request yields the session identifier, the power-consuming entity identifier, and the entity's energy demand information. The entity's energy demand information includes at least one or more of the following: the entity's target power quantity and the entity's target state of charge. Among them, the target energy quantity of the entity refers to the target energy replenishment quantity that the power-consuming entity expects to obtain in this session; the target state of charge of the entity refers to the target SOC that is expected to be achieved. Obtain the current state of charge of the power-consuming entity, and determine the power demand of the power-consuming entity based on the entity's target power, the entity's target state of charge, and the current state of charge. The current state of charge (SOC) is preferably obtained from the BMS of the power-consuming entity. When the BMS is temporarily unavailable, it can be estimated by the power supply control terminal 103 in combination with historical SOC and the metering increment of the current session as a degradation solution. Specifically, the demand for electricity is preferably determined by a demand calculation function or rule engine, which supports at least the following rules: When the power request carries the target electricity of the entity, the net demand for additional electricity is obtained by deducting the portion that has been metered and delivered and confirmed in the current session from the target electricity. When the power request carries the target SOC of the entity, the available battery capacity information is first obtained. The available battery capacity information is preferably obtained from the BMS or learned from the vehicle model file / historical charging and stored in the charging database or asset file. Then, the net demand is calculated based on the difference between the target SOC and the current SOC. When both targets exist simultaneously, the more stringent demand boundary is preferably selected according to the configurable strategy, such as taking the one with the smaller net demand as the final demand, in order to avoid exceeding the user's intention or creating the risk of overcharging. Determine the initial total amount of power to be supplied by the power output equipment to the power-consuming entity based on the demand for power. The initial total power supply refers to the estimated gross power volume that the equipment plans to deliver before individualized loss correction. It is preferably obtained by discounting the net demand according to the nominal efficiency or nominal loss rate of the equipment. The nominal efficiency / loss rate can be given by the equipment model specification or the site configuration, and different parameter values ​​can be set according to the power segment. Based on the identifier of the electricity user entity, the charging database is retrieved to obtain the historical charging records of the electricity user entity. The charging database is used to store metering and execution data of historical sessions, including at least the source-side metered output power, entity-side SOC changes or charging energy, session temperature range, average power level, and abnormal / interruption flags; historical charging records are sets of multiple historical sessions associated with the same power-consuming entity identifier. Based on historical charging records and the output parameters of the power output device, a power output loss factor is generated. Among them, the preferred output parameters of the equipment include cable specifications and length information, power conversion module efficiency characteristics, metering accuracy level, temperature derating characteristics, maximum output power / current limit, etc., which can be obtained from the equipment factory calibration, on-site configuration or operation self-learning. Based on the power output loss factor, the initial total amount of power to be supplied is corrected, the corrected total amount of power to be supplied to the power-consuming entity is generated, and the corrected total amount of power to be supplied is determined as the total amount of power to be supplied by the power output device to the power-consuming entity. Among them, the corrected total amount of power to be supplied refers to the result after adding the above loss amplification factor to the initial total amount of power to be supplied, thereby incorporating non-ideal factors such as line loss, transformation loss and execution deviation into the power supply target boundary in the form of interpretable parameters, so that the final total amount of power to be supplied is closer to the actual deliverable and achievable power supply demand.

[0023] Specifically, the generation of the power output loss factor is preferably achieved through the following methods: Extract corresponding samples of source-side output power and physical-side power obtained from multiple sessions from historical charging records. The physical-side power obtained is preferably obtained from the cumulative charging energy reported by the BMS. If it cannot be obtained directly, it is obtained by combining the SOC increment with the battery's available capacity. The samples are screened for validity, and session samples with communication interruption, abnormal SOC transition, abnormal measurement, or marked as abnormal termination are removed. It is preferable to use time-weighted average or median / quantile methods to obtain representative loss levels from effective samples using robust statistics, so as to reduce the impact of extreme values; Secondary corrections can be made based on the equipment output parameters. For example, if the cable is longer, the temperature is higher, or the loss level is increased under high current conditions, this can be achieved by looking up table rules or calibration curves. The representative loss level is converted into an energy output loss factor, which serves as an amplification factor for converting net demand into equipment-side gross delivery. The amplification factor is preferably set with upper and lower limit protection and is issued as a configurable parameter or stored locally. For example, it can be limited to a range slightly greater than one to avoid unreasonable amplification. The upper and lower limit values ​​can be calibrated according to the equipment model, cable specifications and metering accuracy level or configured by the operation strategy. The specific values ​​do not constitute a limitation.

[0024] Specifically, in this embodiment, the power request is structured and parsed to obtain the session identifier, the power-consuming entity identifier, and the entity's energy demand information. The required power is then derived by combining the current state of charge of the power-consuming entity with the constraint of target power / target state of charge - current state of charge. This transforms the determination of the amount of power to be supplied from a single request value into an interpretable calculation based on the actual battery state. Simultaneously, by retrieving historical charging records based on the power-consuming entity identifier and combining them with the device output parameters to generate a power output loss factor, the initial total amount of power to be supplied is corrected using this loss factor. This incorporates non-ideal factors such as line loss, conversion loss, and execution deviation into the energy supply target boundary, making the final determined total amount of power to be supplied closer to the deliverable and achievable actual power supply demand. Therefore, it can reduce over-supply / under-supply caused by target estimation deviation, improve energy supply accuracy, and reduce energy waste and settlement deviation caused by metering inconsistencies.

[0025] In one embodiment, a pre-supply risk score for the electricity-consuming entity is determined based on interaction data between the electricity-consuming entity and the power output device, equipment operation data of the power output device, and scenario data corresponding to the location of the power output device. This includes: The interaction data between the electricity-consuming entity and the power output device, the device operation data of the power output device, and the scene data corresponding to the region where the power output device is located are obtained respectively. The interaction behavior data is analyzed to obtain a set of behavioral feature parameters. The stability of the interaction behavior between the power-consuming entity and the power output device is determined based on the set of behavioral feature parameters, and the behavioral risk index is determined based on the stability of the interaction behavior. The behavioral feature parameter set includes at least: number of handshake failures / retries, number of message timeouts, number of connection interruptions, number of power request mutations, and number of allowed repeated switching of charging states. Specifically, the stability of interactive behavior is preferably obtained by: normalizing the above features and then aggregating them into an anomaly score according to preset weights, and mapping the anomaly score to stability (the higher the anomaly, the lower the stability). The behavioral risk index is preferably obtained by further mapping the stability (the lower the stability, the higher the risk). The weights and mapping relationship can be obtained offline by historical interruption rate, dispute rate, or abnormal session samples, and can be configured according to site type. The normalization process preferably adopts one of the following implementation methods: linear scaling to a uniform numerical range based on historical statistical range; or segmented mapping to discrete levels based on a preset threshold; the mapping range or threshold can be offline calibrated by historical session data and can be configured according to site type; the preferred aggregation method is to weight and superimpose the normalization results of each feature according to preset weights to obtain an anomaly score. The equipment operation data is analyzed to obtain a set of equipment characteristic parameters. The operating stability of the power output equipment is determined based on the set of equipment characteristic parameters, and the equipment risk index is determined based on the operating stability. The equipment characteristic parameter set includes at least: the degree to which the temperature approaches the derating threshold, the severity level of the fault code, the degree of fluctuation in output power / voltage / current, the insulation detection anomaly marker, and the power tracking error statistics. Specifically, the operating stability is preferably obtained in the following way: the equipment characteristics are normalized and aggregated according to weights to form the degree of equipment anomaly, and then mapped to the stability. The equipment risk index is obtained by mapping the stability, so that the more unstable the equipment operation, the higher the risk. The equipment-side weights can be set according to the equipment model protection strategy, historical fault statistics, or experience. The scene data is analyzed to obtain a set of scene feature parameters. The scene risk level of the region where the power output device is located is determined based on the scene feature parameter set, and the scene risk index is determined based on the scene risk level. The scenario feature parameter set includes at least: ambient temperature range, grid voltage fluctuation level, site load rate, network packet loss rate / latency level, and regional alarm level. Specifically, the scenario risk level is preferably obtained through the following method: configuring a level classification threshold and level weight for each scenario feature, and outputting a higher risk level when it falls into a higher risk level; the threshold can be configured based on operational experience or historical stability statistics, and can be configured independently per site. The scenario risk index is obtained by mapping the scenario risk level. Construct a multi-entity relationship graph based on electricity-consuming entities, power output devices, and geographical regions; The nodes in the multi-entity association graph include at least power-consuming entity nodes, equipment nodes, and site / region nodes. The edge relationships include at least the same site, the same distribution circuit / transformer, the same equipment cluster, and the same power-consuming entity having initiated sessions on multiple devices in the past. The edge weights are preferably configured according to the association strength. For example, the edge weight sharing the same distribution circuit is greater than the edge weight sharing only the same region. The association relationships can be generated by site topology configuration, asset management system, or historical co-occurrence statistics. In the multi-entity association graph, the set of neighboring nodes associated with the device node corresponding to the power output device is determined, and the historical anomaly records corresponding to the set of neighboring nodes are parsed to obtain the set of neighboring anomaly feature parameters. The degree of risk propagation in the domain is determined based on the set of neighboring anomaly feature parameters. Among them, the set of neighboring nodes is preferably a set of nodes that are directly associated with the device node or associated with a preset number of hops. The preset number of hops is preferably set to one or two hops to balance the coverage and computational overhead. The historical anomaly record is preferably an event log of the neighboring node within a preset time window, such as alarms, faults, shutdowns, protection actions, and communication interruptions. The preset time window can be configured according to the site's risk sensitivity. Determine the domain risk propagation index based on the domain risk propagation degree; Among them, the domain risk propagation index is preferably the output after the domain risk propagation degree is mapped by a score, so that it can be integrated with other risk indices using a unified dimension; Based on the behavioral risk index, equipment risk index, scenario risk index, and domain risk propagation index, a comprehensive risk value is determined, and a pre-power supply risk score is determined based on the mapping of the comprehensive risk value. The comprehensive risk value is preferably output by the fusion model. The fusion model can adopt a weighted fusion function (aggregating the sub-risk indices according to their weights) or a trained fusion model (such as a lightweight model like logistic regression or gradient boosting tree). The model inputs are the behavioral risk index, equipment risk index, scenario risk index, and domain risk propagation index, and the output is the comprehensive risk value. The model parameters can be obtained through offline training using historical abnormal samples and normal samples, or the initial weights can be configured by the operation strategy and continuously calibrated. The pre-power supply risk score is preferably obtained through a segmented mapping rule: the comprehensive risk value falls into several risk levels and the corresponding score interval is output to ensure that the score is interpretable and easy to link with subsequent pre-power supply.

[0026] Specifically, in this embodiment, interactive behavior data, equipment operation data, and regional scene data are collected separately. Behavioral feature parameter sets, equipment feature parameter sets, and scene feature parameter sets are extracted from these three types of data to form quantitative representations of interaction stability, operational stability, and scene risk. This leads to the construction of behavioral risk indices, equipment risk indices, and scene risk indices, ensuring that risk assessment no longer relies on a single dimension or static rules. Simultaneously, a multi-entity association graph covering power-consuming entities, equipment, and regions is constructed. Historical anomaly records from the neighborhood of equipment nodes are introduced to form a domain risk propagation index, characterizing the spillover and transmission effects of risk in relation to relationships. Therefore, the comprehensive risk value is jointly determined by individual session state + equipment state + scene state + neighborhood propagation, and further mapped to a pre-supply risk score. This enhances the sensitivity and discriminative power assessment of interactive fluctuations, equipment anomalies, and regional disturbances, providing a more reliable risk basis for subsequent power supply control and reducing ineffective delivery and operational losses caused by insufficient risk identification.

[0027] In one embodiment, parsing the historical anomaly records corresponding to the neighborhood node set yields a neighborhood anomaly feature parameter set, and determining the domain risk propagation degree based on the neighborhood anomaly feature parameter set includes: The set of anomalous events is obtained by parsing historical anomaly records, and the set of neighborhood anomaly feature parameters is determined based on the set of anomalous events. The set of neighborhood anomaly feature parameters includes at least one or more of the following: frequency of occurrence of anomalous events, severity of anomalous events, and time decay of anomalous events. Each event entry in the abnormal event set preferably includes at least the event type, occurrence time, duration, and severity level. The abnormal event frequency parameter describes the frequency of anomalies occurring within a preset time window, which can be obtained by statistically analyzing the number of events and calculating based on the time window length. The abnormal event severity parameter describes the degree of impact of the anomaly, preferably by classifying events by level and configuring severity weights for different levels. For example, general alarms, degraded operation, session interruption, and equipment downtime can be mapped to different severity levels (weights can be configured based on operational experience or historical loss statistics). The abnormal event time decay parameter describes how much older an event contributes to the current risk, preferably using a segmented decay rule. The segmented attenuation rule can be implemented as follows: assign higher weights to more recent time periods, gradually reduce weights to intermediate time periods, and assign lower weights or ignore contributions to more distant time periods; the boundaries and weights of each time period can be configured by the operational strategy or determined offline by historical correlation. The intensity of anomalous events in the neighborhood is determined based on the frequency and severity parameters of anomalous events, and the intensity of anomalous events in the neighborhood is attenuated based on the time decay parameter of anomalous events to obtain the attenuated anomalous intensity. Specifically, the intensity of neighborhood anomalies can be obtained as follows: the number of occurrences of each type of anomaly event is combined with the corresponding severity weight to obtain the contribution of that type of anomaly; then the contributions of multiple types of anomalies are summarized to obtain the anomaly intensity; subsequently, the anomaly contribution is reduced according to the time decay rule to obtain the decayed anomaly intensity, so that recent anomalies contribute more to the current propagation risk; Based on the association between multiple neighboring nodes and device nodes in the neighboring node set, the attenuation anomaly intensity is weighted and aggregated to obtain the neighborhood propagation risk value; The weighted aggregation can be achieved in the following way: take the attenuation anomaly intensity of each neighboring node and combine it with the association weight from the neighboring node to the target device node for weighting, and then aggregate all neighboring nodes to obtain the neighborhood propagation risk value; the association weight can be derived from site topology (higher weight for the same circuit / transformer), co-occurrence statistics (higher weight for historical synchronization failure probability) or manual configuration, and can be configured as normalized weight for interpretation. The risk propagation degree of the domain is determined based on the risk value of the neighborhood propagation, so as to at least characterize the risk contribution of the neighborhood node anomaly to the target interaction session through the multi-entity association relationship. Among them, the domain risk propagation degree can be further obtained by segmented mapping to obtain the domain risk propagation index, so as to be integrated with other risk indices using a unified dimension.

[0028] Specifically, in this embodiment, historical anomaly records are parsed into a set of anomaly events, and the neighborhood anomaly strength is constructed using anomaly event frequency and severity parameters. A time decay parameter is introduced to attenuate the anomaly strength, thus ensuring that risk characterization considers both anomaly scale and timeliness, preventing outdated anomalies from unreasonably amplifying the current session. Furthermore, by utilizing the association relationships between multiple neighborhood nodes and device nodes, a weighted aggregation of the attenuated anomaly strength is obtained to obtain a neighborhood propagation risk value, allowing the propagation contribution to adaptively change with the degree of association. Therefore, the resulting domain risk propagation degree can more accurately characterize the risk contribution of neighborhood anomalies propagating to the target interactive session via associated links, thereby improving the interpretability and stability of the domain risk propagation index and enhancing the early warning capability for regional concentrated faults and group anomalies, reducing the unrecoverable risk of continued power output in such situations.

[0029] In one embodiment, determining the pre-supply quantity based on the pre-supply risk score and the total amount of power to be supplied includes: Based on the preset pre-power supply ratio mapping function, the pre-power supply risk score is mapped to obtain the pre-power supply ratio coefficient, so that the pre-power supply ratio coefficient decreases as the pre-power supply risk score increases; The pre-power supply ratio mapping function preferably adopts a monotonically decreasing segmented mapping rule: the risk score is divided into several risk levels (e.g., low risk, medium risk, high risk, and extremely high risk), and a pre-power supply ratio coefficient is pre-configured for each level so that the higher the risk, the lower the corresponding ratio; the level boundary and ratio coefficient can be obtained offline by statistically measuring historical conversion failure rate, bad debt rate, session interruption rate, etc., and can be configured separately according to site type, user level, or time period strategy; The initial pre-supply quantity is obtained by converting the total amount of power to be supplied according to the pre-supply ratio coefficient. The conversion process can be achieved by the pre-supply calculation function, that is, the initial pre-supply is obtained by taking the total amount of power to be supplied as the benchmark and converting it according to the proportional coefficient, so that the deliverable upper limit of the pre-supply stage shrinks adaptively with risk. Based on the preset minimum pre-supply threshold and maximum pre-supply threshold, the initial pre-supply is limited to obtain the pre-supply amount; The minimum pre-supply threshold is used to ensure that the pre-supply phase covers at least the power required for basic handshake stability verification and power establishment, while the maximum pre-supply threshold is used to limit risk exposure before resources are confirmed. The minimum and maximum thresholds can be configured according to equipment power level, site risk preference, or business model (for example, high-power equipment can be configured with a higher minimum threshold, and high-risk sites can be configured with a lower maximum threshold, neither of which constitutes a restriction). The limiting process can be clearly defined as follows: when the initial pre-supply is less than the minimum threshold, the minimum threshold is taken; when the initial pre-supply is greater than the maximum threshold, the maximum threshold is taken; otherwise, the initial pre-supply remains unchanged.

[0030] Specifically, in this embodiment, a pre-supply ratio mapping function is set to map the pre-supply risk score to a pre-supply ratio coefficient, and the ratio coefficient decreases as the risk score increases. This directly transforms the risk assessment result into an executable power supply limit control, enabling the pre-supply amount to have a mechanism for adaptive contraction with risk. At the same time, by applying minimum and maximum threshold limits to the calculated initial pre-supply amount, the pre-supply amount is ensured to be neither too small, affecting the basic charging experience, nor too large, expanding the risk exposure. Therefore, the pre-supply amount forms a controllable upper limit under the dual constraints of risk adaptation and engineering boundary constraints, effectively limiting the scale of potential losses during the unconfirmed resource stage and providing clear power termination conditions for subsequent segmented power regulation, reducing invalid delivery in case of conversion failure or interruption.

[0031] In one embodiment, before supplying power to the power-consuming entity based on a preset first power supply curve, the method further includes: Based on the equipment operating parameters of the power output device and the total amount of power to be supplied, a first power supply curve is generated. Among them, the preferred equipment operating parameters include equipment temperature, heat dissipation status, number of available output modules, and current output limitation information; The first power supply curve is determined in the following way: Analyze the equipment operating parameters to determine the upper limit of the output power and the equipment temperature of the power output equipment; The upper limit of output power is derating based on the equipment temperature to obtain the maximum allowable power supply. Power variation constraints are then determined based on the maximum allowable power supply. The power variation constraints include at least the upper limit of power ramp-up rate and the upper limit of power step. Temperature derating correction can be achieved through a derating lookup table model or segmented derating rules. This means that the equipment has a pre-stored relationship between temperature ranges and allowable power. When the temperature enters a higher range, the maximum allowable power output is lower. This table or rule can be specified by the manufacturer or configured on-site. The upper limit of power ramp-up speed and the upper limit of power step can be given by the default parameters of the equipment model and can be dynamically tightened according to real-time temperature and module availability. The dynamic tightening rule can be achieved through a lookup table or segmented rules to avoid protection actions triggered by sudden power changes. Based on the total amount of power to be supplied and the initial power supply, a preset first power supply cycle is planned, and the power supply process is divided into at least an initial stage, a ramp-up stage and a steady-state stage within the first power supply cycle. The first power supply cycle can be configured to a fixed duration or to end when the first power supply is reached. When a fixed duration is used, it is still preferred to terminate the cycle when the cumulative delivered power reaches the first power supply. The first power supply can be configured as a fixed small amount of power or a small proportion of the total amount of power to be supplied, according to the site strategy, to quickly establish power supply and verify the stability of equipment response. Based on the first power supply and the maximum allowable power supply, determine the target power supply in the steady state stage, and ensure that the target power supply in the steady state stage does not exceed the maximum allowable power supply. Based on the upper limit of power ramp-up speed and the upper limit of power step, the power update rules for the ramp-up phase are determined so that the power supply power gradually ramps up to the target power supply power while meeting the constraints of the upper limit of power ramp-up speed and the upper limit of power step. The power update rule can be implemented by a discrete control update algorithm, which updates the target power cyclically within a preset control cycle. Each update calculates the next adjustment range based on the difference between the current power and the target power, and is simultaneously limited by the upper limit of the climbing speed and the upper limit of the step, until the steady-state target power is reached or the stage termination condition is met. Based on the initial power supply in the initial stage, the power update rules in the ramp-up stage, and the target power supply in the steady-state stage, a piecewise curve of power supply changing over time is constructed, and the execution of the first power supply curve is terminated when the cumulative delivered power reaches the first power supply amount. The initial power supply can be configured to a lower power level to reduce impact, and the specific value can be set by the equipment level or site policy.

[0032] Specifically, in this embodiment, the upper limit of output power and equipment temperature are determined based on the equipment operating parameters, and the upper limit of power is derating based on the temperature to obtain the maximum allowable power supply. This explicitly introduces thermal constraints into the power supply strategy, avoiding unreachable power commands under high temperature or restricted operating conditions. Furthermore, power change constraints (such as upper limit of ramp speed and upper limit of step) are generated from the maximum allowable power supply, and the power supply process is divided into initial, ramp, and steady-state stages within a preset first power supply cycle. In the steady-state stage, continuous power replenishment is achieved with a target power not exceeding the maximum allowable power supply, and in the ramp stage, a smooth increase is achieved with constrained power update rules. Therefore, the first power supply curve can improve the smoothness and controllability of power regulation while meeting the equipment safety boundary, and stop in time when the cumulative delivered power reaches the first power supply amount, thereby reducing energy loss caused by overshoot and fluctuations and improving the stability and predictability of the initial power supply.

[0033] In one embodiment, determining a second power supply curve based on the pre-supplied power, and continuing to supply power to the power-consuming entity based on the second power supply curve, includes: Obtain the power supply amount of the first power supply cycle at the end of the first power supply cycle, the current power supply power, and the current device temperature; Based on the pre-supplied power and the power supply in the first cycle, determine the target power supply for the second cycle; The target power supply for the second cycle is preferably obtained in the following way: the pre-supply amount is used as the total upper limit of the pre-supply phase, and compared with the electricity delivered in the first cycle, the remaining undelivered part is used as the target power supply for the second cycle; when the first cycle has reached or exceeded the pre-supply upper limit, the target power supply for the second cycle can be regarded as zero and can directly enter the resource conversion process. Based on the current equipment temperature, a second temperature derating correction is applied to the upper limit of the output power to obtain the maximum allowable power supply power for the second cycle. Among them, the secondary temperature derating correction preferably reuses the aforementioned derating lookup table model or segmented derating rule to reflect the latest thermal state boundary after the end of the first stage. The execution result of the first power supply curve is obtained and analyzed to obtain at least the power response deviation in the first power supply cycle and at least the power reachable characteristic quantity characterizing the power tracking capability of the device. Among them, the power response deviation can be obtained by the execution log statistics, that is, the target power and the actual power are recorded according to the control sampling period during the first power supply cycle, and the average level, maximum level and fluctuation degree of the deviation are statistically analyzed as the response deviation output; the power reachable characteristic can be obtained by statistically analyzing the percentage of time when the actual power reaches the target power, the time taken from the set change to reaching the target power, the percentage of the limit being reached and unable to continue to rise, etc., which are used to characterize the tracking ability and saturation characteristics. The power correction factor is determined based on the power response deviation, and the maximum allowable power supply in the second cycle is corrected based on the power correction factor to obtain the peak target power supply in the second cycle, so that the peak target power supply in the second cycle does not exceed the maximum allowable power supply in the second cycle and is higher than the target power supply in the steady state stage of the first power supply cycle. The power correction factor is preferably output by the segmented correction rule model: when the response deviation is low and the reachability is good, the peak target power is allowed to be closer to the maximum allowable power supply; when the response deviation is high or the reachability is poor, the peak target power is reduced and the power change constraint is tightened simultaneously; the segmented level and correction magnitude can be calibrated offline by the historical oscillation rate and protection trigger rate and can be configured. The power change constraint parameters for the second cycle are determined based on the power response deviation and the power reachable characteristic, so as to limit the allowable range of power regulation in the second power supply curve; The power change constraint parameters in the second cycle preferably include the allowable adjustment rate threshold and the adjustment amplitude threshold. When the response deviation is large or the reachability characteristic is poor, the allowable rise rate and single adjustment amplitude are reduced to suppress oscillation and overshoot. Based on the peak target power and target power supply of the second cycle, the second power supply cycle is divided into at least a secondary ramp-up phase, a high power phase, and a power drop-off phase. Based on the peak target power of the second cycle, the target power of the high power stage is determined, and the target power of the high power stage is made not to exceed the peak target power of the second cycle. Based on the power change constraint parameters of the second cycle, the power update rules for the second ramp-up stage are determined so that the power supply power can be gradually increased from the current power supply power to the target power supply power of the high power stage under the condition that the adjustment rate threshold and / or adjustment amplitude threshold are limited by the power change constraint parameters of the second cycle. Based on the power change constraint parameters of the second cycle, the power update rules for the power fall-off phase are determined so that the power supply gradually falls off under the condition that the adjustment rate threshold and / or adjustment amplitude threshold are limited by the power change constraint parameters of the second cycle, and the cumulative power supply ends the second power supply cycle when the pre-supply amount is reached. The power update rules for the secondary climb and fall phases can be implemented using a discrete control update algorithm: the target power is updated iteratively according to a preset control cycle, with each update limited by the adjustment rate threshold and the adjustment amplitude threshold. The fall phase ends when the cumulative power supply reaches the pre-supply target, thus ensuring that the risk exposure during the pre-supply phase is capped. Based on the initial power supply during the second ramp-up phase, the power update rules during the second ramp-up phase, the target power supply during the high-power phase, and the power update rules during the power fall-down phase, a piecewise curve of power supply changing over time is constructed and determined as the second power supply curve.

[0034] Specifically, in this embodiment, after the first power supply cycle ends, the power supply amount of the first cycle, the current power supply, and the equipment temperature are obtained. The difference between the pre-supply amount and the power supply amount of the first cycle is used to obtain the target power supply amount of the second cycle, so that the power supply target of the second stage is strictly aligned with the delivery schedule. At the same time, by performing a second temperature derating on the upper limit of the output power and extracting the power response deviation and power reachability characteristics by combining the execution results of the first stage, the power correction factor is determined by the power response deviation to correct the maximum allowable power supply power, thereby obtaining the peak target power supply power of the second cycle that does not exceed the thermal constraint and matches the reachability of the equipment. Furthermore, by generating the power change constraint parameters of the second cycle with the execution deviation and reachability characteristics, and decomposing the second power supply cycle into a two-stage ramp-up, high-power, and fall-down phase, the power increase, maintenance, and convergence are all executed under constraints, and the cycle ends when the cumulative delivered power reaches the pre-supply amount. Therefore, the second power supply curve can take into account both high charging efficiency and reachability in the risk controllable stage, reduce invalid commands, power oscillations, and energy waste caused by insufficient equipment tracking capability, and achieve risk exposure capping by hard termination with power threshold.

[0035] In one embodiment, in response to receiving virtual resources corresponding to the cumulative delivered electricity, a third power supply curve is determined based on the total amount of electricity to be supplied, and power is supplied to the power-consuming entity based on the third power supply curve until the power supply to the power-consuming entity is completed, including: Obtain the cumulative power supply, current power supply, and current device temperature at the end of the second power supply cycle; Obtain the current electricity demand of the electricity-consuming entity after receiving the virtual resources; The current demand for electricity is preferably obtained by combining the target electricity demand or target SOC reported by the electricity user after resource confirmation with the current SOC; when the user modifies the target midway, the latest target shall prevail; if the electricity user does not provide updates, the power supply control terminal can calculate based on the remaining target as a degradation plan. The execution results of the first power supply curve and the second power supply curve are obtained and parsed to obtain at least the change in physical power supply and the change in cumulative power supply on the source side corresponding to the first power supply cycle and the second power supply cycle. Among them, the change in physical power is preferably obtained by using the cumulative charge energy increment reported by the BMS. If it cannot be obtained directly, it is obtained by combining the SOC increment with the available battery capacity. The change in cumulative power supply on the source side is preferably obtained by the metering unit. The second power loss correction factor is determined based on the change in power consumption on the physical side and the change in cumulative power supply on the source side. The second power loss correction factor is used to calibrate the loss online within the session and correct the target power at the end of the session. It is preferably obtained by the following method: inputting the entity-side increment and the source-side output increment within the same time period into the online loss estimation function within the session, and outputting the loss estimation result of this session; the online estimation function can use a sliding time window to count and remove or limit outliers to avoid estimation jumps caused by a single abnormal sampling; the estimation result can be further set with a reasonable range and limited for protection. Based on the current power demand and the second power loss correction factor, determine the remaining power supply. Among them, the remaining power supply is the equipment-side remaining delivery target calculated by discounting the current net power demand based on the actual loss level in the session, thereby reducing oversupply or undersupply at the end of the session. Based on the current equipment temperature, the upper limit of output power is dated to obtain the maximum allowable power supply power for the third cycle. The target power supply for the high power in the third cycle is preferably referenced to the peak target power supply for the second cycle to maintain efficiency continuity, but is still constrained by the maximum allowable power supply for the third cycle; when the allowable power decreases due to temperature or limits, the maximum allowable power supply for the third cycle shall prevail. The target power supply for the high power supply in the third cycle is determined based on the peak target power supply in the second cycle, and the target power supply for the high power supply in the third cycle is kept below the maximum allowable power supply in the third cycle. The execution results of the first and second power supply curves are obtained and parsed to obtain the third cycle power change constraint parameters used to limit power regulation. Among them, the power change constraint parameters of the third cycle are preferably further tightened based on the constraints of the second cycle, combined with the latest temperature and execution deviation, so as to ensure power continuity during the transition from the second stage to the third stage and avoid sudden changes that may cause protection actions or oscillations. Under the constraint that the third power supply process does not have a preset fixed duration and ends when the cumulative power supply reaches the remaining power supply, the third power supply power curve is generated based on the current power supply, the high power target power supply in the third cycle, the remaining power supply, and the power change constraint parameters in the third cycle. Among them, the third power supply process does not have a fixed duration, which means that the power closed loop is used as the termination condition rather than the fixed time to terminate, so as to adapt to the duration changes caused by factors such as temperature derating; the third power supply power curve can be generated and executed by a discrete control update algorithm, which updates the target power according to a preset control cycle and is subject to the power change constraint parameters of the third cycle. Based on the target power supply of the third cycle and the remaining power supply, the third power supply process is divided into at least the direct climb stage, the energy replenishment steady state stage, and the termination fall-down stage. Based on the power change constraint parameters of the third cycle, the power update rules for the direct ramp-up phase are determined so that the power supply power is gradually increased from the current power supply power to the target power supply power of the third cycle high power under the condition that the adjustment rate threshold and / or adjustment amplitude threshold defined by the power change constraint parameters of the third cycle are met. Based on the high-power target power supply in the third cycle, the target power supply in the steady-state stage of energy replenishment is determined, and power supply is carried out under the constraint of the remaining power supply. Based on the power change constraint parameters of the third cycle, the power update rule for terminating the fallback phase is determined so that the power supply gradually falls back and the third power supply process ends when the cumulative power supply reaches the remaining power supply. Based on the initial power supply during the direct climb phase, the power update rule during the direct climb phase, the target power supply during the replenishment steady-state phase, and the power update rule during the termination fall-back phase, a piecewise curve of power supply changing with time is constructed and determined as the third power supply curve.

[0036] Specifically, in this embodiment, after virtual resource confirmation, the cumulative power supply, current power, and temperature at the end of the second stage are obtained. A second power loss correction factor is determined by combining the current power demand of the power-consuming entity after receiving the resource with the relationship between the entity-side power change and the source-side cumulative power supply change in the previous curve execution results. This allows for loss calibration of the remaining power supply, ensuring that the subsequent power supply target aligns with the actual achievable demand. Simultaneously, the maximum allowable power supply for the third cycle is obtained through temperature derating, aligning the high-power target power of the third cycle with the peak target power supply of the second cycle and ensuring it does not exceed the maximum allowable value. This maintains the previous high-efficiency power level while satisfying thermal boundary constraints. Furthermore, by introducing a third-cycle power change constraint parameter and dividing the third power supply process into direct ramp-up, replenishment steady-state, and termination fall-down stages, and using the cumulative power supply reaching the remaining power supply as the termination condition rather than a fixed duration, the third curve can adaptively converge with the remaining target. Therefore, given that the resource has been confirmed, the third stage can guarantee replenishment efficiency and power smoothness, and reduce oversupply and metering deviations at the end through loss calibration and power loop termination, thereby improving the certainty of final power supply completion and reducing energy waste.

[0037] In one embodiment, during the execution of the second power supply curve, the method further includes: Based on real-time collected data on the interaction behavior of electricity users, equipment operation data, and scenario data, the pre-supply risk score is periodically updated according to a preset risk assessment cycle to obtain the current risk score. The risk assessment cycle can be configured by the site strategy to update at a frequency of seconds to ten seconds, and the cycle can be shortened to enhance response when the risk increases or the interaction is unstable; the current risk score is preferably obtained by recalculating the real-time data using the aforementioned fusion model or weighted fusion function. The risk offset is determined based on the magnitude of the change between the current risk score and the initial pre-power supply risk score; The risk offset can be obtained by comparing the current risk score with the initial risk score, outputting the magnitude of risk increase or decrease, and normalizing it according to the scoring dimensions to ensure scale consistency; the initial pre-power supply risk score is preferably the benchmark value calculated at the beginning of the second curve or at the beginning of pre-power supply. The risk offset is coupled with the current cumulative delivered electricity to generate a risk delivery coupling factor, which characterizes the impact of risk changes on the remaining pre-power supply process under the current delivery progress. The risk delivery coupling factor is preferably output by a coupling function, which includes: first determining the current cumulative delivered electricity level relative to the pre-supply limit (e.g., early stage, middle stage, near the limit), and then assigning different weights to the risk offset based on the progress level; preferably, the impact of risk increase is amplified as the delivery gets closer to the limit, thereby more conservatively limiting the power to continue to rise; the coupling function can be implemented as a piecewise function or a lookup table rule, which is easy to interpret and configure. When the risk delivery coupling factor exceeds the preset locking threshold, the current power supply is locked and the subsequent power supply is restricted from increasing, thus forming a pre-power supply locking state. In the pre-power supply locked state, the risk delivery coupling factor is continuously monitored. When the risk delivery coupling factor falls below the release threshold, the pre-power supply locked state is released and power supply control based on the second power supply curve is restored. The locking and releasing thresholds can be configured by the operation strategy, and preferably the releasing threshold is lower than the locking threshold to form hysteresis and avoid frequent power locking / unlocking causing jitter. The thresholds can be set at different levels according to the site's risk preference. Locking the current power supply means that after entering the locking state, the current power will be used as the upper limit for the future. It is allowed to maintain or lower the current power supply, but not to raise it. After unlocking, control will continue according to the second power supply curve.

[0038] Specifically, in this embodiment, the risk score is updated at a preset period during the execution of the second power supply curve, and the risk offset is determined based on the change in the current risk score relative to the initial score. This extends the risk assessment from static evaluation to real-time quantification that evolves dynamically with the session. Furthermore, a risk delivery coupling factor is generated by coupling the risk offset with the current cumulative delivered power. This gives the impact of risk changes on the remaining deliverable space a differentiated weight under different delivery schedules. When the coupling factor exceeds the locking threshold, the current power is locked and subsequent power increases are restricted. When the coupling factor falls below the release threshold, the lock is released and curve control is restored. This forms a power lock / release mechanism with hysteresis characteristics. This can suppress power increases in real time when the risk increases sharply or uncertainty increases significantly, reduce the loss exposure caused by continuing to expand delivery in a high-risk window, and avoid control jitter caused by frequent start-stops, thereby improving the safety and stability of the pre-power supply phase.

[0039] In one embodiment, during the execution of the first power supply curve and / or the second power supply curve, the method further includes: The power execution deviation between the target power supply and the actual output power is collected in real time to obtain the power execution deviation sequence; The power execution deviation sequence can be formed by the control system recording the difference between the target power and the actual power according to a preset sampling period, and the sampling period is preferably consistent with the control period. Based on the power execution deviation sequence, power execution characteristic parameters including at least steady-state deviation amplitude, transient response hysteresis and power oscillation frequency are extracted; Among them, the steady-state deviation amplitude can be obtained by statistically analyzing the average level or fluctuation range of the deviation in the steady-state interval; the transient response lag can be obtained by statistically analyzing the time required for the actual power to reach the vicinity of the target after the target power changes by setting a value or the degree of lag; the power oscillation frequency can be obtained by statistically analyzing the number of peak and valley changes of the actual power or deviation within a certain time window, which is used to reflect control instability. Based on the power execution characteristic parameters, a power supply execution reliability index is generated to characterize the power controllability of the power output device in the current session. The power supply execution reliability index can be generated in the following way: steady-state deviation, transient lag, and oscillation frequency are mapped to anomalies of a uniform scale (the larger the anomaly, the higher the score), and then aggregated into an overall anomaly level according to a preset weight. The overall anomaly level is then mapped to a reliability score, so that the higher the anomaly level, the lower the reliability score. The weights can be calibrated offline based on the equipment control characteristics or historical oscillation / protection trigger sensitivity, and can be configured according to the equipment model. The power supply execution reliability index is used as a risk correction factor to participate in the correction calculation of the equipment risk index and / or comprehensive risk value, so as to obtain the corrected pre-power supply risk score. The risk correction can adopt segmented correction rules, including: no correction or slight correction when the confidence level is in the high range; increase the contribution ratio of the equipment risk index or comprehensive risk value when the confidence level is in the medium to low range; trigger stronger correction when the confidence level is in the extremely low range and can be linked to power lockout / derating strategies; after correction, the risk score is preferably protected by upper and lower limits, and can be smoothed by using sliding window or rate limit update methods to avoid drastic score jumps affecting control stability. The power supply execution reliability index is used as a risk correction factor to participate in the correction calculation of the equipment risk index and / or comprehensive risk value to obtain the corrected pre-power supply risk score. The correction calculation can be implemented through feasible segmented correction rules: no correction or slight correction when the reliability is in the high range; increase the risk contribution of the equipment risk index or comprehensive risk value when the reliability is in the medium to low range; trigger stronger correction and link power lock-in / derating strategies when the reliability is in the extremely low range. The correction results are preferably protected by upper and lower limits and can be updated smoothly using a sliding window to avoid drastic score jumps affecting control stability. Based on the corrected pre-supply risk score, the subsequent pre-supply quantity, power supply curve or risk control strategy are dynamically adjusted; Dynamic adjustments may include: lowering the upper limit of subsequent pre-supply, reducing the target power of subsequent curve peaks, tightening power change constraint parameters, entering the fallback phase earlier, triggering power lock-in strategies, or increasing the frequency of risk assessment updates, so as to make risk assessment and power control form a closed loop.

[0040] Specifically, in this embodiment, the deviation between the target power supply and the actual output power is collected in real time to form a deviation sequence. Then, execution characteristic parameters such as steady-state deviation amplitude, transient response hysteresis, and power oscillation frequency are extracted from the deviation sequence to provide a multi-dimensional characterization of the power controllability of the device in the current session, and a power supply execution reliability index is generated accordingly. Furthermore, this reliability index is used as a risk correction factor to participate in the correction of the device risk index and / or comprehensive risk value, so that the risk score not only reflects external interaction and scenario risks, but also reflects the inherent uncertainty source of control accessibility. Therefore, when the device tracking capability decreases or the control quality deteriorates, the risk score can be corrected in time and drive the dynamic adjustment of subsequent pre-supply power, power curve, or risk strategy, thereby reducing overshoot, oscillation, and invalid delivery caused by uncontrollable power, improving the closed-loop reliability of power regulation, and reducing energy waste.

[0041] It should be understood that, although Figure 2The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0042] In one embodiment, such as Figure 3 As shown, a power output control device is provided, comprising: The request receiving module is used to, in response to receiving a power request from an electricity-consuming entity, parse the power request and determine the total amount of power to be supplied by the power output device to the electricity-consuming entity. The risk assessment module is used to determine the pre-supply risk score for the electricity user based on the interaction data between the electricity user and the power output device, the equipment operation data of the power output device, and the scenario data corresponding to the location of the power output device. Based on the pre-supply risk score and the total amount of power to be supplied, the pre-supply amount is determined. The pre-power supply module is used to supply power to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, it determines a second power supply curve based on the pre-power supply amount, so as to continue to supply power to the power-consuming entity based on the second power supply curve. The resource conversion module is used to generate a virtual resource conversion request based on the cumulative delivered electricity and send it to the electricity-consuming entity when the cumulative delivered electricity reaches the pre-supply amount. The power supply module is used to respond to the receipt of virtual resources corresponding to the cumulative delivered power, determine the third power supply curve based on the total amount of power to be supplied, and supply power to the power-consuming entity based on the third power supply curve until the power supply to the power-consuming entity is completed.

[0043] Specific limitations regarding the power output control device can be found in the limitations of the power output control method described above, and will not be repeated here. Each module in the aforementioned power output control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in a computer device, or stored in software in the memory of a computer device, so that the processor can call and execute the corresponding operations of each module.

[0044] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a power output control method. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0045] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0046] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: In response to receiving a power request from an electricity user, the power request is parsed to determine the total amount of power to be supplied by the power output device to the electricity user. Based on the interaction data between the electricity-consuming entity and the power output device, the equipment operation data of the power output device, and the scenario data corresponding to the location of the power output device, a pre-supply risk score for the electricity-consuming entity is determined, and the pre-supply quantity is determined based on the pre-supply risk score and the total amount of power to be supplied. Power is supplied to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, a second power supply curve is determined based on the pre-supply amount, so as to continue to supply power to the power-consuming entity based on the second power supply curve. When the cumulative delivered electricity reaches the pre-supplied amount, a virtual resource conversion request is generated based on the cumulative delivered electricity and sent to the electricity-consuming entity; In response to receiving virtual resources corresponding to the cumulative delivered electricity, a third power supply curve is determined based on the total amount of electricity to be supplied, and power is supplied to the electricity-consuming entity based on the third power supply curve until the power supply to the electricity-consuming entity is completed.

[0047] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: In response to receiving a power request from an electricity user, the power request is parsed to determine the total amount of power to be supplied by the power output device to the electricity user. Based on the interaction data between the electricity-consuming entity and the power output device, the equipment operation data of the power output device, and the scenario data corresponding to the location of the power output device, a pre-supply risk score for the electricity-consuming entity is determined, and the pre-supply quantity is determined based on the pre-supply risk score and the total amount of power to be supplied. Power is supplied to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, a second power supply curve is determined based on the pre-supply amount, so as to continue to supply power to the power-consuming entity based on the second power supply curve. When the cumulative delivered electricity reaches the pre-supplied amount, a virtual resource conversion request is generated based on the cumulative delivered electricity and sent to the electricity-consuming entity; In response to receiving virtual resources corresponding to the cumulative delivered electricity, a third power supply curve is determined based on the total amount of electricity to be supplied, and power is supplied to the electricity-consuming entity based on the third power supply curve until the power supply to the electricity-consuming entity is completed.

[0048] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0049] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0050] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for controlling electrical energy output, characterized in that, include: In response to receiving a power request from an electricity-consuming entity, the power request is parsed to determine the total amount of power to be supplied by the power output device to the electricity-consuming entity; Based on the interaction data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scene data corresponding to the region where the power output device is located, a pre-supply risk score is determined for the power-consuming entity, and the pre-supply amount is determined based on the pre-supply risk score and the total amount of power to be supplied. Power is supplied to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the preset first power supply amount, a second power supply curve is determined based on the preset power supply amount, so as to continue to supply power to the power-consuming entity based on the second power supply curve. When the cumulative delivered electricity reaches the pre-supplied amount, a virtual resource conversion request is generated based on the cumulative delivered electricity and sent to the electricity-consuming entity; In response to receiving virtual resources corresponding to the cumulative delivered electricity, a third power supply curve is determined based on the total amount of electricity to be supplied, and power is supplied to the electricity-consuming entity based on the third power supply curve until the power supply to the electricity-consuming entity is completed.

2. The power output control method according to claim 1, characterized in that, The process of parsing the power request and determining the total amount of power to be supplied by the power output device to the power-consuming entity includes: Parsing the power request yields a session identifier, a power-consuming entity identifier, and entity energy demand information. The entity energy demand information includes at least one or more of the following: entity target power quantity and entity target state of charge. Obtain the current state of charge of the power-consuming entity, and determine the power demand of the power-consuming entity based on the entity's target power, the entity's target state of charge, and the current state of charge. The initial total amount of power to be supplied by the power output device to the power-consuming entity is determined based on the required power consumption. Based on the electricity-consuming entity identifier, the charging database is retrieved to obtain the historical charging records of the electricity-consuming entity; Based on the historical charging records and the device output parameters of the power output device, a power output loss factor is generated. Based on the power output loss factor, the initial total amount of power to be supplied is corrected, a corrected total amount of power to be supplied to the power-consuming entity is generated, and the corrected total amount of power to be supplied is determined as the total amount of power to be supplied by the power output device to the power-consuming entity.

3. The power output control method according to claim 1, characterized in that, The step of determining a pre-supply risk score for the electricity user based on the interaction data between the electricity user and the power output device, the device operation data of the power output device, and the scenario data corresponding to the location of the power output device includes: The interaction behavior data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scene data corresponding to the region where the power output device is located are obtained respectively. The interaction behavior data is analyzed to obtain a set of behavior feature parameters. The stability of the interaction behavior between the power-consuming entity and the power output device is determined based on the set of behavior feature parameters. The behavior risk index is determined based on the stability of the interaction behavior. The equipment operation data is analyzed to obtain a set of equipment characteristic parameters. The operating stability of the power output equipment is determined based on the set of equipment characteristic parameters, and the equipment risk index is determined based on the operating stability. The scene data is analyzed to obtain a scene feature parameter set. The scene risk level of the region where the power output device is located is determined based on the scene feature parameter set, and the scene risk index is determined based on the scene risk level. Based on the electricity-consuming entities, the power output devices, and the geographical region, a multi-entity association graph is constructed. In the multi-entity association graph, a set of neighboring nodes associated with the device node corresponding to the power output device is determined, and the historical anomaly records corresponding to the set of neighboring nodes are parsed to obtain a set of neighboring anomaly feature parameters. The degree of domain risk propagation is determined based on the set of neighboring anomaly feature parameters. Determine the domain risk propagation index based on the domain risk propagation degree; A comprehensive risk value is determined based on the behavioral risk index, the equipment risk index, the scenario risk index, and the domain risk propagation index, and the pre-power supply risk score is determined based on the mapping of the comprehensive risk value.

4. The power output control method according to claim 3, characterized in that, The process of parsing the historical anomaly records corresponding to the neighboring node set to obtain a neighborhood anomaly feature parameter set, and determining the domain risk propagation degree based on the neighborhood anomaly feature parameter set, includes: The historical anomaly records are parsed to obtain an anomaly event set, and a neighborhood anomaly feature parameter set is determined based on the anomaly event set. The neighborhood anomaly feature parameter set includes at least one or more of the following: anomaly event occurrence frequency parameter, anomaly event severity parameter, and anomaly event time decay parameter. The intensity of a neighborhood anomaly is determined based on the frequency parameter of the anomaly event and the severity parameter of the anomaly event, and the intensity of the neighborhood anomaly is attenuated based on the time decay parameter of the anomaly event to obtain the attenuated anomaly intensity. Based on the association between multiple neighboring nodes in the neighboring node set and the device node, the attenuation anomaly intensity is weighted and aggregated to obtain the neighborhood propagation risk value; The risk propagation degree of the neighborhood is determined based on the neighborhood propagation risk value, so as to at least characterize the risk contribution of the neighborhood node anomaly to the target interactive session through multi-entity association relationship.

5. The power output control method according to claim 1, characterized in that, The determination of the pre-supply quantity based on the pre-supply risk score and the total amount of power to be supplied includes: Based on a preset pre-power supply ratio mapping function, the pre-power supply risk score is mapped to obtain a pre-power supply ratio coefficient, so that the pre-power supply ratio coefficient decreases as the pre-power supply risk score increases; The initial pre-powered quantity is obtained by calculating the total amount of power to be supplied based on the pre-powered quantity ratio coefficient. Based on preset minimum and maximum pre-supply thresholds, the initial pre-supply is limited to obtain the pre-supply amount.

6. The power output control method according to claim 1, characterized in that, Before supplying power to the power-consuming entity based on a preset first power supply curve, the method further includes: Based on the device operating parameters of the power output device and the total amount of power to be supplied, a first power supply curve is generated; The first power supply curve is determined in the following way: Analyze the operating parameters of the equipment to determine the upper limit of the output power and the equipment temperature of the power output equipment; Based on the device temperature, the upper limit of the output power is derating to obtain the maximum allowable power supply, and power variation constraints are determined based on the maximum allowable power supply. The power variation constraints include at least the upper limit of power ramp-up speed and the upper limit of power step. Based on the total amount of power to be supplied and the first power supply, a preset first power supply cycle is planned, and the power supply process is divided into at least an initial stage, a ramp-up stage and a steady-state stage within the first power supply cycle. Based on the first power supply and the maximum allowable power supply, the target power supply for the steady-state stage is determined, and the target power supply for the steady-state stage does not exceed the maximum allowable power supply. Based on the power ramp-up speed limit and the power step limit, the power update rule for the ramp-up stage is determined so that the power supply power gradually ramps up to the target power supply power while satisfying the constraints of the power ramp-up speed limit and the power step limit. Based on the initial power supply in the initial stage, the power update rule in the ramp-up stage, and the target power supply in the steady-state stage, a piecewise curve of power supply changing over time is constructed, and the execution of the first power supply curve is terminated when the cumulative delivered power reaches the first power supply amount.

7. The power output control method according to claim 6, characterized in that, The step of determining a second power supply curve based on the pre-supply amount, and continuing to supply power to the electricity-consuming entity based on the second power supply curve, includes: Obtain the power supply amount of the first cycle at the end of the first power supply cycle, the current power supply power, and the current device temperature; Based on the pre-supply amount and the first cycle supply amount, determine the target supply amount for the second cycle; Based on the current device temperature, the upper limit of the output power is corrected by a second temperature derating to obtain the maximum allowable power supply power for the second cycle. The execution result of the first power supply curve is obtained and parsed to obtain at least the power response deviation within the first power supply cycle and at least the power reachable characteristic quantity characterizing the device's power tracking capability. Based on the power response deviation, a power correction factor is determined, and the maximum allowable power supply power of the second cycle is corrected based on the power correction factor to obtain the peak target power supply power of the second cycle, so that the peak target power supply power of the second cycle does not exceed the maximum allowable power supply power of the second cycle, and is higher than the steady-state target power supply power of the first power supply cycle. The second-cycle power change constraint parameters are determined based on the power response deviation and the power achievable characteristic to limit the allowable range of power regulation in the second power supply curve; Based on the peak target power and target power supply of the second cycle, the second power supply cycle is divided into at least a two-stage ramp-up phase, a high-power phase, and a power drop-off phase. Based on the second cycle peak target power supply, the target power supply for the high power phase is determined, and the target power supply for the high power phase is made not to exceed the second cycle peak target power supply. Based on the second cycle power change constraint parameters, the power update rules for the second ramp-up stage are determined so that the power supply power can be gradually increased from the current power supply power to the target power supply power of the high power stage, provided that the adjustment rate threshold and / or adjustment amplitude threshold defined by the second cycle power change constraint parameters are met. Based on the second cycle power change constraint parameters, the power update rules for the power fall-off phase are determined so that the power supply gradually falls off under the condition that the adjustment rate threshold and / or adjustment amplitude threshold defined by the second cycle power change constraint parameters are met, and the cumulative power supply ends the second power supply cycle when the pre-supply amount is reached. Based on the initial power supply of the second ramp-up phase, the power update rule of the second ramp-up phase, the target power supply of the high-power phase, and the power update rule of the power fall-down phase, a piecewise curve of power supply changing with time is constructed and determined as the second power supply curve.

8. A power output control device, characterized in that, The device includes: The request receiving module is used to, in response to receiving a power request from an electricity-consuming entity, parse the power request and determine the total amount of power to be supplied by the power output device to the electricity-consuming entity; The risk assessment module is used to determine the pre-supply risk score for the power-consuming entity based on the interaction behavior data between the power-consuming entity and the power output device, the device operation data of the power output device, and the scenario data corresponding to the region where the power output device is located, and to determine the pre-supply amount based on the pre-supply risk score and the total amount of power to be supplied. The pre-supply module is used to supply power to the power-consuming entity based on a preset first power supply curve, and when the cumulative delivered power reaches the first power supply amount, to determine a second power supply curve based on the pre-supply amount, so as to continue supplying power to the power-consuming entity based on the second power supply curve. The resource conversion module is used to generate a virtual resource conversion request based on the cumulative delivered electricity and send it to the electricity-consuming entity when the cumulative delivered electricity reaches the pre-supply amount. The power supply module is used to respond to receiving virtual resources corresponding to the cumulative delivered power, determine a third power supply curve based on the total amount of power to be supplied, and supply power to the power-consuming entity based on the third power supply curve until the power supply to the power-consuming entity is completed.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images