A virtual power plant scheduling method and system based on multiple interaction modes

Abstract

The application relates to a virtual power plant scheduling method and system based on multiple interaction modes. The scheduling method comprises the following steps: acquiring a stress signal of a distributed energy resource group, and quantifying a mode stress index of the resource group according to the stress signal; monitoring the mode stress index in real time, and issuing a stress early warning signal when the mode stress index approaches a preset stress limit; adjusting the interaction mode parameters of the resource group according to the stress early warning signal and a current power scheduling demand; predicting whether there is a scheduling gap or whether the early warning level is high after the adjustment based on the adjusted interaction mode parameters; if there is a scheduling gap or the early warning level is high, the adjustment is made in advance in cooperation with a standby resource group, and a scheduling instruction is issued based on the availability intention and acceptance conditions of the standby resource group; scheduling the power of each resource group according to the scheduling instruction, monitoring and verifying the actual scheduling response effect of each resource group, and feeding back the actual scheduling response effect to the stress signal acquisition link.

Description

Technical Field

[0001] This application relates to the field of virtual power plant dispatching, and in particular to a virtual power plant dispatching method and system based on multiple interaction modes. Background Technology

[0002] Virtual power plants are playing an increasingly critical role in aggregating distributed energy resources and controllable loads, but their scheduling faces multiple complex challenges, particularly the need to manage various interaction methods and diverse resources simultaneously.

[0003] The core challenge of dispatching lies in integrating diverse interaction methods with grid commands of varying priorities: virtual power plants control equipment through direct control, local system command forwarding, and manual intervention, each differing significantly in response speed, control accuracy, and reliability; meanwhile, grid commands are categorized into emergency peak shaving and routine load adjustment. The key to improving the response efficiency of virtual power plants and the grid's support capacity lies in precisely matching these interaction capabilities with the adjustment capabilities of various resources.

[0004] Furthermore, problems can easily arise in the time calibration stage during scheduling execution: To ensure that distributed resources (such as energy storage and industrial loads) accurately execute instructions, resource units need to perform microsecond-level delay calibration between the scheduling instruction time and local time to eliminate communication delays and equipment response differences, ensuring that instructions take effect on time. However, when the accuracy of the virtual power plant's central server's time base decreases, coupled with the cumulative deviation of the distributed terminal's local clock over a long period of time, the time difference between the two can exceed the microsecond-level tolerance range, causing misjudgments in the timestamp-dependent calibration logic—for example, an instruction that should be received and executed 100 microseconds later may be incorrectly interpreted as being executed immediately or delayed by hundreds of microseconds, thus disrupting the order and timing of instruction execution.

[0005] To address this, we propose a virtual power plant scheduling method and system based on multiple interaction modes. Summary of the Invention

[0006] This application provides a virtual power plant dispatching method and system based on multiple interaction modes, which at least solves the problem that the limitations of related technologies in determining trunk line coordinated control schemes lead to poor control effects.

[0007] In a first aspect, this application provides a virtual power plant scheduling method based on multiple interaction modes, comprising the following steps: The pressure signal of the distributed energy resource group is obtained, and the mode pressure index of the resource group is quantified and generated based on the pressure signal. The resource group includes a high-voltage resource group, a low-voltage resource group and a backup resource group. The pressure signal includes user experience pressure, equipment health pressure and communication carrying pressure. The mode pressure index is monitored in real time, and a pressure warning signal is issued when the mode pressure index approaches or reaches the preset pressure limit. Based on the pressure warning signal and the current power dispatch demand, the interaction mode parameters of the resource group are adjusted, wherein the adjustment includes reducing the dispatch intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. Based on the adjusted interaction mode parameters, it is anticipated whether there is a scheduling gap or a high warning level after the adjustment. If a scheduling gap or a high warning level is anticipated, a proactive consultation is held with the backup resource group, and a scheduling instruction is issued based on the availability intention and acceptance conditions of the backup resource group. The power of each resource group is dispatched according to the dispatching instructions, the actual dispatching response effect of each resource group is monitored and verified, and the actual dispatching response effect is fed back to the pressure signal acquisition stage.

[0008] Optionally, adjusting the interaction mode parameters of the resource group based on the pressure warning signal and current power dispatch demand includes: Acquire instantaneous voltage and instantaneous current data of the battery, and extract the micro-degradation characteristic index of the battery based on the instantaneous voltage and instantaneous current data; The first deviation between the actual output energy of the battery and the theoretically expected output energy is obtained, and the first deviation is used as the energy conversion efficiency fluctuation index. Obtain instruction data packet information and identify a communication perturbation fingerprint based on the instruction data packet information, wherein the instruction data packet information includes a timestamp, a receiving timestamp, a sequence number, and an arrival order; The instantaneous power consumption change of the battery is obtained, and it is determined whether there is a time correlation between the communication perturbation fingerprint and the instantaneous power consumption change; Obtain the actual response data of the resource group, quantify the second deviation between the actual response data and the pre-established expected response baseline of the resource group, and use the second deviation as the silent adjustment index; Based on the micro-deterioration characteristic index, the energy conversion efficiency fluctuation index, the communication perturbation fingerprint, the time correlation, and the silent adjustment index, the combined effect is evaluated using a fuzzy logic reasoning mechanism to generate a composite stress index. Based on the composite pressure index and the current power dispatch demand, the interaction mode parameters of the resource groups are adjusted, wherein the adjustment includes reducing the dispatch intensity of the high-voltage resource groups and adjusting the interaction parameters of the low-voltage resource groups to obtain a response.

[0009] Optionally, adjusting the interaction mode parameters of the resource group based on the composite pressure index and current power dispatch demand includes: Based on the composite pressure index and pre-acquired historical power dispatch data, a long-term impact baseline for resource groups is established, wherein the long-term impact baseline includes user comfort threshold, equipment lifespan degradation rate, and the trend of changes in user participation willingness. Based on the long-term impact baseline, the degree of deviation of the adjustment from the long-term impact baseline is predicted, and based on the degree of deviation, a dynamic adjustment mechanism is introduced, wherein the dynamic adjustment mechanism includes dynamically adjusting the scheduling intensity limit of the resource group, introducing a rotation scheduling mechanism, and initiating deep negotiation of the standby resource group; Based on the aforementioned dynamic adjustment mechanism, the interaction mode parameters of the resource group are dynamically adjusted, wherein the adjustment includes reducing the scheduling intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response.

[0010] Optionally, adjusting the interaction mode parameters of the resource group based on the composite pressure index and current power dispatch demand includes: The rate of change of environmental parameters and the rate of change of power grid load are continuously monitored. When the rate of change of environmental parameters or the rate of change of power grid load exceeds a preset rate of change threshold, a rapid reassessment of the composite pressure index is initiated. During the rapid reassessment process, the weights related to the environment and power grid conditions in the calculation of the composite pressure index are dynamically increased. When the composite pressure index of the high-pressure resource group rises in a short period of time and exceeds the preset warning threshold, a secondary adjustment process is triggered. The secondary adjustment process further reduces the scheduling intensity of the high-voltage resource group and simultaneously initiates fine-tuning of the interaction parameters of the low-voltage resource group.

[0011] Optionally, the continuous monitoring of the rate of change of environmental parameters includes: The rate of change of single-domain environmental parameters collected by an environmental sensor network in different sub-regions is obtained. The environmental sensor network includes temperature and humidity sensors deployed in commercial complexes, as well as temperature and humidity sensors deployed near industrial energy storage systems. Acquire satellite remote sensing data, and extract the rate of change of macroscopic environmental parameters in the virtual power plant coverage area based on the satellite remote sensing data; Acquire environmental sensor data integrated within the distributed energy resource group itself, and calculate the rate of change of local environmental parameters of the distributed energy resource group based on the environmental sensor data; Determine the sensitivity of the distributed energy resource group to local environmental changes; Based on the rate of change of the single-domain environmental parameters, the rate of change of the macro-environmental parameters, the rate of change of the local environmental parameters, and the sensitivity, the rate of change of the environmental parameters of each sub-region is weighted and fused to obtain the rate of change of the environmental parameters of the entire domain.

[0012] Optionally, the continuous monitoring of the power grid load change rate includes: Acquire real-time telemetry data from the power grid side, and calculate the instantaneous load change rate of each sub-region based on the real-time telemetry data, wherein the real-time telemetry data includes feeder power, bus voltage and current data of each substation; The system acquires real-time power output and consumption data of each distributed energy resource group within the virtual power plant, and aggregates and calculates the instantaneous load change rate of the entire virtual power plant based on the real-time power output and consumption data. Obtain short-term load forecast data and actual load data provided by the power grid dispatch center, and calculate the rate of change of the deviation between the short-term load forecast data and the actual load data based on the short-term load forecast data and the actual load data; Determine the response characteristics of distributed energy resource groups to changes in local grid load; Based on the instantaneous load change rate of each sub-region, the instantaneous load change rate of the virtual power plant as a whole, the deviation change rate, and the response characteristics, the power grid load change rate of each sub-region is weighted and fused to obtain the power grid load change rate of the entire region.

[0013] Optionally, the step of initiating a rapid reassessment of the composite stress index when the rate of change of the environmental parameters or the rate of change of the power grid load exceeds a preset rate of change threshold includes: Acquire historical environmental parameter change data, historical power grid load change data, and the sensitivity of each resource group to local environmental changes within the coverage area of ​​the virtual power plant; Based on the historical environmental parameter change data, the historical power grid load change data, and the sensitivity, dynamically adjust the environmental parameter change rate threshold and the power grid load change rate threshold for each sub-region; The rate of change of environmental parameters in the entire region is compared with the dynamically adjusted threshold of the rate of change of environmental parameters, and the rate of change of power grid load in the entire region is compared with the dynamically adjusted threshold of the rate of change of power grid load. When the rate of change of environmental parameters in the entire region exceeds the threshold of the dynamically adjusted rate of change of environmental parameters, or when the rate of change of power grid load in the entire region exceeds the threshold of the dynamically adjusted rate of change of power grid load, a rapid reassessment of the composite pressure index is initiated.

[0014] Optionally, in the rapid reassessment process, dynamically increasing the weights related to the environment and power grid status in the calculation of the composite stress index includes: During the rapid reassessment process, the deviation trend of user comfort is continuously monitored, and the cumulative changes of key operating parameters of the equipment are continuously monitored. When the user comfort deviation trend continues to worsen or the cumulative changes in the key operating parameters of the device exceed a preset change threshold, the weights of the user experience stress and the device health stress are increased compensatorily.

[0015] Optionally, during the rapid reassessment process, continuously monitoring the trend of user comfort deviation includes: Acquire environmental parameter data related to user comfort, wherein the environmental parameter data includes indoor temperature, humidity, CO2 concentration, and light intensity; Acquire device operating status data and local operation records from the user terminal. The device operating status data includes the set temperature, operating mode, and fan speed of the smart air conditioner, and the brightness and color temperature of the smart lighting. The local operation records include the user's manual adjustment behavior of the smart air conditioner and smart lighting. Acquire information on external interference events, including construction noise outside the building and early warnings of abnormal weather. Based on the environmental parameter data, the equipment operating status data, the local operation records, and the external interference event information, identify the non-scheduled impact of non-scheduled factors on user comfort deviation; Based on the non-scheduling effects, the user comfort deviation trend is corrected to obtain the comfort deviation trend caused by scheduling.

[0016] Secondly, this application provides a virtual power plant dispatching system based on multiple interaction modes, the system comprising: The pressure index generation module is used to acquire pressure signals of distributed energy resource groups and quantify and generate mode pressure indicators of the resource groups based on the pressure signals. The resource groups include high-voltage resource groups, low-voltage resource groups and backup resource groups. The pressure signals include user experience pressure, equipment health pressure and communication carrying pressure. The pressure warning module is used to monitor the mode pressure index in real time and issue a pressure warning signal when the mode pressure index approaches or reaches the preset pressure limit. The parameter adjustment module is used to adjust the interaction mode parameters of the resource group according to the pressure warning signal and the current power dispatch demand. The adjustment includes reducing the dispatch intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. The backup resource negotiation module is used to predict whether there is a scheduling gap or whether the warning level is high after the adjustment based on the adjusted interaction mode parameters. If a scheduling gap or a high warning level is expected, it will proactively negotiate with the backup resource group and issue a scheduling instruction based on the availability intention and acceptance conditions of the backup resource group. The scheduling module is used to schedule the power of each resource group according to the scheduling instructions, monitor and verify the actual scheduling response effect of each resource group, and feed back the actual scheduling response effect to the pressure signal acquisition stage.

[0017] Compared with related technologies, the virtual power plant scheduling method and system based on multiple interaction modes provided in this application have at least the following technical advantages: By acquiring various pressure signals from distributed energy resource groups, such as user experience pressure, equipment health pressure, and communication capacity pressure, and quantifying them to generate mode pressure indicators, the system reflects the real-time operating status of the virtual power plant. When the mode pressure indicators approach or reach preset pressure limits, the system promptly issues pressure warning signals, providing early warning information for subsequent dispatch adjustments. Based on the pressure warning signals and current power dispatch needs, the system dynamically adjusts the dispatch intensity of high-voltage resource groups and the interaction parameters of low-voltage resource groups to obtain responses, achieving differentiated and refined management of different resource groups. Furthermore, this application proactively negotiates with backup resource groups and issues dispatch instructions when necessary, ensuring system stability in the event of dispatch gaps or high warning levels. By monitoring and verifying the actual dispatch response effects of each resource group and feeding these effects back to the pressure signal acquisition stage, a closed-loop control is formed, further optimizing the dispatch strategy.

[0018] In summary, this application, through multi-dimensional pressure perception, dynamic scheduling adjustment, and closed-loop feedback mechanisms, can fully address the complex challenges faced in the scheduling of existing virtual power plants. It also improves scheduling efficiency, system reliability, and grid support capabilities, overcoming shortcomings in existing technologies such as instruction execution errors caused by time synchronization deviations. This demonstrates significant technological advancement and practical value.

[0019] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart illustrating a virtual power plant scheduling method based on multiple interaction modes, according to an exemplary embodiment.

[0021] Figure 2 This is a flowchart illustrating step S3 according to an exemplary embodiment.

[0022] Figure 3 This is a flowchart illustrating step S37 according to an exemplary embodiment.

[0023] Figure 4 This is a flowchart illustrating step S37 according to another exemplary embodiment.

[0024] Figure 5 This is a flowchart illustrating step S37b2 according to an exemplary embodiment.

[0025] Figure 6 This is a block diagram illustrating a virtual power plant dispatching system based on multiple interaction modes according to an exemplary embodiment. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to 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. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0027] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any creative effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0028] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0029] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0030] In related technologies, the core challenge of dispatching lies in integrating diverse interaction methods with grid commands of varying priorities. Virtual power plants control equipment through direct control, local system command forwarding, and manual intervention, each differing significantly in response speed, control accuracy, and reliability. Meanwhile, grid commands are categorized into emergency peak shaving and routine load adjustment. The key to improving the response efficiency of virtual power plants and the grid's support capacity lies in precisely matching these interaction capabilities with the adjustment capabilities of various resources.

[0031] Furthermore, problems can easily arise in the time calibration stage during scheduling execution: To ensure that distributed resources (such as energy storage and industrial loads) accurately execute instructions, resource units need to perform microsecond-level delay calibration between the scheduling instruction time and local time to eliminate communication delays and equipment response differences, ensuring that instructions take effect on time. However, when the accuracy of the virtual power plant's central server's time base decreases, coupled with the cumulative deviation of the distributed terminal's local clock over a long period of time, the time difference between the two can exceed the microsecond-level tolerance range, causing misjudgments in the timestamp-dependent calibration logic—for example, an instruction that should be received and executed 100 microseconds later may be incorrectly interpreted as being executed immediately or delayed by hundreds of microseconds, thus disrupting the order and timing of instruction execution.

[0032] Based on the above, embodiments of the present invention provide a virtual power plant scheduling method and system based on multiple interaction modes, which will be described in detail below with reference to specific embodiments and accompanying drawings.

[0033] Example 1 This invention provides a virtual power plant scheduling method based on multiple interaction modes. Figure 1 This is a flowchart illustrating a virtual power plant scheduling method based on multiple interaction modes, according to an exemplary embodiment. Figure 1 As shown, this scheduling method is implemented in a virtual power plant dispatch center environment. This dispatch center is connected to various distributed energy resource groups through an advanced communication network and is equipped with a data acquisition, processing, analysis, and decision support system, including the following steps: S1. Obtain the pressure signal of the distributed energy resource group, and quantify the mode pressure index of the resource group based on the pressure signal. The resource group includes high-voltage resource group, low-voltage resource group and backup resource group. The pressure signal includes user experience pressure, equipment health pressure and communication carrying pressure. In this embodiment, a distributed energy resource group refers to a collection of multiple decentralized energy production, storage, and consumption units, such as solar power systems, wind turbines, energy storage systems, and controllable loads. These resource groups can be further divided into high-voltage resource groups, low-voltage resource groups, and reserve resource groups based on their grid response characteristics and scheduling priorities. High-voltage resource groups typically refer to resources that respond quickly to scheduling commands, have high control precision, and have a significant impact on the grid, such as large-scale energy storage power stations or industrial interruptible loads. Low-voltage resource groups may include resources with slower response times, relatively lower control precision, or those sensitive to user experience, such as air conditioning systems in commercial buildings. Reserve resource groups refer to resources that can be activated to provide additional support when conventional scheduling cannot meet demand, such as backup generator sets or additional interruptible loads.

[0034] Stress signals are indicators used to measure the operational status of resource groups and user experience, including user experience stress, equipment health stress, and communication load stress. User experience stress reflects the impact of scheduling on user comfort or production activities. Equipment health stress focuses on the potential damage scheduling can cause to equipment lifespan and operational status. Communication load stress measures the load and reliability of the communication network during scheduling command transmission. The mode stress index is a comprehensive indicator quantified from the above stress signals, used to assess the overall stress level of resource groups under the current scheduling mode.

[0035] Furthermore, stress signals are acquired through sensors and monitoring devices deployed across various distributed energy resource clusters. For example, user experience stress is assessed by monitoring environmental parameters such as indoor temperature, humidity, and light intensity, combined with user feedback data or pre-defined user comfort models. Equipment health stress is obtained by monitoring key operating parameters of equipment, such as operating temperature, vibration, current, and voltage, combined with equipment lifespan models and fault prediction algorithms. Communication capacity stress is assessed by monitoring indicators such as bandwidth utilization, packet loss rate, and latency of the communication network. After acquiring these raw stress signals, methods such as weighted averaging, fuzzy logic inference, or machine learning models are used to quantify and integrate these multi-dimensional stress signals into a unified pattern stress index. For example, weights are assigned to user experience stress, equipment health stress, and communication capacity stress, and then they are weighted and summed to obtain the pattern stress index.

[0036] S2. Real-time monitoring of mode pressure indicators, and issuance of pressure warning signals when mode pressure indicators approach or reach preset pressure limits; In this embodiment, the preset pressure limit is a threshold for the model pressure index. When the model pressure index approaches or reaches this limit, it indicates that the resource group may be facing excessive pressure, requiring intervention. Real-time monitoring of the model pressure index is achieved by periodically repeating the above-described pressure signal acquisition and model pressure index generation process. For example, the model pressure index can be updated every one minute or five minutes. The preset pressure limit can be determined based on historical data, expert experience, or system design requirements. When the monitored model pressure index exceeds a certain percentage (e.g., 90%) of the limit, a "approaching the preset pressure limit" warning signal is issued; when the model pressure index fully reaches or exceeds the preset pressure limit, a "reaching the preset pressure limit" warning signal is issued. Furthermore, these warning signals can be internal system notifications or displayed to the dispatcher through a visual interface.

[0037] S3. Based on the pressure warning signal and the current power dispatch demand, adjust the interaction mode parameters of the resource group, including reducing the dispatch intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. In this embodiment, interaction mode parameters refer to parameters used to control the manner and intensity of resource groups' response to dispatch instructions, such as dispatch intensity, response time, and willingness to participate. When a pressure warning signal is received, the dispatch system will combine the current power dispatch demand (such as peak or off-peak load or frequency regulation demand of the power grid) to determine how to adjust the interaction mode parameters. For example, if the warning signal indicates that a high-voltage resource group is facing significant equipment health pressure, and the current power dispatch demand allows, the dispatch system can reduce the dispatch intensity of that high-voltage resource group, reducing its output or load reduction to alleviate equipment burden. For low-voltage resource groups, because they are sensitive to user experience, the dispatch system may adjust their interaction parameters, such as through a gentler incentive mechanism, a longer response time window, or more flexible dispatch instructions, to improve their willingness to participate in dispatch and the reliability of their response. For example, a "comfort-first" dispatch instruction can be sent to a commercial complex, allowing it to adjust the air conditioning set temperature within a certain range, rather than forcibly reducing the load.

[0038] S4. Based on the adjusted interaction mode parameters, predict whether there is a scheduling gap or whether the warning level is high after the adjustment. If a scheduling gap or a high warning level is expected, proactively negotiate with the backup resource group and issue a scheduling instruction based on the availability intention and acceptance conditions of the backup resource group. In this embodiment, after adjusting the interaction mode parameters, the dispatching system performs a predictive assessment to simulate the impact of the adjusted dispatching scheme on grid load balance and pressure indicators. If the prediction results show that a dispatching gap still exists (i.e., power supply and demand imbalance) or the overall warning level remains high, the system will proactively initiate negotiations with the reserve resource group. The negotiation process may include sending dispatching intentions to the reserve resource group, obtaining its availability (e.g., available power capacity) and acceptance conditions (e.g., price, response time) within a specific time period. Based on this information, the dispatching system selects the most suitable reserve resource group and issues specific dispatching instructions to it.

[0039] S5. Dispatch the power of each resource group according to the dispatch instructions, monitor and verify the actual dispatch response effect of each resource group, and feed back the actual dispatch response effect to the pressure signal acquisition link. In this embodiment, when a dispatch command is issued, the virtual power plant dispatch center monitors the power output or load reduction of each resource group in real time and compares it with the dispatch command to verify the actual dispatch response effect. For example, real-time power data is obtained through smart meters or SCADA systems. This actual response effect data, including the timeliness, accuracy, and continuity of the response, is fed back to the pressure signal acquisition stage as a new pressure signal (such as user experience pressure, equipment health pressure, or communication capacity pressure), forming a closed-loop control system. This feedback mechanism enables the system to dynamically adjust the generation strategy of mode pressure indicators and the adjustment strategy of interaction mode parameters according to the actual operating conditions, thereby achieving continuous optimization and adaptive dispatch.

[0040] In the technical solutions of the above embodiments, an intelligent, flexible, and adaptive scheduling system is formed by introducing mode pressure indicators, pressure early warning mechanisms, and interactive mode parameter adjustments based on early warning signals and scheduling requirements, combined with the predictive negotiation of the reserve resource group and the feedback loop of scheduling instructions. Specifically, step S1 of this application solves the problem of the lack of comprehensive and quantitative evaluation of the operating status of resource groups and user experience in the prior art, providing a data foundation for subsequent intelligent decision-making. For example, traditional methods may only focus on power parameters, while ignoring non-power factors such as user comfort or equipment lifespan, which may lead to scheduling schemes that, while meeting power demand, impair user experience or accelerate equipment aging. This application, by comprehensively considering these pressure signals, more comprehensively reflects the true state of the resource group.

[0041] Secondly, the early warning mechanism in step S2 of this application enables the scheduling system to detect potential risks in advance, preventing resource groups from failing due to over-scheduling or severely degrading user experience. Compared to existing technologies that may only respond passively after a problem occurs, the early warning mechanism of this application improves the foresight and security of scheduling.

[0042] Furthermore, step S3 of this application can adopt differentiated scheduling strategies based on the characteristics and current pressure status of different resource groups. For example, for high-voltage resource groups, when their pressure is too high, the system will actively reduce the scheduling intensity to protect the health of the equipment; for low-voltage resource groups, more flexible adjustment of interactive parameters will be used to maximize their response while ensuring user experience. This contrasts sharply with the "one-size-fits-all" scheduling method that may be used in existing technologies, which often fails to take into account the differences between different resource groups, resulting in low scheduling efficiency or significant negative impacts.

[0043] Furthermore, in step S4 of this application, when a scheduling gap is expected to persist after adjustments or the warning level is high, the system proactively negotiates with the backup resource group and issues scheduling instructions based on their availability intentions and acceptance conditions. This mechanism addresses the problem that a single resource group may not be able to meet scheduling needs in complex and ever-changing environments. By introducing backup resources, it enhances the overall resilience and reliability of the virtual power plant. Traditional methods may only urgently search for backup resources when a scheduling gap occurs, resulting in long response times and high costs. In contrast, the predictive negotiation of this application significantly improves the efficiency and economy of scheduling.

[0044] Finally, the feedback mechanism in step S5 of this application forms a closed-loop control system. This feedback mechanism enables the scheduling system to continuously learn and optimize based on actual operating conditions, thereby continuously improving the accuracy of mode pressure indicators and the effectiveness of interactive mode parameter adjustment strategies. This has significant advantages compared to existing technologies that may lack effective feedback mechanisms, leading to scheduling strategies failing to adapt to changes in a timely manner.

[0045] In one possible design, Figure 2 This is a flowchart illustrating step S3 according to an exemplary embodiment. (Refer to the attached diagram.) Figure 2 Step S3 includes: S31. Obtain the instantaneous voltage and instantaneous current data of the battery, and extract the micro-degradation characteristic index of the battery based on the instantaneous voltage and instantaneous current data. In this embodiment, after acquiring the instantaneous voltage and current data of the battery, the equivalent circuit model of the battery or machine learning algorithm is used to analyze the changing trend of these instantaneous data over time, thereby extracting a micro-degradation characteristic index that reflects changes in the internal chemical or physical structure of the battery. The micro-degradation characteristic index is used to quantify the degree of aging or health status of the battery at the microscopic level, such as an increase in internal resistance or a rate of capacity decay. Specifically, the micro-degradation characteristic index can be understood as a refined indicator of the battery's State of Health (SOH), used to capture early, subtle changes in battery performance.

[0046] S32. Obtain the first deviation between the actual output energy of the battery and the theoretical expected output energy, and use the first deviation as the energy conversion efficiency fluctuation index; In this embodiment, the first deviation is obtained by measuring the actual output energy of the battery under a specific scheduling command in real time and comparing it with the expected output energy calculated based on the battery's current health state and theoretical model. The first deviation is used as an energy conversion efficiency fluctuation index to reflect whether there is abnormal loss or efficiency decline in the battery during the energy conversion process, such as efficiency fluctuations caused by factors such as temperature and charge / discharge rate.

[0047] S33. Obtain instruction data packet information and identify the communication perturbation fingerprint based on the instruction data packet information, wherein the instruction data packet information includes timestamp, receiving timestamp, sequence number and arrival order; In this embodiment, the instruction data packet information specifically refers to the data packet containing control instructions sent by the virtual power plant dispatch center to the distributed energy resource group. The data packet includes information such as timestamps, reception timestamps, sequence numbers, and arrival order, which can be used to analyze delays, losses, or out-of-order delivery of data packets during transmission. Based on this information, communication perturbation fingerprints can be identified. For example, by calculating fluctuations in round-trip time (RTT), packet loss rate, and jitter, the stability and reliability of the communication link can be quantified.

[0048] S34. Obtain the instantaneous power consumption change of the battery and determine whether there is a time correlation between the communication perturbation fingerprint and the instantaneous power consumption change; In this embodiment, the determination of time correlation is used to investigate whether communication quality issues directly or indirectly affect the actual operating performance of the battery. For example, if the increase in communication latency is highly synchronized with the abnormal fluctuations in the instantaneous power consumption of the battery in time, it may indicate that the communication problem is affecting the battery's responsiveness or stability.

[0049] S35. Obtain the actual response data of the resource group, quantify the second deviation between the actual response data and the pre-established expected response baseline of the resource group, and use the second deviation as the silent adjustment index. In this embodiment, the actual response data of the resource group refers to the actual changes in the power output or consumption of the distributed energy resource group after receiving the dispatch command. By quantifying the second deviation between the actual response data and the pre-established expected response baseline of the resource group, the second deviation can be used as a silent adjustment index. The expected response baseline is an ideal response curve preset based on the historical performance, current state, and dispatch command of the resource group. The silent adjustment index is used to capture subtle deviations in the response capability or behavior pattern of the resource group in the absence of explicit external pressure signals, thereby identifying potential, non-obvious operational problems.

[0050] S36. Based on the micro-decay characteristic index, energy conversion efficiency fluctuation index, communication perturbation fingerprint, time correlation and silent adjustment index, evaluate the combined effect based on the fuzzy logic reasoning mechanism and generate a composite pressure index. In this embodiment, the fuzzy logic reasoning mechanism can handle the above-mentioned multi-source indicators that may have uncertainties. By defining fuzzy rules and membership functions, the comprehensive impact of these micro-indicators is quantified into a unified composite pressure index. The composite pressure index can more comprehensively and precisely reflect the comprehensive pressure level faced by the resource group.

[0051] S37. Based on the composite pressure index and the current power dispatch demand, adjust the interaction mode parameters of the resource group, including reducing the dispatch intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. In this embodiment, the system can intelligently determine how to adjust the interaction mode parameters based on the overall pressure level faced by the resource group and the current scheduling needs.

[0052] The technical solutions described above significantly improve the accuracy and adaptability of virtual power plant dispatch parameter adjustments. By comprehensively considering factors such as battery micro-degradation characteristics, energy conversion efficiency fluctuations, communication disturbances, and actual response deviations, the generated composite stress index can more comprehensively and accurately reflect the true operating status and potential risks of distributed energy resource groups. This enables the dispatch system to detect and respond to subtle anomalies in resource groups earlier, avoiding dispatch errors or excessive resource depletion caused by the lag of a single macro-indicator. Consequently, it effectively reduces the dispatch intensity of high-voltage resource groups, protects their long-term operational health, and adjusts the interaction parameters of low-voltage resource groups to obtain responses, thereby optimizing overall dispatch efficiency and reliability and extending the service life of distributed energy resource groups.

[0053] In one example, suppose a virtual power plant manages multiple distributed energy resource groups, including a low-voltage resource group consisting of multiple energy storage battery units. When the dispatch center needs to perform power dispatch on this low-voltage resource group, the method of this application will be implemented as follows: First, the system continuously acquires instantaneous voltage and current data for each energy storage battery cell. Based on this data, a pre-trained battery health model is used to extract micro-degradation characteristic indices for each battery, such as the rate of change of internal resistance. Simultaneously, the system monitors the actual charge and discharge energy of each battery cell and compares it with the theoretically expected output energy calculated based on its current health status and scheduling instructions. The system quantifies the first deviation between the two and uses it as an energy conversion efficiency fluctuation index. Furthermore, the system captures information such as the timestamp, reception timestamp, sequence number, and arrival order of scheduling instruction data packets during transmission, analyzes packet delays and jitter, and identifies communication perturbation fingerprints.

[0054] Next, the system acquires instantaneous power consumption change data of the battery and analyzes whether there is a temporal correlation between the communication perturbation fingerprint and these power consumption changes to determine whether communication problems affect battery performance. The system also records the actual power response data of each battery cell after receiving scheduling instructions and compares it with a pre-established expected response baseline, quantifying the second deviation between the two as a silent adjustment index to capture subtle deviations in battery response.

[0055] Finally, the system inputs the aforementioned micro-degradation characteristic index, energy conversion efficiency fluctuation index, communication perturbation fingerprint, time correlation, and silent adjustment index into a fuzzy logic reasoning module. This module evaluates the combined effect of these indicators based on preset fuzzy rules (e.g., "if the micro-degradation index is high and the communication perturbation fingerprint is obvious, then the composite stress index is high"), generating a comprehensive composite stress index.

[0056] Based on this composite pressure index and current power dispatch requirements, the system will dynamically adjust the interaction mode parameters of this low-voltage resource group. For example, if the composite pressure index is high, the system may reduce the dispatch intensity of this battery group or adjust its charging and discharging strategy to avoid further pressure accumulation. At the same time, it may prioritize dispatching other low-voltage resources with lower pressure or initiate preliminary negotiations with the backup resource group to ensure the stability of power supply.

[0057] In one possible design, Figure 3 This is a flowchart illustrating step S37 according to an exemplary embodiment. (Refer to the attached document.) Figure 3 Step S37 includes: S37a. Based on the composite pressure index and pre-acquired historical power dispatch data, establish a long-term impact baseline for resource groups. The long-term impact baseline includes user comfort threshold, equipment lifespan degradation rate, and the trend of changes in user participation willingness. In this embodiment, the long-term impact baseline of the resource group refers to the reference standard used to assess the impact of dispatching behavior on various key indicators of the resource group during the long-term operation of the virtual power plant. Specifically, the user comfort threshold is the range of comfort degradation that users can tolerate when receiving dispatching responses, such as the allowable fluctuation range of environmental parameters like indoor temperature and lighting, used to ensure that users can maintain basic living or working comfort while participating in virtual power plant dispatching; the equipment lifespan degradation rate is the rate at which the expected lifespan of distributed energy equipment is depleted under different dispatching intensities and frequencies, used to avoid premature aging or damage to equipment due to excessive dispatching; and the user participation willingness change trend is the pattern of how users' responsiveness to virtual power plant dispatching instructions changes over time, used to assess and maintain long-term user participation. These baselines are established through analysis and modeling of historical power dispatching data, reflecting the potential impact of different dispatching strategies on the long-term health of the resource group and user experience.

[0058] S37b. Based on the long-term impact baseline, predict the degree of deviation of the adjustment from the long-term impact baseline, and based on the degree of deviation, introduce a dynamic adjustment mechanism. The dynamic adjustment mechanism includes dynamically adjusting the upper limit of the scheduling intensity of the resource group, introducing a rotation scheduling mechanism, and initiating in-depth negotiation of the standby resource group. In this embodiment, the dynamic adjustment mechanism refers to a mechanism that can flexibly adjust the scheduling strategy based on the degree of deviation from the long-term impact baseline. Specifically, dynamically adjusting the upper limit of the scheduling intensity of resource groups refers to setting dynamic upper limits for the scheduling intensity of high-pressure and low-pressure resource groups based on the prediction results of the long-term impact baseline, to prevent over-scheduling from causing long-term damage to resources; introducing a rotation scheduling mechanism refers to periodically or strategically switching scheduling objects among multiple resource groups of the same type to avoid a single resource group bearing high-intensity scheduling pressure for a long time, thereby achieving balanced utilization and maintenance of resources; initiating in-depth consultation with backup resource groups refers to proactively communicating and coordinating more deeply with backup resource groups when it is predicted that regular scheduling adjustments may lead to a serious deviation from the long-term impact baseline, in order to obtain their more flexible or larger-scale response capabilities as a supplement or alternative solution.

[0059] S37c. Based on a dynamic adjustment mechanism, the interaction mode parameters of the resource group are dynamically adjusted, including reducing the scheduling intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. In this embodiment, by introducing a dynamic adjustment mechanism, the system can adopt more refined and flexible scheduling strategies based on the predicted degree of deviation. For example, when it is predicted that the equipment lifespan degradation rate of a certain high-voltage resource group will exceed a preset threshold, the system can dynamically reduce its scheduling intensity limit, or transfer some scheduling tasks to other resource groups through a rotation scheduling mechanism, thereby effectively alleviating the long-term pressure on a single resource. Simultaneously, when it is predicted that conventional adjustments are insufficient to avoid severe deviations that will have a long-term impact on the baseline, the system can promptly initiate in-depth negotiations with backup resource groups to obtain additional response capabilities, thereby ensuring grid stability while maximizing the long-term health and sustainability of resource groups.

[0060] The technical solutions described above, by establishing a long-term impact baseline for resource groups, enable the scheduling system to more comprehensively assess the potential consequences of scheduling decisions, avoiding the sacrifice of long-term interests for short-term gains. The introduction of a dynamic adjustment mechanism makes the scheduling strategy more adaptable and forward-looking, allowing for flexible adjustments to scheduling intensity and resource allocation based on long-term impact predictions, and timely introduction of reserve resources. This effectively reduces user discomfort, extends equipment lifespan, and enhances user participation. Compared to solutions that adjust solely based on the composite stress index, the solution presented in this application achieves long-term optimization of the virtual power plant scheduling strategy, thereby improving the overall operational efficiency and sustainable development of the virtual power plant.

[0061] In one example, suppose a virtual power plant covers an area containing multiple commercial complexes and industrial energy storage systems, forming high-voltage and low-voltage resource groups. When adjusting dispatch parameters, the system first establishes a long-term impact baseline for these resource groups based on historical power dispatch data. For example, for commercial complexes, the user comfort threshold is set to indoor temperature fluctuations not exceeding ±1.5℃; for industrial energy storage systems, the equipment lifespan degradation rate is set to annual cycle life loss not exceeding 5%. Simultaneously, the system also monitors user response rates to dispatch commands to assess trends in user participation willingness.

[0062] Specifically, when the system initially determines, based on the composite pressure index and current power dispatching needs, that a high-intensity dispatching of a certain high-voltage resource group (such as a large commercial complex) is required, the system will first predict the degree of deviation of this dispatching from the baseline of the long-term impact on the commercial complex. If the prediction results show that continuous high-intensity dispatching will lead to a continued deterioration in the user comfort trend of the commercial complex, or that the lifespan degradation rate of its equipment such as air conditioning systems will significantly exceed a preset threshold, the system will activate a dynamic adjustment mechanism.

[0063] As a specific implementation method, the dynamic adjustment mechanism can manifest itself in the following ways: First, the system dynamically reduces the upper limit of the dispatch intensity for the commercial complex to avoid over-exploiting its resources. Second, if multiple similar commercial complexes exist, the system may introduce a rotation dispatch mechanism to transfer some dispatch tasks to other commercial complexes with lower current pressure and smaller deviations from the long-term impact baseline, thereby balancing dispatch pressure. Third, if it is predicted that even with the above measures, the long-term impact baseline may still deviate significantly, the system will initiate in-depth negotiations with backup resource groups (such as some interruptible loads or additional energy storage facilities) to obtain their availability intentions and acceptance conditions in advance, so as to conduct supplementary dispatch when necessary. This ensures grid stability while maximizing the comfort of users and the health of equipment in the commercial complex. In this way, the dispatch strategy of the virtual power plant can balance short-term response efficiency and long-term sustainability.

[0064] In one possible design, Figure 4 This is a flowchart illustrating step S37 according to another exemplary embodiment. (Refer to the attached diagram.) Figure 4 Step S37 also includes: S37d: Continuously monitor the rate of change of environmental parameters and the rate of change of power grid load. When the rate of change of environmental parameters or the rate of change of power grid load exceeds the preset rate of change threshold, initiate a rapid reassessment of the composite stress index. In this embodiment, the system continuously acquires and analyzes the rate of change of external environmental factors (such as temperature, humidity, and light) and power grid operating status (such as load, frequency, and voltage) related to the operation of the virtual power plant. The rate of change of environmental parameters is the numerical change of environmental parameters per unit time, such as the degree increase or decrease in temperature per hour; the rate of change of power grid load is the increase or decrease in power grid load per unit time, such as the megawatt-level change in load per minute. This is used to promptly capture external dynamic changes that may significantly affect the operation of the virtual power plant. A preset rate of change threshold is a critical value pre-set based on historical data, system design requirements, and safe operation standards. When the monitored rate of change exceeds the preset rate of change threshold, it indicates that the external environment or power grid status is undergoing abnormal or rapid changes, requiring a higher level of system response. Rapid reassessment involves the system immediately initiating an accelerated, high-frequency composite pressure index calculation and evaluation process. Traditional composite pressure index evaluations may have a certain periodicity, while rapid reassessment breaks this periodicity, recalculating and updating the composite pressure index at a faster speed and higher frequency, ensuring that the system can make decisions based on the latest and most accurate pressure conditions.

[0065] S37e. During the rapid reassessment process, dynamically increase the weights related to the environment and power grid status in the calculation of the composite stress index; In this embodiment, when recalculating the composite pressure index, the system will selectively increase the weight of indicators reflecting environmental pressure (such as the environment-related portion of user experience pressure) and power grid pressure (such as the power grid communication-related portion of communication carrying capacity pressure) in the composite pressure index calculation, based on the rapid changes in the current environment and power grid. This makes the composite pressure index more sensitive and accurate in reflecting the pressure brought about by current external dynamic changes, and guides subsequent scheduling adjustments to focus more on addressing these external factors.

[0066] S37f: When the composite pressure index of the high-pressure resource group rises in a short period of time and exceeds the preset warning threshold, a secondary adjustment process is triggered. In this embodiment, after rapid reassessment, if it is found that the overall pressure on the high-pressure resource group has increased sharply in a short period of time and exceeds a pre-set higher-level warning threshold, the system will immediately initiate an emergency and more powerful scheduling and adjustment process. The pre-set warning threshold is a critical value higher than the normal pressure limit, indicating that the high-pressure resource group is already in a state of high tension.

[0067] S37g, the secondary adjustment process further reduces the scheduling intensity of the high-voltage resource group, and simultaneously initiates fine-tuning of the interaction parameters of the low-voltage resource group; In this embodiment, further reducing the dispatch intensity means, on the basis of the high-voltage resource group having already undergone one adjustment in dispatch intensity, further reducing its power output or increasing its power consumption to quickly alleviate its operational pressure. Simultaneously initiating fine-tuning of the interaction parameters of the low-voltage resource group refers to making small, refined adjustments to the dispatch strategy of the low-voltage resource group while simultaneously making emergency adjustments to the high-voltage resource group. For example, its response time, response amplitude, or participation mode can be fine-tuned to compensate for the power gap caused by the reduction in the dispatch intensity of the high-voltage resource group as much as possible without significantly increasing its pressure, and to maintain the balanced operation of the entire virtual power plant. The technical solution described above, by introducing continuous monitoring of the rate of change, rapid reassessment, and dynamic weight adjustment mechanisms, enables the system to identify potential risks earlier and more accurately, and quickly initiate targeted secondary adjustment processes. This not only effectively prevents high-voltage resource groups from becoming overloaded due to sudden increases in external pressure, but also ensures the continuity and stability of power supply through coordinated fine-tuning of low-voltage resource groups, thereby avoiding dispatch imbalances and user experience degradation caused by external dynamic changes.

[0068] In one example, suppose a sudden extreme heat wave occurs in the summer within the coverage area of ​​a virtual power plant, causing the ambient temperature to rise sharply at a rate of 5 degrees Celsius per hour. Simultaneously, due to the activation of a large number of air conditioning units, the grid load also increases rapidly at a rate of megawatts per minute. The system continuously monitors and finds that both the rate of change of environmental parameters and the rate of change of grid load exceed preset thresholds.

[0069] At this point, the system immediately initiates a rapid reassessment of the composite stress index. During the reassessment, the weights related to user experience stress (affected by high temperatures) and communication load stress (affected by increased grid load) are dynamically increased, enabling the composite stress index to more sensitively reflect the stress brought about by the current high temperature and high load. If the rapid reassessment results show that the composite stress index of the high-voltage resource group (such as a large industrial energy storage system) rises from 0.6 to 0.9 in a short period of time and exceeds the preset warning threshold of 0.85, the system will immediately trigger a secondary adjustment process. In this secondary adjustment process, the dispatch intensity of the high-voltage resource group is reduced again, for example, its original discharge power is further reduced from 50MW to 30MW to quickly alleviate its internal stress and equipment health stress.

[0070] At the same time, the system will simultaneously initiate fine-tuning of the interaction parameters of low-voltage resource groups (such as smart air conditioning and lighting systems in commercial complexes). For example, without significantly affecting user comfort, the set temperature of some air conditioners will be increased by 0.5 degrees Celsius, or the lighting brightness in non-critical areas will be reduced by 5% to obtain additional responsiveness, thereby making up for the power gap caused by the reduced scheduling intensity of high-voltage resource groups and ensuring the overall power balance and stable operation of the virtual power plant.

[0071] In one possible design, step S37d involves continuously monitoring the rate of change of environmental parameters, including: S37d1. Obtain the rate of change of single-domain environmental parameters collected by the environmental sensor network in different sub-regions. The environmental sensor network includes temperature and humidity sensors deployed in commercial complexes, as well as temperature and humidity sensors deployed near industrial energy storage systems. In this embodiment, firstly, an environmental sensor network deployed in different sub-regions, such as temperature and humidity sensors deployed within a commercial complex and near an industrial energy storage system, can collect and calculate the rate of change of single-domain environmental parameters in each sub-region in real time. These sensor networks provide refined local environmental data.

[0072] S37d2. Acquire satellite remote sensing data and extract the rate of change of macroscopic environmental parameters in the virtual power plant coverage area based on the satellite remote sensing data; In this embodiment, by acquiring satellite remote sensing data, the rate of change of macroscopic environmental parameters in the virtual power plant coverage area can be extracted from a broader perspective, which helps to capture large-scale environmental trends.

[0073] S37d3: Obtain environmental sensor data integrated within the distributed energy resource group itself, and calculate the rate of change of local environmental parameters of the distributed energy resource group based on the environmental sensor data; In this embodiment, the distributed energy resource group itself usually integrates environmental sensors, such as internal sensors of smart buildings or temperature sensors of energy storage batteries. These data are used to calculate the rate of change of local environmental parameters of the distributed energy resource group, reflecting the micro-environmental changes of individual resources.

[0074] S37d4. Determine the sensitivity of distributed energy resource groups to local environmental changes; In this embodiment, to more accurately assess the impact of environmental changes, it is necessary to determine the sensitivity of distributed energy resource groups to local environmental changes. Specifically, for commercial complexes, the sensitivity can be determined based on the thermal inertia of the building envelope, the cooling capacity of the air conditioning system, and the rate of increase of the user comfort deviation index under different environmental change rates in historical dispatch data. For example, buildings with high thermal inertia respond more slowly to instantaneous temperature changes, while air conditioning systems with strong cooling capacity can better cope with temperature rises. For industrial energy storage systems, the sensitivity can be determined based on the battery's temperature resistance characteristics, the battery's energy storage conversion efficiency, and the rate of change of the battery health status index under different environmental change rates in historical dispatch data. For example, some batteries are more sensitive to high temperatures, and their health status may deteriorate more rapidly when the temperature rises quickly.

[0075] S37d5. Based on the rate of change of environmental parameters in a single domain, the rate of change of environmental parameters in a macroscopic domain, the rate of change of environmental parameters in a local domain, and sensitivity, the rate of change of environmental parameters in each sub-region is weighted and fused to obtain the rate of change of environmental parameters in the entire domain. In this embodiment, the rate of change of environmental parameters across the entire virtual power plant coverage area is obtained by weighted fusion. Then, environmental data from different sources and scales are comprehensively considered and adjusted according to the response characteristics of each resource group to environmental changes, so as to obtain a comprehensive and representative environmental change index.

[0076] The technical solution described above integrates multi-source, multi-scale environmental parameter change data, including single-domain data from local sensor networks, macroscopic data provided by satellite remote sensing, and local data integrated by the distributed energy resource groups themselves. Combined with the specific sensitivity of each resource group to environmental changes, this achieves comprehensive and refined monitoring of the rate of change of environmental parameters across the entire domain. Consequently, it can more accurately capture the dynamic characteristics of environmental changes and their impact on different types of distributed energy resource groups, avoiding scheduling deviations or resource pressure accumulation caused by insufficient assessment of environmental factors, thereby enhancing the resilience and adaptability of the virtual power plant.

[0077] In one possible design, step S37d involves continuously monitoring the rate of change of the power grid load, including: S37d5. Obtain real-time telemetry data from the power grid side, and calculate the instantaneous load change rate of each sub-region based on the real-time telemetry data. The real-time telemetry data includes feeder power, bus voltage and current data of each substation. In this embodiment, by interfacing with the power grid dispatching system or the SCADA system of the substation, real-time data on feeder power, bus voltage, and current of each substation are collected. These data are the most direct indicators reflecting local load changes in the power grid. By analyzing these instantaneous data, the instantaneous load change rate of each sub-region can be calculated, thereby gaining a real-time understanding of the power grid load dynamics.

[0078] S37d6. Obtain real-time power output and consumption data of each distributed energy resource group within the virtual power plant, and aggregate and calculate the instantaneous load change rate of the entire virtual power plant based on the real-time power output and consumption data. In this embodiment, acquiring internal data from the virtual power plant is from the perspective of the virtual power plant itself, to understand the overall trend of its internal load changes. Distributed energy resource groups, such as photovoltaics, energy storage, and controllable loads, directly affect the virtual power plant's overall response capability to the power grid through changes in their power output and consumption. By aggregating this internal data, the contribution or impact of the virtual power plant as a whole on changes in grid load can be obtained.

[0079] S37d7. Obtain short-term load forecast data and actual load data provided by the power grid dispatch center, and calculate the rate of change of the deviation between the short-term load forecast data and the actual load data based on the short-term load forecast data and the actual load data. In this embodiment, the accuracy and trend of power grid load forecasting are evaluated by the rate of change of the deviation. The rate of change of the forecast deviation can reveal the adaptability of the power grid load forecasting model within a specific time period, as well as whether there are sudden and unpredictable load fluctuations.

[0080] S37d8. Determine the response characteristics of distributed energy resource groups to changes in local grid load; This embodiment analyzes in depth the inherent behavioral patterns of different types of resources in response to changes in grid load. For example, for commercial complexes, their load reduction response may have a certain lag time, and the response magnitude is limited by user comfort thresholds; while for industrial energy storage systems, their response characteristics mainly depend on physical characteristics such as battery charge / discharge rate and cycle life. By using historical dispatch response data, these characteristics can be quantified, thereby enabling a more accurate assessment of the actual response capabilities and potential impacts of each resource group in subsequent dispatch decisions.

[0081] S37d9. Based on the instantaneous load change rate of each sub-region, the instantaneous load change rate of the virtual power plant as a whole, the deviation change rate, and the response characteristics, the power grid load change rate of each sub-region is weighted and fused to obtain the power grid load change rate of the entire region. In this embodiment, multi-source information is comprehensively considered to form a comprehensive, accurate, and forward-looking assessment of the load change rate across the entire power grid. The weights in the weighted fusion can be dynamically adjusted based on the reliability, real-time performance, and importance of the data to scheduling decisions.

[0082] The technical solutions described above, through multi-dimensional and multi-level data acquisition and analysis, improve the accuracy and comprehensiveness of the virtual power plant's monitoring of the grid load change rate. By integrating grid-side telemetry data, virtual power plant internal data, load forecasting deviations, and the response characteristics of various resource groups, a more robust and refined grid load change rate assessment system is constructed. This enables the virtual power plant to identify abnormal fluctuations or rapid changes in grid load earlier and more accurately. Consequently, it effectively avoids dispatch delays or misjudgments caused by untimely or inaccurate monitoring, further enhancing the adaptability and stability of the virtual power plant in complex and ever-changing grid environments.

[0083] In one example, suppose a virtual power plant covers multiple commercial complexes and industrial energy storage systems.

[0084] At a certain moment, the power grid dispatch center reported a sharp increase in feeder power in a certain area within a short period, while bus voltage and current data showed a slight decrease, indicating a high instantaneous load change rate in that sub-area. Simultaneously, monitoring data within the virtual power plant showed that air conditioning loads in some commercial complexes increased synchronously due to rising external temperatures, and the charging power of industrial energy storage systems also changed due to electricity price signals. Aggregating these internal data revealed that the overall instantaneous load change rate of the virtual power plant also showed an upward trend. Furthermore, a continuously widening positive deviation appeared between the short-term load forecast data provided by the power grid dispatch center and the actual load data, with the rate of change of this deviation indicating that the actual load growth exceeded expectations.

[0085] Here, considering the approximately 15-minute lag in the response of commercial complexes to load reduction and the rapid increase in their user comfort deviation index during load reduction, while industrial energy storage systems have higher charge / discharge rates and can respond quickly to load changes, the system performs weighted fusion of the instantaneous load change rate of each sub-region, the overall instantaneous load change rate of the virtual power plant, the prediction deviation change rate, and the response characteristics of each resource group based on these multi-source data and response characteristics. For example, real-time telemetry data from the grid side is given a higher weight, the prediction deviation change rate is given a medium weight, and adjustments are made based on the response characteristics of each resource group. Finally, a grid load change rate for the entire region is calculated, which is assessed as exceeding a preset change rate threshold, thus triggering a rapid reassessment process for the composite stress index. Through this comprehensive monitoring method, the virtual power plant comprehensively and accurately grasps the dynamics of the grid load.

[0086] In one possible design, in step S37d, when the rate of change of environmental parameters or the rate of change of power grid load exceeds a preset rate of change threshold, a rapid reassessment of the composite stress index is initiated, including: S37d10: Obtain historical environmental parameter change data, historical power grid load change data, and sensitivity of each resource group to local environmental changes in each sub-region within the coverage area of ​​the virtual power plant. In this embodiment, the system continuously collects and stores records of changes in environmental parameters (e.g., temperature, humidity, illumination) and grid load (e.g., power, current, voltage) over a period of time within the geographical area covered by the virtual power plant. Simultaneously, the system acquires or calculates the response characteristics and sensitivity of various distributed energy resource groups (e.g., commercial complexes, industrial energy storage systems) to local environmental changes or grid load changes. For example, for a commercial complex, its sensitivity to temperature changes may be related to the building's thermal inertia, the cooling capacity of its air conditioning system, and the rate of increase of the comfort deviation index under different environmental change rates in historical dispatch data. For an industrial energy storage system, its sensitivity to grid load changes may be related to the battery's charge / discharge rate, cycle life characteristics, and the rate of change of the battery health status index under different grid load change rates in historical dispatch data. These sensitivity data can be obtained in advance through modeling, simulation, or historical data analysis.

[0087] S37d11. Based on historical environmental parameter change data, historical power grid load change data, and sensitivity, dynamically adjust the environmental parameter change rate threshold and power grid load change rate threshold for each sub-region. In this embodiment, using the acquired historical data and sensitivity information, the environmental parameter change rate threshold and the power grid load change rate threshold for each sub-region are updated in real time or periodically through machine learning algorithms, adaptive control strategies, or expert systems. For example, if historical data shows that a sub-region is relatively insensitive to temperature changes or has a strong tolerance for load fluctuations in a specific season, the corresponding threshold can be appropriately relaxed; conversely, if historical data shows that the region is very sensitive to a certain change or is prone to stress under specific operating conditions, the threshold can be tightened.

[0088] S37d12. Compare the rate of change of environmental parameters across the entire region with the dynamically adjusted threshold rate of change of environmental parameters, and compare the rate of change of power grid load across the entire region with the dynamically adjusted threshold rate of change of power grid load. In this embodiment, the rate of change of environmental parameters in the entire virtual power plant coverage area at the current moment is compared with the threshold of the rate of change of environmental parameters dynamically adjusted for that area. At the same time, the rate of change of grid load in the entire virtual power plant coverage area is also compared with the threshold of the rate of change of grid load dynamically adjusted.

[0089] S37d13. When the rate of change of environmental parameters in the entire region exceeds the threshold of the rate of change of environmental parameters after dynamic adjustment, or when the rate of change of power grid load in the entire region exceeds the threshold of the rate of change of power grid load after dynamic adjustment, a rapid reassessment of the composite pressure index is initiated. In this embodiment, once any global rate of change exceeds its corresponding dynamic adjustment threshold, a rapid reassessment process for the composite pressure index is immediately triggered. This indicates that the current environmental or grid load changes have exceeded the region's tolerance under current conditions, requiring the system to quickly reassess the overall pressure status of the virtual power plant in order to take timely dispatching measures.

[0090] The technical solution described above, by incorporating historical data and resource group sensitivity, dynamically adjusts the thresholds for environmental parameter change rates and grid load change rates, achieving intelligent and adaptive optimization of the rapid reassessment trigger mechanism for the composite pressure index. Specifically, by acquiring historical environmental parameter change data, historical grid load change data, and the sensitivity of each resource group to local environmental changes in each sub-region, the system can comprehensively understand the response characteristics and resilience of different regions under different conditions. Based on this information, the thresholds for each sub-region are dynamically adjusted, allowing the thresholds to be adaptively optimized according to actual conditions, avoiding the limitations of a single fixed threshold. Therefore, when the rate of change of environmental parameters or the rate of change of grid load across the entire region exceeds these dynamically adjusted thresholds, a rapid reassessment is initiated, ensuring that the reassessment trigger is more accurate and timely, and can more accurately reflect the actual pressure faced by the virtual power plant.

[0091] In one possible design, Figure 5 This is a flowchart illustrating step S37d according to an exemplary embodiment. (Refer to the attached document.) Figure 5 Step S37d includes: S37d1. During the rapid reassessment process, continuously monitor the trend of user comfort deviation and continuously monitor the cumulative changes of key operating parameters of the equipment; In this embodiment, continuous monitoring of user comfort deviation trends refers to the continuous tracking and evaluation of the user's environmental comfort to identify whether it deviates from the user's expectations or preset comfort range. Deviation trend monitoring can be based on various data sources, such as environmental parameters like indoor temperature, humidity, CO2 concentration, and light intensity, as well as operational status data from user terminal devices like smart air conditioners and smart lighting, and local operation records such as user manual adjustment behaviors. Through comprehensive data analysis, the real-time status of user comfort and its direction of change can be quantified.

[0092] Continuous monitoring of the cumulative changes in key operating parameters of equipment refers to the continuous collection and analysis of operating status parameters of key equipment in a distributed energy resource cluster to assess the equipment's health status and potential failure risks. Key operating parameters may include battery charge-discharge cycle count, temperature, voltage, current fluctuations, inverter efficiency, and cooling system status. Cumulative changes reflect the degree of performance degradation or wear and tear of the equipment during long-term operation.

[0093] S37d2. When the user comfort deviation trend continues to deteriorate or the cumulative change of key operating parameters of the device exceeds the preset change threshold, the weight of user experience pressure and device health pressure is increased compensatorily. In this embodiment, when the user comfort deviation trend continues to worsen, it means that the user's satisfaction with the current environment is continuously declining, which may manifest as increased complaints, frequent manual adjustments, or a comfort index that remains below the threshold. When the cumulative changes in key equipment operating parameters exceed a preset change threshold, it indicates that the equipment's health status has reached or is approaching a warning level, such as excessively high battery capacity degradation, abnormally high temperatures in key components, or a significant decrease in operating efficiency. Based on this, in the calculation model of the composite stress index, the weight of the user experience stress and equipment health stress components in the overall stress assessment is dynamically increased according to the user comfort deviation trend and the cumulative changes in key equipment operating parameters. It is understood that this increase is not a simple fixed increase, but rather an adaptive adjustment based on the actual monitored degree of deterioration or exceeding the threshold, to ensure that these internal stress signals receive sufficient attention during the rapid reassessment process.

[0094] The technical solution of the above embodiments, by introducing continuous monitoring of user comfort deviation trends and cumulative changes in key equipment operating parameters, and using these as triggering conditions, achieves refined and adaptive adjustment of weight allocation in the calculation of the composite stress index. Specifically, by continuously monitoring user comfort deviation trends, potential discomfort or negative feedback from users regarding scheduling strategies can be captured in a timely manner, avoiding sacrificing user experience due to excessive pursuit of external response. Simultaneously, by continuously monitoring the cumulative changes in key equipment operating parameters, the health status of the equipment can be monitored in real time, preventing irreversible damage or accelerated aging of the equipment under emergency scheduling. When these internal stress signals reach preset deterioration or exceed threshold states, the weight of user experience stress and equipment health stress is compensatorily increased, making these internal factors play a more important role in the calculation of the composite stress index. Therefore, even under significant external pressure, the scheduling system can fully weigh internal and external pressures when making decisions, avoiding a "robbing Peter to pay Paul" situation and ensuring the comprehensiveness and sustainability of scheduling decisions.

[0095] In one possible design, step S37d1 involves continuously monitoring trends in user comfort deviations, including: S37d11. Obtain environmental parameter data related to user comfort, including indoor temperature, humidity, CO2 concentration, and light intensity. In this embodiment, the environmental parameter data related to user comfort refers to the physical quantities that directly affect the user's perceived comfort. The aforementioned data can be collected in real time by various environmental sensors deployed within the coverage area of ​​the virtual power plant to provide basic environmental background information for assessing user comfort.

[0096] S37d12. Obtain device operation status data and local operation records from the user terminal. The device operation status data includes the set temperature, operating mode, and fan speed of the smart air conditioner, and the brightness and color temperature of the smart lighting. The local operation records include the user's manual adjustment behavior of the smart air conditioner and smart lighting. In this embodiment, the device operating status data and local operation records of the user terminal are used to reflect the user's direct intervention and preferences regarding the environment. The device operating status data may include the set temperature, operating mode, and fan speed of the smart air conditioner, as well as the brightness and color temperature of the smart lighting. This data reflects the current operating status of the devices and their potential impact on user comfort. The local operation records cover the user's manual adjustment behaviors on smart devices such as smart air conditioners and smart lighting, such as actively raising or lowering the temperature or changing the lighting brightness. These behaviors directly reflect the user's perception and expectations of current comfort. By acquiring this data, it is possible to understand the user's proactive adjustment behaviors in specific environments, thereby helping to determine the actual deviation of user comfort.

[0097] S37d13. Obtain information on external interference events, including construction noise outside the building and warnings of abnormal weather. In this embodiment, external interference event information refers to external factors that may affect user comfort but are unrelated to virtual power plant dispatch instructions. For example, construction noise outside a building may cause user discomfort, and abnormal weather warnings (such as extreme heat or cold waves) may cause users to change their comfort requirements for the indoor environment. This information can be obtained through external data sources (such as meteorological bureaus or urban management departments) or specific sensors to identify and distinguish user comfort deviations caused by changes in the external environment rather than dispatch behavior.

[0098] S37d14. Based on environmental parameter data, equipment operating status data, local operation records, and external interference event information, identify the non-scheduled impact of non-scheduled factors on user comfort deviation. In this embodiment, by comprehensively analyzing the above-mentioned data, it is possible to distinguish which comfort deviations are caused by the virtual power plant's dispatch instructions (e.g., adjusting the air conditioning load to respond to grid demand) and which are caused by non-dispatch factors such as the user's own active adjustments, changes in the external environment, or equipment failures. For example, if a user manually raises the air conditioning temperature, their comfort deviation may not be caused by dispatch.

[0099] S37d15. Based on the non-scheduling influence, correct the user comfort deviation trend to obtain the comfort deviation trend caused by scheduling; In this embodiment, the correction process aims to eliminate interference from non-scheduling factors, so that the final user comfort deviation trend can more accurately reflect the actual impact of virtual power plant scheduling behavior on user comfort.

[0100] The technical solution of the above embodiments constructs a multi-dimensional data foundation by comprehensively acquiring environmental parameter data related to user comfort, device operating status data and local operation records of user terminals, as well as information on external interference events. Based on this, by finely identifying the non-scheduling impact of non-scheduling factors on user comfort deviations and correcting the original user comfort deviation trend, it is possible to accurately quantify user comfort deviations caused by scheduling behavior. This avoids misjudging comfort changes caused by non-scheduling factors as scheduling pressure, ensuring that subsequent increases in the weight of user experience pressure are based on real comfort deterioration caused by scheduling, making the virtual power plant's scheduling decisions more accurate and reasonable.

[0101] In summary, the virtual power plant scheduling method based on multiple interaction modes provided by this invention acquires various pressure signals from distributed energy resource groups, such as user experience pressure, equipment health pressure, and communication carrying capacity pressure, and quantifies them to generate mode pressure indicators, reflecting the real-time operating status of the virtual power plant. When the mode pressure indicators approach or reach preset pressure limits, a pressure warning signal is issued in a timely manner. Based on the pressure warning signal and current power dispatching needs, the scheduling intensity of high-voltage resource groups is dynamically adjusted, and the interaction parameters of low-voltage resource groups are adjusted to obtain responses, achieving differentiated and refined management of different resource groups. In addition, this application also proactively negotiates with backup resource groups and issues dispatching instructions when necessary, ensuring system stability when dispatching gaps occur or warning levels are high. By monitoring and verifying the actual dispatching response effects of each resource group and feeding back the actual dispatching response effects to the pressure signal acquisition stage, a closed-loop control is formed, further optimizing the dispatching strategy and fully addressing the complex challenges faced in existing virtual power plant scheduling. At the same time, it also improves dispatching efficiency, system reliability, and grid support capabilities, overcoming the shortcomings of existing technologies such as instruction execution errors caused by time synchronization deviations, demonstrating significant technological progress and practical value.

[0102] Example 2 Embodiment 2 of the present invention provides a virtual power plant dispatching system based on multiple interaction modes, the system comprising: The pressure index generation module 01 is used to acquire the pressure signal of the distributed energy resource group and generate the mode pressure index of the resource group based on the pressure signal. The resource group includes high-voltage resource group, low-voltage resource group and backup resource group. The pressure signal includes user experience pressure, equipment health pressure and communication carrying pressure. The pressure warning module 02 is used to monitor the mode pressure index in real time and issue a pressure warning signal when the mode pressure index approaches or reaches the preset pressure limit. The parameter adjustment module 03 is used to adjust the interaction mode parameters of the resource group according to the pressure warning signal and the current power dispatch demand. The adjustment includes reducing the dispatch intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. The backup resource negotiation module 04 is used to predict whether there is a scheduling gap or whether the warning level is high after the adjustment based on the adjusted interaction mode parameters. If a scheduling gap or a high warning level is expected, it will proactively negotiate with the backup resource group and issue scheduling instructions based on the availability intention and acceptance conditions of the backup resource group. The scheduling module 05 is used to schedule the power of each resource group according to the scheduling instructions, monitor and verify the actual scheduling response effect of each resource group, and feed back the actual scheduling response effect to the pressure signal acquisition link.

[0103] In summary, the virtual power plant scheduling method and system based on multiple interaction modes provided by this invention acquires various pressure signals from distributed energy resource groups, such as user experience pressure, equipment health pressure, and communication carrying capacity pressure, and quantifies them to generate mode pressure indicators, reflecting the real-time operating status of the virtual power plant. When the mode pressure indicators approach or reach preset pressure limits, a pressure warning signal is issued in a timely manner. Based on the pressure warning signal and current power dispatching needs, the scheduling intensity of high-voltage resource groups is dynamically adjusted, and the interaction parameters of low-voltage resource groups are adjusted to obtain responses, achieving differentiated and refined management of different resource groups. Furthermore, this application also proactively negotiates with backup resource groups and issues dispatching instructions when necessary, ensuring system stability when dispatching gaps occur or warning levels are high. By monitoring and verifying the actual dispatching response effects of each resource group and feeding back the actual dispatching response effects to the pressure signal acquisition stage, a closed-loop control is formed, further optimizing the dispatching strategy and fully addressing the complex challenges faced in existing virtual power plant scheduling. It also improves dispatching efficiency, system reliability, and grid support capabilities, overcoming shortcomings in existing technologies such as instruction execution errors caused by time synchronization deviations, demonstrating significant technological advancements and practical value.

[0104] 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.

[0105] The embodiments described above are merely illustrative of 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 virtual power plant scheduling method based on multiple interaction modes, characterized in that, Includes the following steps: The pressure signal of the distributed energy resource group is obtained, and the mode pressure index of the resource group is quantified and generated based on the pressure signal. The resource group includes a high-voltage resource group, a low-voltage resource group and a backup resource group. The pressure signal includes user experience pressure, equipment health pressure and communication carrying pressure. The mode pressure index is monitored in real time, and a pressure warning signal is issued when the mode pressure index approaches or reaches the preset pressure limit. Based on the pressure warning signal and the current power dispatch demand, the interaction mode parameters of the resource group are adjusted, wherein the adjustment includes reducing the dispatch intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. Based on the adjusted interaction mode parameters, it is anticipated whether there is a scheduling gap or a high warning level after the adjustment. If a scheduling gap or a high warning level is anticipated, a proactive consultation is held with the backup resource group, and a scheduling instruction is issued based on the availability intention and acceptance conditions of the backup resource group. The power of each resource group is dispatched according to the dispatching instructions, the actual dispatching response effect of each resource group is monitored and verified, and the actual dispatching response effect is fed back to the pressure signal acquisition link. The step of adjusting the interaction mode parameters of the resource group based on the pressure warning signal and the current power dispatch demand includes: Acquire instantaneous voltage and instantaneous current data of the battery, and extract the micro-degradation characteristic index of the battery based on the instantaneous voltage and instantaneous current data; The first deviation between the actual output energy of the battery and the theoretically expected output energy is obtained, and the first deviation is used as the energy conversion efficiency fluctuation index. Obtain instruction data packet information and identify a communication perturbation fingerprint based on the instruction data packet information, wherein the instruction data packet information includes a timestamp, a receiving timestamp, a sequence number, and an arrival order; The instantaneous power consumption change of the battery is obtained, and it is determined whether there is a time correlation between the communication perturbation fingerprint and the instantaneous power consumption change; Obtain the actual response data of the resource group, quantify the second deviation between the actual response data and the pre-established expected response baseline of the resource group, and use the second deviation as the silent adjustment index; Based on the micro-deterioration characteristic index, the energy conversion efficiency fluctuation index, the communication perturbation fingerprint, the time correlation, and the silent adjustment index, the combined effect is evaluated using a fuzzy logic reasoning mechanism to generate a composite stress index. Based on the composite pressure index and the current power dispatch demand, the interaction mode parameters of the resource groups are adjusted, wherein the adjustment includes reducing the dispatch intensity of the high-voltage resource groups and adjusting the interaction parameters of the low-voltage resource groups to obtain a response.

2. The method according to claim 1, characterized in that, The adjustment of the interaction mode parameters of the resource group based on the composite pressure index and the current power dispatch demand includes: Based on the composite pressure index and pre-acquired historical power dispatch data, a long-term impact baseline for resource groups is established, wherein the long-term impact baseline includes user comfort threshold, equipment lifespan degradation rate, and the trend of changes in user participation willingness. Based on the long-term impact baseline, the degree of deviation of the adjustment from the long-term impact baseline is predicted, and based on the degree of deviation, a dynamic adjustment mechanism is introduced, wherein the dynamic adjustment mechanism includes dynamically adjusting the scheduling intensity limit of the resource group, introducing a rotation scheduling mechanism, and initiating deep negotiation of the standby resource group; Based on the aforementioned dynamic adjustment mechanism, the interaction mode parameters of the resource group are dynamically adjusted, wherein the adjustment includes reducing the scheduling intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response.

3. The method according to claim 2, characterized in that, The step of adjusting the interaction mode parameters of the resource group based on the composite pressure index and the current power dispatch demand also includes: The rate of change of environmental parameters and the rate of change of power grid load are continuously monitored. When the rate of change of environmental parameters or the rate of change of power grid load exceeds a preset rate of change threshold, a rapid reassessment of the composite pressure index is initiated. During the rapid reassessment process, the weights related to the environment and power grid status in the calculation of the composite pressure index are dynamically increased. When the composite pressure index of the high-pressure resource group rises in a short period of time and exceeds the preset warning threshold, a secondary adjustment process is triggered. The secondary adjustment process further reduces the scheduling intensity of the high-voltage resource group and simultaneously initiates fine-tuning of the interaction parameters of the low-voltage resource group.

4. The method according to claim 3, characterized in that, The continuous monitoring of the rate of change of environmental parameters includes: The rate of change of single-domain environmental parameters collected by an environmental sensor network in different sub-regions is obtained. The environmental sensor network includes temperature and humidity sensors deployed in commercial complexes, as well as temperature and humidity sensors deployed near industrial energy storage systems. Acquire satellite remote sensing data, and extract the rate of change of macroscopic environmental parameters in the virtual power plant coverage area based on the satellite remote sensing data; Acquire environmental sensor data integrated within the distributed energy resource group itself, and calculate the rate of change of local environmental parameters of the distributed energy resource group based on the environmental sensor data; Determine the sensitivity of the distributed energy resource group to local environmental changes; Based on the rate of change of the single-domain environmental parameters, the rate of change of the macro-environmental parameters, the rate of change of the local environmental parameters, and the sensitivity, the rate of change of the environmental parameters of each sub-region is weighted and fused to obtain the rate of change of the environmental parameters of the entire domain.

5. The method according to claim 3, characterized in that, The continuous monitoring of the rate of change of power grid load includes: Acquire real-time telemetry data from the power grid side, and calculate the instantaneous load change rate of each sub-region based on the real-time telemetry data, wherein the real-time telemetry data includes feeder power, bus voltage and current data of each substation; The system acquires real-time power output and consumption data of each distributed energy resource group within the virtual power plant, and aggregates and calculates the instantaneous load change rate of the entire virtual power plant based on the real-time power output and consumption data. Obtain short-term load forecast data and actual load data provided by the power grid dispatch center, and calculate the rate of change of the deviation between the short-term load forecast data and the actual load data based on the short-term load forecast data and the actual load data; Determine the response characteristics of distributed energy resource groups to changes in local grid load; Based on the instantaneous load change rate of each sub-region, the instantaneous load change rate of the virtual power plant as a whole, the deviation change rate, and the response characteristics, the power grid load change rate of each sub-region is weighted and fused to obtain the power grid load change rate of the entire region.

6. The method according to claim 3, characterized in that, When the rate of change of the environmental parameters or the rate of change of the power grid load exceeds a preset rate of change threshold, a rapid reassessment of the composite stress index is initiated, including: Acquire historical environmental parameter change data, historical power grid load change data, and the sensitivity of each resource group to local environmental changes within the coverage area of ​​the virtual power plant; Based on the historical environmental parameter change data, the historical power grid load change data, and the sensitivity, dynamically adjust the environmental parameter change rate threshold and the power grid load change rate threshold for each sub-region; The rate of change of environmental parameters in the entire region is compared with the dynamically adjusted threshold of the rate of change of environmental parameters, and the rate of change of power grid load in the entire region is compared with the dynamically adjusted threshold of the rate of change of power grid load. When the rate of change of environmental parameters in the entire region exceeds the threshold of the dynamically adjusted rate of change of environmental parameters, or when the rate of change of power grid load in the entire region exceeds the threshold of the dynamically adjusted rate of change of power grid load, a rapid reassessment of the composite pressure index is initiated.

7. The method according to claim 3, characterized in that, The process of rapidly reassessing the composite stress index involves dynamically increasing the weights related to the environment and power grid status, including: During the rapid reassessment process, the deviation trend of user comfort is continuously monitored, and the cumulative changes of key operating parameters of the equipment are continuously monitored. When the user comfort deviation trend continues to worsen or the cumulative changes in the key operating parameters of the device exceed a preset change threshold, the weights of the user experience stress and the device health stress are increased compensatorily.

8. The method according to claim 7, characterized in that, The continuous monitoring of user comfort deviation trends during the rapid reassessment process includes: Acquire environmental parameter data related to user comfort, wherein the environmental parameter data includes indoor temperature, humidity, CO2 concentration, and light intensity; Acquire device operating status data and local operation records from the user terminal. The device operating status data includes the set temperature, operating mode, and fan speed of the smart air conditioner, and the brightness and color temperature of the smart lighting. The local operation records include the user's manual adjustment behavior of the smart air conditioner and smart lighting. Acquire information on external interference events, including construction noise outside the building and early warnings of abnormal weather. Based on the environmental parameter data, the equipment operating status data, the local operation records, and the external interference event information, identify the non-scheduled impact of non-scheduled factors on user comfort deviation; Based on the non-scheduling effects, the user comfort deviation trend is corrected to obtain the comfort deviation trend caused by scheduling.

9. A virtual power plant dispatching system based on multiple interaction modes, characterized in that, The system includes: The pressure index generation module is used to acquire pressure signals of distributed energy resource groups and quantify and generate mode pressure indicators of the resource groups based on the pressure signals. The resource groups include high-voltage resource groups, low-voltage resource groups and backup resource groups. The pressure signals include user experience pressure, equipment health pressure and communication carrying pressure. The pressure warning module is used to monitor the mode pressure index in real time and issue a pressure warning signal when the mode pressure index approaches or reaches the preset pressure limit. The parameter adjustment module is used to adjust the interaction mode parameters of the resource group according to the pressure warning signal and the current power dispatch demand. The adjustment includes reducing the dispatch intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. The module includes: acquiring instantaneous voltage and current data of the battery, and extracting the battery's micro-degradation characteristic index based on the instantaneous voltage and current data; acquiring the first deviation between the battery's actual output energy and the theoretically expected output energy, and using the first deviation as the energy conversion efficiency fluctuation index; acquiring command data packet information, and identifying a communication perturbation fingerprint based on the command data packet information, wherein the command data packet information includes a timestamp, reception timestamp, sequence number, and arrival order; acquiring the battery's... The system analyzes instantaneous power consumption changes to determine if there is a temporal correlation between the communication perturbation fingerprint and the instantaneous power consumption changes. It acquires actual response data of the resource group and quantifies the second deviation between the actual response data and a pre-established baseline for the expected response of the resource group, using this second deviation as a silent adjustment index. Based on the micro-degradation characteristic index, the energy conversion efficiency fluctuation index, the communication perturbation fingerprint, the temporal correlation, and the silent adjustment index, it evaluates the combined effect using a fuzzy logic reasoning mechanism to generate a composite pressure index. Based on the composite pressure index and the current power dispatch demand, it adjusts the interaction mode parameters of the resource group, including reducing the dispatch intensity of the high-voltage resource group and adjusting the interaction parameters of the low-voltage resource group to obtain a response. The backup resource negotiation module is used to predict whether there is a scheduling gap or whether the warning level is high after the adjustment based on the adjusted interaction mode parameters. If a scheduling gap or a high warning level is expected, it will proactively negotiate with the backup resource group and issue a scheduling instruction based on the availability intention and acceptance conditions of the backup resource group. The scheduling module is used to schedule the power of each resource group according to the scheduling instructions, monitor and verify the actual scheduling response effect of each resource group, and feed back the actual scheduling response effect to the pressure signal acquisition stage.

Images