Multi-scenario power supply load management system and method

Abstract

The application discloses a multi-scene power load management system and method, and relates to the technical field of power control. The system comprises: a data acquisition module that acquires first load data of multiple areas under a preset scene; a first data processing module that pre-processes data to obtain a power consumption characteristic sequence, which is composed of sequence units sorted by time stamps and contains scene type identification, scene switching critical time, instantaneous load rate and regional load adjustment coefficient; a second data processing module that generates a load adjustment control signal based on the sequence, corresponding to the control type mapped by the data type in the adjustment sequence unit; a control module that issues signals to controlled equipment for execution and synchronously samples to acquire second load data to update the sequence. The application realizes dynamic and accurate regulation and control of multi-scene and multi-area power loads and data closed-loop feedback, effectively improving the stability and scheduling efficiency of the power supply system under complex working conditions.

Description

Technical Field

[0001] This invention relates to the field of industrial power control technology, specifically to a multi-scenario power load management system and method. Background Technology

[0002] With the rapid development of the Industrial Internet of Things (IIoT) and smart power distribution technologies, load management across multiple regions and scenarios has become a core element in ensuring the safe operation of power systems and improving energy efficiency. Existing load management systems mostly employ fixed time windows and independent monitoring modes for single regions, relying on static thresholds for simple start-stop control or capacity allocation of electrical equipment. However, in real-world, complex power consumption environments, different regions (such as production areas, storage areas, and office areas) exhibit significant temporal differences and scenario dependencies in their power consumption behavior under different scenarios (such as peak production, off-peak standby, and emergency backup). Traditional methods struggle to dynamically capture peak power consumption periods, baseline loads, and coupling relationships between loads in various regions across multiple scenarios, leading to incomplete power consumption characteristic assessments and delayed strategy development.

[0003] Furthermore, existing management strategies are typically limited to closed-loop control within a given region, lacking collaborative management mechanisms such as cross-regional load transfer, scenario-priority scheduling, and dynamic capacity limiting. When faced with localized overloads or rapid scenario switching, this can easily lead to wasted distribution capacity or cascading tripping risks. Simultaneously, the system's feedback mechanism for strategy execution is weak. When controlled equipment fails to respond to scheduling commands or load data exhibits abnormal fluctuations, there is a lack of rapid isolation and global strategy reconstruction capabilities, severely impacting the stability and energy efficiency management level of the power supply network.

[0004] Therefore, there is an urgent need in this field for a load management system and method capable of deeply analyzing the power consumption characteristics of multiple regions and scenarios, and possessing dynamic collaborative scheduling and closed-loop adaptive capabilities, in order to overcome the technical shortcomings of existing technologies, such as static monitoring, simplistic strategies, and delayed feedback. In view of this, there is an urgent need to provide a multi-scenario power load management system and method. Summary of the Invention

[0005] To address the aforementioned issues, this invention provides a multi-scenario power load management system and method that can deeply analyze the power consumption characteristics of multiple regions and scenarios, and possesses dynamic collaborative scheduling and closed-loop adaptive capabilities.

[0006] A first aspect of the present invention provides a multi-scenario power load management system, comprising: The data acquisition module is configured to acquire at least the first load data of the first region to the Nth region under a preset power consumption scenario, wherein the first load data includes real-time load and historical load; The first data processing module is configured to preprocess the first load data to obtain the power consumption characteristic sequence of each region under each preset power consumption scenario. The power consumption characteristic sequence consists of multiple sequence units sorted by timestamp. Each sequence unit includes at least the scenario type identifier corresponding to the timestamp, the scenario switching critical time, the instantaneous load rate, and the regional load adjustment coefficient. The second data processing module is configured to generate a load regulation control signal based on the power consumption characteristic sequence, wherein the load regulation control signal corresponds to the control type mapped to one or more data types in the sequence unit; The control module is configured to send the load regulation control signal to the controlled device in the corresponding area for execution, and synchronously trigger the data acquisition module to sample the corresponding controlled device to obtain the second load data of the controlled device, and return the second load data to the first data processing module to update the power consumption characteristic sequence.

[0007] As a preferred embodiment, the second data processing module is further configured to generate the load regulation control signal through the following steps: The power consumption response characteristics of each controlled device are extracted from the power consumption characteristic sequence. The power consumption response characteristics include at least the device response delay tolerance and the load transferability coefficient. Based on the instantaneous load rate and the load adjustment coefficient of each region, a multi-region load state matrix is ​​constructed, and based on the device response delay tolerance and the load transferability coefficient, a multi-device response feature matrix is ​​constructed; the multi-region load state matrix and the multi-device response feature matrix are fused in multiple dimensions to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios. Based on the comprehensive adjustment weight and the scene switching critical time, the load adjustment control signal is generated to perform coordinated load distribution on multiple controlled devices across multiple regions; The load adjustment control signal includes a timing control type mapped to the scene switching critical time, a spatial transfer control type mapped to the regional load adjustment coefficient, and a priority control type mapped to the scene type identifier.

[0008] As a preferred embodiment, each quantized feature in the multi-region load state matrix and the multi-device response feature matrix is ​​a feature value normalized to the [0,1] interval; The second data processing module performs multi-dimensional feature fusion of the multi-region load state matrix and the multi-device response feature matrix to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios, specifically including the following steps: Extract the regional state features containing the instantaneous load rate and the regional load adjustment coefficient from the multi-region load state matrix, and extract the device response features containing the device response delay tolerance and the load transferability coefficient from the multi-device response feature matrix; Obtain the assigned weight value corresponding to each of the quantization features, and the assigned weight value is a preset weight; Determine the first correction factor and the second correction factor; Wherein, the first correction coefficient represents the correlation between the controlled device and the current preset power consumption scenario, and the second correction coefficient represents the correlation between the controlled device and the current area, specifically: At each timestamp of the power consumption characteristic sequence, there exists a probability that any of the mapped load adjustment control signals will cause the controlled device to adjust the corresponding control signal in the current preset power consumption scenario or the current area, and the values ​​of the first correction coefficient and the second correction coefficient are less than 1 in the power consumption characteristic sequence to which the current controlled device belongs. When the first correction coefficient or the second correction coefficient is greater than 1, the preset power consumption scenario and the region to which the controlled device belongs in the power consumption characteristic sequence are corrected, and the first correction coefficient and the second correction coefficient with a value less than 1 are re-determined based on the corrected scenario and region. The preset adjustment value is obtained by weighting the regional state features and the device response features according to the assigned weight values. The load jump probability is obtained by weighting the preset adjustment value with the negative correlation weight values ​​of the first correction coefficient and the second correction coefficient. The load jump probability is the comprehensive adjustment weight. The negative correlation weighted value is calculated using the negative correlation preset value of the first correction coefficient and the second correction coefficient.

[0009] As a preferred embodiment, the second data processing module is further configured to: When executing the priority adjustment type mapped to the scene type identifier, priority labels are assigned to each of the controlled devices based on the comprehensive adjustment weight; When the total system load triggers the overload threshold, controlled devices with priority tags lower than the preset level are immediately disconnected in descending order of the comprehensive adjustment weight. For controlled devices whose priority label is higher than or equal to the preset level, the load is reduced to a preset ratio based on the device response latency tolerance and the scene switching critical time.

[0010] As a preferred embodiment, the second data processing module is further configured to: When generating a load regulation control signal of the spatial transfer regulation type mapped to the regional load regulation coefficient, the regional load regulation coefficients of the first region and the second region are compared in real time. When it is determined that the instantaneous load rate of the first region exceeds the first warning threshold, and the regional load adjustment coefficient of the second region indicates that the load margin is greater than the safety threshold, the controlled device in the first region whose load transfer coefficient is higher than the preset transfer threshold is selected, and a load migration instruction carrying a migration delay time is generated to transfer the load of the selected controlled device to the second region.

[0011] As a preferred embodiment, the second data processing module is further configured to: When generating a load regulation control signal of the timing regulation type mapped to the scene switching critical time, the scene switching transition period is determined based on the scene switching critical time; During the scenario switching transition period, redundant capacity channels are allocated to controlled devices whose device response latency tolerance is greater than a preset tolerance threshold, and load blocking is performed on capacity increase requests issued by controlled devices whose device response latency tolerance is less than or equal to the preset tolerance threshold. The load blocking is released after the scenario switching transition period ends.

[0012] As a preferred approach, when acquiring the first load data, the data acquisition module dynamically configures the sampling period according to the operating condition fluctuation frequency corresponding to the scenario type identifier of the preset power consumption scenario to which each region belongs, and defines a dynamic monitoring time window with the end aligned to the current moment for each of the first to Nth regions.

[0013] A second aspect of the present invention provides a multi-scenario power load management method, comprising the following steps: Acquire first load data for the first region to the Nth region under a preset power consumption scenario. The first load data includes real-time load and historical load. The first load data is preprocessed to obtain the power consumption characteristic sequence of each region under each preset power consumption scenario. The power consumption characteristic sequence is composed of multiple sequence units sorted by timestamp. Each sequence unit includes at least the scenario type identifier corresponding to the timestamp, the scenario switching critical time, the instantaneous load rate, and the regional load adjustment coefficient. Based on the power consumption characteristic sequence, a load adjustment control signal is generated. The load adjustment control signal corresponds to the control type mapped to one or more data types in the sequence unit. The load regulation control signal is sent to the controlled device in the corresponding area for execution, and the corresponding controlled device is sampled simultaneously to obtain the second load data. The second load data is then returned to update the power consumption characteristic sequence. The power consumption response characteristics of each controlled device are extracted from the power consumption characteristic sequence. The power consumption response characteristics include at least the device response delay tolerance and the load transferability coefficient. A multi-region load state matrix is ​​constructed based on the instantaneous load rate and the regional load adjustment coefficient of each region, and a multi-device response feature matrix is ​​constructed based on the device response delay tolerance and the load transferability coefficient. The multi-region load state matrix and the multi-device response feature matrix are fused in multiple dimensions to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios. The load adjustment control signal is generated based on the comprehensive adjustment weight and the scene switching critical time to perform coordinated load distribution to multiple controlled devices across multiple regions.

[0014] Compared with the prior art, the present invention has the following advantages: 1. This invention acquires first load data from multiple regions through a data acquisition module, and generates a power consumption characteristic sequence containing scene type identifiers, scene switching critical times, instantaneous load rates, and regional load adjustment coefficients through a first data processing module. A second data processing module generates load adjustment control signals based on this sequence, accurately mapping and adjusting the control types corresponding to various data types within the sequence unit. Simultaneously, after issuing the signal, the control module synchronously triggers sampling to acquire second load data to update the sequence. Combined with dynamically configuring the sampling period based on the frequency of operating condition fluctuations and defining a dynamic monitoring time window for end-point alignment, real-time closed-loop feedback and high-frequency dynamic tracking of load data are achieved. This architecture effectively overcomes the technical shortcomings of traditional load management systems, such as sluggish response during complex scene switching, single control dimensions, and a lack of data self-verification capabilities.

[0015] 2. When calculating the comprehensive adjustment weight, this invention first establishes a theoretical benchmark for load regulation through multi-source features and allocated weight values. This invention normalizes the regional state features and equipment response features to the [0,1] interval, and performs weighted calculations based on preset allocated weight values ​​to obtain preset adjustment values. The core role of these allocated weight values ​​and other quantitative features in load regulation is to establish a theoretical evaluation benchmark for the basic load regulation capability of controlled equipment, and to quantify the theoretical regulation contribution and basic response potential of equipment under ideal operating conditions. Secondly, the probability of complete load change in actual scheduling is quantified through first and second correction coefficients. This invention innovatively introduces first and second correction coefficients, the core purpose of which is to realistically represent the probability of a controlled device experiencing a complete load change in the current preset power consumption scenario or current region during the scheduling process. In its specific implementation, the system determines the correction coefficient by statistically analyzing the probability that a load regulation control signal with any mapping at each time point in the electricity consumption characteristic sequence would cause the controlled equipment to undergo a complete adjustment. The system strictly limits the correction coefficient to a value less than 1. When the original evaluation value representing the correlation is detected to be greater than 1, the system determines that the equipment's operating state has seriously deviated. It then automatically corrects the preset electricity consumption scenario and region corresponding to the controlled equipment in the electricity consumption characteristic sequence, and re-determines a correction coefficient less than 1 based on the corrected scenario and region. This mechanism effectively eliminates interference from abnormal correlation data, ensuring the physical rigor of the probabilistic representation.

[0016] Finally, through negative correlation weighted calculation, the system of this invention recalculates the preset adjustment value representing the theoretical capability with the negative correlation weighted values ​​of the first and second correction coefficients to obtain the load jump probability as the comprehensive adjustment weight. The larger the correction coefficient, the smaller its negative correlation weighted value. Since the controlled equipment itself has a relatively higher probability of load adjustment, the controlled equipment corresponding to the correction coefficient plays a lower role in load adjustment in this control signal, resulting in a lower calculated load jump probability. Therefore, it effectively overcomes the technical defects of traditional load management methods that rely solely on theoretical parameters or fixed thresholds, leading to missed dispatch commands, inadequate equipment response, or secondary impacts on the power grid. This provides highly reliable data support for subsequent high-precision priority cutoff, cross-regional spatial transfer, and scene switching timing control.

[0017] 3. Based on the calculated comprehensive adjustment weights, this invention can perform multi-dimensional coordinated control: In terms of priority control, when the total system load triggers the overload threshold, it breaks the conventional fixed priority logic and immediately cuts off low-priority devices according to the comprehensive adjustment weights from high to low, while performing step-by-step load reduction on high-priority devices, effectively avoiding transient impacts on the power grid; in terms of spatial transfer control, by comparing the regional load adjustment coefficients in real time, it accurately selects devices with high load transfer coefficients to generate instructions carrying migration delay durations, achieving smooth peak shaving and valley filling of cross-regional loads; in terms of timing control, during the scenario switching transition period, it allocates redundant capacity channels differently based on the device response delay tolerance and performs capacity expansion interception on devices with low tolerance. The coordinated operation of multiple control types maximizes the continuous power supply to core devices and improves the global balance capability of power loads in multiple regions. Attached Figure Description

[0018] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0019] Figure 1 This is a structural block diagram of the system provided in the embodiments of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] In a first aspect, this embodiment provides a multi-scenario power load management system, such as... Figure 1 As shown, it includes: The data acquisition module is configured to acquire at least the first load data of the first region to the Nth region under a preset power consumption scenario, wherein the first load data includes real-time load and historical load; The first data processing module is configured to preprocess the first load data to obtain the power consumption characteristic sequence of each region under each preset power consumption scenario. The power consumption characteristic sequence consists of multiple sequence units sorted by timestamp. Each sequence unit includes at least the scenario type identifier corresponding to the timestamp, the scenario switching critical time, the instantaneous load rate, and the regional load adjustment coefficient. The second data processing module is configured to generate a load regulation control signal based on the power consumption characteristic sequence, wherein the load regulation control signal corresponds to the control type mapped to one or more data types in the sequence unit; The control module is configured to send the load regulation control signal to the controlled device in the corresponding area for execution, and synchronously trigger the data acquisition module to sample the corresponding controlled device to obtain the second load data of the controlled device, and return the second load data to the first data processing module to update the power consumption characteristic sequence.

[0022] As a preferred embodiment, the second data processing module is further configured to generate the load regulation control signal through the following steps: The power consumption response characteristics of each controlled device are extracted from the power consumption characteristic sequence. The power consumption response characteristics include at least the device response delay tolerance and the load transferability coefficient. Based on the instantaneous load rate and the load adjustment coefficient of each region, a multi-region load state matrix is ​​constructed, and based on the device response delay tolerance and the load transferability coefficient, a multi-device response feature matrix is ​​constructed; the multi-region load state matrix and the multi-device response feature matrix are fused in multiple dimensions to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios. Based on the comprehensive adjustment weight and the scene switching critical time, the load adjustment control signal is generated to perform coordinated load distribution on multiple controlled devices across multiple regions; The load adjustment control signal includes a timing control type mapped to the scene switching critical time, a spatial transfer control type mapped to the regional load adjustment coefficient, and a priority control type mapped to the scene type identifier.

[0023] As a preferred embodiment, each quantized feature in the multi-region load state matrix and the multi-device response feature matrix is ​​a feature value normalized to the [0,1] interval; The second data processing module performs multi-dimensional feature fusion of the multi-region load state matrix and the multi-device response feature matrix to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios, specifically including the following steps: Extract the regional state features containing the instantaneous load rate and the regional load adjustment coefficient from the multi-region load state matrix, and extract the device response features containing the device response delay tolerance and the load transferability coefficient from the multi-device response feature matrix; Obtain the assigned weight value corresponding to each of the quantization features, and the assigned weight value is a preset weight; Determine the first correction factor and the second correction factor; Wherein, the first correction coefficient represents the correlation between the controlled device and the current preset power consumption scenario, and the second correction coefficient represents the correlation between the controlled device and the current area, specifically: At each timestamp of the power consumption characteristic sequence, there exists a probability that any of the mapped load adjustment control signals will cause the controlled device to adjust the corresponding control signal in the current preset power consumption scenario or the current area, and the values ​​of the first correction coefficient and the second correction coefficient are less than 1 in the power consumption characteristic sequence to which the current controlled device belongs. When the first correction coefficient or the second correction coefficient is greater than 1, the preset power consumption scenario and the region to which the controlled device belongs in the power consumption characteristic sequence are corrected, and the first correction coefficient and the second correction coefficient with a value less than 1 are re-determined based on the corrected scenario and region. The preset adjustment value is obtained by weighting the regional state features and the device response features according to the assigned weight values. The load jump probability is obtained by weighting the preset adjustment value with the negative correlation weight values ​​of the first correction coefficient and the second correction coefficient. The load jump probability is the comprehensive adjustment weight. The negative correlation weighted value is calculated using the negative correlation preset value of the first correction coefficient and the second correction coefficient.

[0024] As a preferred embodiment, the second data processing module is further configured to: When executing the priority adjustment type mapped to the scene type identifier, priority labels are assigned to each of the controlled devices based on the comprehensive adjustment weight; When the total system load triggers the overload threshold, controlled devices with priority tags lower than the preset level are immediately disconnected in descending order of the comprehensive adjustment weight. For controlled devices whose priority label is higher than or equal to the preset level, the load is reduced to a preset ratio based on the device response latency tolerance and the scene switching critical time.

[0025] As a preferred embodiment, the second data processing module is further configured to: When generating a load regulation control signal of the spatial transfer regulation type mapped to the regional load regulation coefficient, the regional load regulation coefficients of the first region and the second region are compared in real time. When it is determined that the instantaneous load rate of the first region exceeds the first warning threshold, and the regional load adjustment coefficient of the second region indicates that the load margin is greater than the safety threshold, the controlled device in the first region whose load transfer coefficient is higher than the preset transfer threshold is selected, and a load migration instruction carrying a migration delay time is generated to transfer the load of the selected controlled device to the second region.

[0026] As a preferred embodiment, the second data processing module is further configured to: When generating a load regulation control signal of the timing regulation type mapped to the scene switching critical time, the scene switching transition period is determined based on the scene switching critical time; During the scenario switching transition period, redundant capacity channels are allocated to controlled devices whose device response latency tolerance is greater than a preset tolerance threshold, and load blocking is performed on capacity increase requests issued by controlled devices whose device response latency tolerance is less than or equal to the preset tolerance threshold. The load blocking is released after the scenario switching transition period ends.

[0027] As a preferred approach, when acquiring the first load data, the data acquisition module dynamically configures the sampling period according to the operating condition fluctuation frequency corresponding to the scenario type identifier of the preset power consumption scenario to which each region belongs, and defines a dynamic monitoring time window with the end aligned to the current moment for each of the first to Nth regions.

[0028] A second aspect of this embodiment provides a multi-scenario power load management method, including the following steps: Acquire first load data for the first region to the Nth region under a preset power consumption scenario. The first load data includes real-time load and historical load. The first load data is preprocessed to obtain the power consumption characteristic sequence of each region under each preset power consumption scenario. The power consumption characteristic sequence is composed of multiple sequence units sorted by timestamp. Each sequence unit includes at least the scenario type identifier corresponding to the timestamp, the scenario switching critical time, the instantaneous load rate, and the regional load adjustment coefficient. Based on the power consumption characteristic sequence, a load adjustment control signal is generated. The load adjustment control signal corresponds to the control type mapped to one or more data types in the sequence unit. The load regulation control signal is sent to the controlled device in the corresponding area for execution, and the corresponding controlled device is sampled simultaneously to obtain the second load data. The second load data is then returned to update the power consumption characteristic sequence. The power consumption response characteristics of each controlled device are extracted from the power consumption characteristic sequence. The power consumption response characteristics include at least the device response delay tolerance and the load transferability coefficient. A multi-region load state matrix is ​​constructed based on the instantaneous load rate and the regional load adjustment coefficient of each region, and a multi-device response feature matrix is ​​constructed based on the device response delay tolerance and the load transferability coefficient. The multi-region load state matrix and the multi-device response feature matrix are fused in multiple dimensions to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios. The load adjustment control signal is generated based on the comprehensive adjustment weight and the scene switching critical time to perform coordinated load distribution to multiple controlled devices across multiple regions.

[0029] This embodiment has the following advantages over the prior art: This embodiment acquires first load data from multiple regions through a data acquisition module, and a first data processing module generates a power consumption characteristic sequence containing scene type identifiers, scene switching critical times, instantaneous load rates, and regional load adjustment coefficients. A second data processing module generates load adjustment control signals based on this sequence, accurately mapping and adjusting the control types corresponding to various data types within the sequence unit. Simultaneously, after issuing the signal, the control module synchronously triggers sampling to acquire second load data to update the sequence. Combined with dynamically configuring the sampling period based on the frequency of operating condition fluctuations and defining a dynamic monitoring time window for end-point alignment, real-time closed-loop feedback and high-frequency dynamic tracking of load data are achieved. This architecture effectively overcomes the technical shortcomings of traditional load management systems, such as sluggish response during complex scene switching, single control dimensions, and a lack of data self-verification capabilities.

[0030] In calculating the comprehensive adjustment weight, this embodiment first establishes a theoretical benchmark for load regulation through multi-source features and allocated weight values. This embodiment normalizes the regional state features and equipment response features to the [0,1] interval, and performs weighted calculations based on preset allocated weight values ​​to obtain preset adjustment values. The core role of these allocated weight values ​​and other quantitative features in load regulation is to establish a theoretical evaluation benchmark for the basic load regulation capability of controlled equipment, and to quantify the theoretical regulation contribution and basic response potential of equipment under ideal operating conditions. Secondly, the probability of complete load change in actual scheduling is quantified through first and second correction coefficients. This embodiment innovatively introduces first and second correction coefficients, the core purpose of which is to realistically represent the probability of a complete load change occurring in the current preset power consumption scenario or current region during the scheduling process. In its specific implementation, the system determines the correction coefficient by statistically analyzing the probability that a load regulation control signal with any mapping at each time point in the electricity consumption characteristic sequence would cause the controlled equipment to undergo a complete adjustment. The system strictly limits the correction coefficient to a value less than 1. When the original evaluation value representing the correlation is detected to be greater than 1, the system determines that the equipment's operating state has seriously deviated. It then automatically corrects the preset electricity consumption scenario and region corresponding to the controlled equipment in the electricity consumption characteristic sequence, and re-determines a correction coefficient less than 1 based on the corrected scenario and region. This mechanism effectively eliminates interference from abnormal correlation data, ensuring the physical rigor of the probabilistic representation.

[0031] Finally, through negative correlation weighted calculation, the system in this embodiment recalculates the preset adjustment value representing the theoretical capability with the negative correlation weighted values ​​of the first and second correction coefficients to obtain the load jump probability as the comprehensive adjustment weight. The larger the correction coefficient, the smaller its negative correlation weighted value. Since the controlled equipment itself has a relatively higher probability of load adjustment, the controlled equipment corresponding to the correction coefficient plays a lower role in load adjustment in this control signal, resulting in a lower calculated load jump probability. Therefore, it effectively overcomes the technical defects of traditional load management methods that rely solely on theoretical parameters or fixed thresholds, leading to missed dispatch commands, inadequate equipment response, or secondary impacts on the power grid. This provides highly reliable data support for subsequent high-precision priority cutoff, cross-regional spatial transfer, and scene switching timing control.

[0032] Based on the calculated comprehensive adjustment weights, this embodiment can perform multi-dimensional coordinated control: In terms of priority control, when the total system load triggers the overload threshold, it breaks the conventional fixed priority logic and immediately cuts off low-priority devices according to the comprehensive adjustment weights from high to low, while performing step-by-step load reduction on high-priority devices, effectively avoiding transient impacts on the power grid; in terms of spatial transfer control, by comparing the regional load adjustment coefficients in real time, it accurately selects devices with high load transfer coefficients to generate instructions carrying migration delay durations, achieving smooth peak shaving and valley filling of cross-regional loads; in terms of timing control, during the scenario switching transition period, it allocates redundant capacity channels differently based on the device response delay tolerance and performs capacity expansion interception on devices with low tolerance. The coordinated operation of multiple control types maximizes the continuous power supply to core devices and improves the global balance capability of power loads in multiple regions.

[0033] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent variations only. Individual components and functions are optional unless explicitly required, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for descriptive purposes only and is not intended to limit the claims. As used in the description of the embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application refers to any and all combinations of one or more of the associated listed elements. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, then the relevant parts can be referred to the description of the method section.

[0034] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to achieve the described functions, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the described devices, apparatuses, and units can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0035] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, function, and operation of implementations of apparatus, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based device that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A multi-scenario power load management system, characterized in that, include: The data acquisition module is configured to acquire at least the first load data of the first region to the Nth region under a preset power consumption scenario, wherein the first load data includes real-time load and historical load; The first data processing module is configured to preprocess the first load data to obtain the power consumption characteristic sequence of each region under each preset power consumption scenario. The power consumption characteristic sequence consists of multiple sequence units sorted by timestamp. Each sequence unit includes at least the scenario type identifier corresponding to the timestamp, the scenario switching critical time, the instantaneous load rate, and the regional load adjustment coefficient. The second data processing module is configured to generate a load regulation control signal based on the power consumption characteristic sequence, wherein the load regulation control signal corresponds to the control type mapped to one or more data types in the sequence unit; The control module is configured to send the load regulation control signal to the controlled device in the corresponding area for execution, and synchronously trigger the data acquisition module to sample the corresponding controlled device to obtain the second load data of the controlled device, and return the second load data to the first data processing module to update the power consumption characteristic sequence.

2. The multi-scenario power load management system according to claim 1, characterized in that, The second data processing module is also configured to generate the load regulation control signal through the following steps: The power consumption response characteristics of each controlled device are extracted from the power consumption characteristic sequence. The power consumption response characteristics include at least the device response delay tolerance and the load transferability coefficient. Based on the instantaneous load rate and the load adjustment coefficient of each region, a multi-region load state matrix is ​​constructed, and based on the device response delay tolerance and the load transferability coefficient, a multi-device response feature matrix is ​​constructed. The multi-region load state matrix and the multi-device response feature matrix are fused in multiple dimensions to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios. Based on the comprehensive adjustment weight and the scene switching critical time, the load adjustment control signal is generated to perform coordinated load distribution on multiple controlled devices across multiple regions; The load adjustment control signal includes a timing control type mapped to the scene switching critical time, a spatial transfer control type mapped to the regional load adjustment coefficient, and a priority control type mapped to the scene type identifier.

3. The multi-scenario power load management system according to claim 2, characterized in that, Each quantized feature in the multi-region load state matrix and the multi-device response feature matrix is ​​a feature value normalized to the [0,1] interval; The second data processing module performs multi-dimensional feature fusion of the multi-region load state matrix and the multi-device response feature matrix to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios, specifically including the following steps: Extract the regional state features containing the instantaneous load rate and the regional load adjustment coefficient from the multi-region load state matrix, and extract the device response features containing the device response delay tolerance and the load transferability coefficient from the multi-device response feature matrix; Obtain the assigned weight value corresponding to each of the quantization features, and the assigned weight value is a preset weight; Determine the first correction factor and the second correction factor; Wherein, the first correction coefficient represents the correlation between the controlled device and the current preset power consumption scenario, and the second correction coefficient represents the correlation between the controlled device and the current area, specifically: At each timestamp of the power consumption characteristic sequence, there exists a probability that any of the mapped load adjustment control signals will cause the controlled device to adjust the corresponding control signal in the current preset power consumption scenario or the current area, and the values ​​of the first correction coefficient and the second correction coefficient are less than 1 in the power consumption characteristic sequence to which the current controlled device belongs. When the first correction coefficient or the second correction coefficient is greater than 1, the preset power consumption scenario and the region to which the controlled device belongs in the power consumption characteristic sequence are corrected, and the first correction coefficient and the second correction coefficient with a value less than 1 are re-determined based on the corrected scenario and region. The preset adjustment value is obtained by weighting the regional state features and the device response features according to the assigned weight values. The load jump probability is obtained by weighting the preset adjustment value with the negative correlation weight values ​​of the first correction coefficient and the second correction coefficient. The load jump probability is the comprehensive adjustment weight. The negative correlation weighted value is calculated using the negative correlation preset value of the first correction coefficient and the second correction coefficient.

4. The multi-scenario power load management system according to claim 3, characterized in that, The second data processing module is also configured as follows: When executing the priority adjustment type mapped to the scene type identifier, priority labels are assigned to each of the controlled devices based on the comprehensive adjustment weight; When the total system load triggers the overload threshold, controlled devices with priority tags lower than the preset level are immediately disconnected in descending order of the comprehensive adjustment weight. For controlled devices whose priority label is higher than or equal to the preset level, the load is reduced to a preset ratio based on the device response latency tolerance and the scene switching critical time.

5. The multi-scenario power load management system according to claim 3, characterized in that, The second data processing module is also configured as follows: When generating a load regulation control signal of the spatial transfer regulation type mapped to the regional load regulation coefficient, the regional load regulation coefficients of the first region and the second region are compared in real time. When it is determined that the instantaneous load rate of the first region exceeds the first warning threshold, and the regional load adjustment coefficient of the second region indicates that the load margin is greater than the safety threshold, the controlled device in the first region whose load transfer coefficient is higher than the preset transfer threshold is selected, and a load migration instruction carrying a migration delay time is generated to transfer the load of the selected controlled device to the second region.

6. The multi-scenario power load management system according to claim 3, characterized in that, The second data processing module is also configured as follows: When generating a load regulation control signal of the timing regulation type mapped to the scene switching critical time, the scene switching transition period is determined based on the scene switching critical time; During the scenario switching transition period, redundant capacity channels are allocated to controlled devices whose device response latency tolerance is greater than a preset tolerance threshold, and load blocking is performed on capacity increase requests issued by controlled devices whose device response latency tolerance is less than or equal to the preset tolerance threshold. The load blocking is released after the scenario switching transition period ends.

7. The multi-scenario power load management system according to claim 1, characterized in that, When acquiring the first load data, the data acquisition module dynamically configures the sampling period according to the operating condition fluctuation frequency corresponding to the scenario type identifier of the preset power consumption scenario to which each region belongs, and defines a dynamic monitoring time window with the end aligned to the current moment for each of the first region to the Nth region.

8. A multi-scenario power load management method, applied to the multi-scenario power load management system as described in any one of claims 1 to 7, characterized in that, Includes the following steps: Acquire first load data for the first region to the Nth region under a preset power consumption scenario. The first load data includes real-time load and historical load. The first load data is preprocessed to obtain the power consumption characteristic sequence of each region under each preset power consumption scenario. The power consumption characteristic sequence is composed of multiple sequence units sorted by timestamp. Each sequence unit includes at least the scenario type identifier corresponding to the timestamp, the scenario switching critical time, the instantaneous load rate, and the regional load adjustment coefficient. Based on the power consumption characteristic sequence, a load adjustment control signal is generated. The load adjustment control signal corresponds to the control type mapped to one or more data types in the sequence unit. The load regulation control signal is sent to the controlled device in the corresponding area for execution, and the corresponding controlled device is sampled simultaneously to obtain the second load data. The second load data is then returned to update the power consumption characteristic sequence. The power consumption response characteristics of each controlled device are extracted from the power consumption characteristic sequence. The power consumption response characteristics include at least the device response delay tolerance and the load transferability coefficient. A multi-region load state matrix is ​​constructed based on the instantaneous load rate and the regional load adjustment coefficient of each region, and a multi-device response feature matrix is ​​constructed based on the device response delay tolerance and the load transferability coefficient. The multi-region load state matrix and the multi-device response feature matrix are fused in multiple dimensions to calculate the comprehensive adjustment weight of each controlled device under different preset power consumption scenarios. The load adjustment control signal is generated based on the comprehensive adjustment weight and the scene switching critical time to perform coordinated load distribution to multiple controlled devices across multiple regions.

Images