A power distribution intelligent gateway with low-voltage line state perception and load characteristic analysis

Abstract

This application provides a distribution smart gateway with low-voltage line status perception and load characteristic analysis, belonging to the field of power system technology. The gateway includes: a data acquisition module, a perception and analysis module, a communication module, and an execution module. The data acquisition module is configured to acquire the operating status information of the power system coupled to the distribution smart gateway. The perception and analysis module is configured to construct input features based on the operating status information and input the input features into a first identification model to obtain power system operating risk identification results and initial power system operating status analysis results. When the operating risk level is less than or equal to a threshold, the execution module implements the corresponding operating processing strategy based on the initial power system operating status analysis results. When the operating risk level is greater than the threshold, the initial power system operating status analysis results are sent to a cloud processing platform via the communication module. This application can improve risk identification and response speed.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to a distribution smart gateway with low-voltage line status sensing and load characteristic analysis. Background Technology

[0002] A smart distribution gateway is a critical power system device, serving as a key hub for achieving intelligent power distribution. It is typically located at the center of the power system, connecting various components such as sensors, monitoring equipment, data acquisition systems, data processing and analysis platforms, and intelligent control and dispatching systems. Smart distribution gateways have multiple functions, including real-time monitoring and sensing of low-voltage line electrical parameters, load characteristic analysis, anomaly detection, fault diagnosis, and intelligent control and dispatching.

[0003] The power distribution smart gateway plays a crucial role in transmitting data collected by sensors to a cloud data center. After data processing and analysis in the cloud data center, the gateway performs real-time adjustments and optimizations to the power system based on control commands issued by the cloud data center.

[0004] However, with the continuous development of the power system, the data processing pressure of cloud data centers is increasing, resulting in a lag in the processing response of distribution smart gateways. This lag can lead to delays in data processing and analysis, affecting the real-time performance and accuracy of intelligent control and scheduling. Summary of the Invention

[0005] This application provides a power distribution smart gateway with low-voltage line status sensing and load characteristic analysis. The technical solution adopted in this application is as follows: In the first aspect, a distribution smart gateway with low-voltage line status perception and load characteristic analysis is provided, including: a data acquisition module, a perception and analysis module, a communication module, and an execution module; The acquisition module is configured to acquire the operating status information of the power system coupled to the distribution smart gateway; The perception and analysis module contains the first recognition model and is configured as follows: Input features are constructed based on the operating status information, and these features are then input into the first identification model to obtain the power system operation risk identification results and the initial analysis results of the power system operation status. When the operational risk level is less than or equal to the threshold, the corresponding operational processing strategy of the execution module is determined based on the initial analysis results of the power system's operational status. When the operational risk level exceeds the threshold, the initial analysis results of the power system's operational status are sent to the cloud processing platform via the communication module.

[0006] Optionally, the perception analysis module is also configured as follows: The computing power requirement is determined based on the operating status information, and the target computing power pool for the power distribution smart gateway is determined based on the computing power requirement. Based on the computing power in the target computing power pool, perform power system operation status analysis and power system operation risk identification at different accuracy levels.

[0007] Optionally, determining the computing power requirement based on the operating status information and adjusting the computing power pool of the power distribution smart gateway according to the computing power requirement includes: Obtain the idle computing power in the computing power pool of the power distribution smart gateway. If the computing power demand is less than or equal to the idle computing power, construct the target computing power pool based on the idle computing power in the computing power pool of the power distribution smart gateway. When the computing power demand exceeds the available computing power, the available computing power in the shared computing power pool is acquired to construct the target computing power pool.

[0008] Optionally, the shared computing power pool includes idle computing power from the computing power pools of smart distribution gateways within the same deployment area.

[0009] Optionally, depending on the computing power in the target computing power pool, different levels of precision in power system operation status analysis and power system operation risk identification are performed, including: When constructing a target computing pool based on the idle computing power in the computing power pool of the power distribution smart gateway, perform power system operation status analysis and power system operation risk identification operations with the first level of accuracy. When constructing a target computing pool based on the available computing power in the shared computing pool, the second-precision level of power system operation status analysis and power system operation risk identification operations are performed, wherein the second-precision level is higher than the first-precision level.

[0010] Optionally, performing power system operating status analysis and power system operating risk identification at the second level of accuracy includes: Multiple computing units are constructed based on the target computing power pool. In each computing unit, the first-level precision level of power system operation status analysis and power system operation risk identification operations are performed. The results of multiple first-precision level power system operation status analyses and power system operation risk identification operations are combined to obtain second-precision level power system operation status analyses and power system operation risk identification operations.

[0011] Optionally, input features are constructed based on the operating status information, and these features are then input into the first identification model to obtain the initial analysis results of the power system operating risk level and power system operating status, including: Based on the operating status information, a first input feature and a second input feature are constructed. The first input feature is used to characterize the operating status of the low-voltage lines of the power system, and the second input feature is used to characterize the load status of the power system. The first input feature and the second input feature are input into the first recognition model to obtain the first recognition result and the second recognition result; Based on the first and second identification results, the initial analysis results of the power system operation status and the corresponding power system operation risk level are determined.

[0012] Optionally, a second recognition model is deployed on the cloud processing platform, which is configured as follows: Receive the initial analysis results of the power system operating status and input the initial analysis results of the power system operating status into the second identification model to obtain the power system operating status verification analysis results; The power system operation status review and analysis results and the matching operation processing strategies are sent to the distribution smart gateway.

[0013] Optionally, the cloud processing platform is also configured as follows: Acquire historical operating data of the power system and corresponding initial analysis results of historical power system operating status; Based on historical operating data of the power system and the initial analysis results of historical power system operating status, a first identification model is constructed. Knowledge distillation is performed on the second recognition model to obtain the first recognition model. The model accuracy of the second recognition model is higher than that of the first recognition model. The first identification model is deployed to the power distribution smart gateway.

[0014] Optionally, the perception analysis module is also configured as follows: The communication module receives the power system operation status review and analysis results and operation processing strategies sent by the cloud processing platform; Based on the comparison between the power system operation status verification analysis results and the power system operation status initial analysis results, the first identification model is dynamically adjusted. The corresponding operation and processing strategies of the execution modules are determined based on the results of the power system operation status review and analysis.

[0015] In summary, the above achieves the following technical effects: By performing initial identification and analysis locally on the smart distribution gateway, and only sending necessary results to the cloud for processing, the processing pressure on the cloud data center is reduced. This helps reduce data processing and analysis latency and improves the response speed of intelligent control and scheduling. Initial analysis results are only sent to the cloud processing platform when the operational risk level exceeds a threshold, rather than sending all data. This saves bandwidth resources and only consumes cloud resources when needed. When the operational risk level is less than or equal to the threshold, the smart distribution gateway can execute appropriate processing strategies based on the local operational status analysis results. This enhances the system's autonomy and stability and reduces dependence on the cloud. By performing initial analysis and processing locally, the system can respond to problems more quickly and take necessary measures to avoid potential faults and damage, thereby improving the reliability and stability of the power system.

[0016] By deploying the first identification model and local perception and analysis module in the power distribution smart gateway, the real-time performance and accuracy of the system are effectively improved, the dependence on cloud resources is reduced, and thus the intelligence level and reliability of the power system are improved. Attached Figure Description

[0017] Figure 1 This application provides a schematic diagram of a power distribution smart gateway system module with low-voltage line status perception and load characteristic analysis. Detailed Implementation

[0018] Unless the context requires otherwise, throughout the specification and claims, the term "comprising" is interpreted as open-ended and encompassing, meaning "including, but not limited to." In the description of the specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "exemplarily," or "some examples," etc., are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this disclosure. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, materials, or characteristics may be included in any suitable manner in any one or more embodiments or examples.

[0019] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0020] In describing some embodiments, the term "coupled" and its derivative expressions may be used. For example, the term "coupled" may be used in describing some embodiments to indicate that two or more components have direct physical or electrical contact; in this case, "coupled" may also be described as "connected." Furthermore, the term "coupled" may also refer to two or more components that do not have direct contact with each other but still cooperate or interact with each other. The embodiments disclosed herein are not necessarily limited to the content of this document.

[0021] "At least one of A, B and C" has the same meaning as "at least one of A, B or C", both including the following combinations of A, B and C: only A, only B, only C, combinations of A and B, combinations of A and C, combinations of B and C, and combinations of A, B and C.

[0022] "A and / or B" includes three combinations: A only, B only, and a combination of A and B. The use of "applies to" or "configured to" in this document implies open and inclusive language, which does not preclude applicability to or configuration to perform additional tasks or steps on devices. Additionally, the use of "based on" implies openness and inclusivity, as processes, steps, calculations, or other actions "based on" one or more conditions or values ​​may in practice be based on additional conditions or values ​​beyond those conditions.

[0023] The use of “configured as” in this article implies an open and inclusive language that does not exclude the applicability to or configuration of devices to perform additional tasks or steps.

[0024] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0025] Currently, the power distribution smart gateway is a key node connecting sensors and cloud data centers. It is responsible for transmitting the data collected by the sensors to the cloud data center, and then receiving control commands issued by the cloud data center to adjust and optimize the power system in real time.

[0026] This architecture enables intelligent control and dispatching of power systems, improving energy efficiency and system stability. However, with the development of power systems and the improvement of their intelligence level, the amount and complexity of data processed by cloud data centers are also constantly increasing, posing challenges to distribution smart gateways. First, data transmission delays may affect real-time performance, leading to lags in data processing and analysis. Second, increased processing pressure on cloud data centers may slow down the processing response speed of distribution smart gateways, thereby affecting real-time adjustments and optimizations of the power system.

[0027] In the existing architecture, the smart distribution gateway only serves a data sensing function. Based on this, the applicant proposes the following technical concept: Integrating more computing and processing capabilities into the smart distribution gateway to enable a certain degree of edge computing. Low-voltage line status sensing and load characteristic analysis are time-sensitive functional requirements; therefore, these functions can be deployed on the smart distribution gateway, allowing it to perform some data processing and decision-making locally, thus reducing the pressure on the cloud data center. However, a balance needs to be struck between computing power and corresponding cost to achieve a superior cost-performance ratio for the smart distribution gateway.

[0028] Low-voltage line status sensing refers to Reference Figure 1 The basic application provides an embodiment of a power distribution smart gateway with low-voltage line status awareness and load characteristic analysis. The system includes a data acquisition module, a sensing and analysis module, a communication module, and an execution module; The acquisition module is configured to acquire the operating status information of the power system coupled to the distribution smart gateway.

[0029] To achieve status awareness of low-voltage lines, it is necessary to monitor electrical parameters such as current, voltage, and frequency of low-voltage lines in the power system in real time, as well as to sense the line's operating status, such as whether a fault, overload, or short circuit has occurred. This data is collected in real time by sensors and monitoring equipment installed on the low-voltage lines and then transmitted to a data processing system for analysis and processing. To achieve load characteristic analysis, historical power system operating data is required, such as load curves, load factors, peak load, and average load. Based on this data, the characteristics of load consumption, variation patterns, and influencing factors can be analyzed.

[0030] The perception and analysis module is configured as follows: Input features are constructed based on the operating status information and input into the first identification model to obtain the power system operating risk identification results and the initial analysis results of the power system operating status. When the operating risk level is less than or equal to the threshold, the corresponding operating processing strategy of the execution module is implemented based on the initial analysis results of the power system operating status. When the operating risk level is greater than the threshold, the initial analysis results of the power system operating status are sent to the cloud processing platform through the communication module.

[0031] The perception and analysis module deploys a first identification model. Based on collected operational status information, this model performs feature engineering to extract and construct useful features from the raw data. These features can be statistical indicators of certain variables, trend analysis of time-series data, spectral characteristics, etc. The constructed features serve as input, reflecting the current state and performance of the power system. After obtaining the input features, they are fed into the first identification model. The first identification model processes these features to produce two main results: Power system operational risk identification results: identifying whether there are current risks or potential problems in the system, such as abnormal states or fault risks; and initial power system operational status analysis results: providing a preliminary analysis of the system's current operational status, which may include assessments of system stability, performance indicators, etc. Through this process, the operational status of the power system can be monitored and evaluated, potential problems can be identified in a timely manner, and corresponding measures can be taken to ensure the safe and stable operation of the system.

[0032] When conducting a preliminary assessment of the operating status and risk level of the power system, the distribution smart gateway will adaptively adjust the computing pool based on the amount of information in the operating status data.

[0033] In one feasible implementation, the perception and analysis module is further configured to: determine the computing power demand based on the operating status information, determine the target computing power pool of the power distribution smart gateway based on the computing power demand, and perform power system operating status analysis and power system operating risk identification at different accuracy levels based on the computing power in the target computing power pool.

[0034] In this implementation, the smart distribution gateway dynamically adjusts the computing power pool configuration based on the amount of information collected regarding the current operational status. The amount of information can be related to the quantity, type, and quality of the data. When the amount of information is large, more computing power is needed for processing and analysis to ensure accuracy and efficiency. Conversely, when the amount of information is small, the computing power configuration can be reduced to save resources. This adaptive adjustment helps the system maintain efficient operation under different conditions. The perception and analysis module is configured to determine the computing power requirement based on the collected operational status information and accordingly determine the target computing power pool for the smart distribution gateway. The target computing power pool refers to the computing power composition required for this analysis. The perception and analysis module assesses the required computing power level based on the system's current workload and data volume. Once the size of the target computing power pool is determined, the smart distribution gateway can be configured accordingly. Based on the computing power size in the target computing power pool, the smart distribution gateway can perform power system operational status analysis and risk identification at different accuracy levels. This means that with sufficient computing power, more refined and accurate analysis can be performed, improving the accuracy and reliability of system diagnosis. When computing power is limited, it may be necessary to adopt simpler or faster analysis methods to ensure timeliness and efficiency.

[0035] For any smart distribution gateway, its idle computing power is limited during operation, while the computing power demand is uncertain. Therefore, it is necessary to dynamically adjust the target computing power pool of the smart distribution gateway according to the computing power demand.

[0036] In one feasible implementation, determining the computing power requirement based on operational status information and adjusting the computing power pool of the power distribution smart gateway according to the computing power requirement includes: Obtain the idle computing power in the computing power pool of the power distribution smart gateway. If the computing power demand is less than or equal to the idle computing power, construct the target computing power pool based on the idle computing power in the computing power pool of the power distribution smart gateway. When the computing power demand exceeds the available computing power, the available computing power in the shared computing power pool is acquired to construct the target computing power pool.

[0037] In this embodiment, the computing power pool of the power distribution smart gateway can consist of two parts: a local computing power pool and a shared computing power pool. The local computing power pool refers to the computing power resources owned by the gateway itself. These resources are typically used for the gateway's operation and basic functions, and can also be used to process operational status information and perform preliminary data analysis. The shared computing power pool consists of additional computing power resources provided by other nearby smart distribution gateways. These resources can be shared with other gateways via network connections to meet the increased computing power demands of the system under certain circumstances. After determining the computing power demand, the smart distribution gateway adjusts its own computing power pool according to different situations: if the computing power demand is less than or equal to the idle computing power in the local computing power pool, the smart distribution gateway will directly utilize local resources to meet the demand without additional operation. If the computing power demand is greater than the idle computing power in the local computing power pool, the gateway needs to obtain additional computing power resources from the shared computing power pool to make up for the deficiency. When there is no idle computing power in the shared computing power pool, the smart distribution gateway will directly utilize local resources to meet the demand. This ensures that the system can maintain efficient operation even when facing heavy loads or complex tasks.

[0038] Through this mechanism, the distribution smart gateway can make full use of local resources and share resources with surrounding gateways to achieve timely monitoring and analysis of the power system's operating status, thereby ensuring the system's stability and security.

[0039] In one feasible implementation, based on the computing power in the target computing power pool, performing power system operation status analysis and power system operation risk identification at different accuracy levels includes: When constructing a target computing pool based on the idle computing power in the computing power pool of the power distribution smart gateway, perform power system operation status analysis and power system operation risk identification operations with the first level of accuracy. When constructing a target computing pool based on the available computing power in the shared computing pool, the second-precision level of power system operation status analysis and power system operation risk identification operations are performed, wherein the second-precision level is higher than the first-precision level.

[0040] In this embodiment, when the smart distribution gateway has sufficient idle computing power in its computing pool, it will perform power system operation status analysis and power system operation risk identification operations at the first level of accuracy. This means performing analysis and identification with lower precision, possibly using simplified algorithms or models to process the data. Although such operations may result in some minor information loss or errors, it is a more practical and economical choice when resources are limited.

[0041] When the smart distribution gateway needs to obtain additional computing resources from the shared computing pool, it performs second-level precision power system operation status analysis and power system operation risk identification. This level of operation is more advanced than the first level because it utilizes more computing resources for more accurate and detailed analysis. It can use more complex algorithms or models, as well as more data processing and computation, thereby improving the accuracy and reliability of the analysis.

[0042] By fully utilizing local and shared computing resources and flexibly adjusting the analysis precision based on available resources, the system balances performance and resource utilization. When resources are plentiful, the system can perform more in-depth analysis, improving accuracy; while when resources are limited, the system can adopt simplified methods to ensure timely task completion.

[0043] In one feasible implementation, performing power system operating status analysis and power system operating risk identification at the second level of accuracy includes: Multiple computing units are constructed based on the target computing power pool. In each computing unit, the first-level precision level of power system operation status analysis and power system operation risk identification operations are performed. The results of multiple first-precision level power system operation status analyses and power system operation risk identification operations are combined to obtain second-precision level power system operation status analyses and power system operation risk identification operations.

[0044] In this implementation, firstly, based on the size of the target computing power pool and system requirements, the distribution smart gateway constructs multiple computing power units. Each computing power unit represents an independent processing unit or task execution unit, used to perform power system operation status analysis and power system operation risk identification operations at the first level of accuracy. Within each computing power unit, the first level of accuracy analysis operations are performed. This may include simplified algorithms or models, as well as preliminary data processing and analysis. Each computing power unit executes its analysis tasks independently, allowing for parallel data processing and improved efficiency. Once each computing power unit completes its analysis task, its results are collected and combined. This can be achieved by aggregating or integrating the results from each unit. The combination process includes weighting, fusing, or comprehensively evaluating the results to obtain the final second level of accuracy analysis results.

[0045] In this way, the smart distribution gateway can utilize multiple computing units to perform analysis tasks of the first level of accuracy in parallel, and then combine their results to obtain higher-precision analysis results. This method can improve the system's ability to accurately assess the operating status and risks of the power system while ensuring resource utilization efficiency.

[0046] In one feasible implementation, input features are constructed based on operational status information, and these features are input into a first identification model to obtain the power system operational risk level and initial analysis results of the power system operational status, including: Based on the operating status information, a first input feature and a second input feature are constructed. The first input feature is used to characterize the operating status of the low-voltage lines of the power system, and the second input feature is used to characterize the load status of the power system. The first input feature and the second input feature are input into the first recognition model to obtain the first recognition result and the second recognition result; Based on the first and second identification results, the initial analysis results of the power system operation status and the corresponding power system operation risk level are determined.

[0047] In this embodiment, based on the operating status information, a first set of input features is first constructed to characterize the operating status of the low-voltage lines of the power system. These features may include relevant parameters such as current, voltage, and frequency of the low-voltage lines. Secondly, a second set of input features is constructed to characterize the load status of the power system. These features may include relevant indicators such as load size, load type, and load change rate. The constructed first and second input features are then input into a first identification model. This model can be a machine learning model, such as a neural network or decision tree, used to analyze and process the input features. The first identification model outputs two results: a first identification result and a second identification result. The first identification result can be a classification or label regarding the operating status of the power system, while the second identification result can be a prediction or indicator regarding the load status of the power system. Based on the first and second identification results, the system can determine the initial analysis results of the power system's operating status. This may involve an assessment of the current state of the system, including aspects such as system stability and performance indicators. Simultaneously, based on the first and second identification results, the system can also determine the operating risk level of the power system. This can be a risk assessment based on the current state of the system, including possible abnormal situations and fault risks.

[0048] The first identification model deployed through the distribution smart gateway performs a relatively accurate analysis of the low-voltage line status and load characteristics of the power system. When the risk level is less than or equal to the threshold, the power system is in a low-risk state, and the distribution smart gateway can determine the corresponding risk management strategy. However, when the risk level is greater than the threshold, if the distribution smart gateway determines the corresponding risk management strategy, the determined strategy may be insufficient or inflexible. When facing complex system problems, more in-depth professional knowledge and experience may be needed to formulate effective response strategies. Therefore, when the risk level is greater than the threshold, the initial analysis results of the power system's operating status and the power system's operating status information need to be uploaded to the cloud processing platform. In this way, the powerful computing power and professional technology of the cloud processing platform can be used for further judgment and processing.

[0049] In one feasible implementation, the cloud processing platform is deployed with a second identification model, and the cloud processing platform is configured as follows: Receive the initial analysis results of the power system operating status and input the initial analysis results of the power system operating status into the second identification model to obtain the power system operating status verification analysis results; The power system operation status review and analysis results and the matching operation processing strategies are sent to the distribution smart gateway.

[0050] In this embodiment, once the initial analysis results are received, the cloud processing platform inputs these data into a second identification model deployed on it. The second identification model can be a more complex and specialized model with higher accuracy and reliability, used for further analysis of the system's operating status and risk level. By running the second identification model, the cloud processing platform can obtain verification analysis results of the power system's operating status. These results can verify and further refine the initial analysis results, providing a more accurate and comprehensive system status assessment. Finally, the cloud processing platform sends the generated power system operating status verification analysis results and matching operation processing strategies back to the distribution smart gateway. The verification analysis results can include corrections or confirmations regarding the system status, as well as corresponding processing strategies for different risk levels.

[0051] By configuring a cloud processing platform to perform the second identification model and verification analysis, its powerful computing resources and expertise can be fully utilized to improve the monitoring and management of the power system and ensure the safe and stable operation of the system.

[0052] In one feasible implementation, the cloud processing platform is also configured to: Acquire historical operating data of the power system and corresponding initial analysis results of historical power system operating status; Based on historical operating data of the power system and the initial analysis results of historical power system operating status, a first identification model is constructed. Knowledge distillation is performed on the second recognition model to obtain the first recognition model. The model accuracy of the second recognition model is higher than that of the first recognition model. The first identification model is deployed to the power distribution smart gateway.

[0053] In this embodiment, by utilizing historical operating data and corresponding analysis results of the power system, a more accurate and reliable second identification model can be constructed. This second identification model can capture changes and trends in the system's operating state, thereby better predicting future system conditions. Through knowledge distillation, a complex and highly accurate second identification model can be transferred to a simpler and easier-to-deploy first identification model. Without sacrificing accuracy, the model's computational complexity and resource requirements are reduced, making it more suitable for deployment and operation in embedded systems such as distribution smart gateways. By deploying a high-quality identification model in distribution smart gateways, real-time monitoring and risk assessment of the power system's operating state can be achieved. This helps to promptly identify potential problems and take corresponding measures to ensure the safe and stable operation of the system.

[0054] In one feasible implementation, the perception analysis module is further configured as follows: The communication module receives the power system operation status review and analysis results and operation processing strategies sent by the cloud processing platform; Based on the comparison between the power system operation status verification analysis results and the power system operation status initial analysis results, the first identification model is dynamically adjusted. The corresponding operation and processing strategies of the execution modules are determined based on the results of the power system operation status review and analysis.

[0055] In this embodiment, based on a comparison between the received power system operation status verification analysis results and the initial power system operation status analysis results, the perception and analysis module can determine whether the first identification model needs dynamic adjustment. This may involve modifying the model's parameters, updating its structure, or retraining it to improve its performance and adaptability. For example, the model's complexity or flexibility can be increased to better capture system changes and characteristics. Simultaneously, the perception and analysis module also executes corresponding operational processing strategies based on the received power system operation status verification analysis results. This means that, based on the actual situation and the latest analysis results, appropriate measures can be taken to manage the operation status, ensuring safety and stability.

[0056] This configuration allows the system to dynamically adjust its behavior based on the latest analysis results and operational strategies to adapt to changes in power demand. This contributes to improved flexibility and responsiveness while ensuring safe and reliable operation in a constantly changing environment.

[0057] The distribution smart gateway provided in this application, equipped with low-voltage line status awareness and load characteristic analysis, reduces the processing pressure on the cloud data center by completing the initial identification and analysis locally on the distribution smart gateway and sending only necessary results to the cloud for processing. This helps reduce data processing and analysis latency and improves the response speed of intelligent control and scheduling. Initial analysis results are only sent to the cloud processing platform when the operational risk level exceeds a threshold, rather than sending all data. This saves bandwidth resources and only consumes cloud resources when needed. When the operational risk level is less than or equal to the threshold, the distribution smart gateway can execute corresponding processing strategies based on the local operational status analysis results, which enhances the system's autonomy and stability and reduces dependence on the cloud. By performing preliminary analysis and processing locally, the system can respond to problems more quickly and take necessary measures to avoid potential faults and damage, thereby improving the reliability and stability of the power system. By deploying the first identification model and local perception and analysis module in the distribution smart gateway, the system's real-time performance and accuracy are effectively improved, and dependence on cloud resources is reduced, thereby improving the intelligence level and reliability of the power system.

[0058] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions according to the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, a computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a charging management device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0059] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more detailed understanding.

[0060] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0061] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0062] 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 in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented 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 to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0063] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, units, and processes described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0064] In the embodiments provided in this application, it should be understood that the disclosed systems, methods, and approaches can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0065] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0066] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0067] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0068] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A power distribution smart gateway with low-voltage line status sensing and load characteristic analysis capabilities, characterized in that, The power distribution smart gateway includes: a data acquisition module, a sensing and analysis module, a communication module, and an execution module; The acquisition module is configured to acquire the operating status information of the power system coupled to the power distribution smart gateway; The perception and analysis module deploys a first recognition model, and the perception and analysis module is configured as follows: Based on the operational status information, input features are constructed, and the input features are input into the first identification model to obtain the power system operational risk identification results and the initial analysis results of the power system operational status. When the operational risk level is less than or equal to the threshold, the operational processing strategy corresponding to the execution module is adjusted based on the initial analysis results of the power system operating status. If the operational risk level is greater than the threshold, the initial analysis results of the power system's operational status are sent to the cloud processing platform via the communication module.

2. The power distribution smart gateway according to claim 1, characterized in that, The perception and analysis module is also configured to: The computing power requirement is determined based on the operating status information, and the target computing power pool of the power distribution smart gateway is determined based on the computing power requirement. Based on the computing power in the target computing power pool, power system operation status analysis and power system operation risk identification are performed at different accuracy levels.

3. The power distribution smart gateway according to claim 2, characterized in that, The step of determining the computing power requirement based on the operating status information and adjusting the computing power pool of the power distribution smart gateway according to the computing power requirement includes: Obtain the idle computing power in the computing power pool of the power distribution smart gateway. If the computing power demand is less than or equal to the idle computing power, construct the target computing power pool based on the idle computing power in the computing power pool of the power distribution smart gateway. If the computing power demand exceeds the available computing power, the available computing power in the shared computing power pool is obtained to construct the target computing power pool.

4. The intelligent power distribution gateway according to claim 2, characterized in that, The shared computing power pool includes the idle computing power in the computing power pools of power distribution smart gateways within the same deployment area.

5. The intelligent power distribution gateway according to claim 3, characterized in that, The step of performing power system operation status analysis and power system operation risk identification at different accuracy levels based on the computing power in the target computing power pool includes: When constructing the target computing pool based on the idle computing power in the computing pool of the power distribution smart gateway, perform power system operation status analysis and power system operation risk identification operations with the first accuracy level; When constructing the target computing pool based on the available computing power in the shared computing pool, a power system operation status analysis and power system operation risk identification operation with a second accuracy level are performed, wherein the second accuracy level is higher than the first accuracy level.

6. The intelligent power distribution gateway according to claim 4, characterized in that, The power system operation status analysis and power system operation risk identification performed at the second accuracy level include: Multiple computing units are constructed based on the target computing power pool, and power system operation status analysis and power system operation risk identification operations of the first accuracy level are performed in each computing power unit; The results of multiple power system operation status analyses and power system operation risk identification operations at the first accuracy level are combined to obtain the results of power system operation status analyses and power system operation risk identification operations at the second accuracy level.

7. The intelligent power distribution gateway according to claim 1, characterized in that, The step of constructing input features based on the operating status information and inputting the input features into the first identification model to obtain the power system operating risk level and the initial analysis results of the power system operating status includes: Based on the operating status information, a first input feature and a second input feature are constructed. The first input feature is used to characterize the operating status of the low-voltage lines of the power system, and the second input feature is used to characterize the load status of the power system. The first input feature and the second input feature are input into the first recognition model to obtain a first recognition result and a second recognition result; Based on the first identification result and the second identification result, the initial analysis result of the power system operation status and the corresponding power system operation risk level are determined.

8. The intelligent power distribution gateway according to claim 1, characterized in that, The cloud processing platform is deployed with a second recognition model, and the cloud processing platform is configured as follows: Receive the initial analysis results of the power system operating status and input the initial analysis results of the power system operating status into the second identification model to obtain the power system operating status review analysis results; The power system operation status review and analysis results and the matching operation processing strategies are sent to the power distribution smart gateway.

9. The intelligent power distribution gateway according to claim 8, characterized in that, The cloud processing platform is also configured to: Acquire historical operating data of the power system and corresponding initial analysis results of historical power system operating status; Based on the historical operating data of the power system and the initial analysis results of the historical power system operating status, a first identification model is constructed. The second recognition model is subjected to knowledge distillation to obtain a first recognition model, wherein the model accuracy of the second recognition model is higher than that of the first recognition model; The first identification model is deployed to the power distribution smart gateway.

10. The intelligent power distribution gateway according to claim 8, characterized in that, The perception and analysis module is also configured to: The communication module receives the power system operation status review and analysis results and the operation processing strategy sent by the cloud processing platform. Based on the comparison between the power system operation status verification analysis results and the power system operation status initial analysis results, the first identification model is dynamically adjusted. The corresponding operation processing strategy of the execution module is determined based on the power system operation status review and analysis results.

Images