A low-voltage direct-current power distribution network edge digital twin instruction pre-rehearsal safety checking method, system, device and medium

Abstract

The present application relates to the technical field of low-voltage direct-current power distribution network dispatching control, and particularly relates to a low-voltage direct-current power distribution network edge digital twin instruction pre-play safety checking method, system, device and medium. A digital twin model is constructed in the edge intelligent gateway based on the physical parameters of the power distribution system, and the physical layer device parameters and the topological structure are continuously synchronized to the digital twin model; in combination with environmental influence factors and historical operation data, dynamic operation constraint boundaries including power supply and demand balance boundaries and bus voltage fluctuation boundaries are generated; when the control instruction is issued by the power distribution automation system, the edge intelligent gateway intercepts the instruction and inputs the digital twin model for simulation pre-play to obtain power supply and demand pre-play values and bus voltage pre-play values; the pre-play state quantities are compared with the dynamic operation constraint boundaries item by item, and if the comparison is correct, the instruction is issued, otherwise the execution is rejected and an alarm is fed back; after the instruction is executed, the actual operation state of the physical device is read and compared with the control target to complete the safety control closed loop.

Description

Technical Field

[0001] This invention relates to the field of low-voltage DC distribution network dispatch and control technology, and in particular to a method, system, equipment and medium for security verification of edge digital twin commands in low-voltage DC distribution networks. Background Technology

[0002] Low-voltage direct current (LVDC) distribution systems are an important form of new power distribution networks. They connect distributed energy resources (DERs) such as photovoltaics and energy storage to various DC loads via DC buses, offering advantages in reducing the number of power conversion stages and improving distribution efficiency. With the continuous increase in the penetration rate of distributed energy resources, LVDC distribution systems are gradually introducing distribution automation systems (DAS) to implement unified scheduling and control of various distributed energy resources and energy storage devices. Control commands are generated by the master station and then sent to the field execution equipment.

[0003] However, the existing low-voltage DC power distribution dispatch and control architecture has the following problems: First, the generation of dispatch commands on the master station side relies on offline tuning parameters or periodic simulation results, which makes it difficult to reflect the actual operating status of the system under scenarios of distributed power output fluctuations and load changes in real time, and there is a deviation between the dispatch assumptions and the actual operating status; Second, after the control commands are issued, they directly drive the physical equipment to act, lacking a local safety verification step before execution. When the system operating status does not match the dispatch expectations, it is very easy to cause safety risks such as DC bus voltage exceeding the limit or local power imbalance. The hidden dangers are particularly prominent under extreme conditions such as islanded operation and sudden increase of high power load; Third, the field communication link is affected by environmental interference, and there is a lack of adaptive adjustment means when the link quality fluctuates. The reliable arrival of key control commands and alarm information cannot be guaranteed, further aggravating the safety risks in the dispatch execution link. Summary of the Invention

[0004] In view of the problems existing in the prior art, the present invention is proposed.

[0005] Therefore, the problem to be solved by this invention is how to address the lack of local real-time security pre-verification on the edge side before the execution of control commands in existing low-voltage DC power distribution systems, which leads to the risk of system instability caused by dispatch commands under extreme operating conditions; at the same time, the existing edge communication architecture lacks the ability to adaptively adjust to changes in link quality, and cannot guarantee the reliable transmission and timing consistency of critical control commands and alarm information in complex communication environments.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide a method for security verification of edge digital twin command pre-simulation in low-voltage DC distribution network, which includes constructing a digital twin model in the edge smart gateway based on the physical parameters of the distribution system, and synchronizing the physical layer device parameters and topology to the digital twin model; Collect power distribution system operation status data, combine environmental impact factors with historical operation data, and generate dynamic operation constraint boundaries; The system receives control commands from the power distribution automation system and sends them to the edge smart gateway. The edge smart gateway intercepts the control commands and inputs them into the digital twin model for simulation and pre-run, thereby obtaining the pre-run state variables. The pre-simulated state variables are compared with the dynamic operation constraint boundaries one by one. If the comparison is successful, the edge smart gateway sends control commands to the physical devices. Otherwise, the commands are rejected and alarm information is fed back to the power distribution automation system. After the control command is executed, the edge smart gateway reads the actual operating status of the physical device and compares it with the control target to complete the security control closed loop.

[0007] As a preferred embodiment of the low-voltage DC distribution network edge digital twin command pre-simulation safety verification method described in this invention, the step of synchronizing physical layer equipment parameters and topology to the digital twin model includes loading the rated parameters and operating constraints of each distributed power source, energy storage device, DC feeder and DC load in the distribution system into the digital twin model to establish a virtual simulation model consistent with the physical system topology. The system monitors the operating status of physical layer devices in real time. When the operating status of physical devices changes, the changed parameters and connection relationships are updated to the digital twin model to maintain the continuous consistency between the digital twin model and the physical system.

[0008] As a preferred embodiment of the low-voltage DC distribution network edge digital twin command pre-simulation safety verification method described in this invention, the step of generating dynamic operation constraint boundaries by combining environmental impact factors and historical operation data includes: using historical operation data and real-time collected operation status data as time-series feature inputs, combining environmental impact factors that affect the output of distributed power sources, and calculating the predicted value of the system's operation capacity in future periods through a safety boundary prediction model. Based on the predicted operating capacity, power supply and demand balance boundary and bus voltage fluctuation boundary are generated respectively, which together constitute the dynamic operating constraint boundary.

[0009] As a preferred embodiment of the low-voltage DC distribution network edge digital twin command pre-simulation safety verification method described in this invention, the step of comparing the pre-simulation state variables with the dynamic operation constraint boundary item by item includes, in the digital twin model, simulating and deducing the power supply and demand changes and DC bus voltage changes after the execution of the control command, respectively, to obtain the power supply and demand pre-simulation values ​​and the bus voltage pre-simulation values. Compare the power supply and demand forecast values ​​with the power supply and demand balance boundary, and compare the bus voltage forecast values ​​with the bus voltage fluctuation boundary; When both the power supply and demand balance boundary and the bus voltage fluctuation boundary pass the comparison, the control command is determined to be executable. If any comparison fails, the control command will be refused and the corresponding alarm information will be fed back to the power distribution automation system.

[0010] As a preferred embodiment of the low-voltage DC distribution network edge digital twin command pre-simulation safety verification method described in this invention, the step of simulating and extrapolating the power supply and demand changes after the execution of the control command includes, in the digital twin model, calculating the maximum power supply that the system can provide based on the current output capacity of each distributed power source and the current available discharge power of the energy storage device. The maximum power supply is compared with the expected load power demand after the control command is executed. When the maximum power supply is lower than the expected load power demand, the power supply and demand balance boundary comparison is deemed to fail, and a power supply and demand imbalance alarm is generated.

[0011] As a preferred embodiment of the low-voltage DC distribution network edge digital twin command pre-simulation safety verification method described in this invention, the step of simulating and extrapolating the DC bus voltage change after the execution of the control command includes, in the digital twin model, calculating the expected DC bus voltage after the execution of the control command based on the current DC bus voltage and the power change after the execution of the control command; Calculate the voltage deviation of the expected DC bus voltage relative to the current DC bus voltage. When the voltage deviation exceeds the bus voltage fluctuation boundary, it is determined that the bus voltage fluctuation boundary comparison fails and a bus voltage over-limit alarm is generated.

[0012] As a preferred embodiment of the low-voltage DC distribution network edge digital twin command pre-simulation security verification method described in this invention, wherein: receiving the control command issued by the distribution automation system to the edge smart gateway includes, after receiving the control command, the edge smart gateway suspends forwarding to physical devices; The control commands are input into the digital twin model to drive the digital twin model to simulate the execution process, and the system power state and bus voltage state after execution are output as pre-execution state variables. The edge intelligent gateway reads the actual operating status of the physical device and compares it with the control target, including actively reading the actual operating status returned by the physical device after the edge intelligent gateway sends a control command to the physical device. Compare the actual operating status with the control objectives corresponding to this control command item by item; If the comparison matches, the result of this control execution is recorded, completing the control loop. If the comparison is inconsistent, an execution error alarm will be generated and reported to the power distribution automation system.

[0013] Secondly, embodiments of the present invention provide a low-voltage DC distribution network edge digital twin command pre-simulation security verification system, which includes a twin mapping module deployed on an edge smart gateway for constructing a digital twin model based on the physical parameters of the distribution system and synchronizing the physical layer device parameters and topology to the digital twin model; The boundary prediction module is used to collect power distribution system operation status data and combine it with environmental impact factors and historical operation data to generate dynamic operation constraint boundaries. The command pre-simulation module is used to receive control commands issued by the power distribution automation system, intercept the control commands, and input the control commands into the digital twin model for simulation pre-simulation to obtain the pre-simulation state variables; The safety verification module is used to compare the pre-simulated state variables with the dynamic operation constraint boundaries item by item. If the comparison is successful, control commands are sent to the physical devices; otherwise, execution is refused and alarm information is fed back to the power distribution automation system. The closed-loop verification module is used to read the actual operating status of the physical device after the control command is executed and compare it with the control target to complete the safety control closed loop.

[0014] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of the low-voltage DC distribution network edge digital twin instruction pre-simulation security verification method as described in the first aspect of the present invention.

[0015] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of the low-voltage DC distribution network edge digital twin instruction pre-simulation security verification method as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By constructing and continuously synchronizing a digital twin model locally on the edge smart gateway, the twin model maintains consistency with the physical system topology and equipment parameters at any time, eliminating the risk of simulation distortion caused by model lag; In terms of generating dynamic operational constraint boundaries, the joint prediction of environmental impact factors and historical operating data is introduced, so that the boundary values ​​on which safety verification is based are dynamically adjusted according to the actual output capacity of the system, avoiding the problem of misjudgment or omission when using fixed setting values ​​under the condition of large fluctuations in the output of distributed power sources; In the command simulation and safety verification stage, the control command completes the dual-dimensional simulation and comparison of power supply and demand balance and bus voltage fluctuation before reaching the physical equipment, and moves the safety interception point to the execution end in advance, so that the risk of voltage exceeding the limit and power imbalance caused by scheduling assumption deviations under extreme conditions such as islanded operation and sudden increase of high power load can be blocked in advance; By comparing the state back and the control target, a complete execution closed loop is formed to ensure that each control action has a verification record of the actual execution result. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a security verification method for edge digital twin commands in low-voltage DC distribution networks; Figure 2 A computer equipment diagram for a security verification method of digital twin command simulation at the edge of a low-voltage DC distribution network; Figure 3 System collaborative interaction architecture diagram of intelligent interactive system for security verification method of digital twin command pre-drill at the edge of low voltage DC distribution network; Figure 4 Flowchart of the digital twin verification module for the security verification method of digital twin command rehearsal at the edge of low-voltage DC distribution network; Figure 5 A schematic diagram illustrating the construction and calling logic of the physical system model library for the security verification method of digital twin command pre-simulation at the edge of low-voltage DC distribution network. Detailed Implementation

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0020] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1 Reference Figure 1 This is the first embodiment of the present invention, which provides a security verification method for edge digital twin command simulation in low-voltage DC distribution networks, including: S100: In the edge smart gateway, a digital twin model is built based on the physical parameters of the power distribution system, and the physical layer device parameters and topology are synchronized to the digital twin model.

[0023] S200: Collects power distribution system operation status data, combines environmental impact factors with historical operation data, and generates dynamic operation constraint boundaries.

[0024] S300: Receives control commands from the power distribution automation system to the edge smart gateway. The edge smart gateway intercepts the control commands and inputs them into the digital twin model for simulation and pre-run, obtaining the pre-run state variables.

[0025] S400: The pre-simulated state variables are compared with the dynamic operation constraint boundaries one by one. If the comparison is successful, the edge smart gateway sends control commands to the physical devices. Otherwise, the commands are rejected and alarm information is fed back to the power distribution automation system.

[0026] S500: After the control command is executed, the edge smart gateway reads the actual operating status of the physical device and compares it with the control target to complete the security control closed loop.

[0027] It should be noted that after low-voltage DC distribution systems are connected to distributed power sources such as photovoltaics and energy storage, the system's operating status continuously changes with output fluctuations and load variations. The dispatching instructions issued by the distribution automation system (DAS) are usually generated based on periodic calculation results, making it difficult to reflect the real-time status of the current bus voltage and power supply and demand. When the system is in islanded operation or under conditions such as a sudden increase in high-power load, if the control instructions are not verified and directly drive the physical equipment, it is very easy to cause the bus voltage to exceed the limit or the power imbalance. Moreover, there is a lag in post-event handling, making it impossible to intervene before the fault occurs.

[0028] Through steps S100-S500, a digital twin model continuously synchronized with the physical system is built locally on the edge smart gateway to achieve real-time mapping of topology and parameters. Combining historical operating data and environmental influencing factors, power supply and demand balance boundaries and bus voltage fluctuation boundaries are dynamically generated. When the distribution automation system issues control commands, the edge smart gateway intercepts the commands and drives the digital twin model to complete a pre-simulation. The pre-simulated state variables are compared with the dynamic constraint boundaries item by item. If they pass, the command is executed; if they fail, the command is rejected and an alarm is reported. After the control is executed, the actual state of the physical equipment is read and compared with the control target to form a complete execution closed loop. This enables edge-side security verification to be completed before the command acts on the physical equipment, preventing unsafe commands from causing system instability.

[0029] Example 2 Reference Figure 1 - Figure 5 This is the second embodiment of the present invention.

[0030] In this embodiment, step S100 involves constructing a digital twin model in the edge smart gateway based on the physical parameters of the power distribution system, and synchronizing the physical layer device parameters and topology to the digital twin model, referring to... Figure 3 The system collaborative interaction architecture diagram shown depicts a system composed of three layers: a physical layer, an edge intelligent gateway layer, and a distribution automation system layer. The physical layer is responsible for the actual operation and status feedback of distributed power sources, energy storage devices, and DC loads. The edge intelligent gateway layer is responsible for the local deployment of the digital twin model, command interception and pre-simulation, and security verification. The distribution automation system layer is responsible for the generation and issuance of scheduling commands. The three layers communicate with each other through a bidirectional interaction channel to complete command transmission, status reporting, and alarm feedback, together forming the complete technical architecture of this invention. This includes the following A1 steps: Reference Figure 5 The diagram shown illustrates the construction and calling logic of the physical system model library. During the initialization phase, the edge smart gateway stores the rated parameters and topology connection relationships of various types of equipment in the power distribution system into the physical system model library according to equipment category. During operation, the digital twin model calls the corresponding equipment parameters from the model library based on the current topology configuration, and triggers the parameter refresh of the corresponding entry in the model library when the physical equipment status changes, thereby realizing the continuous synchronous mapping between the model library and the physical system.

[0031] A1: Synchronize the physical layer device parameters and topology to the digital twin model, including loading the rated parameters and operating constraints of each distributed power source, energy storage device, DC feeder and DC load in the power distribution system into the digital twin model, and establishing a virtual simulation model consistent with the physical system topology; The system monitors the operating status of physical layer devices in real time. When the operating status of physical devices changes, the changed parameters and connection relationships are updated to the digital twin model to maintain the continuous consistency between the digital twin model and the physical system.

[0032] Specifically, the physical structure of a low-voltage direct current distribution system (LVDC) in a park typically consists of five core elements: mains access point, photovoltaic (PV) array, energy storage system (ESS), DC feeder, and DC load.

[0033] During the initialization phase, the edge smart gateway obtains the rated peak power and maximum power point tracking range of the photovoltaic array, the rated capacity and maximum charging and discharging power of the energy storage device, the line impedance value of each DC feeder, the rated power and allowable fluctuation range of each DC load, and the topology node information of each device connected to the DC bus by reading the preset engineering parameter tables of each device.

[0034] Based on the above parameters, a digital twin model is built locally on the edge smart gateway. The digital twin model uses the access nodes of each distributed power source, energy storage device and DC load as the basic computing unit, and the line impedance parameters of each DC feeder as the connection weights between nodes to establish a directed simulation graph that corresponds one-to-one with the physical system topology. Each node in the simulation graph holds a copy of the real-time parameters of the corresponding physical device. When the state of the physical device changes, the parameters of the corresponding node are updated synchronously.

[0035] The overall power balance relationship, as the core constraint equation of the digital twin model, runs through the entire process of subsequent instruction pre-simulation and safety verification, and its expression is as follows: in, Let be the actual output power of the photovoltaic array at time t. Let t be the charging and discharging power of the energy storage device at time t (the discharge direction is defined as positive and the charging direction as negative). Let t be the total power demand of the DC load. Let t be the total line loss of the DC feeder and converter at time t. Preliminary calculations yield: 50 kW + 30 kW - 90 kW - <0. Preliminary results indicate that the system cannot maintain power balance in islanded mode.

[0036] The aforementioned power balance constraint equations are expressed in the form of nodal power injection equations in the digital twin model. Whenever an external stimulus (such as load power changes caused by control commands or distributed power output adjustments) acts on the digital twin model, the power state is solved based on these equations.

[0037] Dynamic synchronization of topology and parameters is continuously performed through the state-aware interface built into the edge smart gateway. The data acquisition unit collects operational status feedback signals from each physical node at a fixed sampling period, including DC bus voltage. The current output power of each distributed power source, the current state of charge (SOC) of the energy storage device, and the current available discharge power.

[0038] When a change in the online status, operating mode, or power parameters of any physical device is detected, the edge smart gateway immediately writes the change to the parameter storage area of ​​the corresponding node in the digital twin model and refreshes the topology connections between nodes, ensuring that the digital twin model remains consistent with the real state of the physical system at all times. This continuous synchronization process is the fundamental guarantee for the accuracy of subsequent security boundary predictions and the reliability of command rehearsals.

[0039] In this embodiment, step S200 involves collecting power distribution system operation status data and combining it with environmental impact factors and historical operation data to generate dynamic operation constraint boundaries, including the following step B1: B1: Combining environmental impact factors and historical operating data, a dynamic operating constraint boundary is generated. This includes using historical operating data and real-time collected operating status data as time-series feature inputs, combining environmental impact factors that affect the output of distributed power sources, and calculating the predicted operating capacity of the system in future periods through a safety boundary prediction model. Based on the predicted operating capacity, power supply and demand balance boundary and bus voltage fluctuation boundary are generated respectively, which together constitute the dynamic operating constraint boundary.

[0040] Specifically, the generation of dynamic operational constraint boundaries relies on a security boundary prediction model deployed on the edge smart gateway. This model takes a time-series feature sequence composed of historical operational data and real-time collected data as input, and environmental impact factors affecting distributed power output as auxiliary input. It then uses a prediction function to predict the operational capacity for future periods. The general expression of the prediction model is as follows: Where B(t+Δt) is the predicted future operational safety boundary, Δt is the prediction time step, W(t) is the current environmental impact factor vector (containing two components: light intensity and ambient temperature), H(t) is the historical operational data sequence aligned with the time window, and f(·) is the prediction model function.

[0041] The safety boundary prediction model adopts a time-series regression architecture based on a long-short-term-memory (LSTM) network, consisting of three parts: an input encoding layer, an LSTM hidden layer group, and a fully connected output layer. The input encoding layer is responsible for standardizing and concatenating the multi-source time-series features. The input vector contains the DC bus voltage at each time step. Photovoltaic output power Energy storage charging and discharging power DC load power The four operational state variables, along with the two environmental influencing factors of light intensity and ambient temperature, together constitute a six-dimensional temporal feature vector.

[0042] The LSTM hidden layer consists of two stacked LSTM units. Each LSTM unit selectively memorizes and transmits long-term dependencies in the input temporal features through the synergistic effect of the forget gate, input gate and output gate, and outputs the hidden state vector.

[0043] The fully connected output layer receives the hidden state vector of the final time step and outputs the predicted operating capacity for future periods through linear mapping. Specifically, it includes two target quantities: the predicted power supply margin and the predicted DC bus voltage.

[0044] The dataset required for model training is generated by dividing historical operation records into sliding time windows. Training samples use time segments of fixed window length as input, with the actual power supply margin and bus voltage values ​​occurring after the end of the corresponding time window as labels. The training process uses mean squared error (MSE) as the loss function, employs an adaptive moment estimation (Adam) optimizer for gradient updates, dynamically adjusts the learning rate using a cosine annealing strategy, and introduces an early stopping strategy to terminate training if the validation set loss does not decrease for several consecutive rounds, preventing overfitting.

[0045] Based on the output of the prediction model, two types of dynamic operating constraint boundaries are generated. The first type is the power supply and demand balance boundary, which uses the sum of the predicted current output capacity of photovoltaic power and the current maximum discharge power of energy storage devices as the upper limit of power supply, and compares it with the real-time load power demand as the lower limit to determine whether power balance can be maintained under the current operating mode. in, The first category represents the maximum discharge power of the energy storage device under its current state of charge (SOC), determined by both the current SOC and the rated maximum discharge power. The second category is the bus voltage fluctuation boundary, achieved by constraining the expected bus voltage deviation. The DC bus voltage fluctuation rate Δ... Udc Defined as: in, This is the current measured DC bus voltage. The expected bus voltage after command execution is derived from the simulation of the digital twin model. The bus voltage fluctuation boundary requirement Δ... U dc satisfy: in, The maximum allowable bus voltage fluctuation ratio is determined by engineering design parameters. The power supply and demand balance boundary and the bus voltage fluctuation boundary together constitute the dynamic operation constraint boundary, which serves as the basis for subsequent command safety verification.

[0046] Power boundary of operating safety boundary: Voltage constraint: Voltage fluctuation constraints: in, This refers to the allowable voltage fluctuation range.

[0047] When the power distribution automation system issues control commands, the edge smart gateway does not execute the commands directly. Instead, it first inputs them into a digital twin model for simulation. During the simulation, the system power balance is checked. If the above conditions are not met, it indicates that the system cannot maintain power supply in islanded mode, and the control command is deemed unexecutable. Next, the bus voltage variation is evaluated: in: This represents the simulated bus voltage. This represents the current bus voltage.

[0048] When satisfied If the voltage is deemed to meet safety constraints, the control command is only allowed to be executed if both the power balance constraint and the voltage constraint are met; otherwise, execution is rejected and an error message is returned.

[0049] In this embodiment, step S300 involves receiving control commands from the power distribution automation system to the edge smart gateway. The edge smart gateway intercepts the control commands and inputs them into the digital twin model for simulation and pre-running to obtain the pre-running state variables. This includes the following C1 steps: C1: Upon receiving a control command from the power distribution automation system to the edge smart gateway, the edge smart gateway suspends forwarding the command to the physical devices. The control commands are input into the digital twin model to drive the digital twin model to simulate the execution process, and the system power state and bus voltage state after execution are output as pre-simulation state variables.

[0050] Specifically, the distribution automation system (DAS) sends scheduling and control commands to the edge smart gateway through the communication link. The command content includes the target device identifier, the control action type (such as load access, load shedding, energy storage charging and discharging switching, etc.) and the corresponding target operating parameter values.

[0051] After the edge smart gateway receives the complete control command message in the communication receiving buffer, it performs integrity and legality verification on the command message. If the verification is successful, the command is parsed into a mapping relationship between the device identifier and the target parameters, stored in the command interception queue, and the forwarding process of the command to the corresponding physical device is suspended.

[0052] Subsequently, the edge smart gateway transforms the parsed control commands into parameter excitation quantities for the digital twin model. Specifically, based on the action type of the control command, it converts the corresponding target parameter change (such as the increase in load power Δ) into the parameter excitation quantities. Or adjust the energy storage output Δ The current parameter value is applied incrementally to the corresponding node in the digital twin model to form the virtual parameter state after the instruction is executed.

[0053] Under this virtual parameter state, the digital twin model solves the node power balance equation and the bus voltage equation simultaneously to deduce the power supply and demand distribution and DC bus voltage response after the command is executed. The digital twin model outputs the power supply and demand state quantity and the DC bus voltage state quantity after execution, which are recorded as the power supply and demand pre-simulation value and the bus voltage pre-simulation value, respectively. The two together constitute the pre-simulation state quantity, which is used for item-by-item comparison in the subsequent safety verification process. The entire pre-simulation calculation process is completed entirely within the local digital twin model of the edge smart gateway without generating any actual operation on the physical equipment. The operating state of the physical system remains unchanged during the pre-simulation period.

[0054] Reference Figure 4The flowchart of the digital twin verification module shown shows that after the edge smart gateway receives the control command issued by the distribution automation system, it first pauses the forwarding to the physical device, and then inputs the control command into the digital twin model to drive the simulation pre-run, and obtains the power supply and demand pre-run value and the bus voltage pre-run value respectively. Then, it compares the above pre-run state variables with the power supply and demand balance boundary and the bus voltage fluctuation boundary in the dynamic operation constraint boundary item by item. If all pass, the command is released to be issued to the physical device. If any fails, the execution is rejected and the corresponding alarm information is fed back to the distribution automation system. The entire verification process is completed locally on the edge side.

[0055] In this embodiment, step S400 compares the pre-simulated state variables with the dynamic operating constraint boundaries item by item. If the comparison is successful, the edge smart gateway sends control commands to the physical devices; otherwise, it refuses to execute and sends alarm information back to the power distribution automation system. This includes the following steps D1-D3: D1: Compare the pre-simulated state variables with the dynamic operation constraint boundaries item by item. In the digital twin model, simulate and deduce the changes in power supply and demand and DC bus voltage after the execution of control commands to obtain the pre-simulated values ​​of power supply and demand and bus voltage. Compare the power supply and demand forecast values ​​with the power supply and demand balance boundary, and compare the bus voltage forecast values ​​with the bus voltage fluctuation boundary; When both the power supply and demand balance boundary and the bus voltage fluctuation boundary pass the comparison, the control command is determined to be executable. If any comparison fails, the control command will be refused and the corresponding alarm information will be fed back to the power distribution automation system.

[0056] D2: Simulate and extrapolate the changes in power supply and demand after the execution of control commands, including calculating the maximum power supply that the system can provide based on the current output capacity of each distributed power source and the current available discharge power of the energy storage device in the digital twin model; The maximum power supply is compared with the expected load power demand after the control command is executed. When the maximum power supply is lower than the expected load power demand, the power supply and demand balance boundary comparison is deemed to fail, and a power supply and demand imbalance alarm is generated.

[0057] D3: Simulate and extrapolate the DC bus voltage change after the control command is executed, including calculating the expected DC bus voltage after the control command is executed based on the current DC bus voltage and the power change after the control command is executed in the digital twin model; Calculate the voltage deviation of the expected DC bus voltage relative to the current DC bus voltage. When the voltage deviation exceeds the bus voltage fluctuation boundary, it is determined that the bus voltage fluctuation boundary comparison fails and a bus voltage over-limit alarm is generated.

[0058] Specifically, the safety verification process is initiated immediately after the digital twin model completes the pre-simulation and outputs the pre-simulation state variables. The pre-simulation state variables are compared with the dynamic operation constraint boundaries item by item. The verification dimensions are divided into two independent dimensions: power supply and demand balance verification (D2) and bus voltage fluctuation verification (D3). Both must pass before the control command can be determined to be executable (D1).

[0059] In terms of power supply and demand balance verification (D2), the edge smart gateway reads the predicted current output capacity of each unit of the photovoltaic power generation array from the current node parameters of the digital twin model, and sums them to obtain the current total available photovoltaic output. Simultaneously, the current state of charge (SOC) value of the energy storage device is read, and combined with the rated maximum discharge power of the energy storage device, the maximum usable discharge power of the energy storage device under the current operating conditions is calculated. .Will and The sum of these two values ​​represents the maximum power supply available under the current operating mode, and the expected DC load power demand following the execution of the control command. The following judgment is made regarding the line loss PLoss(t): If the above power balance inequality does not hold, it indicates that under the current islanded operation mode, the sum of photovoltaic output and available energy storage discharge power is insufficient to cover the load power demand and line losses, and will fall into a power imbalance state. The power supply and demand balance boundary check is determined to be unsuccessful, the edge smart gateway generates a power supply and demand imbalance alarm, refuses to forward control commands to physical devices, and reports the alarm information to the distribution automation system.

[0060] Regarding bus voltage fluctuation verification (D3), the digital twin model is based on the current DC bus voltage. The expected DC bus voltage after the control command is executed is calculated using the node voltage equation based on the node power change ΔP caused by the control command. In the test scenario, if the current bus voltage The voltage is 745V. After the control command is executed, power imbalance causes the bus voltage to drop. This is determined by simulation using a digital twin model. If the voltage is 650V, then the voltage fluctuation rate is calculated as follows: That is, (745 - 650) / 745 ≈ 12.75%. Let Δ U dc With the upper limit of allowable bus voltage fluctuation Compare: like Exceeding If the bus voltage fluctuation boundary check fails, the edge smart gateway will generate a bus voltage over-limit alarm, refuse to execute the control command, and feed back the corresponding alarm information to the distribution automation system to avoid voltage over-limit or system instability in the physical distribution network.

[0061] Only when both the power supply and demand balance check and the bus voltage fluctuation check pass (D1) will the edge smart gateway release the control command from the interception queue and issue the control command to the corresponding physical device. If any check fails, the rejection execution process will be triggered immediately to ensure that the physical device responds to the scheduling command only when all safety constraints are met.

[0062] In this embodiment, after the control command is executed in step S500, the edge smart gateway reads the actual operating status of the physical device and compares it with the control target to complete the security control closed loop, including the following E1 steps: E1: The edge smart gateway reads the actual operating status of the physical device and compares it with the control target. This includes the edge smart gateway actively reading the actual operating status returned by the physical device after sending control commands to the physical device. Compare the actual operating status with the control objectives corresponding to this control command item by item; If the comparison matches, the result of this control execution is recorded, completing the control loop. If the comparison is inconsistent, an execution error alarm will be generated and reported to the power distribution automation system.

[0063] Specifically, after issuing control commands, the edge intelligent gateway proactively sends status query requests to the corresponding physical devices, reading the actual operating status feedback signals returned by the physical devices, including the device's current operating mode confirmation signal, the actual executed power value, and the actual DC bus voltage value collected after execution. The actual operating status is then compared item by item with the control target parameters corresponding to the current control command: if the actual operating status matches the control target, the control execution result is recorded, and the operating status parameters of the corresponding node in the digital twin model are updated synchronously, completing the current safety control closed loop; if the comparison results are inconsistent, the edge intelligent gateway generates an execution anomaly alarm and reports it to the distribution automation system, while simultaneously writing the actual operating deviation into the digital twin model as a correction input for the next round of safety boundary prediction and command rehearsal, ensuring the continuous accuracy of subsequent scheduling control.

[0064] In the event of a communication link interruption, the edge intelligent gateway performs local hierarchical caching of the data to be transmitted according to priority, in the following order: event sequence record data, alarm information, and routine telemetry data. After communication is restored, the data is sequentially retransmitted to the distribution automation system according to the above priority order, while simultaneously controlling the data upload rate to meet the following requirements: in, For upload speed; This represents the threshold of available network bandwidth.

[0065] To avoid communication network congestion caused by sudden surges in data retransmission, and to ensure the accuracy of the retransmission data timing, the edge intelligent gateway uses precise time synchronization to uniformly time-synchronize all system event records, ensuring that the time error of event records at each node meets the following requirements: in, This is due to time synchronization error; To specify the upper limit of error.

[0066] To ensure the consistency of the timing markers in the event sequence records after retransmission, the power distribution automation system can perform complete traceability and accurate analysis of the entire control execution process based on the retransmitted data, thereby achieving the traceability of the control closed loop and the accuracy of system operation status analysis.

[0067] Example 3 Reference Figure 2 This is the third embodiment of the present invention.

[0068] The above is a schematic scheme for a low-voltage DC distribution network edge digital twin command pre-simulation security verification method. It should be noted that the technical solution of this low-voltage DC distribution network edge digital twin command pre-simulation security verification system belongs to the same concept as the technical solution of the aforementioned low-voltage DC distribution network edge digital twin command pre-simulation security verification method. Details not described in detail in this embodiment of the low-voltage DC distribution network edge digital twin command pre-simulation security verification system can be found in the description of the aforementioned low-voltage DC distribution network edge digital twin command pre-simulation security verification method.

[0069] This embodiment also provides a low-voltage DC distribution network edge digital twin command pre-simulation security verification system, including: a twin mapping module, deployed on the edge smart gateway, used to construct a digital twin model based on the physical parameters of the distribution system, and synchronize the physical layer device parameters and topology to the digital twin model; The boundary prediction module is used to collect power distribution system operation status data and combine it with environmental impact factors and historical operation data to generate dynamic operation constraint boundaries. The command pre-simulation module is used to receive control commands issued by the power distribution automation system, intercept the control commands, and input the control commands into the digital twin model for simulation pre-simulation to obtain the pre-simulation state variables; The safety verification module is used to compare the pre-simulated state variables with the dynamic operation constraint boundaries item by item. If the comparison is successful, control commands are sent to the physical devices; otherwise, execution is refused and alarm information is fed back to the power distribution automation system. The closed-loop verification module is used to read the actual operating status of the physical device after the control command is executed and compare it with the control target to complete the safety control closed loop.

[0070] This embodiment also provides an electronic device suitable for security verification of digital twin instructions at the edge of a low-voltage DC distribution network, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the security verification method for digital twin instructions at the edge of a low-voltage DC distribution network as proposed in the above embodiment.

[0071] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the security verification method for implementing edge digital twin instructions of low-voltage DC distribution network as proposed in the above embodiments.

[0072] The storage medium proposed in this embodiment and the method for security verification of digital twin command pre-simulation at the edge of low-voltage DC distribution network proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0073] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0074] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for security verification of digital twin command pre-simulation at the edge of a low-voltage DC distribution network, characterized in that: This includes building a digital twin model in the edge smart gateway based on the physical parameters of the power distribution system, and synchronizing the physical layer device parameters and topology to the digital twin model; Collect power distribution system operation status data, combine environmental impact factors with historical operation data, and generate dynamic operation constraint boundaries; The system receives control commands from the power distribution automation system and sends them to the edge smart gateway. The edge smart gateway intercepts the control commands and inputs them into the digital twin model for simulation and pre-run, thereby obtaining the pre-run state variables. The pre-simulated state variables are compared with the dynamic operation constraint boundaries one by one. If the comparison is successful, the edge smart gateway sends control commands to the physical devices; otherwise, it refuses to execute and sends alarm information back to the power distribution automation system. After the control command is executed, the edge smart gateway reads the actual operating status of the physical device and compares it with the control target to complete the security control closed loop.

2. The low-voltage DC distribution network edge digital twin command pre-simulation security verification method as described in claim 1, characterized in that: The step of synchronizing physical layer device parameters and topology to the digital twin model includes loading the rated parameters and operating constraints of each distributed power source, energy storage device, DC feeder and DC load in the power distribution system into the digital twin model to establish a virtual simulation model consistent with the physical system topology. The system monitors the operating status of physical layer devices in real time. When the operating status of physical devices changes, the changed parameters and connection relationships are updated to the digital twin model to maintain the continuous consistency between the digital twin model and the physical system.

3. The low-voltage DC distribution network edge digital twin command pre-simulation security verification method as described in claim 2, characterized in that: The process of generating dynamic operational constraint boundaries by combining environmental impact factors and historical operational data includes using historical operational data and real-time collected operational status data as time-series feature inputs, combining environmental impact factors that affect the output of distributed power sources, and calculating the predicted value of the system's operational capacity in future periods through a safety boundary prediction model. Based on the predicted operating capacity, power supply and demand balance boundary and bus voltage fluctuation boundary are generated respectively, which together constitute the dynamic operating constraint boundary.

4. The low-voltage DC distribution network edge digital twin command pre-simulation security verification method as described in claim 3, characterized in that: The step of comparing the pre-simulated state variables with the dynamic operation constraint boundary item by item includes, in the digital twin model, simulating and extrapolating the changes in power supply and demand and the changes in DC bus voltage after the execution of control commands, to obtain the pre-simulated values ​​of power supply and demand and the pre-simulated values ​​of bus voltage. Compare the power supply and demand forecast values ​​with the power supply and demand balance boundary, and compare the bus voltage forecast values ​​with the bus voltage fluctuation boundary; When both the power supply and demand balance boundary and the bus voltage fluctuation boundary pass the comparison, the control command is determined to be executable. If any comparison fails, the control command will be refused and the corresponding alarm information will be fed back to the power distribution automation system.

5. The low-voltage DC distribution network edge digital twin command pre-simulation security verification method as described in claim 4, characterized in that: The simulation and deduction of power supply and demand changes after the execution of control commands includes, in the digital twin model, calculating the maximum power supply that the system can provide based on the current output capacity of each distributed power source and the current available discharge power of the energy storage device. The maximum power supply is compared with the expected load power demand after the control command is executed. When the maximum power supply is lower than the expected load power demand, the power supply and demand balance boundary comparison is deemed to fail, and a power supply and demand imbalance alarm is generated.

6. The low-voltage DC distribution network edge digital twin command pre-simulation security verification method as described in claim 5, characterized in that: The simulation and deduction of the DC bus voltage change after the execution of the control command includes, in the digital twin model, calculating the expected DC bus voltage after the execution of the control command based on the current DC bus voltage and the power change after the execution of the control command; Calculate the voltage deviation of the expected DC bus voltage relative to the current DC bus voltage. When the voltage deviation exceeds the bus voltage fluctuation boundary, it is determined that the bus voltage fluctuation boundary comparison fails and a bus voltage over-limit alarm is generated.

7. The low-voltage DC distribution network edge digital twin command pre-simulation security verification method as described in claim 6, characterized in that: The receipt of a control command from the power distribution automation system to the edge smart gateway includes the edge smart gateway pausing forwarding to physical devices after receiving the control command; The control commands are input into the digital twin model to drive the digital twin model to simulate the execution process, and the system power state and bus voltage state after execution are output as pre-execution state variables. The edge intelligent gateway reads the actual operating status of the physical device and compares it with the control target, including actively reading the actual operating status returned by the physical device after the edge intelligent gateway sends a control command to the physical device. Compare the actual operating status with the control objectives corresponding to this control command item by item; If the comparison matches, the result of this control execution is recorded, completing the control loop. If the comparison is inconsistent, an execution error alarm will be generated and reported to the power distribution automation system.

8. A low-voltage DC distribution network edge digital twin command pre-simulation security verification system, based on the low-voltage DC distribution network edge digital twin command pre-simulation security verification method according to any one of claims 1 to 7, characterized in that: It also includes a twin mapping module, deployed on the edge smart gateway, used to build a digital twin model based on the physical parameters of the power distribution system, and to synchronize the physical layer device parameters and topology to the digital twin model; The boundary prediction module is used to collect power distribution system operation status data and combine it with environmental impact factors and historical operation data to generate dynamic operation constraint boundaries. The command pre-simulation module is used to receive control commands issued by the power distribution automation system, intercept the control commands, and input the control commands into the digital twin model for simulation pre-simulation to obtain the pre-simulation state variables; The safety verification module is used to compare the pre-simulated state variables with the dynamic operation constraint boundaries one by one. If the comparison is successful, control commands are sent to the physical devices; otherwise, execution is refused and alarm information is fed back to the power distribution automation system. The closed-loop verification module is used to read the actual operating status of the physical device after the control command is executed and compare it with the control target to complete the safety control closed loop.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the low-voltage DC distribution network edge digital twin instruction pre-simulation security verification method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the low-voltage DC distribution network edge digital twin instruction pre-simulation security verification method according to any one of claims 1 to 7.

Images