Purification lamp power supply network intelligent scheduling system based on digital twinning

Abstract

The application discloses a purification lamp power supply network intelligent scheduling system based on digital twinning, relates to the technical field of power supply network intelligent scheduling, and comprises a data acquisition unit, a health assessment unit, a twinning construction unit, a scheduling optimization unit and an execution unit, wherein the data acquisition unit is used for collecting health original parameters of each purification lamp and electrical operation parameters of the power supply network in real time; the health assessment unit is used for acquiring the health original parameters of each purification lamp and calculating health indexes of each purification lamp according to the health original parameters; the twinning construction unit is used for acquiring the electrical operation parameters of the power supply network, constructing an electrical digital twin body based on the electrical operation parameters, acquiring the health indexes of each purification lamp, constructing a health digital twin body based on the health indexes, and fusing the electrical digital twin body and the health digital twin body; the purification lamp health state can be brought into a scheduling decision system, the life balance of equipment groups is realized while the power supply reliability is ensured.

Description

Technical Field

[0001] This invention relates to the field of intelligent power supply network scheduling technology, specifically to an intelligent scheduling system for power supply networks of cleanroom lights based on digital twins. Background Technology

[0002] With the rapid development of IoT, digital twin, and AI technologies, intelligent dispatching systems for power supply networks have been increasingly widely used in fields such as industrial lighting and cleanroom environmental control. In the scenario of cleanroom lighting power supply networks, existing advanced dispatching systems typically rely on intelligent sensing devices deployed on power lines and terminal lighting fixtures to collect electrical operating parameters such as voltage, current, power, and power factor in real time. A virtual mirror model corresponding to the physical power supply network is then constructed in the digital twin platform. Subsequently, through power flow calculation, load forecasting, and optimization algorithms, a dispatching strategy aimed at power supply reliability, power quality, and operational economy is generated to achieve closed-loop monitoring and control of the power supply network.

[0003] However, the existing systems mentioned above suffer from a fundamental cognitive limitation in their technical architecture. The information dimension of their digital twin models is strictly confined to the scope of electrical parameters, abstracting all terminal loads into power nodes with only electrical attributes. Under this architecture, the scheduling system can accurately perceive voltage fluctuations, current changes, and power distribution in the power supply network, but it completely lacks the ability to perceive the physical health status of the core load it serves—the air purification lamp itself. This is because the air purification lamp is not an ordinary lighting load; its integrated ultraviolet sterilization module has a clear performance degradation characteristic. The radiation intensity of the lamp beads continuously decreases with the increase of cumulative operating time, and the operating temperature history and switching frequency of the drive power supply are also affected. Factors also profoundly affect the remaining lifespan of equipment. Because this health status information has never been incorporated into the information model of the digital twin, the scheduling system cannot distinguish which cleanroom lamps are in a healthy and active period and which are nearing the end of their lifespan when formulating load allocation strategies. It can only perform single-target power allocation under the constraints of electrical boundary conditions, which leads to the scheduling optimization target being limited to instantaneous power supply indicators, ignoring the lifespan balance between individual cleanroom lamps under long-term operating conditions. This accelerates the unbalanced degradation of the equipment group, drags the operation and maintenance mode into the predicament of passive emergency repair, increases the overall replacement frequency and operation and maintenance costs, and restricts the leap of power network scheduling from local instantaneous optimization to global optimization throughout the entire life cycle.

[0004] Therefore, in view of this, the present invention proposes an intelligent scheduling system for the power supply network of purification lamps based on digital twins to make up for and improve the shortcomings of the existing technology. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides an intelligent scheduling system for the power supply network of purification lamps based on digital twins, thereby resolving the corresponding technical issues raised in the background section.

[0006] To achieve the above objectives, the technical solution adopted by this invention is: an intelligent scheduling system for the power supply network of purification lamps based on digital twins, comprising a data acquisition unit, a health assessment unit, a twin construction unit, a scheduling optimization unit, and an execution unit, wherein:

[0007] The data acquisition unit is used to collect the original health parameters of each purification lamp and the electrical operation parameters of the power supply network in real time, and send the original health parameters to the health assessment unit, and the electrical operation parameters to the twin construction unit and the scheduling optimization unit.

[0008] The health assessment unit is used to obtain the raw health parameters of each purification lamp, calculate the health index of each purification lamp based on the raw health parameters, and send it to the twin construction unit and the scheduling optimization unit.

[0009] The twin construction unit is used to obtain the electrical operating parameters of the power supply network, construct an electrical digital twin based on the electrical operating parameters, obtain the health index of each purification lamp, construct a health digital twin based on the health index, and merge the electrical digital twin and the health digital twin to generate a dual-domain digital twin, which is then sent to the scheduling optimization unit.

[0010] The scheduling optimization unit is used to obtain a dual-domain digital twin, and construct a multi-objective optimization function with electrical operating parameters as constraints and the health index of each purification lamp as dynamic scheduling constraints. The function aims to maximize power supply reliability and minimize the variance of the health index distribution of each purification lamp. The multi-objective optimization is then performed in the dual-domain digital twin to obtain the optimal scheduling scheme, which is then sent to the execution unit.

[0011] The execution unit is used to obtain the optimal scheduling scheme and simulate the optimal scheduling scheme in a dual-domain digital twin to verify whether the power flow distribution of the power supply network meets the safety boundary conditions after the scheme is executed. If the verification is successful, the optimal scheduling scheme is converted into a control command and issued for execution. If the verification fails, the unit returns to the scheduling optimization unit to regenerate the optimal scheduling scheme until the verification is successful or the preset number of iterations is reached.

[0012] Preferably, the original health parameters include cumulative running time, ultraviolet module radiation intensity attenuation rate, drive power supply operating temperature and switching frequency, and the electrical operating parameters include voltage, current, power and power factor.

[0013] As a preferred method, the specific process for calculating the health index of each purification lamp based on the original health parameters is as follows:

[0014] S101. Obtain the original health parameters of a single purification lamp, and take the ratio of the cumulative running time to the design rated life of the purification lamp as the first sub-indicator, the attenuation rate of the ultraviolet module radiation intensity as the second sub-indicator, the ratio of the operating temperature of the driving power supply to the safe operating temperature threshold of the driving power supply of the purification lamp as the third sub-indicator, and the ratio of the switching frequency to the design threshold of the switching frequency of the purification lamp as the fourth sub-indicator.

[0015] S102. Multiply the first sub-index, the second sub-index, the third sub-index and the fourth sub-index by their respective preset weight coefficients and then sum them to obtain the health index of the purification lamp, wherein each weight coefficient is a positive number and the sum is 1.

[0016] S103. Traverse all purification lamp nodes in the power supply network and repeat steps S101 to S102 to obtain the health index set of each purification lamp.

[0017] As a preferred approach, the specific process for constructing an electrical digital twin based on electrical operating parameters is as follows:

[0018] S201. Obtain the topology of the power supply network and the electrical operating parameters of each acquisition node. The topology includes the connection between each bus, feeder, transformer and cleanroom lamp terminal.

[0019] S202. Based on the topological connection relationship and the preset impedance parameters of each line, establish a node admittance matrix to describe the electrical coupling relationship between each node of the power supply network.

[0020] S203. The topology connection relationship, node admittance matrix and electrical operating parameters of each node are encapsulated into an electrical digital twin. The electrical digital twin is used to respond to the input of scheduling instructions and simulate the voltage distribution and power distribution of the power supply network under different scheduling schemes through power flow calculation.

[0021] As a preferred approach, the specific process for constructing a health digital twin based on a health index is as follows:

[0022] S301. Obtain the health index set of each air purifier lamp;

[0023] S302. Using the unique identifier of each purification lamp in the power supply network topology as an index, associate the health index of each purification lamp with the node position corresponding to that purification lamp in the topology.

[0024] S303. The health index of all purification lamp nodes in the power supply network topology and their mapping relationship with each node are encapsulated together into a health digital twin, wherein the health digital twin shares the same topology as the electrical digital twin.

[0025] As a preferred method, the specific process for generating a two-domain digital twin is as follows:

[0026] S401. Using the unique identifier of each node in the power supply network topology as the association index, establish a one-to-one correspondence between nodes in the electrical digital twin and the health digital twin.

[0027] S402. Use the health index of each purification lamp node in the health digital twin as a health status label and map it to the attribute field of the corresponding node in the electrical digital twin.

[0028] After mapping, each purification lamp node in the electrical digital twin simultaneously has an electrical attribute label and a health status label, forming a dual-domain digital twin.

[0029] As a preferred option, the specific process for constructing a multi-objective optimization function with the joint optimization objectives of maximizing power supply reliability and minimizing the variance of the health index distribution of each purification lamp is as follows:

[0030] S501. The power distribution of each purification lamp is used as a decision variable. The power distribution of each purification lamp must be adjustable within the range of zero to its rated power limit.

[0031] S502. Using electrical operating parameters as constraints, set power balance constraints, node voltage constraints, and line capacity constraints. Among them, the power balance constraint requires that the sum of the power allocated to all purification lamps and the sum of the line losses equal the total power input to the power supply network. The node voltage constraint requires that the voltage amplitude of each node does not exceed the allowable upper and lower voltage limits. The line capacity constraint requires that the transmission power of each line does not exceed its maximum allowable transmission capacity.

[0032] S503. With the goal of minimizing the total active power loss of all lines in the power supply network, construct a first objective function to characterize the reliability of the power supply.

[0033] S504. With the goal of minimizing the dispersion of the health index of each purification lamp relative to its average value, a second objective function is constructed to characterize the degree of balance of health status among individual purification lamps.

[0034] S505. Multiply the first objective function and the second objective function by their respective preset weight coefficients and then sum them to form a joint optimization objective function.

[0035] As a preferred option, the specific process for obtaining the optimal scheduling scheme is as follows:

[0036] S601. Set dynamic scheduling constraints:

[0037] For purification lamps whose health index is lower than the preset health threshold, their allocated power is limited to a first preset proportion of their rated power during the scheduling cycle.

[0038] For purification lamps with a health index higher than or equal to a preset health threshold, their power allocation is allowed to reach a second preset ratio of their rated power, and the second preset ratio is greater than the first preset ratio.

[0039] S602. In the dual-domain digital twin, a multi-objective optimization algorithm is adopted to iteratively optimize the joint optimization objective function under the constraints of power balance, node voltage, line capacity and dynamic scheduling.

[0040] S603. When the preset iteration termination condition is reached, the optimal solution is selected from the solution set output by the multi-objective optimization algorithm as the optimal scheduling scheme, wherein the optimal scheduling scheme includes the power allocation value of each purification lamp.

[0041] As a preferred option, the specific process of simulating and rehearsing the optimal scheduling scheme in a dual-domain digital twin is as follows:

[0042] S701. The power allocation values ​​of each purification lamp in the optimal scheduling scheme are used as input conditions and loaded into the electrical digital twin layer of the dual-domain digital twin. Power flow calculation is performed with the loaded power allocation values ​​of each purification lamp as boundary conditions to obtain the voltage amplitude of each node and the transmission power of each line in the power supply network under the scheduling scheme.

[0043] S702. Verify the safety boundary conditions of the power flow calculation results:

[0044] Check that the voltage of all nodes is within the allowable upper and lower limits, check that the transmission power of all lines does not exceed their maximum allowable transmission capacity, and check that the health index of each purification lamp node is lower than the preset safe operation threshold.

[0045] If all three checks above pass, the optimal scheduling scheme is determined to meet the safety boundary conditions, and the optimal scheduling scheme is converted into a control command and sent to the execution mechanism of the physical power supply network for execution.

[0046] If any check fails, the check is deemed unsuccessful, and the result is fed back to the scheduling optimization unit.

[0047] Compared with existing technologies, the beneficial effects of this invention are as follows: By incorporating the health status information of the cleanroom lamps as an independent dimension into the digital twin model, the scheduling system simultaneously possesses the dual capabilities of sensing the electrical status of the power grid and the health status of terminal equipment. This fundamentally compensates for the information blind spots in existing systems that rely solely on electrical parameters for scheduling. Furthermore, by embedding the health index of each cleanroom lamp as a dynamic scheduling constraint into the multi-objective optimization model, the scheduling strategy proactively balances the aging process of each individual cleanroom lamp while ensuring power supply reliability. This avoids the problem of collective aging mismatch, where lamps with superior power supply conditions are overloaded for extended periods while end-point lamps have idle capacity. This achieves a leap in scheduling optimization from instantaneous optimal operating conditions to global optimality throughout the entire lifecycle. Simultaneously, through simulation pre-running and closed-loop feedback mechanisms, it effectively prevents unsafe scheduling commands from being directly issued and executed, improving the system's adaptability and robustness. Consequently, it not only significantly reduces operation and maintenance costs and the risk of unplanned downtime but also provides a reliable technical path for the intelligent evolution of power network scheduling from passive operation and maintenance to proactive prevention. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of the overall structure of a preferred embodiment of the present invention;

[0049] Figure 2 This is a system flowchart of the present invention. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Embodiments of the present invention:

[0052] Please refer to Figures 1 to 2 As shown, the intelligent scheduling system for the power supply network of air purifier lights based on digital twins includes a data acquisition unit, a health assessment unit, a twin construction unit, a scheduling optimization unit, and an execution unit, wherein:

[0053] The data acquisition unit is used to collect the original health parameters of each purification lamp and the electrical operation parameters of the power supply network in real time, and send the original health parameters to the health assessment unit, and the electrical operation parameters to the twin construction unit and the scheduling optimization unit.

[0054] The health assessment unit is used to obtain the raw health parameters of each purification lamp, calculate the health index of each purification lamp based on the raw health parameters, and send it to the twin construction unit and the scheduling optimization unit.

[0055] The twin construction unit is used to obtain the electrical operating parameters of the power supply network, construct an electrical digital twin based on the electrical operating parameters, obtain the health index of each purification lamp, construct a health digital twin based on the health index, and merge the electrical digital twin and the health digital twin to generate a dual-domain digital twin, which is then sent to the scheduling optimization unit.

[0056] The scheduling optimization unit is used to obtain a dual-domain digital twin, and construct a multi-objective optimization function with electrical operating parameters as constraints and the health index of each purification lamp as dynamic scheduling constraints. The function aims to maximize power supply reliability and minimize the variance of the health index distribution of each purification lamp. The multi-objective optimization is then performed in the dual-domain digital twin to obtain the optimal scheduling scheme, which is then sent to the execution unit.

[0057] The execution unit is used to obtain the optimal scheduling scheme and simulate the optimal scheduling scheme in a dual-domain digital twin to verify whether the power flow distribution of the power supply network meets the safety boundary conditions after the scheme is executed. If the verification is successful, the optimal scheduling scheme is converted into a control command and issued for execution. If the verification fails, the unit returns to the scheduling optimization unit to regenerate the optimal scheduling scheme until the verification is successful or the preset number of iterations is reached.

[0058] The health parameters include cumulative running time, UV module radiation intensity attenuation rate, drive power supply operating temperature and switching frequency, and electrical operating parameters include voltage, current, power and power factor.

[0059] The specific process for calculating the health index of each purification lamp based on the original health parameters is as follows:

[0060] S101. Obtain the original health parameters of a single purification lamp, and take the ratio of the cumulative running time to the design rated life of the purification lamp as the first sub-indicator, the attenuation rate of the ultraviolet module radiation intensity as the second sub-indicator, the ratio of the operating temperature of the driving power supply to the safe operating temperature threshold of the driving power supply of the purification lamp as the third sub-indicator, and the ratio of the switching frequency to the design threshold of the switching frequency of the purification lamp as the fourth sub-indicator.

[0061] S102. Multiply the first sub-index, the second sub-index, the third sub-index and the fourth sub-index by their respective preset weight coefficients and then sum them to obtain the health index of the purification lamp, wherein each weight coefficient is a positive number and the sum is 1.

[0062] S103. Traverse all purification lamp nodes in the power supply network, repeating steps S101 to S102 to obtain the health index set of each purification lamp. .

[0063] The specific process of constructing an electrical digital twin based on electrical operating parameters is as follows:

[0064] S201. Obtain the topology of the power supply network and the electrical operating parameters of each acquisition node. The topology includes the connection between each bus, feeder, transformer and cleanroom lamp terminal.

[0065] S202. Based on the topology and preset line impedance parameters, establish a node admittance matrix to describe the electrical coupling relationship between nodes in the power supply network. ;

[0066] Diagonal elements of the nodal admittance matrix The sum of the admittances of all branches connected to node i, and the off-diagonal elements. It is the negative value of the branch admittance connecting node i and node j;

[0067] S203. The topology connection relationship, node admittance matrix and electrical operating parameters of each node are encapsulated into an electrical digital twin. The electrical digital twin is used to respond to the input of dispatching instructions and simulate the voltage distribution and power distribution of the power supply network under different dispatching schemes through power flow calculation.

[0068] Power flow calculations are performed by solving the nodal voltage equations. The solution is obtained by solving the problem using Newton's iteration method, where I is the node injected current vector and U is the node voltage vector.

[0069] The specific process of constructing a health digital twin based on health indices is as follows:

[0070] S301. Obtain the health index set of each air purifier lamp;

[0071] S302. Using the unique identifier of each purification lamp in the power supply network topology as an index, associate the health index of each purification lamp with the node position corresponding to that purification lamp in the topology.

[0072] S303. The health index of all purification lamp nodes in the power supply network topology and their mapping relationship with each node are encapsulated together into a health digital twin, wherein the health digital twin and the electrical digital twin share the same topology.

[0073] The specific process for generating a two-domain digital twin is as follows:

[0074] S401. Using the unique identifier of each node in the power supply network topology as the association index, establish a one-to-one correspondence between nodes in the electrical digital twin and the health digital twin.

[0075] S402. Use the health index of each purification lamp node in the health digital twin as a health status label and map it to the attribute field of the corresponding node in the electrical digital twin.

[0076] After mapping, each purification lamp node in the electrical digital twin has both electrical attribute tags and health status tags, forming a dual-domain digital twin.

[0077] The specific process for constructing a multi-objective optimization function with the joint optimization objectives of maximizing power supply reliability and minimizing the variance of the health index distribution of each purification lamp is as follows:

[0078] S501, Use the power distribution of each purification lamp as a decision variable. The power of each purification lamp must be adjustable within the range of zero to its rated power limit. ,in This represents the upper limit of the rated power of the i-th purification lamp;

[0079] S502. Using electrical operating parameters as constraints, set power balance constraints, node voltage constraints, and line capacity constraints. Among them, the power balance constraint requires that the sum of the power allocated to all cleanroom lamps and the sum of line losses equal the total input power of the power supply network. The node voltage constraint requires that the voltage amplitude of each node does not exceed the allowable upper and lower voltage limits. Line capacity constraints require that the transmission power of each line does not exceed its maximum allowable transmission capacity;

[0080] S503. Construct a first objective function to characterize power supply reliability, with the goal of minimizing the total active power loss of all lines in the power supply network. Where m is the total number of lines in the power supply network. Let K be the effective value of the current on the k-th line. Let be the resistance value of the k-th line;

[0081] S504. With the goal of minimizing the dispersion of the health index of each purifying lamp relative to its average value, a second objective function is constructed to characterize the degree of balance in health status among individual purifying lamps. Where n is the total number of purification lamps, This represents the average health index of all air purifiers.

[0082] The smaller the value, the more balanced the health status among the various purifying lamps;

[0083] S505. Multiply the first objective function and the second objective function by their respective preset weight coefficients and then sum them to form a joint optimization objective function. ,in and For the preset weighting coefficients, and .

[0084] The specific process of obtaining the optimal scheduling scheme is as follows:

[0085] S601. Set dynamic scheduling constraints:

[0086] For purification lamps whose health index is lower than the preset health threshold, their allocated power is limited to a first preset proportion of their rated power during the scheduling cycle.

[0087] For purification lamps with a health index higher than or equal to a preset health threshold, their power allocation is allowed to reach a second preset ratio of their rated power, and the second preset ratio is greater than the first preset ratio.

[0088] S602. In the dual-domain digital twin, a multi-objective optimization algorithm is adopted to iteratively optimize the joint optimization objective function under the constraints of power balance, node voltage, line capacity and dynamic scheduling.

[0089] S603. When the preset iteration termination condition is reached, the optimal solution is selected from the solution set output by the multi-objective optimization algorithm as the optimal scheduling scheme. The optimal scheduling scheme includes the power allocation value of each purification lamp.

[0090] The specific process of simulating and rehearsing the optimal scheduling scheme in a two-domain digital twin is as follows:

[0091] S701. The power allocation values ​​of each purification lamp in the optimal scheduling scheme are used as input conditions and loaded into the electrical digital twin layer of the dual-domain digital twin. Power flow calculation is performed with the loaded power allocation values ​​of each purification lamp as boundary conditions to obtain the voltage amplitude of each node and the transmission power of each line in the power supply network under the scheduling scheme.

[0092] S702. Verify the safety boundary conditions of the power flow calculation results:

[0093] Check that the voltage of all nodes is within the allowable upper and lower limits, check that the transmission power of all lines does not exceed their maximum allowable transmission capacity, and check that the health index of each purification lamp node is lower than the preset safe operation threshold.

[0094] If all three checks above pass, the optimal scheduling scheme is determined to meet the safety boundary conditions, and the optimal scheduling scheme is converted into a control command and sent to the execution mechanism of the physical power supply network for execution.

[0095] If any check fails, the check is deemed unsuccessful, and the result is fed back to the scheduling optimization unit.

[0096] By incorporating the health status information of the cleanroom lamps as an independent dimension into the digital twin model, the dispatching system possesses the dual capability of sensing both the electrical state of the power grid and the health status of terminal equipment. This fundamentally compensates for the information blind spots in existing systems that rely solely on electrical parameters for dispatching. Furthermore, by embedding the health index of each cleanroom lamp as a dynamic dispatching constraint into the multi-objective optimization model, the dispatching strategy proactively balances the aging process of each individual cleanroom lamp while ensuring power supply reliability. This avoids the collective aging mismatch problem of lamps with superior power supply conditions being overloaded for extended periods and end-point lamps having idle capacity. It achieves a leap in dispatching optimization from instantaneous operating condition optimization to global optimization throughout the entire lifecycle. Simultaneously, through simulation pre-running and closed-loop feedback mechanisms, it effectively prevents unsafe dispatching commands from being directly issued and executed, improving the system's adaptability and robustness. Consequently, it not only significantly reduces operation and maintenance costs and the risk of unplanned downtime but also provides a reliable technical path for the intelligent evolution of power network dispatching from passive operation and maintenance to proactive prevention.

[0097] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value.

[0098] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0099] In the two embodiments provided in this application, it should be understood that the disclosed apparatus and system can be implemented in other ways; for example, the apparatus embodiments described above are merely illustrative, and the division of modules is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed; furthermore, the coupling or direct coupling or communication connection between the shown or discussed mutuals can be through some interfaces, and the indirect coupling or communication connection between the apparatus or modules can be electrical, mechanical or other forms.

[0100] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A smart scheduling system for the power supply network of air purifier lamps based on digital twins, characterized in that, It includes a data acquisition unit, a health assessment unit, a twin construction unit, a scheduling optimization unit, and an execution unit, among which: The data acquisition unit is used to collect the original health parameters of each purification lamp and the electrical operation parameters of the power supply network in real time, and send the original health parameters to the health assessment unit, and the electrical operation parameters to the twin construction unit and the scheduling optimization unit. The health assessment unit is used to obtain the raw health parameters of each purification lamp, calculate the health index of each purification lamp based on the raw health parameters, and send it to the twin construction unit and the scheduling optimization unit. The twin construction unit is used to obtain the electrical operating parameters of the power supply network, construct an electrical digital twin based on the electrical operating parameters, obtain the health index of each purification lamp, construct a health digital twin based on the health index, and merge the electrical digital twin and the health digital twin to generate a dual-domain digital twin, which is then sent to the scheduling optimization unit. The scheduling optimization unit is used to obtain a dual-domain digital twin, and construct a multi-objective optimization function with electrical operating parameters as constraints and the health index of each purification lamp as dynamic scheduling constraints. The function aims to maximize power supply reliability and minimize the variance of the health index distribution of each purification lamp. The multi-objective optimization is then performed in the dual-domain digital twin to obtain the optimal scheduling scheme, which is then sent to the execution unit. The execution unit is used to obtain the optimal scheduling scheme and simulate the optimal scheduling scheme in a dual-domain digital twin to verify whether the power flow distribution of the power supply network meets the safety boundary conditions after the scheme is executed. If the verification is successful, the optimal scheduling scheme is converted into a control command and issued for execution. If the verification fails, the unit returns to the scheduling optimization unit to regenerate the optimal scheduling scheme until the verification is successful or the preset number of iterations is reached.

2. The intelligent scheduling system for the power supply network of purification lamps based on digital twins according to claim 1, characterized in that, The original health parameters include cumulative running time, UV module radiation intensity attenuation rate, drive power supply operating temperature and switching frequency, and the electrical operating parameters include voltage, current, power and power factor.

3. The intelligent scheduling system for the power supply network of purification lamps based on digital twins according to claim 1, characterized in that, The specific process for calculating the health index of each purification lamp based on the original health parameters is as follows: S101. Obtain the original health parameters of a single purification lamp, and take the ratio of the cumulative running time to the design rated life of the purification lamp as the first sub-indicator, the attenuation rate of the ultraviolet module radiation intensity as the second sub-indicator, the ratio of the operating temperature of the driving power supply to the safe operating temperature threshold of the driving power supply of the purification lamp as the third sub-indicator, and the ratio of the switching frequency to the design threshold of the switching frequency of the purification lamp as the fourth sub-indicator. S102. Multiply the first sub-index, the second sub-index, the third sub-index and the fourth sub-index by their respective preset weight coefficients and then sum them to obtain the health index of the purification lamp, wherein each weight coefficient is a positive number and the sum is 1. S103. Traverse all purification lamp nodes in the power supply network and repeat steps S101 to S102 to obtain the health index set of each purification lamp.

4. The intelligent scheduling system for the power supply network of purification lamps based on digital twins according to claim 1, characterized in that, The specific process of constructing an electrical digital twin based on electrical operating parameters is as follows: S201. Obtain the topology of the power supply network and the electrical operating parameters of each acquisition node. The topology includes the connection between each bus, feeder, transformer and cleanroom lamp terminal. S202. Based on the topological connection relationship and the preset impedance parameters of each line, establish a node admittance matrix to describe the electrical coupling relationship between each node of the power supply network. S203. The topology connection relationship, node admittance matrix and electrical operating parameters of each node are encapsulated into an electrical digital twin. The electrical digital twin is used to respond to the input of scheduling instructions and simulate the voltage distribution and power distribution of the power supply network under different scheduling schemes through power flow calculation.

5. The intelligent scheduling system for the power supply network of purification lamps based on digital twins according to claim 1, characterized in that, The specific process of constructing a health digital twin based on health indices is as follows: S301. Obtain the health index set of each air purifier lamp; S302. Using the unique identifier of each purification lamp in the power supply network topology as an index, associate the health index of each purification lamp with the node position corresponding to that purification lamp in the topology. S303. The health index of all purification lamp nodes in the power supply network topology and their mapping relationship with each node are encapsulated together into a health digital twin, wherein the health digital twin shares the same topology as the electrical digital twin.

6. The intelligent scheduling system for the power supply network of the purification lamp based on digital twin as described in claim 1, characterized in that, The specific process for generating a two-domain digital twin is as follows: S401. Using the unique identifier of each node in the power supply network topology as the association index, establish a one-to-one correspondence between nodes in the electrical digital twin and the health digital twin. S402. Use the health index of each purification lamp node in the health digital twin as a health status label and map it to the attribute field of the corresponding node in the electrical digital twin. After mapping, each purification lamp node in the electrical digital twin simultaneously has an electrical attribute label and a health status label, forming a dual-domain digital twin.

7. The intelligent scheduling system for the power supply network of purification lamps based on digital twins according to claim 1, characterized in that, The specific process for constructing a multi-objective optimization function with the joint optimization objectives of maximizing power supply reliability and minimizing the variance of the health index distribution of each purification lamp is as follows: S501. The power distribution of each purification lamp is used as a decision variable. The power distribution of each purification lamp must be adjustable within the range of zero to its rated power limit. S502. Using electrical operating parameters as constraints, set power balance constraints, node voltage constraints, and line capacity constraints. Among them, the power balance constraint requires that the sum of the power allocated to all purification lamps and the sum of the line losses equal the total power input to the power supply network. The node voltage constraint requires that the voltage amplitude of each node does not exceed the allowable upper and lower voltage limits. The line capacity constraint requires that the transmission power of each line does not exceed its maximum allowable transmission capacity. S503. With the goal of minimizing the total active power loss of all lines in the power supply network, construct a first objective function to characterize the reliability of the power supply. S504. With the goal of minimizing the dispersion of the health index of each purification lamp relative to its average value, a second objective function is constructed to characterize the degree of balance of health status among individual purification lamps. S505. Multiply the first objective function and the second objective function by their respective preset weight coefficients and then sum them to form a joint optimization objective function.

8. The intelligent scheduling system for the power supply network of purification lamps based on digital twins according to claim 1, characterized in that, The specific process of obtaining the optimal scheduling scheme is as follows: S601. Set dynamic scheduling constraints: For purification lamps whose health index is lower than the preset health threshold, their allocated power is limited to a first preset proportion of their rated power during the scheduling cycle. For purification lamps with a health index higher than or equal to a preset health threshold, their power allocation is allowed to reach a second preset ratio of their rated power, and the second preset ratio is greater than the first preset ratio. S602. In the dual-domain digital twin, a multi-objective optimization algorithm is adopted to iteratively optimize the joint optimization objective function under the constraints of power balance, node voltage, line capacity and dynamic scheduling. S603. When the preset iteration termination condition is reached, the optimal solution is selected from the solution set output by the multi-objective optimization algorithm as the optimal scheduling scheme, wherein the optimal scheduling scheme includes the power allocation value of each purification lamp.

9. The intelligent scheduling system for the power supply network of purification lamps based on digital twins according to claim 1, characterized in that, The specific process of simulating and rehearsing the optimal scheduling scheme in a two-domain digital twin is as follows: S701. The power allocation values ​​of each purification lamp in the optimal scheduling scheme are used as input conditions and loaded into the electrical digital twin layer of the dual-domain digital twin. Power flow calculation is performed with the loaded power allocation values ​​of each purification lamp as boundary conditions to obtain the voltage amplitude of each node and the transmission power of each line in the power supply network under the scheduling scheme. S702. Verify the safety boundary conditions of the power flow calculation results: Check that the voltage of all nodes is within the allowable upper and lower limits, check that the transmission power of all lines does not exceed their maximum allowable transmission capacity, and check that the health index of each purification lamp node is lower than the preset safe operation threshold. If all three checks above pass, the optimal scheduling scheme is determined to meet the safety boundary conditions, and the optimal scheduling scheme is converted into a control command and sent to the execution mechanism of the physical power supply network for execution. If any check fails, the check is deemed unsuccessful, and the result is fed back to the scheduling optimization unit.

Images