Power distribution control method and system for prefabricated equipment compartment based on digital twinning

Abstract

The invention relates to the field of power equipment management, and discloses a prefabricated equipment cabin power distribution control method and system based on digital twinning. The control method comprises the steps of establishing a power equipment model through a digital twinning technology, collecting data in real time and updating the model, and optimizing a power distribution strategy to minimize energy consumption, optimize load distribution and guarantee equipment safety. A control instruction is generated by using an optimal control algorithm, a power distribution strategy is executed and dynamically adjusted through an edge computing node, and efficient and safe operation of equipment is ensured; the invention also provides a control system which comprises a digital twin module, an optimal control module, an edge calculation module and a sensor group. According to the method, the equipment state is monitored in real time and the power distribution strategy is optimized through a digital twin technology, an optimal control algorithm and edge calculation, and the problems of real-time feedback, strategy adjustment lag and equipment overload in a traditional scheme are solved by combining multi-objective optimization and flexibly adjusting energy efficiency, load balance and equipment safety.

Description

Technical Field

[0001] The present invention relates to the field of power equipment management, and specifically to a prefabricated equipment compartment power distribution control method and system based on digital twins. Background Art

[0002] In the current field of power equipment management, many systems rely on traditional manual monitoring and regular inspections to ensure the normal operation of power equipment. Although these methods can meet basic operating requirements, they have many shortcomings. First, traditional methods cannot obtain detailed status information of equipment in real time, and monitoring data lags and cannot promptly reflect abnormal conditions in equipment operation. This makes the system often only respond when equipment has obvious faults, and cannot foresee and prevent potential problems in advance. Especially in the scenario of large-scale equipment deployment, manual inspection is not only inefficient, but also prone to omissions.

[0003] Existing power distribution control systems mainly rely on empirical rules and simple optimization algorithms for optimization, which makes it difficult to perform precise scheduling in a real-time changing environment; traditional technologies are usually unable to optimize multiple goals at the same time, such as energy efficiency, load balancing, and equipment safety. Many systems can only focus on a single goal, ignoring the coordination and load balancing between devices. This single-goal optimization strategy often cannot give full play to the overall performance of the system, and may cause individual devices to fail due to overload operation.

[0004] In addition, most power systems still rely on central servers for data processing and issuing control instructions. This centralized processing method is not efficient enough when facing large-scale distributed power equipment. Especially when there are a large number of equipment and complex operating conditions, network delays and data transmission bottlenecks may cause the system to respond slowly and fail to adjust the power distribution strategy in time. This delay not only affects the response speed of the system, but also reduces the safety and energy efficiency of power equipment. Therefore, the present invention proposes a prefabricated equipment compartment power distribution control method and system based on digital twins to solve the shortcomings of the prior art. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a prefabricated equipment compartment power distribution control method and system based on digital twins, which solves the problems of traditional monitoring lag, single optimization strategy and control response delay; by establishing and updating the digital twin model in real time and combining it with the optimal control algorithm, the present invention can accurately reflect the operating status of the equipment, dynamically optimize the power distribution strategy, and ensure energy efficiency optimization, load balancing and equipment safety; at the same time, the edge computing module is used to execute control instructions, which significantly improves the system's response speed and real-time adjustment capability, thereby improving the overall efficiency and stability of the power distribution system.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A prefabricated equipment compartment power distribution control method based on digital twins, comprising the following steps: S1. Establish a model of the power equipment in the prefabricated equipment cabin through digital twin technology, where the operating status of the power equipment is represented by state variables; S2. Update the digital twin model based on the real-time collected data to reflect the operating status of the power equipment in real time, and perform optimization calculations on the power distribution strategy based on the model; S3. In the process of optimizing the power distribution strategy, the optimization goals including minimizing energy consumption, optimizing load distribution and ensuring equipment safety are set, and the optimal power distribution strategy is generated according to the maximum power, load and temperature constraints of each device; S4. Use the optimal control algorithm to perform real-time calculations and generate control instructions, execute the control instructions in the equipment cabin through the edge computing node, and dynamically adjust the power distribution strategy based on the execution results.

[0007] Preferably, real-time data collection is performed through sensors installed on the equipment, which collect current, voltage, temperature, and load data in real time and transmit the data to edge computing nodes for processing and optimization calculations.

[0008] Preferably, the sensor comprises: Current sensor, used to monitor the current changes of the equipment in real time; Voltage sensor, used to monitor voltage changes of equipment in real time; Temperature sensor, used to monitor the temperature change of the device and ensure that the temperature of the device does not exceed the temperature limit; Load sensors are used to monitor equipment load conditions and ensure that the load is within a safe range; The data collected by the sensors in real time are weighted and processed to generate dynamic information related to the status of the power equipment, which is fed back to the digital twin model for analysis.

[0009] Preferably, the state variables of each electrical device in the equipment compartment include current, voltage, temperature, and power, wherein temperature and power limits are used as constraints to generate an optimal power distribution strategy.

[0010] Preferably, the state update equation for each power device in the digital twin model is expressed by the following formula: ; in, Indicates Devices at time The state vector of For the Devices at time The control strategy vector of For the Devices at time The model error; Indicates Devices at time The state vector of the device is updated based on the control strategy and error.

[0011] Preferably, the optimization objectives include minimizing the total energy consumption of equipment operation, ensuring that the load of the equipment does not exceed its maximum carrying capacity, and distributing redundant loads according to the health status of the equipment; the optimal control algorithm includes a control strategy generation method based on dynamic programming and constrained optimization.

[0012] Preferably, the optimal power distribution strategy generation process is constrained by Lagrange multiplier method. The constraints include the maximum power, load and temperature limit of each device. The optimization result is used to adjust the power and load parameters of the device in real time.

[0013] The present invention also provides a prefabricated equipment compartment power distribution control system based on digital twin, comprising: A digital twin module, used to establish and update a digital twin model of the power equipment in the prefabricated equipment compartment, wherein the model reflects the operating status of the power equipment in real time; An optimal control module, which is used to calculate the power distribution strategy in real time based on the digital twin model. The power distribution strategy is generated by the optimal control algorithm and adjusted according to the set minimum energy consumption and load distribution optimization goals; The edge computing module is used to execute the calculated control instructions and feed them back to the device to adjust the operating status of the device in real time; The sensor group is used to monitor the real-time data of current, voltage, temperature and load of the equipment. The data is collected by sensors and transmitted to the digital twin module and edge computing module.

[0014] Preferably, the digital twin module obtains sensor data of equipment in the equipment cabin through a real-time data acquisition system, and inputs the data into the digital twin model for real-time updating.

[0015] Preferably, the optimal control module uses a control algorithm based on dynamic programming and constraint optimization to perform optimization calculations, and the control algorithm generates control instructions according to the load, power and temperature limits of the equipment.

[0016] The present invention provides a prefabricated equipment compartment power distribution control method and control system based on digital twins. It has the following beneficial effects: 1. The present invention adopts a solution that combines digital twin technology and optimal control algorithm to establish and update the digital twin model of power equipment in real time, which can accurately reflect the operating status of the equipment and generate an optimized power distribution strategy based on this; it achieves the technical effect of accurately monitoring the equipment status and dynamically optimizing the power distribution strategy; compared with the traditional technology that only relies on static monitoring or simple optimization algorithms, the present invention solves the problems of insufficient real-time feedback on the equipment operating status and delayed adjustment of the power distribution strategy, so that the system can respond and adjust quickly according to real-time data.

[0017] 2. Through the edge computing module, the present invention realizes the local execution and feedback adjustment of control instructions, ensuring that the control instructions can be quickly transmitted to the device and take effect immediately; this not only improves the system response speed, but also reduces the delay that may be caused by external network transmission, and ensures the stability of the power distribution system under various complex conditions; compared with the remote control mode that relies on the central processing unit in the existing solution, the present invention avoids the influence of network delay on the control effect through the distributed processing of edge computing, and improves the real-time and reliability of the system.

[0018] 3. The present invention utilizes a sensor group to collect key data such as current, voltage, temperature, etc. of the equipment in real time, and combines the digital twin model and the optimal control module to realize dynamic monitoring and real-time adjustment of the equipment status; compared with the traditional technology that only relies on manual monitoring and regular maintenance, the present invention effectively solves the problem of insufficient prediction and early warning of equipment operation failures, and improves the equipment's fault prevention capabilities and operation and maintenance efficiency through automated data collection and feedback mechanisms.

[0019] 4. The present invention combines multiple optimization objectives together, and uses a weighted combination method to dynamically adjust the priority of the optimization objectives, thereby achieving the effect of flexibly responding to different operating environments; compared with the prior art solutions that only focus on single-objective optimization, the present invention can be adjusted according to the real-time status of the equipment and changes in the external environment, solving the efficiency deviation and equipment overload risks that may be caused by single-objective optimization, thereby ensuring comprehensive optimization and efficient operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the method of the present invention; Figure 2 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] See also Figure 1 , an embodiment of the present invention provides a prefabricated equipment compartment power distribution control method based on digital twin, comprising the following steps: S1. Establish a model of the power equipment in the prefabricated equipment cabin through digital twin technology, where the operating status of the power equipment is represented by state variables; In the present invention, a digital twin model of the power equipment in the prefabricated equipment compartment is first established through the digital twin technology; the model aims to accurately reflect the actual operating status of the power equipment in a digital way, so as to provide a basis for subsequent power distribution strategy optimization and real-time control; digital twin technology can continuously update real-time data to provide real-time feedback on the operating status and health status of the equipment, thereby ensuring the efficient, safe and intelligent operation of the power equipment.

[0023] Generally speaking, the power equipment in the equipment compartment includes multiple subsystems such as transformers, switch cabinets, battery energy storage devices, circuit breakers, etc. The operating status of each subsystem will directly affect the overall power distribution system of the equipment compartment; therefore, the present invention constructs a comprehensive digital twin model that integrates the operating data of each device and the mutual influence between devices, so that the power distribution control system can perform optimization calculations and dynamic adjustments more accurately.

[0024] As an option, the digital twin model is modeled based on the state variables of the power equipment; the state variables of each device include key parameters such as current, voltage, temperature, power, and load; these parameters are collected in real time through sensors and fed back to the digital twin model for processing, thereby generating the real-time status of the power equipment; at this point, the digital twin model not only provides the equipment's operating status information, but also simulates the equipment's future status and predicts possible problems and abnormalities in the equipment.

[0025] Specifically, the state variables of each power device are described and updated by the following state equation: ; in, Indicates Devices at time The state vector of For the Devices at time The control strategy vector of For the Devices at time The model error; Indicates Devices at time The state vector of the device is updated based on the control strategy and error.

[0026] In some embodiments, for the update process of state variables, a filtering algorithm such as Kalman filtering can be used to perform more accurate state estimation; Kalman filtering is a recursive optimal estimation method that can estimate the system state using historical data and current observations in the case of noisy data; specifically, the state update equation can be changed to: ; in, For equipment The state transition matrix describes the dynamic evolution of the device state; is the control matrix, which represents the control input Impact on equipment status; is the system noise or disturbance, representing the unmodeled dynamic changes, usually assumed to be Gaussian noise with zero mean.

[0027] In one possible implementation, the digital twin model is optimized and updated by combining the physical model with a data-driven model (such as a machine learning model); the physical model is used to describe the basic operating laws of power equipment, such as the linear relationship between current and voltage, the correlation between temperature and power, etc.; the data-driven model corrects and supplements the uncertain parts of the physical model by analyzing historical data; for example, regression analysis, support vector machines, or neural networks can be used to predict the future state of the equipment, thereby improving the accuracy of the model.

[0028] As an option, the digital twin model in the present invention can also introduce an adaptive learning algorithm to dynamically adjust the model parameters; in this way, the model can be automatically optimized according to real-time data to adapt to the changing characteristics of the equipment and fluctuations in the external environment; specifically, the data fed back by the sensor can be used to dynamically adjust the weights and parameters in the system model through the algorithm, so that the digital twin model can more accurately reflect the operating status of the equipment.

[0029] In another possible implementation, the digital twin model is not limited to the status description of the device itself, but can also be coupled with external environmental factors; for example, considering the impact of external factors such as ambient temperature and humidity, air circulation status in the equipment cabin on the operation of the equipment, the digital twin model can use these environmental factors as additional inputs to correct the operating status of the equipment; this enables the model to simulate actual operating conditions more comprehensively and improve prediction accuracy.

[0030] Specifically, during the update process of the digital twin model of the device, the real-time data of the device status and the environmental data are combined to adjust the status through the following formula: ; in, Indicates Devices at time The state vector of For the Devices at time The control strategy vector of For external environmental factors at all times Impact vector on device status; For the Devices at time The model error; Indicates Devices at time The state vector of the device is updated based on the control strategy and error.

[0031] In some embodiments, the real-time update capability of the equipment model can be enhanced by introducing a distributed sensor network; by deploying multiple sensor nodes, all key locations in the equipment cabin can be monitored in real time, thereby improving the coverage and accuracy of the data; these sensors can work together to transmit the status information of the equipment in real time, and send it to the digital twin model module for comprehensive calculation and status prediction.

[0032] S2. Update the digital twin model based on the real-time collected data to reflect the operating status of the power equipment in real time, and perform optimization calculations on the power distribution strategy based on the model; In the present invention, step S2 follows step S1, and further optimizes the power distribution strategy by updating the digital twin model based on the real-time collected data. This process ensures that the digital twin model is always consistent with the actual operating status of the equipment, and generates the optimal power distribution strategy through the optimization algorithm to achieve efficient and safe operation of the power equipment in the equipment compartment. The digital twin model not only provides real-time reflection of the equipment status, but also provides a basis for subsequent control instruction generation and strategy adjustment.

[0033] Generally speaking, in this step, the real-time collected data includes state variables such as current, voltage, temperature, power, and load from the equipment. These variables are continuously monitored and updated in real time under the action of sensors; these data are processed by the edge computing module and then input into the digital twin model module; through the dynamic input of real-time data, the digital twin model can more accurately describe the operating status of the equipment and optimize the power distribution strategy on this basis.

[0034] In this embodiment, after the digital twin model is updated, the power distribution strategy is first optimized and calculated. The main purpose of this calculation is to determine a set of control instructions that can ensure the energy efficiency optimization and load reasonable distribution of the power equipment in the equipment compartment, and ensure the safe operation of each device. The optimization calculation is not only based on the real-time status data of the equipment, but also takes into account the constraints of the equipment operation (such as power limit, temperature limit, load capacity, etc.) to generate an optimal power distribution plan that meets the equipment operation requirements.

[0035] Specifically, the optimization calculation of the power distribution strategy is carried out through multiple objectives such as minimizing energy consumption, optimizing load distribution, and ensuring equipment safety; the optimization objectives can be described by the following objective function: ; in, Represents the total optimization cost function, reflecting the goal of the optimization calculation; For the The unit energy consumption cost coefficient of each device indicates the energy consumption cost of the device under unit power; For the Devices at time The power output is used as the decision variable for optimization; For the Devices at time The greater the load, the heavier the equipment load, which may lead to higher energy consumption and greater load risk; The total number of electrical equipment in the equipment room.

[0036] Through this formula, the minimization of the optimization objective function will take into account both energy consumption and load conditions, thereby achieving the goal of comprehensively optimizing the power distribution strategy.

[0037] As an option, in order to avoid the risks that may be caused by the optimization of a single objective, a multi-objective optimization algorithm is also adopted in the present invention; in the multi-objective optimization, multiple objective functions can be set and solved by weighted combination; specifically, the optimization objectives can include the following items: ; in, It represents the overall optimization cost function, which reflects the effect of power distribution strategy optimization; and are the weight coefficients of energy consumption cost and load cost, which respectively indicate the importance of energy consumption and load in the optimization objective; For the The unit energy consumption cost coefficient of each device indicates the energy consumption cost of the device under unit power; For the Devices at time Power output; For the The load of a device indicates the workload of the device.

[0038] In one possible implementation, the optimization calculation uses a constraint-based optimization technique; the optimization of the power distribution strategy must not only consider minimizing the total energy consumption, but also ensure that the equipment operates within a safe range, that is, the power, load, temperature and other state variables of each device must meet the constraints; for example, set the maximum power output and safe temperature range of each device. The specific constraints can be expressed by the following formula: ; ; ; in, Indicates Devices at time Power output; Indicates Maximum power output limit for each device; Indicates Devices at time Temperature; Indicates The maximum operating temperature of the device; Indicates Devices at time Load; Indicates The maximum load capacity of a device.

[0039] Specifically, in order to meet these constraints, the optimization process adopts a constrained optimization method based on the Lagrange multiplier method; this method incorporates the constraints into the objective function by introducing Lagrange multipliers, thereby optimizing multiple objectives and meeting the constraints at the same time; the optimization process determines the power output and load distribution of each device by solving the optimal control strategy.

[0040] In another possible implementation, the present invention can also be combined with machine learning algorithms (such as reinforcement learning) for strategy optimization; in this way, the system can automatically adjust the power distribution strategy according to real-time data feedback, and gradually improve the adaptability and stability of the system; in reinforcement learning, the state variables of the equipment are used as inputs, the adjustment of the power distribution strategy is used as an action, and the optimization goal of the strategy is to guide the system to learn the optimal control strategy through a reward function; for example, the reward function can be designed as: ; in, For the Devices at time The reward value indicates the strategy effect of the device at that moment. The higher the value, the better the strategy. For the Devices at time Power output; For the Devices at time Load; is the power penalty coefficient, which controls the influence of power output on the reward value. It is the penalty coefficient of load, which controls the influence of load on reward value.

[0041] In some embodiments, in order to enhance the robustness of the system to faults, the power distribution strategy optimization may also consider the health status of the equipment; the health status of the equipment may be comprehensively evaluated by the equipment's state variables such as temperature, current, and load; in this case, the equipment health status function It can be calculated by the following comprehensive evaluation formula: ; in, For the The health status value of a device, the larger the value, the better the health status of the device; is the weighting coefficient of each parameter, indicating the influence weight of different equipment status on health assessment; Respectively The current, voltage, temperature, and power status of each device.

[0042] In some cases, in order to further improve the effectiveness of the optimization strategy, the present invention can combine load prediction and power scheduling algorithms to dynamically adjust the power distribution strategy; by predicting future load demand and power supply, the system can pre-generate the power distribution strategy and make real-time adjustments during actual operation, thereby ensuring efficient operation of the equipment.

[0043] S3. In the process of optimizing the power distribution strategy, the optimization goals including minimizing energy consumption, optimizing load distribution and ensuring equipment safety are set, and the optimal power distribution strategy is generated according to the maximum power, load and temperature constraints of each device; In the present invention, step S3 is inherited from step S2, and mainly generates the optimal distribution strategy by setting the optimization goal and according to the real-time data, operation constraints and optimization goals of the equipment; through this process, the digital twin model further guides the distribution control system to achieve energy efficiency optimization, load balancing, safety assurance and other goals on the basis of real-time reflection of the operating status of the power equipment, so as to ensure the stable, efficient and reliable operation of all power equipment in the equipment compartment.

[0044] In general, the optimization objectives of a power distribution strategy usually consist of multiple aspects, including minimizing energy consumption, optimizing load distribution, ensuring safe operation of equipment, etc.; these objectives need to be dynamically adjusted according to the current status of the equipment and changes in the operating environment; the setting of optimization objectives must not only meet the requirements of equipment safety, but also maximize the cost-effectiveness of the overall system, thereby improving the performance and reliability of the entire power distribution system.

[0045] In this embodiment, the optimization objectives of the power distribution strategy include the following core objectives: Minimize energy consumption: The goal is to reduce energy consumption throughout the equipment compartment, thereby reducing operating costs. Specifically, by adjusting the power output of the equipment, the system can reduce power consumption and reduce electricity costs without affecting the normal operation of the equipment. This goal can be expressed by the following formula: ; in, is the objective function of minimizing energy consumption, which represents the total energy consumption of the system; For the The unit energy consumption cost coefficient of each device indicates the cost per unit of power consumption; For the Devices at time Power output; The total number of all electrical equipment in the equipment room.

[0046] Load distribution optimization: The goal is to reasonably distribute the load of each device, avoid overloading the equipment and ensure that the equipment works smoothly within the safe load range; load distribution optimization can not only improve equipment efficiency, but also prevent some equipment from malfunctioning due to excessive load; the objective function of load distribution can be expressed by the following formula: ; in, It represents the load distribution optimization objective function, which measures the degree of load balancing among all devices; is the total number of electrical equipment in the equipment room, indicating the number of equipment that needs to optimize load distribution; For the Devices at time The load indicates the current load condition of the device; It is the average load of all equipment in the equipment room.

[0047] This objective function is used to measure the degree of load imbalance between devices. Minimizing this value helps to ensure load balance and avoid the risk of device failure due to excessive load.

[0048] Equipment safety assurance: The goal is to ensure that the equipment does not exceed its maximum power, temperature, and load limits during operation. By monitoring the equipment status, the power distribution strategy can ensure that the equipment operates within a safe operating range, thereby preventing equipment overload, overheating, and other problems, and ensuring system stability. This goal can be expressed by the following constraints: ; ; ; in, Indicates Devices at time Power output; Indicates Maximum power output limit for each device; Indicates Devices at time Temperature; Indicates The maximum operating temperature of the device; Indicates Devices at time Load; Indicates The maximum load capacity of a device.

[0049] Specifically, in the comprehensive optimization process, the above multiple objective functions and constraints can be weighted and combined; by selecting appropriate weight coefficients, the optimization calculation can balance the priorities among the objectives, ensuring that the system can achieve low energy consumption, load balancing, and safe operation of the equipment; the comprehensive objective function can be described by the following formula: ; in, is the comprehensive optimization objective function, which represents the optimization goal of the entire power distribution strategy; are the weight coefficients of energy consumption, load distribution and safety objectives, respectively, reflecting the relative importance of each objective in the optimization process; is the energy consumption objective function, which represents the energy consumption of the system; is the load optimization objective function, which indicates the balance of load distribution; is the safety objective function, which represents the operational safety of the equipment and ensures that the equipment works within a safe range; is the total number of electrical equipment in the equipment room, representing all electrical equipment involved in the optimization process.

[0050] As an option, in order to dynamically adjust the weight of the optimization objective, the weight coefficient It can be automatically adjusted according to the real-time status of the system; for example, when the system is heavily loaded, the weight of the load distribution It can be increased to prioritize load distribution and reduce the risk of equipment overload. When the equipment is in good health, the weight of safety assurance can be appropriately reduced, focusing on optimizing energy efficiency.

[0051] In one possible implementation, a machine learning algorithm can be combined to optimize the objective function and weight distribution. Specifically, by using historical data and equipment operating status, the machine learning model can automatically learn the optimal weight distribution scheme for different scenarios. This method can dynamically adjust the optimization target according to real-time feedback data, thereby improving the intelligence and adaptability of the system.

[0052] In some embodiments, the optimization of the objective function can also be solved by combining other algorithms (such as genetic algorithms, particle swarm algorithms, etc.); through these global optimization algorithms, the global optimal solution or near-optimal solution can be quickly searched in a large-scale equipment system to avoid falling into a local optimal solution, thereby further improving the effectiveness of the power distribution strategy.

[0053] Specifically, when using a genetic algorithm, the optimization process of the objective function includes generating multiple solutions through operations such as crossover and mutation, evaluating the quality of each solution through a fitness function, and finally selecting the solution with the highest fitness as the optimal strategy; this process can find the optimal power distribution plan under multiple equipment states and constraints.

[0054] In another possible implementation, the optimization process of the present invention can be implemented through distributed computing; especially in large-scale equipment systems, the optimization tasks can be distributed to multiple computing nodes for parallel computing, which greatly improves the efficiency and computing speed of the optimization process; this distributed computing can effectively handle complex multi-objective optimization problems and adapt to the operating requirements of large-scale systems.

[0055] S4. Use the optimal control algorithm to perform real-time calculations and generate control instructions, execute the control instructions in the equipment cabin through the edge computing node, and dynamically adjust the power distribution strategy according to the execution results; In the present invention, step S4 inherits the power distribution strategy optimization result in step S3, and the control instructions generated by the optimal control algorithm will be passed to the edge computing node for execution; the core task of this step is to apply the optimal power distribution strategy obtained by the optimization calculation to the actual equipment, and ensure that the equipment maintains efficient and safe operation under continuously changing load and environmental conditions through dynamic adjustment; the edge computing node is not only responsible for executing control instructions, but also dynamically adjusts the power distribution strategy according to real-time feedback, thereby continuously optimizing system performance.

[0056] Generally speaking, the optimal power distribution strategy generated in step S3 provides the ideal load distribution, energy consumption minimization and equipment safety assurance goals for the entire power equipment system, but these strategies are limited to theoretical calculations and need to be implemented through control instructions in actual operations; in this process, the edge computing node, as the execution layer, is responsible for converting the theoretical calculation results into specific operation instructions. The control instructions include power regulation, load distribution, temperature control, etc., to ensure that the operation of the equipment remains in the best state under the established constraints.

[0057] In this embodiment, the control instructions generated by the optimal control algorithm include the following categories: Power regulation: Based on the real-time power demand of each device, the control instructions will adjust the power output of each device to ensure that the device has the optimal power output based on the current load demand and energy efficiency target; by controlling the power output of the device, the system can maximize energy efficiency and reduce energy consumption while meeting the load demand; Load distribution: Load distribution instructions adjust the load of each device according to the health status of the device, load capacity and the coordination between devices to avoid overloading of some devices due to excessive load. The goal of load distribution is to ensure balanced load of the equipment to improve the efficiency of equipment use and reduce the risk of failure. Temperature control: Temperature control instructions are designed to ensure that the device operates within a safe temperature range to prevent damage to the device due to overheating. Based on the thermal management requirements of the device, the control system will dynamically adjust the power output or load distribution according to the device's temperature data to maintain a stable operating temperature for the device. Specifically, the generation of control instructions depends on the optimal control algorithm; assuming that the system adopts an optimal control algorithm such as model predictive control (MPC) or dynamic programming (DP), the following is the control instruction generation process based on dynamic programming: Determine the state space: Each device in the system has multiple state variables (such as current, voltage, power, load, temperature, etc.), which constitute the state space of the device; at each moment, the state variables are updated according to the control instructions and the operating conditions of the device and serve as the input of dynamic programming; Establishing control strategies: For each device, the optimal control algorithm calculates a set of control inputs, including control variables such as power and load, to meet the optimization goal and ensure the constraints. Through this process, the control algorithm can generate the optimal control instructions based on the current state of the device. Phased optimization: The dynamic programming algorithm calculates the optimal control instructions at each moment through phased optimization, thereby generating a globally optimal power distribution strategy. The control instructions at each stage are adjusted according to the current status and load conditions of the equipment to ensure the optimal operation of each device under its working condition.

[0058] In one possible implementation, if the system uses model predictive control (MPC), then in each control cycle, the system will generate a set of optimal control instructions based on the current state information of the equipment and the predicted future state; MPC can adjust the control strategy in real time by predicting the future state to deal with potential load fluctuations and external environmental changes; the MPC optimization process can be expressed as: ; exist ; in: For the moment The optimal control input of For the Energy consumption cost coefficient of each device; For the Devices at time Power output; For the Devices at time Load; For the Maximum power limit for each device; For the Maximum temperature limit for each device; For the The maximum load capacity of each device; is the total number of devices, indicating the number of all devices in the system.

[0059] This formula describes the MPC algorithm by optimizing the control input To minimize the total energy consumption and load sharing , while ensuring the device operates within maximum power, temperature, and load limits.

[0060] As an option, control instructions can also be generated using adaptive optimization methods such as reinforcement learning (RL). The goal of reinforcement learning is to optimize the control strategy through a reward function. The system intelligently finds the optimal control strategy based on real-time feedback data (such as temperature, power, load, etc.) by continuously adjusting the control input. For example, the system can design the following reward function: ; in, For the Devices at time The reward value indicates the strategy effect of the device at that moment. The higher the value, the better the strategy. For the Devices at time Power output; For the Devices at time Load; is the power penalty coefficient, which controls the influence of power output on the reward value. It is the penalty coefficient of load, which controls the influence of load on reward value.

[0061] Through this method, the system can continuously adjust the control strategy based on feedback data from actual operation and optimize the overall performance of the distribution system.

[0062] In some embodiments, the edge computing node dynamically adjusts the control strategy based on the real-time feedback from each device; for example, when the temperature of a device approaches a critical value, the system will automatically adjust the power output or load distribution of the device to ensure that the device is within a safe temperature range; at the same time, the collaborative work between devices will also be optimized in this process to ensure load balancing and reduce the risk of overloading a single device.

[0063] In another possible implementation, in order to further improve control efficiency, the control instruction generation process in the present invention can also be combined with distributed computing; when multiple devices work together, distributed computing can quickly calculate the optimal control strategy for each device and process data in parallel on multiple edge computing nodes, thereby improving computing efficiency and reducing system response time.

[0064] Specifically, when executing control instructions in the equipment cabin, the edge computing node will update the status of each device based on real-time feedback data and generate new control instructions; these instructions will guide the device to adjust parameters such as power, load and temperature to ensure that the equipment operates efficiently within a safe range.

[0065] See also Figure 2 , a prefabricated equipment compartment power distribution control system based on digital twin, including: Digital twin module: The digital twin module is used to establish and update the digital twin model of the power equipment in the equipment cabin in real time. The model is dynamically connected with the real-time operating status of the equipment to ensure that the behavior of the power equipment is accurately reflected in the digital space. Specifically, the digital twin model contains all state variables of the power equipment, such as current, voltage, power, load, temperature, etc. This information is collected by sensors in real time and input into the model. Through the digital twin module, the system can realize real-time monitoring and prediction of the equipment operating status, thereby providing data support for optimization calculation and decision-making. Optimal control module: The optimal control module calculates the power distribution strategy and generates control instructions in real time based on the real-time data of the digital twin model. Through the optimal control algorithm, the module generates control instructions and ensures that the equipment operates in the best state according to the set optimization goals such as minimum energy consumption, load balancing and equipment safety. By implementing these optimization strategies, the optimal control module enables the power equipment in the equipment compartment to operate efficiently, avoid overload, overheating and other problems, and make necessary adjustments to the strategy based on real-time feedback to ensure system stability and energy efficiency. Edge computing module: The edge computing module is responsible for converting the calculation results generated by the optimal control module into specific control instructions and transmitting them to the device. This module ensures that the control instructions can respond quickly on the device side to avoid delays through local calculation, control and execution. The edge computing module also monitors the operating status of the device in real time, dynamically adjusts the control instructions through the data feedback system, and maintains the optimal operating status of the system. The distributed computing capabilities of the edge computing nodes support efficient and low-latency control execution in large-scale device systems. Sensor group: The sensor group is responsible for monitoring the real-time data of the equipment, such as current, voltage, temperature and load, and transmitting this data to the digital twin module and edge computing module. The sensor group provides continuous input for the digital twin model by collecting the status data of the equipment in real time, ensuring that the model reflects the latest operation status of the equipment. In addition, the sensor is also responsible for transmitting key feedback information to the edge computing module to help adjust control instructions and power distribution strategies. While ensuring the safe and stable operation of the system, these sensors also provide the necessary raw data support for equipment status prediction and fault diagnosis.

[0066] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A prefabricated equipment compartment power distribution control method based on digital twin, characterized in that: The following steps are involved: S1. Establish a model of the power equipment in the prefabricated equipment cabin through digital twin technology, where the operating status of the power equipment is represented by state variables; S2. Update the digital twin model based on the real-time collected data to reflect the operating status of the power equipment in real time, and perform optimization calculations on the power distribution strategy based on the model; S3. In the process of optimizing the power distribution strategy, the optimization goals including minimizing energy consumption, optimizing load distribution and ensuring equipment safety are set, and the optimal power distribution strategy is generated according to the maximum power, load and temperature constraints of each device; S4. Use the optimal control algorithm to perform real-time calculations and generate control instructions, execute the control instructions in the equipment cabin through the edge computing node, and dynamically adjust the power distribution strategy based on the execution results.

2. According to the digital twin-based prefabricated equipment compartment power distribution control method of claim 1, it is characterized in that: The data collected in real time is collected through sensors installed on the equipment. The sensors collect current, voltage, temperature, and load data in real time and transmit the data to the edge computing node for processing and optimization calculation.

3. According to the digital twin-based prefabricated equipment compartment power distribution control method of claim 2, it is characterized in that: The sensor comprises: Current sensor, used to monitor the current changes of the equipment in real time; Voltage sensor, used to monitor voltage changes of equipment in real time; Temperature sensor, used to monitor the temperature change of the device and ensure that the temperature of the device does not exceed the temperature limit; Load sensors are used to monitor equipment load conditions and ensure that the load is within a safe range; The data collected by the sensors in real time are weighted and processed to generate dynamic information related to the status of the power equipment, which is fed back to the digital twin model for analysis.

4. According to a digital twin-based prefabricated equipment compartment power distribution control method according to claim 1, it is characterized in that: The state variables of each electrical device in the equipment compartment include current, voltage, temperature, and power, wherein temperature and power limits are used as constraints to generate an optimal power distribution strategy.

5. According to a digital twin-based prefabricated equipment compartment power distribution control method according to claim 1, it is characterized in that: The state update equation for each power device in the digital twin model is expressed by the following formula: ； in, Indicates Devices at time The state vector of For the Devices at time The control strategy vector of For the Devices at time The model error; Indicates Devices at time The state vector of the device is updated based on the control strategy and error.

6. According to a digital twin-based prefabricated equipment compartment power distribution control method according to claim 1, it is characterized in that: The optimization objectives include minimizing the total energy consumption of equipment operation, ensuring that the load of the equipment does not exceed its maximum carrying capacity, and distributing redundant loads according to the health status of the equipment; the optimal control algorithm includes a control strategy generation method based on dynamic programming and constrained optimization.

7. According to the digital twin-based prefabricated equipment compartment power distribution control method of claim 1, it is characterized in that: The optimal power distribution strategy generation process is constrained by Lagrange multiplier method. The constraints include the maximum power, load and temperature limit of each device. The optimization result is used to adjust the power and load parameters of the device in real time.

8. A prefabricated equipment cabin power distribution control system based on digital twin, applied to a prefabricated equipment cabin power distribution control method based on digital twin as claimed in any one of claims 1 to 7, characterized in that: include: A digital twin module, used to establish and update a digital twin model of the power equipment in the prefabricated equipment compartment, wherein the model reflects the operating status of the power equipment in real time; An optimal control module, which is used to calculate the power distribution strategy in real time based on the digital twin model. The power distribution strategy is generated by the optimal control algorithm and adjusted according to the set minimum energy consumption and load distribution optimization goals; The edge computing module is used to execute the calculated control instructions and feed them back to the device to adjust the operating status of the device in real time; The sensor group is used to monitor the real-time data of current, voltage, temperature and load of the equipment. The data is collected by sensors and transmitted to the digital twin module and edge computing module.

9. A prefabricated equipment compartment power distribution control system based on digital twin according to claim 8, characterized in that: The digital twin module obtains sensor data of equipment in the equipment cabin through a real-time data acquisition system, and inputs the data into the digital twin model for real-time updating.

10. The prefabricated equipment compartment power distribution control system based on digital twin according to claim 8, characterized in that: The optimal control module uses a control algorithm based on dynamic programming and constraint optimization to perform optimization calculations, and the control algorithm generates control instructions according to the load, power and temperature limits of the equipment.

Images