Automatic power distribution control method for prefabricated equipment compartment

Abstract

The invention relates to the technical field of electric power system control, and discloses an automatic power distribution control method for a preassembled equipment cabin, which comprises the following steps: step 1, constructing state variables and control signals of an electric power system in the equipment cabin, the state variables comprising electric power demand, generator power output and energy storage equipment charging and discharging power; step 2, constructing an objective function including power consumption cost and equipment operation cost; 3, solving an optimal control signal under a constraint condition, and optimizing a power distribution strategy; 4, independently carrying out local optimization on each device, and realizing global optimization of the system through coordination; 5, modeling is carried out on the uncertainty of the power demand and the generating capacity, and dynamic scheduling is optimized in combination with random disturbance; and step 6, dynamically adjusting the power distribution strategy according to real-time feedback. By adopting the power system dispatching technical scheme based on the distributed optimization framework, the technical effect of improving the dispatching efficiency and flexibility of the power system is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system control, and in particular to an automatic power distribution control method for a prefabricated equipment cabin. Background Art

[0002] With the continuous growth of electricity demand and the increasing complexity of equipment, the power system faces huge challenges in efficient, flexible scheduling and stable operation. Especially in some special application scenarios, such as prefabricated equipment cabins, it is required to realize intelligent management and efficient scheduling of power equipment under limited space and resource conditions. Traditional power system scheduling methods are mostly based on centralized control. Although they can provide basic power distribution functions, they are prone to slow response and low efficiency when faced with complex equipment networks and dynamically changing needs. Therefore, how to optimize power system scheduling and improve the system's flexibility, real-time response capabilities, and adaptability to uncertain environments has become a technical problem that needs to be solved urgently.

[0003] In the prior art, power systems usually rely on centralized control systems to achieve the allocation of power resources through unified scheduling. However, this scheduling mode has poor adaptability in large-scale equipment and complex environments, and is prone to excessive calculations, slow scheduling response, and even equipment overload or power waste. In addition, many existing methods handle the uncertainty of power demand and power generation too simply, lack accurate modeling and dynamic adjustment capabilities, resulting in the system being unable to effectively respond and adjust when sudden demand changes or equipment failures occur. Although some methods have introduced real-time feedback mechanisms, most technologies still have problems such as insufficient flexibility and slow response.

[0004] The current technical defects mainly focus on how to achieve efficient power dispatch in complex environments. When faced with a large number of independent devices, the traditional centralized dispatch system has too much calculation and slow response speed, which makes it impossible to quickly adjust under dynamic demand changes, and is prone to problems such as overload and power waste. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an automatic power distribution control method for a prefabricated equipment cabin, which solves the problems of slow response, excessive calculation and insufficient uncertainty processing capability of the traditional power system centralized dispatching mode when dealing with large-scale equipment and complex environments.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an automatic power distribution control method for a prefabricated equipment cabin, comprising the following steps: Step 1: construct state variables and control signals of the power system in the equipment cabin, wherein the state variables include power demand, generator power output, and energy storage device charge and discharge power, and the control signals include generator power output and energy storage device charge and discharge power; Step 2: Based on the state variables and control signals, an objective function including power consumption cost and equipment operation cost is constructed, and the operation benefit of the power system is quantified through optimal control theory; Step 3: Combine the objective function, solve the optimal control signal under the constraint conditions, and optimize the power distribution strategy; Step 4: Decompose the power distribution strategy based on a distributed optimization framework, perform local optimization on each device independently, and achieve the global optimization of the system through coordination; Step 5: Based on the global optimum, a random process model is further introduced to model the uncertainty of power demand and power generation, and the dynamic scheduling is optimized in combination with random disturbances; Step 6: Dynamically adjust the power distribution strategy based on real-time feedback to cope with power demand fluctuations and equipment status changes.

[0007] Preferably, the objective function in step 2 includes: The cost of electricity consumption, expressed as the weighted sum of electricity demand and generator output power; The penalty term of the control signal is expressed as the weighted sum of the charging and discharging power of the energy storage device and the power output of the generator, which is used to avoid equipment overload and power fluctuation.

[0008] Preferably, the constraints in step three include: The balance between electricity demand and generator output; Charge and discharge power limits for energy storage devices, where the charge and discharge power fluctuates within a predetermined range; The power output limitation of a power generating device, where the power output does not exceed the maximum output capability of the device.

[0009] Preferably, in step 4, the distributed optimization framework includes: The control signal of each device is solved through independent local optimization problems to obtain the local optimal control strategy; The devices exchange information and coordinate scheduling through the communication network, gradually approaching the global optimal solution of the system.

[0010] Preferably, in step five, the random process model models the electricity demand and power generation through a Markov process, specifically including: the changes in electricity demand and power generation in each time period are determined by the electricity demand and power generation in the previous time period, and are affected by random disturbances, wherein the random disturbances represent the uncertainty of electricity demand and power generation, respectively.

[0011] Preferably, the real-time feedback in step six includes: Real-time monitoring of power demand, energy storage device status, and generator output power through sensors; Dynamically adjust control signals based on monitoring data and optimize power distribution strategies to ensure a balance between power supply and demand in the equipment compartment.

[0012] Preferably, the optimal control law is based on the Pontryagin maximum principle to solve the optimal control signal so that the objective function is minimized while satisfying system constraints.

[0013] Preferably, the various devices in the equipment compartment include: a generator, an energy storage device and a load device, wherein the generator is used to provide electricity, the energy storage device is used to balance power fluctuations, and the load device is adjusted according to power demand.

[0014] Preferably, the power distribution control method is based on a real-time power demand prediction model and adjusts the charging and discharging power of the energy storage device and the output power of the generator through an optimal control strategy, specifically including: Based on the predicted power demand and the status of the energy storage equipment, the power output for each period is determined to optimize the allocation of power resources within the system, ensure the balance of power supply and demand, and maximize the utilization efficiency of power resources.

[0015] Preferably, the method can be implemented by a computer program, which is stored in a computer-readable storage medium and can automatically schedule and control power distribution in the equipment compartment when executed.

[0016] The present invention provides an automatic power distribution control method for a prefabricated equipment compartment, which has the following beneficial effects: 1. The present invention achieves the technical effect of improving the efficiency and flexibility of power system dispatch by adopting a power system dispatching technical solution based on a distributed optimization framework. Compared with the single dispatching mode of the centralized control system in the prior art, the present invention reduces the amount of calculation and improves the response speed by dividing the power system into multiple independent devices for local optimization, thus avoiding system overload and dispatching delay when facing a large number of devices.

[0017] 2. The present invention uses a random process modeling method to deal with the uncertainty of power demand and power generation, thereby improving the ability of the power system to adapt to uncertain environments. Compared with the relatively simple technical solutions for dealing with the uncertainty of demand and supply in the prior art, the present invention introduces a Markov process model to more accurately model the fluctuations in power demand and power generation, which can effectively predict and respond to sudden changes in power demand and ensure the stable operation of the system in a complex environment.

[0018] 3. The present invention dynamically adjusts the power system through a real-time feedback mechanism, achieving more efficient power resource allocation and real-time response capabilities. Compared with the fixed scheduling mode in the prior art that lacks flexible response, the present invention can quickly adjust the control signal according to the real-time collected power demand, equipment status and other data, avoiding equipment overload, power waste and other problems, and significantly improving the system's operating stability and resource utilization efficiency.

[0019] 4. The present invention combines the optimal control theory with the predictive control method to achieve the technical effect of minimizing power consumption and equipment operating costs. Compared with the prior art solution that relies only on real-time data for scheduling, the present invention combines the prediction of power demand with real-time feedback to adjust the power output of energy storage equipment and generators in advance, avoiding power waste or equipment load problems caused by slow response, and further improving the economy and stability of the power 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 flow chart of automatic power distribution control of the electric power system of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the specification of the present invention Figures 1 to 2 , the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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] Please refer to the attached Figure 1 The embodiment of the present invention provides an automatic power distribution control method for a prefabricated equipment compartment, comprising the following steps: Step 1: Construct state variables and control signals of the power system in the equipment cabin, where the state variables include power demand, generator power output, and energy storage device charging and discharging power, and the control signals include generator power output and energy storage device charging and discharging power; Step 2: Based on the state variables and control signals, construct an objective function including power consumption cost and equipment operation cost, and quantify the operation benefits of the power system through optimal control theory; Step 3: Combine the objective function, solve the optimal control signal under the constraint conditions, and optimize the power distribution strategy; Step 4: Decompose the power distribution strategy based on the distributed optimization framework, perform local optimization on each device independently, and achieve the global optimization of the system through coordination; Step 5: Based on the global optimum, a random process model is further introduced to model the uncertainty of power demand and power generation, and the dynamic scheduling is optimized in combination with random disturbances; Step 6: Dynamically adjust the power distribution strategy based on real-time feedback to cope with fluctuations in power demand and changes in equipment status.

[0023] The objective function in step 2 includes: The cost of electricity consumption, expressed as the weighted sum of electricity demand and generator output power; The penalty term of the control signal is expressed as the weighted sum of the charging and discharging power of the energy storage device and the power output of the generator, which is used to avoid equipment overload and power fluctuation.

[0024] The constraints in step 3 include: The balance between electricity demand and generator output; Charge and discharge power limits for energy storage devices, where the charge and discharge power fluctuates within a predetermined range; The power output limitation of a power generating device, where the power output does not exceed the maximum output capability of the device.

[0025] In step 4, the distributed optimization framework includes: The control signal of each device is solved through independent local optimization problems to obtain the local optimal control strategy; The devices exchange information and coordinate scheduling through the communication network, gradually approaching the global optimal solution of the system.

[0026] In step five, the random process model models the electricity demand and power generation through the Markov process, specifically including: the changes in electricity demand and power generation in each time period are determined by the electricity demand and power generation in the previous time period, and are affected by random disturbances, where the random disturbances represent the uncertainty of electricity demand and power generation respectively.

[0027] Real-time feedback in step six includes: Real-time monitoring of power demand, energy storage device status, and generator output power through sensors; Dynamically adjust control signals based on monitoring data and optimize power distribution strategies to ensure a balance between power supply and demand in the equipment compartment.

[0028] The optimal control law is based on the Pontryagin maximum principle to solve the optimal control signal so that the objective function is minimized while satisfying the system constraints.

[0029] The various devices in the equipment cabin include: generators, energy storage devices and load devices, among which the generators are used to provide electricity, the energy storage devices are used to balance power fluctuations, and the load devices are adjusted according to power demand.

[0030] The power distribution control method is based on the real-time power demand forecasting model and adjusts the charging and discharging power of the energy storage equipment and the output power of the generator through the optimal control strategy, which includes: Based on the predicted power demand and the status of the energy storage equipment, the power output for each period is determined to optimize the allocation of power resources within the system, ensure the balance of power supply and demand, and maximize the utilization efficiency of power resources.

[0031] In the automatic power distribution control method, it is necessary to first build a power system model in the equipment cabin. This model is the basis of the entire control method. Its purpose is to provide data support for subsequent optimal control and distributed optimization by defining the core state and control variables of the power system.

[0032] In general, the core elements of a power system include power demand, generator power output, and the charging and discharging power of energy storage devices. During system operation, power demand may fluctuate at any time, and the output power of the generator needs to be adjusted according to the changes in power demand. Energy storage devices play the role of balancing power demand fluctuations. In order to accurately control and optimize the operation of these devices, it is necessary to first clearly define and determine the state variables and control signals of each device.

[0033] In this embodiment, the state variables and control signals of the power system are first defined. The state variables of the power system include: power demand , generator power output and energy storage device charging and discharging power These state variables can fully describe the operating status of each device in the system at a certain moment.

[0034] Power demand : Indicates the system at a point in time The power demand at a given location is a variable that is affected by many factors, including equipment load, environmental factors, and the operating state of the system itself. Power demand often fluctuates over time, especially when equipment loads change or environmental conditions change. Power demand is a key variable in system operation, and accurately measuring and predicting its changes is essential to optimizing power distribution control.

[0035] Generator power output Indicates the generator at time point The output power of the generator needs to be adjusted according to the power demand and the charging and discharging of the energy storage device. The adjustment range of the generator output power is usually limited by the maximum output power of the device. The output power of the generator is not only affected by the power demand, but also by the internal operating characteristics of the equipment and external environmental factors. In general, the generator adjusts the power output according to the changes in power demand to ensure the balance of power supply in the system.

[0036] Energy storage device charging and discharging power :Energy storage devices are used to adjust the difference between power supply and demand. Represents the charging or discharging capability of the energy storage device. The charging and discharging power of the energy storage device is usually limited by the physical characteristics of the device and the operating status. The stability of the power system depends on the charging function of the energy storage device at high load and the discharging function at low load. The charging and discharging process of the energy storage device must be carried out strictly within the set maximum power range to avoid equipment damage or system instability.

[0037] In actual operation, real-time monitoring and prediction of these state variables are crucial for power dispatching. By installing sensors and control units, the real-time values ​​of these state variables can be accurately obtained at every moment and transmitted to the central control system. Through the data acquisition system, the dynamic state of the system can be obtained and the necessary input for subsequent optimization control can be provided.

[0038] As an option, the state variable , and It can be monitored automatically through intelligent sensors, or indirectly predicted through external systems (such as power load forecasting systems or weather forecasting systems). These data will become an important basis for subsequent optimal control, distributed optimization, and dynamic regulation.

[0039] Next, based on these state variables, control signals are defined That is, the power output of the generator and the charging and discharging power of the energy storage device. The control signal is the core regulation method of the power system, which is used to adjust the output of the equipment to ensure the stable operation of the system. Specifically, the control signal includes: Generator power output :As part of the control signal, the generator power output is an important adjustment parameter of the control system. By adjusting the generator power output, the system can cope with fluctuations in power demand and ensure a stable power supply.

[0040] Energy storage device charging and discharging power :The charging and discharging power of the energy storage device is also part of the control signal. By adjusting the charging or discharging strategy of the energy storage device, the system can flexibly respond to short-term fluctuations in power demand and reduce the instability caused by generator load fluctuations.

[0041] Specifically, at a certain moment When power demand is high, the control system may increase generator output power , while providing more power support by discharging. When power demand is low, the system may reduce the power output of the generator and store the excess power in the energy storage device to prepare for possible high demand periods in the future.

[0042] By precisely adjusting these control signals, coordinated cooperation between devices can be ensured, allowing the entire power system to maintain efficient and stable operation in a complex power demand environment.

[0043] In one possible implementation, the control system can also use the model predictive control (MPC) method to predict the power demand and equipment status changes in the future, and adjust the control signal in advance according to the prediction results to achieve more accurate power dispatch. This method can effectively improve the system's response speed and reduce energy waste.

[0044] In addition, the relationship between the state variables and the control signals can be expressed by the following mathematical formula: ; in, Power demand, is the generator power output, is the charging and discharging power of the energy storage device. This formula reflects the balance between power demand and power supply and is one of the most basic control formulas in power system dispatching.

[0045] In general, when applying optimal control theory, the objective function design should include a reasonable evaluation of power consumption and a trade-off between the operating costs of various types of equipment. Through a reasonable objective function, the dispatch of the power system can not only meet power demand, but also use system resources efficiently, avoiding excessive energy consumption or equipment overload.

[0046] In this embodiment, the design of the objective function includes two main aspects: power consumption cost and equipment operation cost. Specifically, the power consumption cost is directly related to the power demand and the generator output power; while the equipment operation cost is related to the power output of the generator and the energy storage device. In terms of power consumption, it is necessary to avoid unnecessary energy waste while providing sufficient power. In terms of equipment operation, considering the power output and adjustment range of each device, the efficiency of equipment use is crucial to the operation of the entire system.

[0047] Specifically, the objective function can be expressed as: ; in, is the cost of electricity consumption, reflecting the demand for electricity and generator power output The power consumption cost is mainly to ensure that the system can provide the required power while controlling the cost. is the equipment operating cost, indicating the charging and discharging power of the energy storage device and generator power output Contribution to cost. The charging and discharging behavior of energy storage devices directly affects their efficiency and device life, so the control strategy should balance these factors to avoid overcharging or overdischarging.

[0048] In practical applications, the cost of electricity consumption Usually related to the power demand of the system is proportional to the generator power output There is a certain relationship between them. Generator output power The increase in the charging and discharging power of energy storage equipment will lead to more fuel consumption, thereby increasing the cost of electricity consumption. It will affect the dispatch of power in the system. Energy storage equipment stores excess power when the load is low and releases power when the load is high to ensure the balance of the system. In this paper, the charging and discharging behavior of energy storage devices is paid special attention to in order to ensure the long-term stable operation of the equipment.

[0049] As an option, additional constraints can be introduced into the objective function, such as the maximum output power limit of the equipment, the charge and discharge rate limit of the energy storage device, etc. These constraints will affect the optimization process of the objective function and ensure that the optimization results meet the actual operation requirements of the system.

[0050] In a possible implementation, the objective function is not limited to power consumption costs and equipment operation costs, but can also be extended to other more complex cost models. For example, the maintenance cost of equipment, the potential risk cost of equipment failure, etc. can be considered. This can make the objective function closer to the actual application scenario and improve the reliability and economy of the system.

[0051] In the optimization process, the minimization of the objective function is not only to reduce electricity costs, but also to comprehensively consider the stability of system operation and the service life of the equipment. Through the combination of mathematical modeling and optimization algorithms, the system can minimize resource waste and improve the overall operating efficiency of the equipment while ensuring power supply.

[0052] In some embodiments, in addition to power consumption and equipment operating costs, an assessment of system stability can also be introduced to ensure that the system can maintain stable operation in the face of large-scale power fluctuations or emergencies. For example, the charging and discharging process of energy storage devices not only affects power distribution, but may also affect the stability of the system, so it needs to be appropriately weighted in the objective function.

[0053] In general, the solution to the optimal control problem relies on the calculus of variations, dynamic programming, or the Hamiltonian function method in optimal control theory. and is constrained, so the Pontryagin maximum principle can be used to solve the optimal control strategy.

[0054] In this embodiment, the mathematical modeling of optimal control is as follows: State equation: The dynamic evolution of the system is described by the following differential equation: ; in: is a state variable, including power demand , generator power output and energy storage device charging and discharging power , is the control signal, including and The amount of adjustment.

[0055] Objective function: In order to minimize the system's electricity consumption cost and equipment operating cost, the optimization objective can be expressed as: ; in: is the instantaneous cost function of the system, which depends on the power consumption, the cost of using the energy storage device, and the loss caused by the power change of the device.

[0056] ; in: is the accompanying variable, indicating the sensitivity to the state variable.

[0057] Optimal control conditions: By solving the Hamiltonian function about The partial derivative of can obtain the optimal control strategy: ; The optimal control signal is obtained: ; in, Represents the optimal regulation strategy of the control variables.

[0058] Adjoint Equation: Adjoint Variable The variation of is described by the adjoint equation: ; This equation is used to calculate the changes in the adjoint variables and, combined with the state equation, can solve the optimal trajectory of the system.

[0059] In some embodiments, the optimal control problem cannot be solved directly, and a numerical optimization method is required. Common numerical solution methods include: Gradient descent method: used to adjust the control signal so that the objective function gradually decreases, suitable for low-dimensional optimization problems.

[0060] Newton iteration method: Combine the second-order derivative information to solve the optimal control equation and improve the convergence speed.

[0061] Dynamic programming: decomposes the problem into multiple sub-problems and is suitable for solving the optimal control of nonlinear systems.

[0062] Trust region method: For large-scale optimal control problems, gradually approach the optimal solution and avoid local minima.

[0063] In one possible implementation, in order to be suitable for numerical solution, the system can use discrete time optimization method to convert the continuous optimal control problem into a discrete time optimal control problem. For example, using finite difference method, the state equation is discretized as: ; in: represents the discrete time step The state variables at is the control signal, is the time step.

[0064] Through discretization optimization, the optimal control problem can be solved using methods such as linear quadratic regulation (LQR) or reinforcement learning (RL) to improve the computational efficiency of the solution.

[0065] In a practical system, solving the optimal control strategy means: During periods of high load, the system will prioritize increasing generator output while reducing the discharge of energy storage devices to ensure that the system can meet power demand.

[0066] During low load periods, the system reduces generator power while increasing the charging of energy storage devices to ensure that energy is stored effectively in preparation for future load peaks.

[0067] In the event of sudden load fluctuations, the system will dynamically adjust the generator power and the response speed of the energy storage device to ensure the stability of the power grid and the safe operation of the equipment.

[0068] In some embodiments, the optimal control strategy can be combined with predictive control (MPC, Model Predictive Control) to calculate the power demand for multiple time periods in the future in advance and optimize the system's scheduling strategy. The key steps of predictive control include: Forecast future electricity demand through time series analysis or machine learning models.

[0069] Calculate the optimal control trajectory within the prediction range so that the system always operates efficiently in the future.

[0070] A rolling optimization method is used to recalculate the optimal control signal at each time step, ensuring that the system can flexibly respond to sudden fluctuations in power demand.

[0071] In general, traditional power system optimization mostly relies on centralized optimization methods. Although this method can obtain the global optimal solution, its computational complexity and execution time are often too long due to the large number of devices and their wide distribution. In order to address this problem, the present invention adopts a distributed optimization framework, that is, decomposing the power system into multiple local optimization problems, each device is independently optimized according to its own status and needs, and then cooperates with other devices through information exchange to finally achieve global optimization.

[0072] In this embodiment, the distributed optimization framework treats each device in the power system (such as generators and energy storage devices) as an independent control unit, and each device performs local optimization based on its own power demand, power output and constraints. The solution to the local optimization problem not only considers the efficiency of a single device, but also the impact of the interaction between devices. This local optimization can not only reduce the computational complexity, but also improve the scalability of the system.

[0073] Local optimization of equipment: The local optimization problem of each equipment mainly includes the control signal and Specifically, the device will and its own operating status (such as the power of the energy storage device, the power limit of the generator, etc.) to adjust the output.

[0074] For example, assuming that the charging power of the energy storage device is Limited by its charging rate , and charging status , then the local optimization problem of energy storage equipment can be expressed as: ; in, represents the cost relationship between electricity demand and energy storage power, It represents the cost relationship between the charging state of the energy storage device and the charging power.

[0075] Information exchange and collaboration mechanism: The devices coordinate through real-time information exchange to ensure the global optimal solution. The content of information exchange includes: the status of each device (such as power demand, generator power, energy storage capacity, etc.), and the control signal calculated by the local optimization algorithm. During the operation of the system, the device adjusts its output strategy according to the status and control signals received from other devices.

[0076] In a specific implementation, information exchange between devices can be completed through wireless communication or wired communication network. The device sends its own state and the calculated local optimal control signal or Send to other devices and make adjustments based on the information received.

[0077] Global goal of collaborative optimization: The goal of the distributed optimization framework is to ensure the realization of the global optimal solution, not just the local optimal solution for each device. When performing global collaborative optimization, the collaborative relationship between devices and load distribution need to be considered. For example, when the energy storage device is fully charged, the system will give priority to meeting the power demand through the discharge of the energy storage device, reducing the power output of the generator, thereby reducing the burden on the generator and extending the service life of the equipment.

[0078] The core of global coordination is to make the control signal of each device and To achieve the optimal ratio of the whole system, the devices must coordinate to balance their respective loads and demands. For example, if the output capacity of a device is too strong or too weak, other devices need to compensate appropriately to ensure that the system does not have local overload or waste.

[0079] Application of optimization algorithms: In the distributed optimization framework, commonly used optimization algorithms include: Gradient descent method: By continuously adjusting the device control signal, the global optimal solution is gradually approached. Each device updates the gradient based on its local information to find the optimal power regulation strategy.

[0080] Lagrange multiplier method: Lagrange multipliers are introduced in the optimization process to deal with the mutual constraints between devices, ensuring that the system is optimized under the constraints and avoiding equipment overload or failure.

[0081] Distributed gradient method: Applicable to situations where the control signals of various devices need to be updated and coordinated in real time. Through information transmission, the device can quickly obtain feedback from other devices and optimize according to the local objective function.

[0082] In some embodiments, information exchange between devices is not only based on fixed time intervals, but the exchange frequency can also be dynamically adjusted according to changes in power demand and feedback from device status, thereby improving the system's response speed and adaptability to load fluctuations.

[0083] Advantages of the distributed optimization framework: By adopting the distributed optimization framework, the optimization problem of the power system no longer requires centralized calculation, which significantly reduces the computational complexity and can respond to changes between devices in real time. Especially when facing a large number of devices, the distributed method can improve the scalability of the system and ensure that the system can flexibly respond to power dispatch of different scales and needs.

[0084] Through the distributed optimization framework, each device can independently perform local optimization based on real-time data and forecast information, and make coordinated adjustments through information exchange. In this process, the system continuously adjusts the power output of each device. and the charging and discharging power of energy storage devices Ensure that the stability and efficiency of power supply are maintained when power demand fluctuates.

[0085] For example, when the demand for electricity suddenly increases during a period of time, the energy storage device can quickly provide additional power, and the generator adjusts its output. The system gradually adjusts the output of the equipment based on information exchange to achieve load balance. The system ultimately achieves optimal power distribution by coordinating the power adjustments between the various devices, avoiding over-regulation or waste of resources in the system.

[0086] In general, power demand and power generation are not static, and they may fluctuate at any time due to various factors. For example, weather changes may cause the output power of power generation equipment to fluctuate; equipment failures or fluctuations in load demand may also affect the stability of the system. In order to cope with these uncertainties, this embodiment uses a Markov process to describe the changing process of power demand and power generation, and dynamically optimizes the power system through a random process model.

[0087] In this embodiment, the random process model is mainly used to describe the power demand and power generation The evolution law in time series. Specifically, the changes in power demand and power generation can be predicted by the state at the previous moment and the random disturbance term. We represent power demand and power generation as Markov processes respectively, and introduce random disturbance terms to simulate the impact of environmental changes on the power system. The basic form of the random process is as follows: Power demand It is a random process, and the demand at the current moment depends not only on the power demand at the previous moment , and is also subject to the random perturbation term The impact is specifically expressed as: ; in, It is a linear transfer function based on historical electricity demand data, which represents the trend of electricity demand over time. It is a random disturbance term, which is usually assumed to conform to a known probability distribution, such as Gaussian distribution, to simulate random fluctuations in electricity demand.

[0088] Likewise, power generation is also affected in a similar way, it depends on the power generation at the previous moment and the random disturbance : ; in, is a linear transfer function based on historical power generation data, It is a random disturbance term related to the state of power generation equipment and the external environment, reflecting the influence of factors such as weather and equipment failure.

[0089] These stochastic process models can effectively describe the volatility of power demand and generation, enabling control strategies to make more reasonable decisions in uncertain environments.

[0090] In this embodiment, the random process model based on Markov process is not only used to predict power demand and power generation, but also provides key data for subsequent optimal control and dynamic scheduling. By predicting future power demand, the control system can take measures in advance to adjust the power output of the generator and optimize the charging and discharging strategy of the energy storage device to cope with future load fluctuations.

[0091] In general, traditional optimal control methods assume that the state of the system is known and certain, but in practical applications, the system is always faced with various uncertainties. By introducing the stochastic process model, the system can better cope with these uncertainties and make more intelligent and adaptive control decisions.

[0092] During the implementation process, the system will predict the power demand in the future and adjust the charging and discharging power of the energy storage equipment and the power output of the generator according to the predicted power demand. For example, when the system predicts that the load demand will increase in the future, it can discharge the energy storage equipment in advance or adjust the output power of the generator to meet the future demand.

[0093] In order to solve the optimal control problem based on stochastic process modeling, this embodiment adopts dynamic programming and Markov decision process (MDP) methods, which can optimize the power system under uncertain environment. Specifically, the system based on Markov process modeling can be optimized in the following ways: Dynamic programming method: By breaking down the problem into multiple stages and solving the optimal control strategy for each stage in turn, the optimal scheduling of the entire system can be achieved. The dynamic programming method can make full use of the system's historical data, predict future demand and supply, and thus achieve accurate scheduling.

[0094] Markov Decision Process (MDP): MDP is an optimization decision framework that is suitable for dealing with decision problems in random processes. By constructing the system state, control signal and reward function, MDP can select the optimal control strategy based on the current state and future predictions. The system calculates the value function , evaluate the optimal control signal at each moment and dynamically adjust the power distribution at each time step.

[0095] In one possible implementation, the system can also combine reinforcement learning methods to update the control strategy in real time by continuously interacting with the environment. Through reinforcement learning, the system can autonomously learn from historical data how to adjust the generator output and energy storage device power under different circumstances to obtain the long-term optimal solution.

[0096] As an option, this embodiment can also consider multi-objective optimization, that is, in addition to power demand and equipment operating costs, other constraints such as system stability and equipment life are introduced. These constraints may affect the selection of control strategies, so on the basis of random process modeling, equipment operating state prediction can be further introduced to improve the accuracy and reliability of optimization.

[0097] For example, when the battery capacity of an energy storage device is approaching its limit, the system can predict the possible risk of insufficient charging or battery damage, and adjust the charging and discharging strategy of the energy storage device to extend the life of the device and reduce the failure rate. By introducing these additional objectives, the optimization algorithm can more comprehensively consider the economy and stability of the device operation.

[0098] Generally speaking, changes in electricity demand and supply are real-time and unpredictable. For example, weather changes may cause fluctuations in the output of power generation equipment, and fluctuations in load demand will affect the dispatch of the power system. In order to make the system operate efficiently in this uncertainty, the control system needs to have real-time response capabilities and dynamically adjust the power dispatch strategy by monitoring the current power demand, power generation and energy storage equipment status.

[0099] In this embodiment, the specific implementation method of real-time feedback is as follows: The system uses sensors and data acquisition equipment to monitor key information such as power demand, generator power output, and energy storage device charging and discharging power in real time. These data are continuously transmitted to the control center and become input signals for the control system. The control system evaluates the current balance of power supply and demand based on the real-time monitoring data.

[0100] By accurately monitoring power demand fluctuations and equipment operation, the control system can respond quickly when needed. For example, when power demand suddenly increases, the system can ensure timely power supply by controlling generator power or adjusting the charging and discharging strategy of energy storage equipment.

[0101] Under the real-time feedback mechanism, the control system adjusts the control signal (such as generator power and energy storage device charging and discharging power To cope with fluctuations in electricity supply and demand.

[0102] When the demand for electricity increases, the system first increases the power output of the generator to ensure sufficient power supply. If the generator power is close to the maximum output limit, it will be supplemented by releasing the power of the energy storage device to avoid excessive system load.

[0103] When electricity demand decreases, the system reduces generator power output and uses excess electricity to charge energy storage devices, ensuring sufficient reserves for possible future fluctuations in electricity demand.

[0104] In some embodiments, the dynamic adjustment process not only relies on the immediate changes in power demand, but also combines forecast data and historical load information to prepare for power dispatch in advance. For example, the control system can pre-adjust the charging and discharging power of the energy storage device based on the forecast of future power demand, thereby avoiding slow system response and enhancing the foresight and flexibility of dispatch.

[0105] The real-time feedback mechanism not only plays a role in the face of fluctuations in power demand, but also responds promptly to equipment failures or abnormal load fluctuations. For example, when a generator fails, the system needs to immediately reduce the power output of the generator and supplement the corresponding power supply through other equipment. This dynamic response capability is the key to the stable operation of the power system.

[0106] In this case, the control system not only relies on real-time load demand data, but also combines the equipment condition monitoring system. When equipment failure is detected, the control system can adjust through feedback signals, reduce reliance on the faulty equipment, and compensate the load of the failed equipment with other normal equipment.

[0107] Through real-time feedback data, the control system can optimize the generator power according to the current power demand, equipment load status and energy storage equipment power. and the charging and discharging power of energy storage devices Specifically, the system is adjusted according to the following goals: Electricity supply and demand balance: When electricity demand suddenly increases, the system gives priority to increasing generator output or extracting electricity from energy storage devices.

[0108] Load balancing and equipment protection: If a device is overloaded, the control system will balance the system load by adjusting the power output of other devices to avoid device overload.

[0109] System stability: The system maintains stable operation of the power system by reasonably adjusting the power output of generators and energy storage devices to avoid frequent power fluctuations or sudden load problems.

[0110] In order to achieve an immediate response to fluctuations in power demand, the present embodiment adopts a PID control algorithm, a fuzzy control algorithm or an optimal control algorithm to adjust the power system. Specifically, by adjusting the control signal, the system can optimize power distribution based on real-time data feedback. For example, when the load increases, the PID control algorithm gradually approaches the optimal power dispatching solution by feedback adjustment of the error between power demand and actual power output.

[0111] Please refer to the attached Figure 2 The present invention can be implemented through a computer program, which is stored in a computer-readable storage medium and can automatically schedule and control the power distribution in the equipment compartment when executed.

[0112] In this embodiment, the automatic power distribution control method of the power system can be implemented by a computer program. The program can be stored in a computer-readable storage medium, such as a hard disk, a solid-state drive, an optical disk, or other storage medium, so as to be executed on a computer. The program may include the following modules: Data acquisition module: This module is responsible for real-time acquisition of key information such as the working status of each device in the power system, load demand, generator power output, etc. Data is collected through sensors and transmitted to the computer system through the communication interface.

[0113] Data processing and prediction module: This module is used to process and analyze the collected real-time data, and to make power demand and power generation forecasts based on historical data and real-time data. The data processing results can be used to adjust the power output of the equipment or provide guidance for system scheduling.

[0114] Optimization algorithm module: This module generates power distribution strategies based on the processed data through optimal control algorithms or distributed optimization algorithms. The optimal control law and constraints (such as generator power limits, energy storage device charging and discharging limits, etc.) will be solved at this stage. This module generates the optimal solution for power dispatch through mathematical modeling.

[0115] Real-time feedback module: This module receives real-time feedback from various devices in the power system and adjusts the power dispatch strategy based on the signals. This module can quickly respond to emergencies such as power demand fluctuations and equipment failures to ensure that the system always maintains efficient operation.

[0116] Control command output module: According to the scheduling plan generated by the optimization algorithm and real-time feedback module, the control command output module transmits commands to each device to adjust the generator power output and the charging and discharging strategy of the energy storage device.

[0117] In a computer system, the program executes the following steps: At startup, the system initializes the data acquisition module and begins to acquire key data from the power system in real time.

[0118] The data processing and forecasting module forecasts electricity demand based on real-time data and makes predictions about electricity demand in the future.

[0119] The optimization algorithm module calculates the best power dispatch plan based on the predicted demand and power generation information, combined with the optimal control law and constraints.

[0120] The real-time feedback module receives feedback signals from devices in the system and dynamically adjusts control signals based on the feedback data to ensure a balance between power supply and demand.

[0121] The control instruction output module outputs the optimal dispatching strategy to each device and adjusts the working status of the power equipment.

[0122] In this way, computer programs can accurately and dynamically dispatch and control the power system, ensuring that the system always operates in the best condition.

[0123] The computer program described in the present invention may be stored in a computer-readable storage medium for execution. Specifically, the program may be stored in the following devices: Hard Drive: Traditional magnetic disk storage media suitable for long-term storage of program code.

[0124] Solid-State Drive: High-speed storage media suitable for quickly loading programs.

[0125] CD-ROM, USB flash drive, mobile storage media: suitable for temporary or convenient program storage and transmission.

[0126] In addition, the program can also be downloaded and updated remotely through network transmission. By loading the program in the computer system, the system can automatically identify and execute the corresponding scheduling control tasks.

[0127] 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. An automatic power distribution control method for a prefabricated equipment compartment, characterized in that: The following steps are involved: Step 1: construct state variables and control signals of the power system in the equipment cabin, wherein the state variables include power demand, generator power output, and energy storage device charge and discharge power, and the control signals include generator power output and energy storage device charge and discharge power; Step 2: Based on the state variables and control signals, an objective function including power consumption cost and equipment operation cost is constructed, and the operation benefit of the power system is quantified through optimal control theory; Step 3: Combine the objective function, solve the optimal control signal under the constraint conditions, and optimize the power distribution strategy; Step 4: Decompose the power distribution strategy based on a distributed optimization framework, perform local optimization on each device independently, and achieve the global optimization of the system through coordination; Step 5: Based on the global optimum, a random process model is further introduced to model the uncertainty of power demand and power generation, and the dynamic scheduling is optimized in combination with random disturbances; Step 6: Dynamically adjust the power distribution strategy based on real-time feedback to cope with power demand fluctuations and equipment status changes.

2. The automatic power distribution control method for a prefabricated equipment compartment according to claim 1, characterized in that: The objective function in step 2 includes: The cost of electricity consumption, expressed as the weighted sum of electricity demand and generator output power; The penalty term of the control signal is expressed as the weighted sum of the charging and discharging power of the energy storage device and the power output of the generator, which is used to avoid equipment overload and power fluctuation.

3. The automatic power distribution control method for a prefabricated equipment compartment according to claim 1, characterized in that: The constraints in step 3 include: The balance between electricity demand and generator output; Charge and discharge power limits for energy storage devices, where the charge and discharge power fluctuates within a predetermined range; The power output limitation of a power generating device, where the power output does not exceed the maximum output capability of the device.

4. The automatic power distribution control method for a prefabricated equipment compartment according to claim 1, characterized in that: In step 4, the distributed optimization framework includes: The control signal of each device is solved through independent local optimization problems to obtain the local optimal control strategy; The devices exchange information and coordinate scheduling through the communication network, gradually approaching the global optimal solution of the system.

5. The automatic power distribution control method for a prefabricated equipment compartment according to claim 1, characterized in that: In the step five, the random process model models the electricity demand and power generation through the Markov process, specifically including: the changes in electricity demand and power generation in each time period are determined by the electricity demand and power generation in the previous time period, and are affected by random disturbances, wherein the random disturbances represent the uncertainty of electricity demand and power generation respectively.

6. The automatic power distribution control method for a prefabricated equipment compartment according to claim 1, characterized in that: The real-time feedback in step six includes: Real-time monitoring of power demand, energy storage device status, and generator output power through sensors; Dynamically adjust control signals based on monitoring data and optimize power distribution strategies to ensure a balance between power supply and demand in the equipment compartment.

7. The automatic power distribution control method for a prefabricated equipment compartment according to claim 1, characterized in that: The optimal control law is based on the Pontryagin maximum principle and solves the optimal control signal so that the objective function is minimized while satisfying the system constraints.

8. The automatic power distribution control method for a prefabricated equipment compartment according to claim 1, characterized in that: The various devices in the equipment cabin include: a generator, an energy storage device and a load device, wherein the generator is used to provide electricity, the energy storage device is used to balance power fluctuations, and the load device is adjusted according to power demand.

9. The automatic power distribution control method for a prefabricated equipment compartment according to claim 1, characterized in that: The power distribution control method is based on a real-time power demand prediction model and adjusts the charging and discharging power of the energy storage device and the output power of the generator through an optimal control strategy, specifically including: Based on the predicted power demand and the status of the energy storage equipment, the power output for each period is determined to optimize the allocation of power resources within the system, ensure the balance of power supply and demand, and maximize the utilization efficiency of power resources.

10. The automatic power distribution control method for a prefabricated equipment cabin according to claim 1, characterized in that: The method can be implemented by a computer program, which is stored in a computer-readable storage medium and can automatically schedule and control power distribution in the equipment compartment when executed.

Images