Campus energy configuration method and system

Abstract

The application discloses a park energy configuration method and system, and belongs to the technical field of park energy dispatching.The method is as follows: power supply adaptation attributes corresponding to various types of power consumption equipment in a park; energy consumption demand of the power consumption equipment is predicted through the power supply adaptation attributes; optimal operation parameters and corresponding power supply connection modes of the power consumption equipment in different time periods are obtained by taking the energy consumption demand and the power supply adaptation attributes as constraint conditions and taking minimization of power supply configuration cost as an optimization target, so that load distribution and power supply switching are performed on a simulation model of the power consumption equipment, and a device energy configuration strategy is obtained; and power supply switching is performed on various power consumption equipment in the park according to real-time power supply conditions based on the device energy configuration strategy. Therefore, by implementing the application, the problem that different power consumption equipment cannot be finely dispatched in the park according to power consumption characteristics of the different power consumption equipment and matched with appropriate power supply types in the prior art can be solved.

Description

Technical Field

[0001] This application belongs to the field of park energy dispatching technology, specifically involving a park energy allocation method and system. Background Technology

[0002] With the advancement of "dual carbon" targets and the development of distributed energy technologies, industrial parks, as concentrated energy consumption units, are gradually introducing green energy sources such as solar and wind power, and supporting energy storage systems to form a hybrid power supply model of "grid power + green energy storage" (grid power refers to the industrial frequency AC power provided by the public power grid, which is more stable than green energy storage; green energy storage is electricity generated by renewable energy and stored through an energy storage system). This model can improve the utilization rate of clean energy and reduce carbon emissions, but it also places higher demands on the scheduling and management of electrical equipment. Currently, the types of electrical equipment in the park are diverse, and their power consumption characteristics vary significantly: some equipment (such as security systems and servers) requires continuous operation and has extremely high requirements for power supply stability; some equipment (such as office air conditioners and lighting) operates intermittently and has flexible power consumption periods; and some equipment (such as large machine tools and charging piles) are impact loads with high instantaneous power consumption at startup, which can easily cause impacts on the power grid. Therefore, how to allocate and schedule energy within the park according to the power consumption characteristics of these devices is an urgent problem to be solved.

[0003] Existing energy dispatching methods in industrial parks often employ a uniform strategy to allocate power resources, failing to adapt power types to the differentiated power consumption characteristics of equipment. This results in low utilization rates of green electricity, excessively high peak-hour loads on the mains power grid, or insufficient equipment operational stability. Furthermore, green electricity is subject to fluctuations due to natural conditions, energy storage systems have limited capacity, and the mains power market experiences peak-valley price differences. Traditional dispatching methods struggle to balance the relationship between power supply reliability, green electricity absorption rate, and operating costs. In addition, power switching processes may involve risks such as momentary power outages and accelerated equipment wear, and current technologies lack simulation verification and dynamic adjustment mechanisms for switching strategies, making it difficult to meet the needs of refined energy management in industrial parks. Summary of the Invention

[0004] This application proposes a method and system for energy allocation in a park, which can solve the problem in the prior art that it is impossible to carry out fine-grained energy scheduling in the park according to the power consumption characteristics of different electrical equipment, and match the appropriate power supply type for the electrical equipment.

[0005] A first aspect of this application provides a method for configuring energy in a park, the method comprising:

[0006] Based on the power consumption characteristics of each electrical device in the park, power adaptation attributes corresponding to each type of electrical device are constructed.

[0007] The energy consumption characteristics of each type of electrical equipment are modeled using the power adaptation attributes to predict the energy consumption requirements of the electrical equipment.

[0008] Using the energy consumption requirements and power supply compatibility attributes as constraints, and minimizing power supply configuration costs as the optimization objective, the optimal operating parameters and corresponding power connection methods of the electrical equipment at different time periods are obtained.

[0009] Based on the optimal operating parameters and the power connection method, the equipment energy configuration strategy is obtained by performing load allocation and power switching on the simulation model of the electrical equipment.

[0010] Based on the equipment energy configuration strategy, power switching is performed on various electrical equipment in the park according to the real-time power supply situation.

[0011] The above scheme first classifies equipment according to its power consumption characteristics, thereby determining the corresponding power supply configuration to ensure normal operation of each piece of equipment, thus obtaining power supply adaptability attributes. Based on these attributes, targeted energy consumption models are constructed for various types of equipment, considering their unique power consumption characteristics and influencing factors. This makes energy consumption prediction more accurate, providing reliable energy consumption data support for subsequent optimized scheduling and further improving the scientific and economical nature of park energy management. Furthermore, the energy configuration process comprehensively considers the costs of various power supply configurations, achieving economic efficiency and obtaining optimal operating parameters and corresponding power connection methods that better meet park management objectives, thus achieving efficient park energy management. A simulation model is built to provide a reliable virtual environment for simulation scheduling, laying the foundation for simulating real-time energy consumption changes, load distribution adjustments, and power switching. Moreover, the simulation process does not affect the operation of equipment in the real scenario, effectively preventing scheduling failures from impacting the overall power consumption of the park. Finally, based on the equipment energy configuration strategy, power switching is performed on various equipment in the park under real-world conditions, achieving reasonable power scheduling and refined management of the park, and improving the operational stability of various equipment.

[0012] In one possible implementation of the first aspect, power adaptation attributes corresponding to each type of electrical equipment are constructed based on the power consumption characteristics of each piece of equipment within the park, specifically as follows:

[0013] Based on the collected energy consumption-related parameters of each electrical device, the energy consumption influencing factors of the electrical device are extracted;

[0014] The historical energy consumption data of the electrical equipment is processed by a long short-term memory network to capture the energy consumption change characteristics of the electrical equipment.

[0015] Based on the energy consumption influencing factors and the energy consumption change characteristics, each type of electrical equipment is classified and the corresponding power consumption characteristics are determined.

[0016] Based on the aforementioned power consumption characteristics, power supply configurations are performed for each type of electrical equipment to construct the power supply adaptation attributes.

[0017] The above scheme effectively captures long-term dependencies in historical energy consumption data by processing it through a long short-term memory network, resulting in energy consumption change characteristics that better reflect the actual power consumption characteristics of the equipment. By integrating the energy consumption influencing factors and the energy consumption change characteristics, the advantages of different data are combined, thus improving the accuracy of classification.

[0018] In one possible implementation of the first aspect, the energy consumption characteristics of each type of electrical equipment are modeled using the power adaptation attribute to predict the energy consumption demand of the electrical equipment, specifically as follows:

[0019] Based on the power supply compatibility attributes, the differential energy consumption characteristics of each type of electrical equipment are extracted by identifying the differences in their operating modes; wherein, the types of electrical equipment include continuously operating equipment, intermittently operating equipment, and equipment subject to impact loads; and the operating modes include operating time and equipment load size.

[0020] Based on the aforementioned differentiated energy consumption characteristics, corresponding energy consumption models are constructed for each type of electrical equipment;

[0021] The collected power supply operating characteristics, equipment operating power and operating time are input into the energy consumption model to predict energy consumption and obtain the energy consumption requirements of each electrical device.

[0022] The above-mentioned solution constructs targeted energy consumption models for different types of equipment, taking into account the unique power consumption characteristics and influencing factors of each type of equipment, thus making energy consumption prediction more accurate. Furthermore, it incorporates the operating characteristics of the power supply, which better ensures the accuracy of energy consumption prediction under stable power supply conditions, providing reliable energy consumption data support for subsequent optimized scheduling, and further improving the scientific and economical nature of energy management in the park.

[0023] In one possible implementation of the first aspect, based on the differentiated energy consumption characteristics, a corresponding energy consumption model is constructed for each type of electrical equipment, specifically as follows:

[0024] Based on the rated power of the continuously operating equipment, the predicted operating time, the mains voltage fluctuation deviation, the mains frequency fluctuation deviation, and the remaining capacity ratio of green energy storage, an energy consumption model for the continuously operating equipment is constructed.

[0025] Based on the relationship between the operating power of the intermittently operating equipment in each time period, the time interval, the total number of time periods, the actual power generation of green energy storage and the maximum power generation in each time period, and the peak-valley coefficient of the grid electricity price, an energy consumption model for the intermittently operating equipment is constructed.

[0026] Based on the relationship between the daily number of starts, rated power, single stable operation duration, start-up impact duration, and the instantaneous and maximum instantaneous carrying capacity of the mains power, an energy consumption model for the impact load equipment is constructed.

[0027] The above scheme incorporates the effects of mains voltage and frequency fluctuations and the remaining capacity of green energy storage when constructing the energy consumption model of continuously operating equipment, which can better ensure the accuracy of energy consumption prediction under stable power supply. When constructing the energy consumption model of intermittently operating equipment, it combines the green energy supply situation and the peak and valley electricity price of the mains, which is conducive to prioritizing the use of green energy and reducing electricity costs. When constructing the energy consumption model of equipment with impulsive loads, it considers the start-up impact energy consumption and the mains power carrying capacity, which can avoid abnormal energy consumption caused by excessive impact on the power grid due to equipment start-up.

[0028] In one possible implementation of the first aspect, the optimal operating parameters and corresponding power connection methods of the electrical equipment at different time periods are obtained, with the energy consumption demand and the power supply adaptability attributes as constraints and minimizing the power supply configuration cost as the optimization objective. Specifically:

[0029] We construct a power configuration cost function by weighted summation of total electricity cost, total power switching cost, and total equipment operation and maintenance and loss cost.

[0030] Based on the power supply compatibility attributes and energy consumption requirements, the power supply duration ratio limit for each power supply corresponding to each type of electrical equipment is set to obtain the constraint conditions.

[0031] The power consumption parameters of the electrical equipment and the corresponding power supply are combined to generate several sets of optimized parameter pairs;

[0032] Based on the constraints, with the goal of minimizing the power supply configuration cost function, the optimization parameter pair is iteratively calculated, and the optimal optimization parameter pair is output when the preset iteration stopping condition is met.

[0033] Based on the optimal parameter pair, the optimal operating parameters of the electrical equipment and the corresponding power connection methods are determined at different time periods.

[0034] The above scheme comprehensively considers total electricity costs, total power switching costs, and total equipment operation and maintenance and loss costs, making the optimization results more comprehensive and able to balance the interests of multiple parties. Moreover, by calculating the optimal parameter pairs through constraints and power configuration cost functions, it can find the most economical and efficient equipment operating parameters and power connection methods under the premise of meeting energy consumption requirements and power adaptation attribute constraints, further improving the optimization level of energy dispatching in the park.

[0035] In one possible implementation of the first aspect, the optimization parameter pair is iteratively calculated, specifically as follows:

[0036] Calculate the power configuration cost value of each of the optimized parameter pairs, and select the optimized parameter pairs by means of a roulette wheel selection method to obtain the selected parameter pairs; wherein, the smaller the power configuration cost value, the greater the probability that the optimized parameter pair is selected;

[0037] Randomly swap the elements in each selected parameter pair to generate a new optimized parameter pair;

[0038] Calculate the power configuration cost value of the new optimized parameter pair, and select the new optimized parameter pair again until the preset iteration stopping condition is met.

[0039] In one possible implementation of the first aspect, based on the optimal operating parameters and the power connection method, a power configuration strategy for the equipment is obtained by performing load allocation and power switching on a simulation model of the electrical equipment, specifically as follows:

[0040] Based on the physical parameters, electrical characteristic models, and operating states of the electrical equipment, a simulation model of each of the electrical equipment is constructed.

[0041] Based on the pre-set mains power supply model, green energy storage power supply model and switching circuit model, a digital twin of the power supply system is constructed;

[0042] By combining the aforementioned simulation model and the digital twin of the power supply system, a collaborative simulation platform is built.

[0043] Based on the optimal operating parameters and the power connection method, a corresponding energy configuration instruction is generated;

[0044] The energy configuration command is input into the collaborative simulation platform to simulate equipment operation. During the simulation process, the operating status parameters output by each simulation model, the load distribution curve of the power supply system digital twin, and the power switching response waveform are recorded to obtain simulation data.

[0045] The simulation data is filtered according to the preset abnormal situation identification criteria, and the equipment energy configuration strategy is output.

[0046] The above solution, by building a collaborative simulation platform that includes simulation models of electrical equipment and power supply systems, can accurately simulate the overall response of the power supply system under various operating conditions, providing more comprehensive and accurate simulation results for power dispatching and management in the park. Furthermore, simulation-based dispatching helps to detect anomalies in advance, avoiding losses caused by improper dispatching in real-world scenarios.

[0047] In one possible implementation of the first aspect, the simulation data is filtered according to a preset anomaly identification standard, and a device energy configuration strategy is output, specifically as follows:

[0048] The simulation data is judged to be abnormal according to the abnormal situation identification standard. If an abnormality is found, the energy configuration command is adjusted. The abnormal situation identification standard is used to detect equipment operating temperature, abnormal power supply interruption, abnormal fluctuation of mains voltage, and abnormal fluctuation of mains frequency.

[0049] If no anomalies are found, the power supply switching conditions of the electrical equipment are configured based on the simulation data, and a corresponding equipment energy configuration strategy is generated.

[0050] In one possible implementation of the first aspect, based on the equipment energy configuration strategy, power switching is performed on various electrical devices within the park according to the real-time power supply situation, specifically as follows:

[0051] The system monitors the real-time power supply status of each electrical device in the park and triggers a dynamic switching mechanism when the power supply switching conditions are met. The power supply switching conditions are that the capacity of green energy storage is lower than the first threshold, the mains electricity price enters the preset peak period, or the load of the electrical device exceeds the second threshold.

[0052] Based on the dynamic switching mechanism, power switching is performed on electrical equipment that meets the power supply switching conditions through the equipment energy configuration strategy.

[0053] The above solution, through real-time monitoring and dynamic switching mechanisms, can respond to emergencies and ensure the stability and economy of the park's power supply.

[0054] The second aspect of this application provides a park energy configuration system, the system comprising: an attribute configuration module, an energy consumption demand prediction module, an optimal operation mode search module, an energy configuration strategy construction module, and a power switching module;

[0055] Among them, the attribute configuration module is used to construct the power adaptation attributes corresponding to each type of electrical equipment based on the power consumption characteristics of each electrical equipment in the park;

[0056] The energy consumption demand prediction module is used to model the energy consumption characteristics of each type of electrical equipment based on the power supply adaptation attributes, and predict the energy consumption demand of the electrical equipment.

[0057] The optimal operation mode search module is used to obtain the optimal operating parameters and corresponding power connection methods of the electrical equipment at different time periods, with the energy consumption requirements and power supply adaptability attributes as constraints and the goal of minimizing power supply configuration costs.

[0058] The energy configuration strategy construction module is used to obtain the equipment energy configuration strategy based on the optimal operating parameters and the power connection method by performing load allocation and power switching on the simulation model of the electrical equipment;

[0059] The power switching module is used to switch the power supply of various electrical devices in the park based on the equipment energy configuration strategy and the real-time power supply situation. Attached Figure Description

[0060] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0061] Figure 1 This is a schematic diagram illustrating the specific process of a park energy allocation method according to an embodiment of this application;

[0062] Figure 2 This is a structural diagram of a park energy configuration system provided in one embodiment of this application. Detailed Implementation

[0063] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0064] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0065] First Embodiment

[0066] As a concentrated energy consumption unit, the park is gradually introducing green energy sources such as solar and wind power, and is equipped with energy storage systems to form a hybrid power supply mode of "grid power + green energy storage". Grid power and green energy storage are two different power sources. Grid power refers to the industrial frequency AC power provided by the public power grid, while green energy storage refers to the electricity generated by renewable energy sources such as solar and wind power and stored through an energy storage system. Grid power is relatively more stable, and green energy storage serves as a backup to ensure continued operation of equipment when grid power fails. Therefore, considering the significant differences in the power consumption characteristics of various electrical devices within the park, configuring power supply and setting relevant power parameters for different time periods for each device can reduce electricity costs and equipment losses while ensuring normal equipment operation, thus ensuring the stability and economy of the park's power supply and achieving refined energy management.

[0067] like Figure 1 As shown, to address the problem in existing technologies that cannot perform refined energy scheduling within a park based on the power consumption characteristics of different electrical devices, and to match appropriate power types to electrical devices, the first embodiment of this application provides a detailed flowchart of a park energy configuration method. This embodiment's park energy configuration method includes steps S1 to S5, detailed below:

[0068] Step S1: Based on the power consumption characteristics of each type of electrical equipment in the park, construct the power adaptation attributes corresponding to each type of electrical equipment.

[0069] First, a comprehensive survey and data collection of all electrical equipment within the park is required. This includes collecting data such as operating time and power changes through smart meters installed on the equipment, thus obtaining energy consumption parameters and historical energy consumption data for each device. Historical energy consumption data includes hourly power consumption, daily operating time, and power fluctuation data; energy consumption parameters include equipment type, ambient temperature, and usage frequency.

[0070] Then, a convolutional neural network (CNN) is used to extract features from energy-related parameters to obtain energy consumption impact factors for electrical equipment. The CNN includes an input layer, two convolutional layers, two pooling layers, and an output layer. The first convolutional layer uses 32 3×3 kernels, the second uses 64 3×3 kernels, and all pooling layers use 2×2 max pooling. The first convolutional layer uses 32 3×3 kernels to convolve the input data, extracting low-level features such as simple features of equipment type and environmental temperature variations. Then, a 2×2 max pooling layer reduces the dimensionality of the convolutional features, retaining important features and reducing the amount of data. The second convolutional layer uses 64 3×3 kernels to further extract high-level features, such as combinations of energy consumption features for different equipment types under specific environmental temperatures. After pooling, the output layer outputs the energy consumption impact factors, which reflect the degree of influence of different parameters on energy consumption.

[0071] Historical energy consumption data is processed using a Long Short-Term Memory (LSTM) network to capture long-term dependencies and obtain the energy consumption variation characteristics of electrical equipment. The LSM network includes an input gate, a forget gate, and an output gate, with 128 hidden layer nodes and a time step of 24, and is trained using the Adam optimizer. The 128 hidden layer nodes allow for the processing of relatively complex historical energy consumption data, while the 24-hour time step corresponds to 24 hours of daily energy consumption data, facilitating the capture of intraday energy consumption variation patterns. Training with the Adam optimizer adaptively adjusts the learning rate, improving training efficiency and model accuracy, thereby better capturing long-term dependencies in historical energy consumption data, such as the energy consumption trends and periodic patterns of equipment over different time periods.

[0072] The energy consumption influencing factors and energy consumption variation features are fused and input into a softmax classifier. The resulting classification of each electrical device is output, and the corresponding power consumption characteristics for each device type are determined. The fused features combine the advantages of different features, improving classification accuracy. The softmax classifier can map the fused features to different class probabilities, resulting in accurate device classification.

[0073] Based on the aforementioned power consumption characteristics, a reasonable power supply configuration is performed for each type of electrical equipment, resulting in power supply compatibility attributes for each equipment type. These power supply compatibility attributes provide data support for subsequent energy consumption model construction and energy optimization scheduling, further enhancing the scientific rigor and rationality of electrical equipment scheduling within the park.

[0074] Optionally, in this application embodiment, electrical equipment is categorized into continuously operating equipment, intermittently operating equipment, and equipment subject to impact loads. Continuously operating equipment, such as security monitoring systems in industrial parks and data center servers, requires uninterrupted operation throughout the year. A power outage exceeding a certain time would cause severe losses. Therefore, its corresponding power adaptation attribute is "mains power priority, green energy storage backup." Intermittently operating equipment, such as air conditioners and printers in office areas, has clearly defined off-peak periods during which power switching can be performed. Therefore, its corresponding power adaptation attribute is "green energy storage priority, mains power supplement," prioritizing the use of green energy and reducing dependence on mains power and electricity costs. Equipment subject to impact loads, such as large industrial machine tools and fast charging piles, has extremely high startup power, which green energy storage cannot withstand. Therefore, its power adaptation attribute is "forced mains power adaptation."

[0075] Step S2: Model the energy consumption characteristics of each type of electrical equipment using the power adaptation attributes, and predict the energy consumption requirements of the electrical equipment.

[0076] This application embodiment constructs corresponding energy consumption models for different types of electrical equipment to predict the energy consumption requirements of each type of electrical equipment. First, based on the power supply adaptation attributes, the differential energy consumption characteristics of each type of electrical equipment are extracted by identifying the differences in their operating modes.

[0077] For example, for continuously operating equipment, due to its high requirements for mains power stability, the energy consumption model will focus on the fluctuations in mains voltage and frequency, as well as the remaining capacity of green energy storage. For instance, when the mains voltage fluctuations exceed a certain range, green energy storage needs to be replenished in a timely manner to ensure stable energy consumption. For intermittently operating equipment, because "green energy storage is prioritized, with mains power as a supplement," the model will focus on the amount of green electricity generated. If solar power generation is sufficient on a certain day, these types of equipment will be prioritized to use green electricity. At the same time, combined with the peak and off-peak electricity prices, if green electricity is insufficient during off-peak hours, mains power will be used to supplement the supply to reduce costs. The model construction for equipment with impulsive loads mainly focuses on the instantaneous carrying capacity of the mains power to ensure that it does not cause excessive impact on the mains power during startup.

[0078] Based on the obtained differentiated energy consumption characteristics, corresponding energy consumption models are constructed for each type of electrical equipment.

[0079] Based on the rated power of the continuously operating equipment, the predicted operating time, the mains voltage fluctuation deviation, the mains frequency fluctuation deviation, and the remaining capacity ratio of green energy storage, an energy consumption model for the continuously operating equipment is constructed.

[0080] The energy consumption model of the continuously operating equipment is specifically expressed as follows:

[0081] ;

[0082] In the formula, E c Predicted energy consumption for continuously operating equipment. P c0 Rated power of the equipment T To predict runtime, The deviation of mains voltage is expressed as % . This represents the mains frequency fluctuation deviation, expressed in % %. k v and k f These are the voltage and frequency fluctuation influence coefficients, respectively, with values ​​ranging from 0.005 to 0.01. s res The percentage of remaining green energy storage capacity is expressed as a percentage (%). k s This is the energy storage capacity influence coefficient, with a value range of 0.002-0.005.

[0083] Among these factors, significant fluctuations in mains voltage reduce equipment operating efficiency and increase energy consumption. This impact can be quantified using voltage and frequency fluctuation influence coefficients. The proportion of remaining green energy storage capacity also affects energy consumption. When sufficient remaining green energy storage capacity is available, it can replenish the mains supply promptly when the mains power is unstable, reducing energy consumption fluctuations. Furthermore, the subsequent index parameters indicate that the higher the remaining green energy storage capacity, the larger this value, and the more significant the energy consumption correction effect.

[0084] Based on the relationship between the operating power of the intermittently operating equipment in each time period, the time interval, the total number of time periods, the actual power generation of green energy storage and the maximum power generation in each time period, and the peak-valley coefficient of the grid electricity price, an energy consumption model for the intermittently operating equipment is constructed.

[0085] The energy consumption model of the intermittently operating equipment is specifically expressed as follows:

[0086] ;

[0087] In the formula, E i Predicted energy consumption for intermittently operating equipment. For the equipment in t Operating power during the time period The time interval is in hours; n This represents the total number of time periods. G t for t Actual power generation from green energy storage during specific time periods; G max for t The maximum power generation of green energy storage during a given period. k g The green electricity supply impact coefficient ranges from 0.03 to 0.08. D t for t The peak-valley coefficient for the municipal electricity price is set at 1.2 during peak hours, 1.0 during normal hours, and 0.8 during off-peak hours. k p This is the electricity price impact coefficient, with a value range of 0.01-0.03.

[0088] The energy consumption model for the intermittently operating equipment is calculated over time periods. The relationship between the actual power generation of the green energy storage and the maximum power generation in each time period characterizes the power supply situation of the green energy storage. If the green energy storage supply is insufficient, it may be necessary to use the more expensive grid power to supplement it. The grid electricity price peak-valley coefficient reflects the price differences in different time periods; higher peak-hour prices will cause the predicted energy consumption value to increase.

[0089] Based on the relationship between the daily number of starts, rated power, single stable operation duration, start-up impact duration, and the instantaneous and maximum instantaneous carrying capacity of the mains power, an energy consumption model for the impact load equipment is constructed.

[0090] The energy consumption model of the impact load equipment is specifically expressed as follows:

[0091] ;

[0092] In the formula, E S Predicted energy consumption for equipment subjected to impact loads. N s The number of times the equipment is started per day. P s0 Rated power of the equipment T s For a single stable run, T p To initiate the impact duration, k s The impact power coefficient has a value ranging from 2 to 4. C grid For the instantaneous carrying capacity of the mains power; C max To the maximum instantaneous carrying capacity of the mains power, k c The value is the influence coefficient of the mains power load, ranging from 0.02 to 0.05.

[0093] Furthermore, the rated power of the equipment mentioned above refers to the power of the equipment under normal operating conditions, which is an inherent parameter of the equipment. The mains voltage fluctuation deviation is the percentage of the difference between the actual voltage and the rated voltage relative to the rated voltage, reflecting the stability of the mains voltage. The maximum generateable capacity of green energy storage is the maximum amount of electricity that a green energy storage system can produce under specific conditions, and it is affected by factors such as weather and season.

[0094] Finally, the collected power supply operating characteristics, equipment operating power and operating time are input into the energy consumption model corresponding to the electrical equipment to predict energy consumption and obtain the energy consumption demand of each electrical equipment.

[0095] Therefore, by considering the differentiated energy consumption characteristics and related influencing factors of different equipment, different energy consumption models are constructed to make energy consumption prediction more accurate. The model for continuously operating equipment incorporates the impact of mains voltage and frequency fluctuations, as well as the remaining capacity of green energy storage, which better ensures the accuracy of energy consumption prediction under stable power supply. The model for intermittently operating equipment combines green energy supply conditions and peak-valley electricity prices, which is conducive to prioritizing the use of green energy and reducing electricity costs. The model for equipment with impulsive loads considers the startup impact energy consumption and mains power carrying capacity, which can avoid abnormal energy consumption caused by excessive impact on the power grid due to equipment startup.

[0096] Step S3: Using the energy consumption requirements and power supply compatibility attributes as constraints, and minimizing power supply configuration costs as the optimization objective, the optimal operating parameters and corresponding power connection methods of the electrical equipment at different time periods are obtained.

[0097] This application embodiment uses a genetic algorithm to calculate the optimal operating parameters and corresponding power connection methods for electrical equipment at different time periods. The genetic algorithm includes a fitness function (here referred to as the power configuration cost function) and constraints.

[0098] The genetic algorithm is executed by first initializing the population so that each individual in the population corresponds to a combination to be searched; then, a selection operator is used to select individuals in the population; a crossover operator is used to crossover the selected individuals, and the crossover operator is associated with a preset crossover probability; a mutation operator is used to mutate the individuals that have undergone the crossover operation, and the mutation operator is associated with a preset mutation probability; iterative calculations are performed, and the iteration stops when the number of iterations reaches a preset number or the change in the fitness function value after a preset number of consecutive iterations is less than a preset threshold, and the optimal combination obtained is output.

[0099] This application embodiment uses total electricity cost, total power switching cost, and total equipment operation and maintenance and loss cost as variables. The power configuration cost function is constructed by weighting and summing these variables using preset weighting coefficients and taking the minimum value. Specifically, total electricity cost is the sum of the costs of mains electricity and green electricity; total power switching cost is the product of the number of power switching operations and the cost per switching operation; and total equipment operation and maintenance and loss cost is the sum of equipment operation and maintenance costs and switching loss costs. All weighting coefficients are positive numbers and their sum is 1.

[0100] Furthermore, assume that the amount of mains electricity used in the park during a certain period is E. city (Unit: kWh), the unit price of municipal electricity is C city (Unit: Yuan / kWh), the amount of green electricity used is E green (Unit: kWh), the cost of green electricity is C. green (Unit: Yuan / kWh, including costs of green electricity production and storage), then the total electricity cost C elec =Ecity ×C city +E green ×C green If the cost of a single power switch (such as switching from mains power to green electricity, or vice versa) is C switch_single (Costs include switching circuit operation, relay lifespan loss, etc.), with N switching operations. switch The total power switching cost C switch =N switch ×C switch_single Total equipment maintenance and depreciation costs C maintain This includes the portion of fixed costs such as routine equipment inspections and fault repairs that are spread over this period, as well as additional equipment losses caused by voltage fluctuations and current surges during power switching (such as shortened capacitor lifespan and component overheating damage).

[0101] Therefore, the expression for the power supply configuration cost function is:

[0102] ;

[0103] In the formula, C elec For total electricity costs, C switch Total power switching cost, C maintain This refers to the total cost of equipment operation, maintenance, and wear and tear. , , These are the weighting coefficients; The green electricity consumption deviation coefficient is set to |actual green electricity consumption - planned green electricity consumption| / planned green electricity consumption. This is the power switching frequency coefficient, which is the ratio of the actual number of switching times to the preset maximum allowed number of switching times. The equipment load fluctuation coefficient is set to max(|real-time power of equipment - rated power of equipment| / rated power of equipment); , , The correction factor is used to amplify the impact of green energy consumption deviation, high-frequency switching, and severe load fluctuations on the total cost, with a value range of 0.5-2.0.

[0104] For example, in a certain industrial park with ample sunlight during the day, the cost of green electricity is 0.3 yuan / kWh, and the peak cost of mains electricity is 0.8 yuan / kWh. If an intermittently operating piece of equipment uses 100 kWh of green electricity and 50 kWh of mains electricity during the day, its total electricity cost for that period would be 50 × 0.8 + 100 × 0.3 = 40 + 30 = 70 yuan. The cost of switching power once within the park is approximately 5 yuan. If a piece of equipment switches power 3 times a day, the total power switching cost would be 3 × 5 = 15 yuan. Assuming the daily maintenance cost of a piece of equipment is averaged at 2 yuan per hour, and the switching loss cost for a certain period is calculated to be 3 yuan, and the equipment runs for 2 hours, the total equipment maintenance and loss cost would be 2 × 2 + 3 = 7 yuan.

[0105] In addition, the weighting coefficients can be set according to the park's emphasis on costs.

[0106] Based on the power supply adaptation attributes and energy consumption requirements, the power supply duration ratio limit for each power supply corresponding to each type of electrical equipment is set to obtain the constraint conditions.

[0107] Optionally, in this embodiment of the application, the constraints include that the proportion of mains power supply time for continuously operating equipment is not less than a first preset proportion, the proportion of green energy storage power supply time for intermittently operating equipment is not less than a second preset proportion, and the impact load equipment is powered only by mains power.

[0108] In other embodiments, taking continuously operating equipment such as security monitoring systems within the park as an example, the first preset ratio is set to 80%. This is because such systems require extremely high power supply stability; the mains power supply time must be at least 80% to ensure basic operational needs and prevent monitoring interruptions due to occasional instability of the green energy storage power source (such as insufficient energy storage or sudden changes in green energy generation). For intermittently operating equipment such as office computers and printers in the park, the second preset ratio is set to 60%. Their usage time is relatively flexible, and to better utilize green electricity, the green energy storage power supply time must be at least 60%. For example, if an office computer is used for 4 hours a day, then the green energy supply time must be at least 4 × 60% = 2.4 hours. This can meet equipment usage needs while improving green energy utilization and reducing the pressure on mains power during peak hours. For impact load equipment such as large industrial stamping presses in the park, the starting current is extremely high, and the green energy storage power source cannot withstand the impact. Therefore, it is powered only by mains power. From the physical connection and control logic, its power input is limited to mains power to ensure equipment startup and operation safety and to avoid damage to the green energy storage system.

[0109] Furthermore, in this embodiment, the population size is set to 50, and each individual in the population is a combination of "electrical parameters - power supply type", called an optimized parameter pair. The optimized parameter pair is obtained by combining the electrical parameters of the electrical equipment with the corresponding power supply, and is related to the rated parameters of the equipment, power supply capacity, etc. For example, for multiple devices in the park, one individual can be represented as device A using mains power from 8:00 to 9:00 with an operating power of 10kW; another individual can be represented as device B using green electricity from 9:00 to 10:00 with an operating power of 8kW, and so on.

[0110] Based on the constraints, with the goal of minimizing the power supply configuration cost function, the optimization parameter pair is iteratively calculated, and the optimal optimization parameter pair is output when the preset iteration stopping condition is met.

[0111] First, the power configuration cost value of each optimized parameter pair is calculated using a power configuration cost function. Based on the power configuration cost value, the optimized parameter pair is selected using a roulette wheel selection method. Since a smaller power configuration cost value increases the probability of the corresponding optimized parameter pair being selected, it is more likely to select a lower-cost optimized parameter pair, thus achieving economical scheduling of energy in the park. After obtaining the selected parameter pair in one search, the elements in each selected parameter pair are randomly swapped based on a preset crossover probability to generate a new optimized parameter pair. Then, the new optimized parameter pair is used for the next iteration selection until a preset iteration stopping condition is met, at which point the iteration stops, and the optimal optimized parameter pair is output.

[0112] For example, individuals A (device A at 8-9 pm AC power, device B at 9-10 pm green power) and B (device A at 9-10 pm green power, device B at 8-9 pm AC power) are randomly swapped to obtain new individuals C (device A at 8-9 pm AC power, device B at 8-9 pm AC power) and D (device A at 9-10 pm green power, device B at 9-10 pm green power). This method is similar to gene recombination and can produce new combinations.

[0113] As an improvement to the above scheme, this application also introduces a mutation operator operation. The new optimization parameter pairs are modified according to a preset mutation probability, similar to gene mutation, introducing new parameter pairs to avoid the algorithm converging prematurely and getting trapped in local optima. For example, in individual E, device C10-11 uses green electricity with an operating power of 5kW; after mutation, it may become device C10-11 using mains electricity with an operating power of 4.5kW.

[0114] Optionally, the iteration stopping condition can be set to stop the iteration when the number of iterations reaches 100, or to stop the iteration when the change in power configuration cost value is less than 0.1 for 10 consecutive iterations.

[0115] Based on the optimal parameter pair, the optimal operating parameters of the electrical equipment and the corresponding power connection methods are determined at different time periods.

[0116] Therefore, this application embodiment performs a global optimization search on the parameter pairs of "power consumption parameters - power type" through set constraints and power configuration cost functions. First, it clarifies different cost calculation methods and weights to ensure that the scheduling scheme takes into account costs from multiple aspects such as power consumption, switching, and operation and maintenance. Then, based on the power supply adaptability attributes of the equipment, it sets reasonable constraints for equipment with continuous operation, intermittent operation, and impact loads to ensure equipment operation safety and green energy consumption goals. Finally, through population initialization, selection, crossover, mutation, and iterative operations of a genetic algorithm, it efficiently finds the optimal scheduling combination.

[0117] Step S4: Based on the optimal operating parameters and the power connection method, load allocation and power switching are performed on the simulation model of the electrical equipment to obtain the equipment energy configuration strategy.

[0118] Based on the physical parameters, electrical characteristic models, and operating states of the electrical equipment, a simulation model corresponding to the equipment is constructed. The physical parameters include the equipment's rated power and starting current coefficient, while the electrical characteristic model relates the power supply type to the equipment's energy conversion efficiency.

[0119] By linking the pre-defined mains power supply model, green energy storage power supply model, and switching circuit model through a data interface, a digital twin of the power supply system is constructed to simulate the overall response characteristics of the power supply system under different operating conditions. Specifically, the mains power supply model is associated with grid voltage stability and frequency fluctuation characteristics, the green energy storage power supply model is associated with energy storage capacity decay curves and charge / discharge efficiency characteristics, and the switching circuit model includes switching response time and contact resistance parameters.

[0120] Specifically, the mains power supply model includes a grid topology module, a voltage regulation module, and a frequency response module. The grid topology module is associated with the transmission line impedance parameters of the park's access point. The voltage regulation module maps the dynamic adjustment curve of the mains voltage as the load changes. The frequency response module simulates the transient fluctuation characteristics of the mains frequency during impulsive load access. The green energy storage power supply model includes a green energy generation prediction module, an energy storage battery characteristics module, and a charge / discharge management module. The green energy generation prediction module outputs predicted power generation values ​​based on historical meteorological data and real-time weather parameters. The energy storage battery characteristics module is associated with the battery capacity decay coefficient with the number of cycles and the charge / discharge efficiency curves at different temperatures. The charge / discharge management module sets charge / discharge thresholds and power limit parameters. The switching circuit model includes a switching device characteristics module, a commutation logic module, and a fault diagnosis module. The switching device characteristics module maps the device's on-state voltage drop and off-state time parameters. The commutation logic module presets timing control rules for different power switching scenarios. The fault diagnosis module is associated with overvoltage and overcurrent detection thresholds during the switching process.

[0121] A collaborative simulation platform is built by combining the simulation model and the digital twin of the power supply system.

[0122] The obtained optimal operating parameters and power connection methods are converted into corresponding energy configuration commands, which are then input into a collaborative simulation platform for synchronous simulation. During the simulation, real-time energy consumption changes of various electrical devices operating according to optimal parameters, the dynamic adjustment process of the load distribution ratio between mains power and green energy storage power, voltage sag amplitude, current surge peak, and switching completion time during power switching are collected. Simultaneously, the operating status parameters of each device's simulation model, the load distribution curve of the power supply system, and the power switching response waveform are also recorded. The load distribution curve visually displays the load ratio borne by mains power and green energy at different times; the power switching response waveform records the changes in voltage and current during the switching process, such as a slight voltage drop at the moment of switching followed by a return to stability.

[0123] Additionally, when setting the simulation time step, if the device's minimum response time is 1 second, the time step can be set to 0.1 seconds to ensure simulation accuracy. The simulation period covers a complete peak-valley electricity consumption cycle, such as 24 hours, to comprehensively simulate electricity consumption at different times.

[0124] The collaborative simulation platform is a software platform that enables data interaction and collaborative operation between multiple simulation models. It allows virtual models of equipment and power supply systems to collaboratively simulate the power consumption process of the entire park, comprehensively reflecting the mutual influence between the two. Moreover, the platform can simulate various power consumption scenarios, synchronously simulating real-time energy consumption changes, load distribution adjustments, and power switching. If problems occur, they will not affect the operation of equipment in the real scenario, effectively preventing scheduling failures from affecting the overall power consumption of the park.

[0125] After obtaining the simulation data output by the collaborative simulation platform, the simulation data is filtered according to the preset abnormal situation identification criteria to obtain the equipment energy configuration strategy that can ensure the stable operation of the park equipment.

[0126] Specifically, the anomaly identification criteria are used to detect equipment operating temperature, abnormal power supply interruptions, abnormal fluctuations in mains voltage, and abnormal fluctuations in mains frequency. Therefore, the anomaly identification criteria are used to determine whether there are anomalies in the simulation data. If anomalies are found, it indicates that there is abnormal operation of the equipment / power supply system during the simulation. Therefore, the operating parameters and power connection methods corresponding to the simulation data cannot be applied in practice, and the energy configuration instructions need to be adjusted for another simulation. If no anomalies are found, the power supply switching conditions of the electrical equipment can be configured based on the simulation data to generate a corresponding equipment energy configuration strategy.

[0127] Step S5: Based on the equipment energy configuration strategy, switch the power supply for each electrical device in the park according to the real-time power supply situation.

[0128] In real-world application scenarios, the system monitors the real-time power supply status of various electrical devices within the park. When the power supply switching conditions are met, a dynamic switching mechanism is triggered. Power switching can be performed on electrical devices that meet the power supply switching conditions through equipment energy configuration strategies, thereby realizing energy configuration and scheduling within the park.

[0129] If any of the following conditions are met: the capacity of green energy storage is lower than the first threshold, the grid electricity price enters the preset peak period, or the load of electrical equipment exceeds the second threshold, dynamic switching will be triggered in a timely manner to ensure the stability, economy and efficiency of power consumption in the park.

[0130] Implementing the embodiments of this application has the following beneficial effects:

[0131] This application first categorizes electrical equipment based on its power consumption characteristics, thereby determining the appropriate power supply configuration to ensure normal operation and obtaining power compatibility attributes. Based on these attributes, targeted energy consumption models are constructed for various electrical devices, considering their unique power consumption characteristics and influencing factors. This results in more accurate energy consumption predictions and provides reliable energy consumption data support for subsequent optimized scheduling, further enhancing the scientific and economical nature of park energy management. Furthermore, the energy configuration process comprehensively considers the costs of various power supply configurations, achieving economic efficiency and obtaining optimal operating parameters and corresponding power connection methods that better align with park management objectives, thus realizing efficient park energy management. A simulation model is built to provide a reliable virtual environment for simulation scheduling, laying the foundation for simulating real-time energy consumption changes, load distribution adjustments, and power switching. Moreover, the simulation process does not affect the operation of equipment in the real-world scenario, effectively preventing scheduling failures from impacting the overall power consumption of the park. Finally, based on the equipment energy configuration strategy, power switching is performed on various electrical devices within the park in a real-world scenario, achieving reasonable power scheduling and refined management of the park, and improving the operational stability of each device.

[0132] Second Embodiment

[0133] Furthermore, in order to implement the park energy configuration system corresponding to the above method embodiments and achieve the corresponding functions and technical effects, Figure 2 A structural diagram of a park energy configuration system is provided. For ease of explanation, only the parts relevant to this embodiment are shown. The park energy configuration system provided in this embodiment includes:

[0134] The attribute configuration module 201 is used to construct power adaptation attributes corresponding to each type of electrical equipment based on the power consumption characteristics of each electrical equipment in the park.

[0135] Based on the collected energy consumption-related parameters of each electrical device, the energy consumption influencing factors of the electrical device are extracted;

[0136] The historical energy consumption data of the electrical equipment is processed by a long short-term memory network to capture the energy consumption change characteristics of the electrical equipment.

[0137] Based on the energy consumption influencing factors and the energy consumption change characteristics, each type of electrical equipment is classified and the corresponding power consumption characteristics are determined.

[0138] Based on the aforementioned power consumption characteristics, power supply configurations are performed for each type of electrical equipment to construct the power supply adaptation attributes.

[0139] The energy consumption demand prediction module 202 is used to model the energy consumption characteristics of each type of electrical equipment based on the power supply adaptation attributes, and predict the energy consumption demand of the electrical equipment.

[0140] Based on the power supply compatibility attributes, the differential energy consumption characteristics of each type of electrical equipment are extracted by identifying the differences in their operating modes; wherein, the types of electrical equipment include continuously operating equipment, intermittently operating equipment, and equipment subject to impact loads; and the operating modes include operating time and equipment load size.

[0141] Based on the aforementioned differentiated energy consumption characteristics, corresponding energy consumption models are constructed for each type of electrical equipment;

[0142] The collected power supply operating characteristics, equipment operating power and operating time are input into the energy consumption model to predict energy consumption and obtain the energy consumption requirements of each electrical device.

[0143] The optimal operation mode search module 203 is used to obtain the optimal operating parameters and corresponding power connection methods of the electrical equipment at different time periods, with the energy consumption requirements and power supply adaptation attributes as constraints and the goal of minimizing power supply configuration costs.

[0144] We construct a power configuration cost function by weighted summation of total electricity cost, total power switching cost, and total equipment operation and maintenance and loss cost.

[0145] Based on the power supply compatibility attributes and energy consumption requirements, the power supply duration ratio limit for each power supply corresponding to each type of electrical equipment is set to obtain the constraint conditions.

[0146] The power consumption parameters of the electrical equipment and the corresponding power supply are combined to generate several sets of optimized parameter pairs;

[0147] Based on the constraints, with the goal of minimizing the power supply configuration cost function, the optimization parameter pair is iteratively calculated, and the optimal optimization parameter pair is output when the preset iteration stopping condition is met.

[0148] Based on the optimal parameter pair, the optimal operating parameters of the electrical equipment and the corresponding power connection methods are determined at different time periods.

[0149] The energy configuration strategy construction module 204 is used to obtain the equipment energy configuration strategy by performing load allocation and power switching on the simulation model of the electrical equipment based on the optimal operating parameters and the power connection method.

[0150] Based on the physical parameters, electrical characteristic models, and operating states of the electrical equipment, a simulation model of each of the electrical equipment is constructed.

[0151] Based on the pre-set mains power supply model, green energy storage power supply model and switching circuit model, a digital twin of the power supply system is constructed;

[0152] By combining the aforementioned simulation model and the digital twin of the power supply system, a collaborative simulation platform is built.

[0153] Based on the optimal operating parameters and the power connection method, a corresponding energy configuration instruction is generated;

[0154] The energy configuration command is input into the collaborative simulation platform to simulate equipment operation. During the simulation process, the operating status parameters output by each simulation model, the load distribution curve of the power supply system digital twin, and the power switching response waveform are recorded to obtain simulation data.

[0155] The simulation data is filtered according to the preset abnormal situation identification criteria, and the equipment energy configuration strategy is output.

[0156] The power switching module 205 is used to switch the power supply of various electrical devices in the park based on the equipment energy configuration strategy and the real-time power supply situation.

[0157] The system monitors the real-time power supply status of each electrical device in the park and triggers a dynamic switching mechanism when the power supply switching conditions are met. The power supply switching conditions are that the capacity of green energy storage is lower than the first threshold, the mains electricity price enters the preset peak period, or the load of the electrical device exceeds the second threshold.

[0158] Based on the dynamic switching mechanism, power switching is performed on electrical equipment that meets the power supply switching conditions through the equipment energy configuration strategy.

[0159] Implementing the embodiments of this application has the following beneficial effects:

[0160] This application first categorizes electrical equipment based on its power consumption characteristics, thereby determining the appropriate power supply configuration to ensure normal operation and obtaining power compatibility attributes. Based on these attributes, targeted energy consumption models are constructed for various electrical devices, considering their unique power consumption characteristics and influencing factors. This results in more accurate energy consumption predictions and provides reliable energy consumption data support for subsequent optimized scheduling, further enhancing the scientific and economical nature of park energy management. Furthermore, the energy configuration process comprehensively considers the costs of various power supply configurations, achieving economic efficiency and obtaining optimal operating parameters and corresponding power connection methods that better align with park management objectives, thus realizing efficient park energy management. A simulation model is built to provide a reliable virtual environment for simulation scheduling, laying the foundation for simulating real-time energy consumption changes, load distribution adjustments, and power switching. Moreover, the simulation process does not affect the operation of equipment in the real-world scenario, effectively preventing scheduling failures from impacting the overall power consumption of the park. Finally, based on the equipment energy configuration strategy, power switching is performed on various electrical devices within the park in a real-world scenario, achieving reasonable power scheduling and refined management of the park, and improving the operational stability of each device.

[0161] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. In particular, it should be noted that any modifications, equivalent substitutions, or improvements made by those skilled in the art within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for configuring energy in a park, characterized in that, include: Based on the power consumption characteristics of each electrical device in the park, power adaptation attributes corresponding to each type of electrical device are constructed. The energy consumption characteristics of each type of electrical equipment are modeled using the power adaptation attributes to predict the energy consumption requirements of the electrical equipment. Using the energy consumption demand and the power supply compatibility attributes as constraints, and minimizing the power supply configuration cost as the optimization objective, the optimal operating parameters and corresponding power connection methods of the electrical equipment at different time periods are obtained. Specifically, the total electricity cost, total power supply switching cost, and total equipment operation and maintenance and loss cost are weighted and summed to construct a power supply configuration cost function; based on the power supply compatibility attributes and the energy consumption demand, the power supply duration ratio limit for each power supply corresponding to each type of electrical equipment is set to obtain the constraints. The power consumption parameters of the electrical equipment and the corresponding power supply are combined to generate several sets of optimized parameter pairs. Based on the constraints, the optimized parameter pairs are iteratively calculated with the goal of minimizing the power supply configuration cost function. When the preset iteration stopping condition is met, the optimal optimized parameter pair is output. Based on the optimal optimized parameter pair, the optimal operating parameters of the electrical equipment and the corresponding power connection method at different time periods are determined. Based on the optimal operating parameters and the power connection method, load allocation and power switching are performed on the simulation models of the electrical equipment to obtain the equipment energy configuration strategy. Specifically, the following steps are taken: Simulation models of each electrical device are constructed based on its physical parameters, electrical characteristic models, and operating states; a digital twin of the power supply system is constructed based on preset mains power supply models, green energy storage power supply models, and switching circuit models; a collaborative simulation platform is built by combining the simulation models and the power supply system digital twin; corresponding energy configuration instructions are generated based on the optimal operating parameters and the power connection method; the energy configuration instructions are input into the collaborative simulation platform to simulate equipment operation, and the operating state parameters output by each simulation model, the load allocation curve of the power supply system digital twin, and the power switching response waveform are recorded during the simulation process to obtain simulation data. The simulation data is filtered according to the preset abnormal situation identification criteria, and the equipment energy configuration strategy is output. Based on the equipment energy configuration strategy, power switching is performed on various electrical equipment in the park according to the real-time power supply situation.

2. The energy allocation method for industrial parks according to claim 1, characterized in that, The process involves constructing power adaptation attributes for each type of electrical equipment based on its power consumption characteristics within the park. Specifically: Based on the collected energy consumption-related parameters of each electrical device, the energy consumption influencing factors of the electrical device are extracted; The historical energy consumption data of the electrical equipment is processed by a long short-term memory network to capture the energy consumption change characteristics of the electrical equipment. Based on the energy consumption influencing factors and the energy consumption change characteristics, each type of electrical equipment is classified and the corresponding power consumption characteristics are determined. Based on the aforementioned power consumption characteristics, power supply configurations are performed for each type of electrical equipment to construct the power supply adaptation attributes.

3. The energy allocation method for industrial parks according to claim 1, characterized in that, The step of modeling the energy consumption characteristics of each type of electrical equipment based on the power adaptation attributes and predicting the energy consumption demand of the electrical equipment is as follows: Based on the power supply compatibility attributes, the differential energy consumption characteristics of each type of electrical equipment are extracted by identifying the differences in their operating modes; wherein, the types of electrical equipment include continuously operating equipment, intermittently operating equipment, and equipment subject to impact loads; and the operating modes include operating time and equipment load size. Based on the aforementioned differentiated energy consumption characteristics, corresponding energy consumption models are constructed for each type of electrical equipment; The collected power supply operating characteristics, equipment operating power and operating time are input into the energy consumption model to predict energy consumption and obtain the energy consumption requirements of each electrical device.

4. The energy allocation method for industrial parks according to claim 3, characterized in that, Based on the differentiated energy consumption characteristics, a corresponding energy consumption model is constructed for each type of electrical equipment, specifically as follows: Based on the rated power of the continuously operating equipment, the predicted operating time, the mains voltage fluctuation deviation, the mains frequency fluctuation deviation, and the remaining capacity ratio of green energy storage, an energy consumption model for the continuously operating equipment is constructed. Based on the relationship between the operating power of the intermittently operating equipment in each time period, the time interval, the total number of time periods, the actual power generation of green energy storage and the maximum power generation in each time period, and the peak-valley coefficient of the grid electricity price, an energy consumption model for the intermittently operating equipment is constructed. Based on the relationship between the daily number of starts, rated power, single stable operation duration, start-up impact duration, and the instantaneous and maximum instantaneous carrying capacity of the mains power, an energy consumption model for the impact load equipment is constructed.

5. The energy allocation method for industrial parks according to claim 1, characterized in that, The iterative calculation of the optimized parameter pair specifically involves: Calculate the power configuration cost value of each of the optimized parameter pairs, and select the optimized parameter pairs by means of a roulette wheel selection method to obtain the selected parameter pairs; wherein, the smaller the power configuration cost value, the greater the probability that the optimized parameter pair is selected; Randomly swap the elements in each selected parameter pair to generate a new optimized parameter pair; Calculate the power configuration cost value of the new optimized parameter pair, and select the new optimized parameter pair again until the preset iteration stopping condition is met.

6. The energy allocation method for industrial parks according to claim 1, characterized in that, The process of filtering simulation data according to preset anomaly identification criteria and outputting equipment energy configuration strategies specifically involves: The simulation data is judged to be abnormal according to the abnormal situation identification standard. If an abnormality is found, the energy configuration command is adjusted. The abnormal situation identification standard is used to detect equipment operating temperature, abnormal power supply interruption, abnormal fluctuation of mains voltage, and abnormal fluctuation of mains frequency. If no anomalies are found, the power supply switching conditions of the electrical equipment are configured based on the simulation data, and a corresponding equipment energy configuration strategy is generated.

7. The energy allocation method for industrial parks according to claim 6, characterized in that, The equipment energy configuration strategy, based on real-time power supply conditions, switches power to various electrical devices within the park, specifically as follows: The system monitors the real-time power supply status of each electrical device in the park and triggers a dynamic switching mechanism when the power supply switching conditions are met. The power supply switching conditions are that the capacity of green energy storage is lower than the first threshold, the mains electricity price enters the preset peak period, or the load of the electrical device exceeds the second threshold. Based on the dynamic switching mechanism, power switching is performed on electrical equipment that meets the power supply switching conditions through the equipment energy configuration strategy.

8. A park energy allocation system, characterized in that, include: Attribute configuration module, energy demand prediction module, optimal operation mode search module, energy configuration strategy construction module and power switching module; Among them, the attribute configuration module is used to construct the power adaptation attributes corresponding to each type of electrical equipment based on the power consumption characteristics of each electrical equipment in the park; The energy consumption demand prediction module is used to model the energy consumption characteristics of each type of electrical equipment based on the power supply adaptation attributes, and predict the energy consumption demand of the electrical equipment. The optimal operation mode search module is used to obtain the optimal operating parameters and corresponding power connection methods of the electrical equipment at different time periods, with the energy consumption demand and power supply adaptability attributes as constraints and minimizing power supply configuration cost as the optimization objective. Specifically, it involves: weighted summation of total electricity consumption cost, total power switching cost, and total equipment operation and maintenance and loss cost to construct a power supply configuration cost function; setting the power supply duration ratio limit for each power supply corresponding to each type of electrical equipment according to the power supply adaptability attributes and energy consumption demand to obtain the constraints; combining the power consumption parameters of the electrical equipment and the corresponding power supply to generate several sets of optimized parameter pairs; iteratively calculating the optimized parameter pairs based on the constraints and minimizing the power supply configuration cost function as the objective, and outputting the optimal optimized parameter pair when a preset iteration stopping condition is met; and determining the optimal operating parameters and corresponding power connection methods of the electrical equipment at different time periods based on the optimal optimized parameter pairs. The energy configuration strategy construction module is used to obtain the equipment energy configuration strategy based on the optimal operating parameters and the power connection method by performing load allocation and power switching on the simulation model of the electrical equipment. Specifically, it involves: constructing simulation models of each electrical device according to the physical parameters, electrical characteristic models, and operating states of the electrical devices; constructing a digital twin of the power supply system according to preset mains power supply models, green energy storage power supply models, and switching circuit models; building a collaborative simulation platform by combining the simulation models and the digital twin of the power supply system; generating corresponding energy configuration instructions according to the optimal operating parameters and the power connection method; inputting the energy configuration instructions into the collaborative simulation platform to simulate equipment operation, recording the operating state parameters output by each simulation model, the load allocation curve of the digital twin of the power supply system, and the power switching response waveform during the simulation process to obtain simulation data; and filtering the simulation data according to preset abnormal situation identification criteria to output the equipment energy configuration strategy. The power switching module is used to switch the power supply of various electrical devices in the park based on the equipment energy configuration strategy and the real-time power supply situation.

Images