Park-oriented energy station remote regulation and control method and system and medium

Abstract

The application discloses a park-oriented energy station remote regulation and control method and system and a medium, relates to the technical field of intelligent dispatching, and comprises the following steps: establishing a park two-way data channel, and collecting data sets in real time; performing operation analysis on an energy station unit, formulating an optimization strategy, performing energy consumption characteristic analysis on a terminal energy consumption unit, and determining time-sharing energy consumption benchmark information; executing optimization strategy regulation and control monitoring according to the time-sharing benchmark, and generating feedback data; and performing collaborative optimization on the energy station and the terminal unit based on the feedback data and real-time data sets, and forming a linkage control scheme. The application solves the technical problems that the existing energy station regulation and control system lacks real-time optimization capability of intelligent dispatching, cannot dynamically adjust the energy consumption distribution between the energy station and the terminal energy consumption unit according to actual demands, and leads to energy waste and low efficiency, and achieves the technical effects that dynamic optimization operation of the energy station and the terminal energy consumption unit is realized through intelligent dispatching, energy utilization efficiency is improved, and energy consumption is reduced.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to remote control methods, systems and media for energy stations in industrial parks. Background Technology

[0002] With the rapid development of urban industrial parks, energy consumption is increasing daily, especially in the coordination and control between energy stations and end-user energy units within the parks. Traditional scheduling methods often rely on manual monitoring and fixed operating modes, lacking flexibility and real-time performance, leading to low energy efficiency and even energy waste. With the development of intelligent technologies, energy management is gradually moving towards intelligent scheduling, which can dynamically adjust energy supply and consumption based on real-time data and operating status, thereby achieving greater efficiency and energy conservation. However, most existing energy management systems are limited to the control of single devices, lacking the ability to coordinate and optimize between energy stations and end-user energy units, and failing to fully consider real-time feedback of multi-dimensional data, resulting in an inability to cope with changes in energy demand under complex environments. Therefore, how to achieve coordinated optimization between energy stations and end-user energy units through intelligent scheduling methods, combined with real-time collection and analysis of various operating data via bidirectional data channels, to improve the overall operating efficiency and energy utilization rate of park energy stations, has become a pressing technical challenge. Summary of the Invention

[0003] This invention provides a method, system, and medium for remote control of energy stations in industrial parks. It addresses the technical problems of existing energy station control systems lacking real-time optimization capabilities for intelligent scheduling, and being unable to dynamically adjust energy consumption distribution between energy stations and end-user energy units according to actual needs, resulting in energy waste and low efficiency. The invention achieves the technical effect of dynamically optimizing the operation of energy stations and end-user energy units through intelligent scheduling, thereby improving energy utilization efficiency and reducing energy consumption.

[0004] In a first aspect, the present invention provides a remote control method for energy stations in industrial parks, wherein the remote control method for energy stations in industrial parks includes:

[0005] A two-way data channel is established for the target park. Real-time data is collected through this channel to obtain a two-way real-time dataset. The two-way data channel includes energy station units and end-user energy consumption units. Equipment operation analysis is performed on the energy station units to formulate dynamic optimization operation strategies. Energy consumption characteristics analysis is performed on the end-user energy consumption units to determine time-of-use energy consumption benchmark information. The dynamic optimization operation strategies are then implemented and monitored according to the time-of-use energy consumption benchmark information to generate control feedback data. Based on the control feedback data and the two-way real-time dataset, the energy station units and the end-user energy consumption units are collaboratively optimized to obtain a coordinated control scheme.

[0006] Secondly, the present invention also provides a remote control system for energy stations in industrial parks, wherein the remote control system for energy stations in industrial parks includes:

[0007] Real-time data acquisition module: Establishes a two-way data channel to the target park, and acquires data in real time through the two-way data channel to obtain a two-way real-time dataset. The two-way data channel includes energy station units and end-user energy consumption units. Data analysis module: Performs equipment operation analysis on the energy station units, formulates dynamic optimization operation strategies, and performs energy consumption characteristic analysis on the end-user energy consumption units to determine time-of-use energy consumption benchmark information. Control and monitoring module: Executes control and monitoring of the dynamic optimization operation strategies according to the time-of-use energy consumption benchmark information, and generates control feedback data. Collaborative optimization module: Based on the control feedback data and the two-way real-time dataset, collaboratively optimizes the energy station units and the end-user energy consumption units to obtain a coordinated control scheme.

[0008] Thirdly, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the remote control method for energy stations in industrial parks provided by the present invention.

[0009] This invention discloses a method, system, and medium for remote control of energy stations in industrial parks, comprising: establishing a two-way data channel to the target industrial park; acquiring real-time data through the two-way data channel to obtain a two-way real-time dataset; the two-way data channel including energy station units and end-user energy units; analyzing the equipment operation of the energy station units and formulating dynamic optimization operation strategies; analyzing the energy consumption characteristics of the end-user energy units and determining time-of-use energy consumption benchmark information; executing the control and monitoring of the dynamic optimization operation strategies according to the time-of-use energy consumption benchmark information and generating control feedback data; and coordinating and optimizing the energy station units and the end-user energy units based on the control feedback data and the two-way real-time dataset to obtain a coordinated control scheme. The remote control method, system, and medium for energy stations in industrial parks disclosed in this invention solve the technical problems of existing energy station control systems lacking intelligent scheduling and real-time optimization capabilities, and being unable to dynamically adjust the energy consumption distribution between energy stations and end-user energy units according to actual needs, leading to energy waste and low efficiency. It achieves the technical effect of dynamically optimizing the operation of energy stations and end-user energy units through intelligent scheduling, improving energy utilization efficiency, and reducing energy consumption. Attached Figure Description

[0010] Figure 1 This is a flowchart illustrating the remote control method for energy stations in industrial parks according to the present invention.

[0011] Figure 2 This is a schematic diagram of the structure of the remote control system for energy stations in industrial parks according to the present invention.

[0012] Explanation of reference numerals in the attached diagram: Real-time acquisition module 11, Data analysis module 12, Control and monitoring module 13, Collaborative optimization module 14. Detailed Implementation

[0013] The above technical solutions will now be described in detail with reference to the accompanying drawings and specific embodiments to provide a better understanding of them. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments used only to explain the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. Furthermore, it should be noted that, for ease of description, only the parts related to the present invention are shown in the drawings, not all of them.

[0014] Example 1, as Figure 1 This is a flowchart illustrating the remote control method for energy stations in industrial parks according to the present invention. The remote control method for energy stations in industrial parks includes:

[0015] A two-way data channel is established for the target park. Real-time data is collected through the two-way data channel to obtain a two-way real-time dataset. The two-way data channel includes energy station units and end-user energy units.

[0016] Specifically, a two-way data exchange network is constructed within the target industrial park, interconnecting the park's energy station units (such as chiller units and energy storage devices) with end-user energy units (such as building air conditioning systems and industrial production lines) via IoT protocols to form a two-way data channel. Energy station units upload equipment operating parameters (such as compressor frequency and supply / return water temperature) in real time, while end-user energy units synchronously feed back end-user energy consumption data (such as instantaneous power and load demand). Finally, based on spatiotemporal coding rules, the equipment operating parameters and end-user energy consumption data are aligned and encapsulated to generate a two-way real-time dataset containing equipment status and energy demand. In summary, this two-way data channel enables seamless data exchange and real-time monitoring between energy stations and end-user energy units, providing reliable data support for subsequent dynamic optimization and coordinated control.

[0017] In some embodiments, a two-way data channel is established for the target park, and real-time data is collected through the two-way data channel to obtain a two-way real-time dataset. The method includes:

[0018] A bidirectional data channel is established between the energy station units and the end-user energy consumption units in the target park through a smart energy management and control platform. Data is synchronously collected from the energy station units through the bidirectional data channel to obtain equipment operating parameters, and data is synchronously collected from the end-user energy consumption units through the bidirectional data channel to obtain end-user energy consumption data. The equipment operating parameters and the end-user energy consumption data are feature-aligned according to spatiotemporal coding rules to construct the bidirectional real-time dataset.

[0019] Specifically, the smart energy management platform connects to energy station units via an industrial IoT gateway using the OPC UA protocol, and simultaneously connects to end-user energy units via Modbus-TCP or BACnet protocols. The platform assigns a unique IP address to each device node, establishing a bidirectional data channel to connect and coordinate real-time data transmission between units, ensuring accurate and timely data flow. Subsequently, through this bidirectional data channel, data is synchronously collected from the energy station units, including key indicators such as equipment operating parameters, power output, operating status, and temperature. Simultaneously, data from end-user energy units is also collected, primarily including information on power consumption, load demand, and consumption patterns of various terminal devices. The bidirectional data channel ensures real-time transmission and synchronization of both types of data. Afterward, the collected equipment operating parameters and end-user energy data are feature-aligned according to spatiotemporal coding rules. This step aims to match the two types of data in both time and space dimensions, ensuring they are compared and analyzed within the same timeframe. Spatiotemporal coding rules typically consider the operational sequence and geographical location of different devices and energy units, enabling data integration under the same standard. Finally, through this series of operations, a two-way real-time dataset is generated, which contains the real-time operating status and energy consumption data of energy station units and end-user energy units. This dataset provides a foundation for subsequent regulation and optimization, and provides real-time feedback for intelligent scheduling.

[0020] In some embodiments, the bidirectional real-time dataset is constructed by aligning the device operating parameters with the end-point energy consumption data according to spatiotemporal coding rules. The method includes:

[0021] A data quality assessment matrix is ​​constructed to score the equipment operating parameters and the end-user energy consumption data, generating a two-way data score value, which includes the equipment operating score value and the end-user energy consumption score value. Based on the equipment operating score value, time-shift compensation is performed on the equipment operating parameters to obtain updated equipment operating parameters. Based on the end-user energy consumption score value, time-shift compensation is performed on the end-user energy consumption data to obtain updated end-user energy consumption data. The updated equipment operating parameters and the updated end-user energy consumption data are correlated and aligned to obtain dynamic correlation data between the energy station and the end-user, and this dynamic correlation data is added to the two-way real-time dataset.

[0022] Specifically, when constructing the bidirectional dataset, the quality of equipment operating parameters and end-user energy consumption data is first evaluated. This is achieved by constructing a data quality evaluation matrix. Each row of the data quality evaluation matrix represents a piece of equipment data or a piece of energy consumption data, and each column represents an evaluation indicator, such as accuracy, completeness, consistency, and timeliness. Accuracy is determined by comparing with benchmark data and calculating the standard deviation. Completeness is determined by calculating the ratio of missing data points to the total number of data points. Consistency is determined by comparing the values ​​of the same data item from different sources or at different time points and calculating the differences between the data. Timeliness is determined by calculating the ratio of the time delay between collection and transmission to the maximum tolerable delay. Subsequently, based on these indicators defined in the data quality evaluation matrix, the equipment operating parameters and end-user energy consumption data are evaluated, and the evaluation results are stored in the data quality evaluation matrix. For each row of data in the data quality evaluation matrix, such as equipment operating parameters or end-user energy consumption data, a score value is calculated by weighted summation, which serves as the equipment operating score value or end-user energy consumption score value. These scores together constitute the bidirectional data score value. Next, time-shift compensation is performed on the equipment operation score and the end-user energy consumption score. Time-shift compensation adjusts the time series of the data to eliminate time misalignment caused by data acquisition delays or other factors. Specifically, the equipment operation score is multiplied by the maximum time offset to obtain the current time offset. The maximum time offset is determined based on the equipment's acquisition frequency, historical experience, and expert decisions. Then, the time interval between adjacent acquired data is compared with the acquisition frequency. If the time interval is greater than the acquisition frequency, it indicates that the acquired data is lagging. In this case, the data is shifted forward according to the time offset, i.e., the data timestamp is adjusted to conform to the actual time series, thus obtaining the updated equipment operation parameters. Similarly, the same time-shift compensation is performed on the end-user energy consumption data to correct its time deviation and obtain updated end-user energy consumption data. Finally, the time-shift compensated updated equipment operation parameters and updated end-user energy consumption data are correlated and aligned. This step matches the two sets of data in time and space to ensure that they can be analyzed and processed in the same time dimension. After the association is completed, the obtained dynamic association data between energy stations and end points will be added to the bidirectional real-time dataset, providing a more accurate and timely data foundation for subsequent collaborative optimization and intelligent scheduling.

[0023] Table 1: Data Quality Assessment Table

[0024]

[0025]

[0026] The data items in Table 1 represent the data items corresponding to different devices or energy-consuming units, including data for Device 1, Device 2, Energy Consumption 1, and Energy Consumption 2. The quality of each data item is evaluated by four main indicators: accuracy, completeness, consistency, and timeliness.

[0027] The energy station unit is analyzed for equipment operation, and a dynamic optimization operation strategy is formulated. The energy consumption characteristics of the end-user energy unit are analyzed to determine the time-of-use energy consumption benchmark information.

[0028] Specifically, when analyzing the operation of energy station units, the first step is to extract data from each energy device within the energy station from a two-way real-time dataset to understand its operating status and energy efficiency. The operating status of each device directly affects energy utilization efficiency. By analyzing the operating data of these devices, their performance can be evaluated and future operational trends predicted, thereby formulating corresponding dynamic optimization operation strategies. This involves dynamically adjusting parameters such as the device's operating mode and runtime to improve overall system efficiency. Simultaneously, the energy consumption characteristics of end-user energy units are analyzed. In this process, the park is divided into zones based on factors such as building function and usage time. Energy consumption characteristics are then extracted for each zone, determining multiple energy consumption patterns and load curves. Subsequently, dynamic time-of-use adjustments are made to the end-user energy units based on these load curves to determine energy consumption baseline values. These baseline values ​​are then added to the time-of-use energy consumption baseline information to improve energy utilization efficiency and avoid energy waste during peak hours. In summary, by determining dynamic optimization operation strategies and time-of-use energy consumption baseline information, the system can achieve precise energy regulation across the entire park, minimizing energy waste and improving the overall energy management efficiency of the park.

[0029] In some embodiments, the method for performing equipment operation analysis on the energy station unit and formulating a dynamic optimization operation strategy includes:

[0030] A multi-dimensional equipment operation analysis is performed on the energy station unit to generate an equipment status assessment matrix; the operation of the energy station unit is predicted using the equipment status assessment matrix, and an operation change trend diagram of the energy station unit is drawn based on the prediction results; the equipment operation deviation is calculated based on the operation change trend diagram to obtain the operation deviation degree; the operation of the energy station unit is corrected based on the operation deviation degree, and the dynamic optimization operation strategy is formulated.

[0031] Specifically, when conducting multi-dimensional equipment operation analysis on energy station units, it is first necessary to extract various types of equipment operation data from the bidirectional real-time dataset. This data includes, but is not limited to, equipment power, temperature, pressure, vibration, and operating time. Based on this data, multi-dimensional operation analysis is then conducted on each piece of equipment in the energy station unit, including dimensions such as temperature, energy efficiency, stability, load distribution, and safety. The results of each indicator obtained from the analysis are then organized into a matrix to obtain the equipment status assessment matrix. Temperature can be determined by the ratio of real-time temperature to safe temperature; energy efficiency can be determined by the ratio of output power to input power; stability can be determined by subtracting downtime from total equipment operating time and then calculating the ratio of the difference to total equipment operating time; load distribution can be determined by dividing the difference between maximum and minimum loads by the sum of maximum and minimum loads and then subtracting the ratio from 1; and safety can be determined by the ratio of normal operating time (the allowable time for the equipment to operate within the safe range of parameters) to total operating time. Subsequently, using the equipment condition assessment matrix as input data, a Long Short-Term Memory (LSTM) network built based on historical data is used to predict the operation of the energy station units, obtaining the operating status indicators of the energy station units, i.e., the future equipment condition assessment matrix. The LSTM is obtained through iterative training based on the historical equipment condition assessment matrix and historical operating status indicators, through forward propagation, loss calculation, backpropagation, and parameter optimization. The loss calculation is based on the mean squared error loss function, and the parameter optimization is based on the Adam optimizer. After predicting the operating status indicators, a visual fitting is performed on them; that is, the predicted operating status indicators are plotted in chronological order to show the operating trend of the energy station units, displaying the changes in equipment operation over a future period. Then, the predicted operating status indicators are compared with the expected operating status indicators, and the differences between the different indicators are calculated to obtain the operating deviation. Based on the operating deviation, appropriate dynamic optimization operation strategies can be formulated to ensure that the equipment operates in the predetermined optimal state. For example, if the temperature of a piece of equipment is too high, the deviation can be corrected by adjusting the equipment load or activating backup cooling equipment. These optimization strategies can adjust the operating status of the equipment in real time, reduce energy waste, ensure equipment operating efficiency, and extend its service life.

[0032] In some embodiments, energy consumption characteristic analysis is performed on the end-user energy unit to determine time-of-use energy consumption benchmark information, including:

[0033] The energy consumption characteristics of the terminal energy-consuming units are extracted by region to determine the energy consumption characteristics of multiple regions. Based on the energy consumption characteristics of multiple regions, an energy consumption behavior feature vector of the terminal energy-consuming units is constructed. Based on the energy consumption behavior feature vector, cluster analysis is performed to determine multiple energy consumption patterns. The load is synchronously recorded by traversing the multiple energy consumption patterns to obtain multiple load curves. The multiple load curves correspond to the multiple energy consumption patterns. Based on the multiple load curves, the terminal energy-consuming units are dynamically adjusted in a time-sharing manner to determine the energy consumption benchmark value. The energy consumption benchmark value is added to the time-sharing energy consumption benchmark information.

[0034] Specifically, end-user energy units are partitioned according to different areas, functions, or energy types, such as office areas, production areas, and warehousing areas within a park. Each area may have different energy consumption characteristics, thus requiring separate analysis. For each partition, energy consumption data (such as electricity, heat, and cooling consumption) is extracted from a bidirectional real-time dataset. Based on this data, the energy consumption characteristics of each area are determined. These characteristics may include total energy consumption, peak energy consumption, valley energy consumption, load fluctuations, peak energy consumption periods, and valley energy consumption periods. By adding these partition energy consumption characteristics to a set, multi-zone energy consumption characteristics are obtained. Subsequently, the energy consumption characteristics of each partition in the multi-zone energy consumption characteristics are concatenated to obtain the energy consumption behavior feature vector of the end-user energy unit. This vector represents the energy consumption pattern of the end-user energy unit under different times and conditions. Subsequently, clustering algorithms (such as K-means and DBSCAN) are used to analyze the energy consumption behavior feature vectors of all end-user energy units. Regions with similar energy consumption behaviors are grouped together using Euclidean distance, thus identifying multiple energy consumption patterns. Each energy consumption pattern represents the mean of its corresponding cluster. After obtaining multiple energy consumption patterns, these patterns are iterated through. For each pattern, load synchronization data under that pattern is statistically analyzed; that is, the mean load of the partition belonging to that pattern at the same time. A load curve for that pattern is then plotted based on the load synchronization data. The load curve reflects the energy consumption change trend of the region over different time periods and corresponds one-to-one with the energy consumption pattern. Then, by analyzing the load curves under each energy consumption pattern, the patterns of load changes and peak energy consumption periods are identified. Energy demand for different time periods is determined, and energy resources are dynamically allocated. For example, during off-peak periods, excess energy can be stored or used to power other low-load areas, thereby reducing energy pressure during peak periods. During peak periods, backup energy can be introduced or the proportion of energy supply can be adjusted to avoid overload operation. Based on the analysis of load curves, a reasonable energy consumption baseline value is set for each time period. This baseline value represents the optimal energy consumption target for end-user energy units within a specific time period, maximizing energy efficiency while meeting demand. For example, a lower baseline value is set during off-peak hours (such as nighttime) to avoid energy waste, while a higher baseline value is set during peak hours (such as daytime office hours), and backup energy may be activated to ensure demand is met. These baseline values ​​are set based on current load curve fluctuations and historical data. Finally, these energy consumption baseline values ​​are added to the time-of-use energy consumption baseline information and adjusted and monitored in real time through the system. This baseline information will guide the control strategies of energy stations and end-user energy units, ensuring the rational allocation of energy.

[0035] The system performs regulation and monitoring based on the time-of-use energy consumption baseline information, and generates regulation feedback data.

[0036] In one embodiment, when executing a dynamic optimization operation strategy, the energy load is first decomposed based on time-of-use energy consumption baseline information to identify and quantify changes in energy demand over different time periods. Subsequently, based on the load decomposition results, the operating status of the energy station units is analyzed to assess the cooling and heating efficiency of the equipment, identify energy usage and optimization potential, thus providing a basis for subsequent control strategy formulation. Next, the dynamic optimization strategy is simulated and executed based on the assessed cooling and heating efficiency. During the simulation, the effects of different energy configurations and scheduling schemes are analyzed, generating a multi-level control instruction set. This instruction set guides how the equipment adjusts its operating mode to ensure energy demand is met under efficient and stable conditions. The hierarchical structure of the instruction set enables comprehensive control from equipment units to the entire energy station, ensuring optimal energy flow. After generating the control instruction set, the energy station units and end-user energy units are controlled according to these instructions. The control parameters of each device and the response data of the end-user energy units are recorded. These control records provide detailed feedback information to the system, aiding in subsequent adjustments and optimization strategies. Finally, continuous monitoring is performed based on the energy station equipment control parameters and end-user energy response data to generate control feedback data. This feedback data provides the system with real-time operational status reports, supporting subsequent collaborative optimization.

[0037] In some embodiments, the method of performing regulation and monitoring of the dynamic optimization operation strategy according to the time-of-use energy consumption benchmark information and generating regulation feedback data includes:

[0038] Load decomposition is performed based on the multiple load curves, and the operation of the energy station unit is analyzed to obtain the cooling and heating operating efficiency. A dynamic optimization strategy is simulated and analyzed according to the cooling and heating operating efficiency to generate a multi-level control instruction set. The energy station unit and the terminal energy consumption unit are controlled and recorded according to the multi-level control instruction set to obtain energy station equipment control parameters and terminal energy consumption response data. Continuous monitoring of the operation control of the energy station unit and the terminal energy consumption unit is performed based on the energy station equipment control parameters and terminal energy consumption response data to generate the control feedback data.

[0039] Specifically, multiple load curves are decomposed based on time-of-use energy consumption benchmark information to identify energy consumption fluctuations and trends in different regions over different time periods, and to understand the actual load demand during peak and off-peak hours. Subsequently, the input power and output cooling capacity of cooling equipment in the corresponding energy station units are extracted from the bidirectional real-time dataset. The cooling operating efficiency for that period is obtained by calculating the ratio of output cooling capacity to input power. Similarly, the input power and output heat of heating equipment are extracted, and the heating operating efficiency for that period is calculated. After obtaining the cooling and heating operating efficiencies, these two efficiencies are added to a set to obtain the cooling and heating operating efficiencies. Then, based on the cooling and heating operating efficiencies, a dynamic optimization strategy is simulated and executed in a simulation platform. The purpose of this simulation process is to understand the effectiveness of the control strategy, determine the optimal scheduling method while meeting the actual load demand in different time periods, and generate a multi-level control instruction set. Each level of instruction represents different control objectives and strategies, from fine-grained control of equipment units to macro-level scheduling of the entire energy station, ensuring that the flow of energy between different regions reaches its optimal state. After generating a multi-level control instruction set, the energy station units and end-user energy units are controlled and recorded according to these instructions. This determines the control parameters of the energy station equipment and the response data of the end-user energy units that need adjustment, such as the operating frequency of the energy station equipment, valve opening and closing, and the load of the refrigeration / heating devices, as well as the electricity consumption and equipment load changes of the end-user energy units. Finally, based on these control records, continuous operational control monitoring is conducted. By continuously monitoring the control parameters of the energy station equipment and the response data of the end-user energy units, and mapping the monitoring results to the multi-level control instruction set, control feedback data is compiled. This feedback data provides real-time feedback for subsequent optimization, adjusting subsequent operating strategies to ensure maximum energy utilization efficiency.

[0040] In some embodiments, the continuous monitoring of the operation and control of the energy station unit and the end-user energy consumption unit based on the energy station equipment control parameters and the end-user energy consumption response data, and the generation of the control feedback data, includes:

[0041] The energy station equipment control parameters and the end-user energy consumption response data are time-normalized and aligned to determine the equipment response timing and control command timing. The energy station unit is then analyzed according to the equipment response timing to obtain a first control effect. The end-user energy consumption unit is then analyzed according to the control command timing to obtain a second control effect. A first correlation mapping parameter is constructed between the energy station equipment control parameters and the multi-level control command set based on the first control effect. A second correlation mapping parameter is constructed between the end-user energy consumption response data and the multi-level control command set based on the second control effect. The first and second correlation mapping parameters are then subjected to dimensionality reduction evaluation to generate the control feedback data.

[0042] Specifically, after recording the control parameters of the energy station equipment and the end-user energy response data at multiple time points, the control parameters and the end-user energy response data are aligned according to timestamps. By aligning the control parameters, the equipment response sequence is obtained, which records the control records of the energy station equipment. Similarly, by aligning the end-user energy response data, the control command sequence is obtained, which records the response of the end-user energy units after equipment control. Subsequently, based on the aligned sequence data, control analysis is performed on both the energy station units and the end-user energy units. For the energy station units, control is performed according to the equipment response sequence, and the control effect data, such as output power, temperature, and load, is recorded to obtain the first control effect, showing the response of the energy station equipment under the control command. At the same time, for the end-user energy units, control analysis is performed according to the control command sequence, and the response effect of the end-user energy units, such as changes in regional energy load and peak-valley fluctuations in electricity consumption, is recorded to obtain the second control effect, reflecting the response of the end-user energy units to the control command. After obtaining the two control effects, the first control effect, energy station equipment control parameters, and multi-level control command sets are mapped to construct a first correlation mapping parameter. This parameter describes the relationship between the actual control effect of the energy station equipment and the command set, helping to understand the specific impact of equipment control commands on equipment operation. Similarly, the second control effect, end-user energy response data, and multi-level control command sets are mapped to construct a second correlation mapping parameter. This parameter reflects the energy consumption changes and load response of end-user energy units under the control commands. Finally, dimensionality reduction methods such as autoencoders and t-SNE are used to evaluate the first and second correlation mapping parameters. Dimensionality reduction aims to reduce data complexity while retaining key influencing factors. Through dimensionality reduction, the main parameters affecting the overall system control effect can be extracted, generating control feedback data. This feedback data includes the control effects of equipment and end-user energy units, and the relationship between various parameters and control commands. The control feedback data will provide a basis for subsequent optimization decisions and adjustments, helping the system further improve control strategies and enhance overall energy management efficiency.

[0043] Based on the control feedback data and the two-way real-time dataset, the energy station unit and the end-user energy unit are coordinated and optimized to obtain a coordinated control scheme.

[0044] Specifically, through data fusion, the regulation feedback data and the two-way real-time data set are integrated into a multi-dimensional optimization space. In this optimization space, through digital twin, the energy station unit and the end-use energy unit are analyzed collaboratively to determine multiple sets of linkage control parameters. These parameters consider the mutual relationship and demand matching between the energy station and the end-use energy unit. For example, when the load of a certain end-use energy unit is too high, its working mode can be adjusted according to the output capacity of the energy station unit to ensure the reasonable distribution of energy; conversely, if the energy supply capacity of the energy station unit is insufficient, the load demand of the end-use energy unit will be automatically adjusted to avoid excessive energy consumption. Finally, based on these collaborative control parameters, multi-objective optimization is carried out to obtain a linkage collaborative control scheme. This scheme adjusts the operation strategies of the energy station unit and the end-use energy unit, enabling the entire system to maximize the energy use efficiency while meeting their respective demands, reducing energy consumption waste, and achieving the linkage regulation between the energy station unit and the end-use energy unit.

[0045] In some embodiments, based on the regulation feedback data and in combination with the two-way real-time data set, the energy station unit and the end-use energy unit are collaboratively optimized to obtain a linkage collaborative control scheme. The method includes:

[0046] Integrate the regulation feedback data and the two-way real-time data set for data fusion to construct a multi-dimensional optimization space; perform digital twin mapping of the energy station unit and the end-use energy unit to the multi-dimensional optimization space to generate a collaborative control simulation scenario; perform collaborative iteration on the energy station unit and the end-use energy unit based on the collaborative control simulation scenario to determine multiple combinations of linkage control parameters; perform multi-objective optimization based on the multiple combinations of linkage control parameters, and perform control verification according to the optimization results. When the verification passes, generate the linkage collaborative control scheme.

[0047] Specifically, after obtaining the control feedback data, it is merged with the two-way real-time dataset into a single dataset. Based on this dataset, a multi-dimensional optimization space is constructed, encompassing parameters such as equipment load, efficiency, and energy consumption. Within this multi-dimensional optimization space, various data not only provide the current operating efficiency of the equipment but also demonstrate the interactions between different devices and regions, thus providing a foundation for subsequent optimization decisions. Subsequently, design information for the energy station units and end-user energy units, such as geometry, internal configuration, and connection relationships, is acquired. This design information is then input into digital twin software (such as PTC ThingWorx, Siemens NX / Simcenter, and Ansys Twin Builder) to construct digital twin models of the energy station units and end-user energy units. Afterward, the constructed digital twin models are mapped onto the multi-dimensional optimization space, and boundary conditions are set, such as maximum load, minimum load, energy efficiency range, and regulation capacity. These boundaries reflect the operational limitations and maximum potential of the equipment, ensuring that all control parameters remain within reasonable operating ranges and preventing equipment overload or inefficient operation. After setting the boundaries, a virtual collaborative control simulation scenario can be generated. This scenario simulates the interaction between energy station units and end-user energy units under different operating conditions, enabling prediction of performance under different scheduling strategies. Then, based on the collaborative control simulation scenario, the operating modes between the energy station units and end-user energy units are gradually adjusted by simulating different control strategies and regulation parameters. In each iteration, optimization is performed based on feedback from the simulation scenario, adjusting control parameters to continuously improve the coordination between the energy station and end-user energy units. Multiple iterations help the system find multiple combinations of linked control parameters. After obtaining these combinations, multi-objective optimization is performed. This process aims to optimize the overall operating efficiency of the energy station units and end-user energy units by adjusting energy flow and scheduling strategies between different devices and areas, ensuring energy supply stability while reducing energy waste. Multi-objective optimization considers not only a single objective (such as minimizing energy costs) but also multiple factors such as system stability, equipment lifespan, and energy demand. Finally, the optimized combinations of multiple linkage control parameters are applied to a collaborative control simulation scenario for control verification, simulating their effect in a real environment. By comparing the simulation results with the expected optimization objectives, it is verified whether each set of linkage control parameter combinations meets the requirements. If a linkage control parameter combination passes verification, the one with the smallest error to the expected optimization objective is extracted from the passed combinations and used as the linkage collaborative control scheme. This scheme is then implemented in actual operation to achieve more intelligent and efficient energy management.

[0048] In summary, the remote control method for energy stations in industrial parks provided by this invention has the following technical effects:

[0049] A two-way data channel is established for the target park. Real-time data is collected through this channel to obtain a two-way real-time dataset. The two-way data channel includes energy station units and end-user energy consumption units. Equipment operation analysis is performed on the energy station units to formulate dynamic optimization operation strategies. Energy consumption characteristics analysis is performed on the end-user energy consumption units to determine time-of-use energy consumption benchmark information. The dynamic optimization operation strategies are then implemented and monitored according to the time-of-use energy consumption benchmark information to generate control feedback data. Based on the control feedback data and the two-way real-time dataset, the energy station units and end-user energy consumption units are collaboratively optimized to obtain a coordinated control scheme. This achieves the technical effect of improving energy utilization efficiency and reducing energy consumption through intelligent scheduling, enabling dynamic optimization of the operation of energy stations and end-user energy consumption units.

[0050] Example 2, as Figure 2 This is a schematic diagram of the structure of the remote control system for energy stations in industrial parks according to the present invention. For example, Figure 1 The flowchart of the remote control method for energy stations in industrial parks according to the present invention can be illustrated as follows: Figure 2 The structure shown is implemented.

[0051] Based on the same concept as the remote control method for energy stations in industrial parks described in the above embodiments, the present invention also provides a remote control system for energy stations in industrial parks, comprising:

[0052] Real-time acquisition module 11: Establishes a two-way data channel for the target park, and performs real-time acquisition through the two-way data channel to obtain a two-way real-time dataset. The two-way data channel includes energy station units and end-user energy consumption units. Data analysis module 12: Performs equipment operation analysis on the energy station units, formulates dynamic optimization operation strategies, and performs energy consumption characteristic analysis on the end-user energy consumption units to determine time-of-use energy consumption benchmark information. Control and monitoring module 13: Executes control and monitoring of the dynamic optimization operation strategies according to the time-of-use energy consumption benchmark information, and generates control feedback data. Collaborative optimization module 14: Based on the control feedback data and the two-way real-time dataset, performs collaborative optimization on the energy station units and the end-user energy consumption units to obtain a coordinated control scheme.

[0053] In some embodiments, the real-time acquisition module 11 includes:

[0054] A bidirectional data channel is established between the energy station units and the end-user energy consumption units in the target park through a smart energy management and control platform. Data is synchronously collected from the energy station units through the bidirectional data channel to obtain equipment operating parameters, and data is synchronously collected from the end-user energy consumption units through the bidirectional data channel to obtain end-user energy consumption data. The equipment operating parameters and the end-user energy consumption data are feature-aligned according to spatiotemporal coding rules to construct the bidirectional real-time dataset.

[0055] In some embodiments, the real-time acquisition module 11 includes:

[0056] A data quality assessment matrix is ​​constructed to score the equipment operating parameters and the end-user energy consumption data, generating a two-way data score value, which includes the equipment operating score value and the end-user energy consumption score value. Based on the equipment operating score value, time-shift compensation is performed on the equipment operating parameters to obtain updated equipment operating parameters. Based on the end-user energy consumption score value, time-shift compensation is performed on the end-user energy consumption data to obtain updated end-user energy consumption data. The updated equipment operating parameters and the updated end-user energy consumption data are correlated and aligned to obtain dynamic correlation data between the energy station and the end-user, and this dynamic correlation data is added to the two-way real-time dataset.

[0057] In some embodiments, the data analysis module 12 further includes:

[0058] A multi-dimensional equipment operation analysis is performed on the energy station unit to generate an equipment status assessment matrix; the operation of the energy station unit is predicted using the equipment status assessment matrix, and an operation change trend diagram of the energy station unit is drawn based on the prediction results; the equipment operation deviation is calculated based on the operation change trend diagram to obtain the operation deviation degree; the operation of the energy station unit is corrected based on the operation deviation degree, and the dynamic optimization operation strategy is formulated.

[0059] In some embodiments, the data analysis module 12 includes:

[0060] The energy consumption characteristics of the terminal energy-consuming units are extracted by region to determine the energy consumption characteristics of multiple regions. Based on the energy consumption characteristics of multiple regions, an energy consumption behavior feature vector of the terminal energy-consuming units is constructed. Based on the energy consumption behavior feature vector, cluster analysis is performed to determine multiple energy consumption patterns. The load is synchronously recorded by traversing the multiple energy consumption patterns to obtain multiple load curves. The multiple load curves correspond to the multiple energy consumption patterns. Based on the multiple load curves, the terminal energy-consuming units are dynamically adjusted in a time-sharing manner to determine the energy consumption benchmark value. The energy consumption benchmark value is added to the time-sharing energy consumption benchmark information.

[0061] In some embodiments, the control monitoring module 13 includes:

[0062] Load decomposition is performed based on the multiple load curves, and the operation of the energy station unit is analyzed to obtain the cooling and heating operating efficiency. A dynamic optimization strategy is simulated and analyzed according to the cooling and heating operating efficiency to generate a multi-level control instruction set. The energy station unit and the terminal energy consumption unit are controlled and recorded according to the multi-level control instruction set to obtain energy station equipment control parameters and terminal energy consumption response data. Continuous monitoring of the operation control of the energy station unit and the terminal energy consumption unit is performed based on the energy station equipment control parameters and terminal energy consumption response data to generate the control feedback data.

[0063] In some embodiments, the control monitoring module 13 includes:

[0064] The energy station equipment control parameters and the end-user energy consumption response data are time-normalized and aligned to determine the equipment response timing and control command timing. The energy station unit is then analyzed according to the equipment response timing to obtain a first control effect. The end-user energy consumption unit is then analyzed according to the control command timing to obtain a second control effect. A first correlation mapping parameter is constructed between the energy station equipment control parameters and the multi-level control command set based on the first control effect. A second correlation mapping parameter is constructed between the end-user energy consumption response data and the multi-level control command set based on the second control effect. The first and second correlation mapping parameters are then subjected to dimensionality reduction evaluation to generate the control feedback data.

[0065] In some embodiments, the collaborative optimization module 14 includes:

[0066] The regulation feedback data is fused with the bidirectional real-time dataset to construct a multi-dimensional optimization space. The energy station unit and the end-user energy unit are digitally twinned and mapped to the multi-dimensional optimization space to generate a collaborative control simulation scenario. Based on the collaborative control simulation scenario, the energy station unit and the end-user energy unit are iteratively coordinated to determine multiple combinations of linkage control parameters. Multi-objective optimization is performed based on the multiple combinations of linkage control parameters, and control verification is performed based on the optimization results. When the verification is successful, the linkage and collaborative control scheme is generated.

[0067] In embodiment three, the present invention also provides a computer-readable storage medium that can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the remote control method for energy stations in parks in the embodiments of the present invention, thereby realizing the above-mentioned remote control method for energy stations in parks.

[0068] It should be understood that the embodiments disclosed in this invention and the above description enable those skilled in the art to implement this invention. However, this invention is not limited to the embodiments mentioned above. It should be understood that those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this invention, and should all be included within the protection scope of this invention.

Claims

1. A remote control method for energy stations in industrial parks, characterized in that, The method includes: A two-way data channel is established for the target park. Real-time data is collected through the two-way data channel to obtain a two-way real-time dataset. The two-way data channel includes energy station units and end-user energy consumption units. The energy station unit is analyzed for equipment operation, and a dynamic optimization operation strategy is formulated. The end-user energy unit is analyzed for energy consumption characteristics, and time-of-use energy consumption benchmark information is determined. The system performs regulation and monitoring based on the time-of-use energy consumption baseline information to implement the dynamic optimization operation strategy and generate regulation feedback data. Based on the regulation feedback data and the two-way real-time dataset, the energy station unit and the end-user energy unit are coordinated and optimized to obtain a coordinated control scheme. The acquisition of bidirectional real-time datasets includes: A two-way data channel is established between the energy station units and the end-user energy units in the target park through a smart energy management and control platform. Data is synchronously collected from the energy station unit through the bidirectional data channel to obtain equipment operating parameters, and data is synchronously collected from the end-user energy unit through the bidirectional data channel to obtain end-user energy data. The device operating parameters and the end-point energy consumption data are aligned according to spatiotemporal coding rules to construct the bidirectional real-time dataset. The construction of the bidirectional real-time dataset includes: A data quality assessment matrix is ​​constructed to score the equipment operating parameters and the end-point energy consumption data, generating a two-way data score value, which includes the equipment operating score value and the end-point energy consumption score value. Based on the equipment operation score, the equipment operation parameters are time-shifted to obtain updated equipment operation parameters; based on the end-point energy consumption score, the end-point energy consumption data is time-shifted to obtain updated end-point energy consumption data. The device operation update parameters are correlated and aligned with the end-point energy consumption update data to obtain dynamic correlation data between energy stations and end-points, and the dynamic correlation data between energy stations and end-points is added to the bidirectional real-time dataset. The formulation of dynamic optimization operation strategies includes: A multi-dimensional equipment operation analysis is performed on the energy station unit to generate an equipment status assessment matrix; The operation of the energy station unit is predicted using the equipment status assessment matrix, and the operation change trend diagram of the energy station unit is drawn based on the prediction results; Based on the aforementioned operational trend chart, calculate the operational deviation of the equipment to obtain the operational deviation degree; Based on the operational deviation, the energy station unit is operated to correct its deviation, and the dynamic optimization operation strategy is formulated.

2. The remote control method for energy stations in industrial parks as described in claim 1, characterized in that, The method includes performing energy consumption characteristic analysis on the terminal energy-consuming unit to determine time-of-use energy consumption benchmark information, and the method includes: The energy consumption features of the end-user energy consumption unit are extracted by partitioning to determine the energy consumption features of multiple zones, and the energy consumption behavior feature vector of the end-user energy consumption unit is constructed based on the energy consumption features of multiple zones. Cluster analysis is performed based on the energy consumption behavior feature vector to determine multiple energy consumption patterns. Load is synchronously recorded by traversing the multiple energy consumption patterns to obtain multiple load curves. The multiple load curves correspond to the multiple energy consumption patterns. Based on the multiple load curves, the terminal energy consumption unit is dynamically adjusted in a time-sharing manner to determine the energy consumption benchmark value, and the energy consumption benchmark value is added to the time-sharing energy consumption benchmark information.

3. The remote control method for energy stations in industrial parks as described in claim 2, characterized in that, The method includes: implementing the dynamic optimization operation strategy based on the time-of-use energy consumption baseline information, and generating control feedback data. Based on the multiple load curves, load decomposition is performed, and the operation analysis of the energy station unit is conducted to obtain the cooling and heating operation efficiency. The dynamic optimization strategy for simulated cold and hot operation efficiency is analyzed to generate a multi-level control instruction set. The energy station unit and the end-user energy unit are controlled and recorded according to the multi-level control instruction set to obtain the energy station equipment control parameters and end-user energy response data. Based on the energy station equipment control parameters and the end-user energy consumption response data, the operation control of the energy station unit and the end-user energy consumption unit is continuously monitored, and the control feedback data is generated.

4. The remote control method for energy stations in industrial parks as described in claim 3, characterized in that, Continuous monitoring of the operation and control of the energy station unit and the end-user energy consumption unit based on the energy station equipment control parameters and the end-user energy consumption response data, generating the control feedback data, includes: The energy station equipment control parameters and the end-point energy consumption response data are time-normalized and aligned to determine the equipment response timing and control command timing. The energy station unit is regulated and analyzed according to the device response timing to obtain a first regulation effect; the end-user energy unit is regulated and analyzed according to the regulation command timing to obtain a second regulation effect. Based on the first control effect, a first association mapping parameter is constructed between the control parameters of the energy station equipment and the multi-level control instruction set; based on the second control effect, a second association mapping parameter is constructed between the end-point energy consumption response data and the multi-level control instruction set. The first and second association mapping parameters are evaluated by dimensionality reduction to generate the regulation feedback data.

5. The remote control method for energy stations in industrial parks as described in claim 1, characterized in that, Based on the control feedback data and the bidirectional real-time dataset, the energy station unit and the end-user energy unit are coordinated and optimized to obtain a coordinated control scheme. The method includes: The regulation feedback data is combined with the two-way real-time dataset to perform data fusion and construct a multi-dimensional optimization space. The energy station unit and the end-user energy unit are digitally twinned and mapped to the multi-dimensional optimization space to generate a collaborative control simulation scenario; Based on the aforementioned collaborative control simulation scenario, the energy station unit and the end-user energy unit are iteratively coordinated to determine multiple combinations of linkage control parameters. Multi-objective optimization is performed based on the combination of multiple linkage control parameters, and control verification is performed based on the optimization results. When the verification is successful, the linkage and cooperative control scheme is generated.

6. A remote control system for energy stations in industrial parks, characterized in that: The method for remote control of energy stations in industrial parks as described in any one of claims 1-5 includes: Real-time acquisition module: Establishes a two-way data channel for the target park, and performs real-time acquisition through the two-way data channel to obtain a two-way real-time dataset. The two-way data channel includes energy station units and end-user energy units. Data analysis module: performs equipment operation analysis on the energy station unit, formulates dynamic optimization operation strategies, performs energy consumption characteristic analysis on the end-user energy unit, and determines time-of-use energy consumption benchmark information; Regulation and monitoring module: Executes the regulation and monitoring of the dynamic optimization operation strategy according to the time-of-use energy consumption benchmark information, and generates regulation and monitoring feedback data; Collaborative optimization module: Based on the regulation feedback data and the bidirectional real-time dataset, the energy station unit and the end-user energy unit are collaboratively optimized to obtain a coordinated control scheme.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the remote control method for energy stations in the park as described in any one of claims 1 to 5.

Images