Cogeneration multi-device capacity collaborative optimization method and system

Abstract

The invention discloses a multi-device capacity collaborative optimization method and system for combined heat and power generation, and relates to the technical field of collaborative optimization, and the method comprises the steps: carrying out the multi-dimensional data scheduling of a plurality of devices, and obtaining a plurality of initial historical operation data; performing data cleaning processing to generate a historical operation data set; performing load prediction on the plurality of devices to obtain a load prediction result; operation analysis is carried out in combination with multiple equipment capacity parameters, and a multi-equipment operation scheduling strategy is formulated; executing the multi-device operation scheduling strategy, and generating a multi-device cooperative operation suggestion; and performing a simulation test, generating an operation test result, and obtaining a multi-device collaborative operation optimization suggestion. According to the method, the technical problems of poor equipment capacity collaboration, inaccurate load prediction, unreasonable operation scheduling and low energy utilization efficiency of the cogeneration system in the prior art are solved, and the technical effects of realizing accurate load prediction, optimizing equipment capacity matching and collaborative operation and improving the energy utilization efficiency are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative optimization, and in particular to a method and system for collaborative optimization of multi-device capacity in cogeneration of heat and power. Background Art

[0002] As an efficient way of energy utilization, cogeneration system occupies an important position in industrial production and residents' lives. However, the current cogeneration technology faces a series of problems that need to be solved urgently. In terms of multi-device coordination, the operation of multiple devices such as power generation equipment and heating equipment in the system lacks precise coordination, and the capacity parameters of different equipment cannot be effectively matched, resulting in unreasonable distribution of energy among devices in actual operation, and the performance advantages of each device cannot be fully utilized, which reduces the overall energy conversion efficiency of the system, causes energy waste, and increases operating costs. Load forecasting is the key basis for optimizing the operation of cogeneration systems, but the existing technology has obvious deficiencies in this regard. Electricity and thermal loads are affected by many complex factors, such as weather changes, economic activity cycles, residents' work and rest habits, etc., and their changing laws are difficult to accurately grasp. Traditional load forecasting methods often fail to fully consider the combined effects of these complex factors, resulting in a large error between the forecast results and the actual load demand. Inaccurate load forecasting makes it difficult for the system to make reasonable operation scheduling arrangements in advance, and it is easy to have an oversupply or undersupply of energy, affecting the stability and reliability of the system.

[0003] The existing technology has technical problems such as poor coordination of equipment capacity in cogeneration systems, inaccurate load forecasting, unreasonable operation scheduling, and low energy utilization efficiency. Summary of the invention

[0004] The present application provides a method and system for collaborative optimization of the capacity of multiple devices in cogeneration, which is used to solve the technical problems in the prior art of poor coordination of the capacity of cogeneration system equipment, inaccurate load forecasting, unreasonable operation scheduling, and low energy efficiency.

[0005] In view of the above problems, the present application provides a method and system for collaborative optimization of multi-device capacity in cogeneration.

[0006] In a first aspect of the present application, a method for collaboratively optimizing the capacity of multiple devices in cogeneration of heat and power is provided, the method comprising:

[0007] Based on the cogeneration system, multi-dimensional data scheduling is performed on multiple devices to obtain multiple initial historical operation data; data cleaning processing is performed on the multiple initial historical operation data to generate a historical operation data set; load forecasting is performed on multiple devices based on the historical operation data set to obtain load forecasting results of the cogeneration system; operation analysis is performed based on the load forecasting results in combination with multiple device capacity parameters to formulate a multi-device operation scheduling strategy; device capacity matching is performed based on multiple devices to obtain capacity matching results, and the multi-device operation scheduling strategy is executed according to the capacity matching results to perform collaborative analysis on multiple devices to generate multi-device collaborative operation suggestions; simulation testing is performed according to the multi-device collaborative operation suggestions to generate operation test results, and the multi-device collaborative operation suggestions are optimized according to the operation test results to obtain multi-device collaborative operation optimization suggestions.

[0008] A second aspect of the present application provides a multi-device capacity collaborative optimization system for cogeneration of heat and power, the system comprising:

[0009] An initial historical operation data acquisition module, wherein the initial historical operation data acquisition module performs multi-dimensional data scheduling on multiple devices based on the cogeneration system to obtain multiple initial historical operation data; a historical operation data set generation module, wherein the historical operation data set generation module is used to perform data cleaning processing on the multiple initial historical operation data to generate a historical operation data set; a load forecast result acquisition module, wherein the load forecast result acquisition module performs load forecasting on multiple devices based on the historical operation data set to obtain a load forecast result of the cogeneration system; an operation scheduling strategy formulation module, wherein the operation scheduling strategy formulation module is used to perform operation analysis based on the load forecast result in combination with multiple device capacity parameters to formulate a multi-device operation scheduling strategy; a collaborative operation suggestion generation module, wherein the collaborative operation suggestion generation module performs device capacity matching based on multiple devices to obtain a capacity matching result, executes the multi-device operation scheduling strategy based on the capacity matching result to perform collaborative analysis on multiple devices to generate a multi-device collaborative operation suggestion; an optimization suggestion acquisition module, wherein the optimization suggestion acquisition module is used to perform simulation testing according to the multi-device collaborative operation suggestion to generate an operation test result, optimize the multi-device collaborative operation suggestion based on the operation test result, and obtain a multi-device collaborative operation optimization suggestion.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] Based on the cogeneration system, multiple devices are scheduled with multi-dimensional data to obtain multiple initial historical operation data; the initial historical operation data are cleaned and processed to generate historical operation data sets; load forecasting is performed on multiple devices to obtain load forecasting results of the cogeneration system; operation analysis is performed based on the load forecasting results combined with multiple device capacity parameters to formulate multi-device operation scheduling strategies; device capacity matching is performed based on multiple devices to obtain capacity matching results, collaborative analysis is performed to generate multi-device collaborative operation suggestions; simulation tests are performed according to the multi-device collaborative operation suggestions to generate operation test results, and the multi-device collaborative operation suggestions are optimized according to the operation test results to obtain multi-device collaborative operation optimization suggestions. The technical effects of realizing accurate load forecasting, optimizing device capacity matching and collaborative operation, and improving energy utilization efficiency are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of a method for collaborative optimization of multi-equipment capacity for cogeneration of heat and power provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a multi-device capacity collaborative optimization system for cogeneration provided in an embodiment of the present application.

[0015] Explanation of the reference numerals: initial historical operation data acquisition module 10, historical operation data set generation module 20, load forecast result acquisition module 30, operation scheduling strategy formulation module 40, collaborative operation suggestion generation module 50, optimization suggestion acquisition module 60. DETAILED DESCRIPTION

[0016] The present application provides a method and system for collaborative optimization of the capacity of multiple devices in cogeneration, which is used to solve the technical problems in the prior art of poor coordination of equipment capacity in cogeneration systems, inaccurate load forecasting, unreasonable operation scheduling, and low energy efficiency.

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a method for collaborative optimization of multi-equipment capacity of cogeneration, the method comprising:

[0019] Step S100: Perform multi-dimensional data scheduling on multiple devices based on the cogeneration system to obtain multiple initial historical operation data.

[0020] Specifically, for power generation equipment, such as steam turbines and generators, key operating parameters such as output power, speed, temperature, and pressure are collected, and time-related data such as operating time and number of starts and stops, as well as auxiliary operating data such as lubricating oil temperature and oil pressure, are recorded to monitor the working status of power generation equipment in all directions. For heating equipment, such as boilers and heat exchangers, key heating indicators such as steam production, steam temperature, hot water flow, and supply and return water temperature are obtained, as well as data related to energy utilization such as fuel consumption rate and combustion efficiency, while paying attention to the stability data of equipment operation, such as pressure fluctuations. In addition, environmental monitoring equipment collects external environmental data such as ambient temperature, humidity, and atmospheric pressure in real time, which helps to analyze the impact of environmental factors on equipment operation. Through the data acquisition network in the cogeneration system, the above multi-dimensional data is accurately obtained from the sensors, monitoring systems, and related records of each device according to the set time interval and data format, so as to obtain multiple initial historical operating data, providing a comprehensive and detailed data basis for subsequent in-depth analysis of equipment operating characteristics and optimization of system operation.

[0021] Step S200: performing data cleaning processing on the plurality of initial historical operation data to generate a historical operation data set.

[0022] Specifically, a series of data cleaning and processing techniques are used to generate high-quality historical operation data sets for the multiple initial historical operation data obtained. First, through data integrity checks, records with missing values ​​in the data set are identified and marked. For key data with a small number of missing values, mean filling, median filling, or model-based prediction filling are used to repair them; for data columns with many missing values ​​that are difficult to accurately supplement, after careful evaluation, the relevant records are directly deleted to ensure the integrity and reliability of the data. Next, data consistency checks are used to detect whether there are logical conflicts between the same parameter data collected from different data sources or the same data source at different times, for example, unreasonable jumps in temperature data collected by the same device at adjacent time points. Once inconsistencies are found, the causes are analyzed in depth. They may be caused by sensor failure, data transmission errors, etc., and data correction or deletion of erroneous data is performed according to the specific situation. At the same time, outlier detection algorithms are used, such as the 3σ rule based on statistical principles, the box plot method, or the clustering method based on machine learning, to find out outliers that are significantly deviated from the normal data range. For data points confirmed as abnormal, analysis is conducted in combination with the equipment operation principle and actual working conditions to determine whether they are real abnormal events (such as sudden equipment failure) or data collection errors. If the data collection is wrong, it will be corrected; if it is a real abnormal event, the abnormal value will be retained and considered as a special case in subsequent analysis. After the above data cleaning and processing steps, invalid, erroneous and redundant data are eliminated, and finally a historical operation data set that can accurately reflect the real operating status of multiple devices in the cogeneration system is generated, providing a solid data foundation for subsequent load forecasting, operation analysis and other work.

[0023] Step S300: performing load forecasting on a plurality of devices based on the historical operation data set to obtain a load forecasting result of a cogeneration system.

[0024] Specifically, the historical operation data set is preprocessed to ensure that the stability and periodicity of the data are obvious. For time series data, check whether there are trends, seasonality and other regularities. If there is a trend, eliminate the trend influence through methods such as difference to make the data stable; if there is seasonality, determine the seasonal cycle and perform corresponding decomposition and processing. Then, select a suitable time series analysis model according to the equipment type and data characteristics, such as ARIMA (autoregressive moving average) model. For power generation equipment, analyze the autocorrelation of its historical power generation data, determine the model parameters such as autoregressive order (p) and moving average order (q); for heating equipment, study the change of its heating load over time and determine the corresponding model structure. Use historical operation data to estimate the parameters of the selected model, and find the optimal parameter value for the model to fit the data through methods such as maximum likelihood estimation. Then, use the trained time series analysis model to predict the equipment load in the future period. According to the prediction formula of the model and the information in the historical data, calculate the load forecast value of the equipment at each time point in the future, including the power load of the power generation equipment and the thermal load of the heating equipment. The forecast results are presented in the form of time series, which clearly show the load change trend over time, provide a forward-looking basis for the operation and scheduling of the cogeneration system, and help the system plan energy production and distribution in advance to ensure efficient operation while meeting future load demands.

[0025] Step S400: Performing operation analysis based on the load forecast result in combination with multiple equipment capacity parameters, and formulating a multi-equipment operation scheduling strategy.

[0026] Specifically, a comprehensive and in-depth operation analysis is carried out based on the load forecast results and closely combined with multiple equipment capacity parameters, and then a scientific and reasonable multi-equipment operation and scheduling strategy is formulated. First, the load forecast results are carefully studied to clarify the demand change trends of power load and thermal load in different periods in the future, such as the sharp rise of power load during peak power consumption periods and the continuous high operation of thermal load in cold seasons. At the same time, the capacity parameters of each device are accurately mastered, including key indicators such as the maximum power output of power generation equipment and the maximum heating capacity of heating equipment. Taking into account the load demand and equipment capacity, the operating status and potential of each device under different load scenarios are analyzed. For power generation equipment, the optimal power generation combination is evaluated to meet the power load demand to avoid overload or inefficient operation of the equipment. For example, when the power load is at its peak and close to the total capacity of the equipment, the output power of different power generation equipment is reasonably allocated, and the high-efficiency units are started first and run at a state close to the rated capacity. At the same time, the standby units are ensured to be ready to start at any time to deal with emergencies. For heating equipment, the start and stop time of the equipment and the heating temperature adjustment strategy are determined according to the thermal load demand and the heating capacity of the equipment. When the demand for heating is low, the operating load of some heating equipment should be appropriately reduced or some standby equipment should be shut down to reduce energy consumption; when the demand for heating is peak, ensure that all heating equipment operates efficiently and the heating temperature is stable. In addition, the synergy between equipment and the energy conversion efficiency should be fully considered. Analyze how the waste heat from power generation can be efficiently used for heating in the cogeneration process, and the impact of changes in heating demand on the operation of power generation equipment. By optimizing the energy transfer and conversion process between equipment, a multi-equipment operation scheduling strategy is formulated to achieve energy cascade utilization and improve the overall energy utilization efficiency of the system. The strategy specifies in detail the operating mode, output power, temperature setting and other parameters of each device at different times, ensuring that the cogeneration system can meet the load demand while the equipment operates safely, stably and efficiently, thereby maximizing economic and energy benefits.

[0027] Step S500: performing device capacity matching based on multiple devices to obtain a capacity matching result, executing the multi-device operation scheduling strategy according to the capacity matching result to perform collaborative analysis on the multiple devices, and generating a multi-device collaborative operation suggestion.

[0028] Specifically, firstly, a comprehensive equipment capacity matching work is carried out based on multiple devices in the cogeneration system. The actual capacity of each device is accurately measured and evaluated, including the power generation capacity of the power generation equipment and the heating capacity of the heating equipment, while considering the capacity changes of the equipment under different working conditions, such as the impact of equipment aging and ambient temperature changes on the capacity. By analyzing the relationship between the capacity of each device and the overall demand of the system in detail, accurate capacity matching results are obtained, and it is clear which devices are mutually compatible in capacity and which devices have capacity gaps that need further coordination. Then, based on this capacity matching result, the previously formulated multi-device operation scheduling strategy is strictly implemented, and an in-depth collaborative analysis is carried out on multiple devices. From an overall perspective, the interactive relationship between the energy flow, material flow and information flow between devices is considered, and the collaborative working mode between devices under different load conditions is analyzed. For example, when the power load is at a peak and the heating demand is large, how to ensure that the waste heat generated by the full-load operation of the power generation equipment is fully utilized by the heating equipment to achieve efficient cascade utilization of energy. At the same time, attention is paid to the dynamic response characteristics between devices, and the impact on other devices and the stability of the entire system when the operating state of a certain device changes is studied. Through the above collaborative analysis process, a multi-device collaborative operation suggestion is generated, which specifies in detail the specific operating parameters of each device at different operation stages, such as the power adjustment timing and amplitude of the power generation equipment, the supply and return water temperature setting value of the heating equipment, the energy distribution ratio between the devices, etc. The coordinated control strategy between the devices is also clarified, including the start and stop sequence of the equipment, the priority of load adjustment, etc., to ensure that multiple devices can work closely together during operation, realize the efficient, stable and economical operation of the cogeneration system, and improve the overall performance and energy utilization efficiency of the system.

[0029] Step S600: Perform simulation test according to the multi-device collaborative operation suggestion, generate operation test results, optimize the multi-device collaborative operation suggestion according to the operation test results, and obtain multi-device collaborative operation optimization suggestion.

[0030] Specifically, first, an accurate simulation model is constructed according to the multi-device collaborative operation suggestions to simulate the actual operating environment of the cogeneration system, including equipment characteristics, energy supply, load demand changes and other factors. The parameter settings and operation strategies in the multi-device collaborative operation suggestions are fully applied to the simulation model to simulate the continuous operation process of the system over a period of time, thereby generating operation test results. The operation test results cover various performance indicators of the system, such as energy conversion efficiency, equipment utilization, pollutant emission levels, and the stability of power and heat supply. The operation test results are analyzed in depth, and the performance indicators obtained by the actual simulation are compared with the expected goals to find out the gaps and deficiencies. For example, if it is found that the energy conversion efficiency does not reach the expected high level, it is analyzed whether it is due to the lack of tacit cooperation between the equipment, resulting in increased energy losses, or because the deviation between the load forecast and the actual demand makes the equipment operation parameter settings unreasonable. In response to these problems, the multi-device collaborative operation suggestions are optimized in a targeted manner, involving adjusting the load distribution ratio between equipment, optimizing the equipment start and stop time, and improving the control strategy to enhance the dynamic response coordination between equipment. After multiple iterations of optimization, the suggestions for coordinated operation of multiple devices were continuously improved until the simulation test results met the performance requirements of the system, and finally the optimization suggestions for coordinated operation of multiple devices were obtained. These optimization suggestions fully considered the complexity of the system and various factors in actual operation, and can effectively improve the overall operation effect of the cogeneration system, achieve multiple goals such as efficient use of energy, reasonable operation of equipment, and environmental friendliness, and provide scientific and reliable guidance for the operation of the actual system.

[0031] In a possible implementation, step S200 further includes:

[0032] Step S210: converting the format of the plurality of initial historical operation data to generate a target conversion data format.

[0033] Step S220: traverse and identify the multiple initial historical operation data according to the target conversion data format, and determine multiple data to be processed, wherein the multiple data to be processed include missing data to be processed, abnormal data to be processed, and duplicate data to be processed.

[0034] Step S230: Filling the plurality of initial historical operation data according to the missing data to be processed to generate first processed data.

[0035] Step S240: performing correction processing on the plurality of initial historical operation data according to the abnormal data to be processed to generate second processed data.

[0036] Step S250: performing padding processing on the plurality of initial historical operation data according to the duplicate data to be processed to generate third processed data.

[0037] Step S260: Integrate the first processed data, the second processed data, and the third processed data to generate the historical operation data set.

[0038] Specifically, since the initial historical operation data may come from a variety of different types of equipment and systems, the data formats are different, such as some equipment data is in text format, and some may be in a specific binary format, etc. Through format conversion, these multiple initial historical operation data in different formats are uniformly converted into a target conversion data format, for example, converted into a structured table format suitable for subsequent data analysis and processing (such as CSV format or database table format), so as to facilitate further processing and analysis of the data.

[0039] According to the determined target conversion data format, multiple initial historical operation data are traversed and identified. In this process, the system will check the data row by row and column by column, and determine the multiple data to be processed through the preset data verification rules and algorithms. These data to be processed include various types, such as missing data to be processed, that is, the data in certain key positions or time periods in the data set are missing, which may be caused by sensor failure, data transmission interruption and other reasons; abnormal data to be processed, whose values ​​are obviously deviated from the normal range, may be due to the sudden abnormal operation of the equipment or external interference. The generated erroneous data; there is also duplicate data to be processed, that is, there are data records that are exactly the same or highly similar in key features, which may be duplicate records in the data collection process or data redundancy caused by system errors.

[0040] For the missing data to be processed, a suitable filling method is used to process multiple initial historical operation data. According to the characteristics and distribution of the data, you can choose to use the mean filling method (when the data presents a certain normal distribution, the missing value is filled with the average value of the column data), the median filling method (for data with skewed distribution, the median is filled), the interpolation method (such as linear interpolation, based on the known data points before and after the missing data to build a linear function to estimate the missing value) or the model-based filling method (using the machine learning model to predict the missing value based on other relevant data features). After the filling process, the first processed data is generated, so that the missing data in the data set is initially repaired, and the integrity of the data is improved to a certain extent.

[0041] Correct the multiple initial historical operation data according to the abnormal data to be processed. The correction of abnormal data requires a comprehensive judgment based on the equipment operation principle, historical data rules and actual working conditions. For obviously erroneous abnormal data, such as data that exceeds the reasonable range, it can be directly corrected according to the normal operating range of the equipment; for some data with unclear reasons but abnormal values, by comparing and analyzing with the surrounding normal data, referring to the data change trend when the equipment is operating normally, smoothing processing (such as weighted moving average method, giving different weights to the abnormal data and its surrounding data for averaging, reducing the impact of abnormal data) or calculating and correcting according to the logical relationship of the data (such as correcting abnormal energy data in combination with other relevant data according to physical laws such as the law of conservation of energy) and other methods. After the correction process, the second processed data is generated, which further improves the accuracy of the data.

[0042] For duplicate data to be processed, multiple initial historical operation data are deduplicated according to their duplication. Duplicate data is identified by comparing key identification fields in data records (such as timestamps, device numbers, data feature values, etc.), and then one valid data record is retained and other duplicate records are deleted. For some records that may have slight differences but belong to the category of duplicate data, they are screened and retained according to the principles of data importance and accuracy. After deduplication, the third processed data is generated, which reduces data redundancy and optimizes the data structure.

[0043] The first processed data after filling missing data, the second processed data after correcting abnormal data, and the third processed data after deduplication are integrated. The integration process ensures that the order, structure, and relevance of the data are correct, and they are merged into a complete data set, that is, a historical operation data set is generated. After the above series of data processing steps, this data set has a high data quality and can more accurately reflect the actual operating status of multiple devices in the cogeneration system, providing a solid and reliable data foundation for subsequent load forecasting, operation analysis, etc., which helps to improve the operation management level and optimization decision-making ability of the entire cogeneration system.

[0044] In a possible implementation, step S300 further includes:

[0045] Step S310: extracting features of multiple devices based on the historical operation data to obtain multiple device operation features.

[0046] Step S320: using correlation analysis to screen the plurality of equipment operation characteristics according to the load change data to determine a plurality of load characteristics.

[0047] Step S330: Perform load analysis according to the load change data and the operating time series, and construct a time series model.

[0048] Step S340: Synchronize the multiple load characteristics to the time series model to perform load forecasting and obtain the load forecasting result.

[0049] Specifically, feature extraction is carried out based on existing historical operating data. Key information closely related to the operating status and performance of the equipment is mined from a large amount of complex historical operating data, and this information is presented in the form of multiple equipment operating characteristics. For power generation equipment, the extracted features include the curve of power generation over time, power generation efficiency under different working conditions, and the correlation characteristics between equipment temperature and power generation; for heating equipment, it involves the fluctuation characteristics of heating flow, the relationship characteristics between heating temperature and energy consumption, and the correlation characteristics between equipment start-stop frequency and heating stability. Through data mining technology and professional analysis algorithms, historical operating data is deeply analyzed to accurately obtain multiple equipment operating characteristics, which will serve as an important basis for subsequent analysis and prediction.

[0050] The correlation analysis method is used to screen multiple equipment operation characteristics according to the load change data. The load change data is the key information reflecting the changes in the power and thermal load demand of the cogeneration system at different time points. By calculating the correlation coefficient between each equipment operation characteristic and the load change data, the degree of correlation between the characteristics and the load change is evaluated. For example, if a certain equipment operation characteristic shows a high linear correlation with the increase or decrease of the power load, then this feature may be of great value in predicting the power load; conversely, if the correlation is low, the contribution of this feature to load prediction may be small. According to the set correlation threshold, multiple load characteristics that are closely related to load changes are screened out to ensure that the characteristics used in the subsequent prediction model have strong representativeness and prediction ability, reduce the interference of irrelevant or redundant characteristics on the prediction results, and improve the accuracy and efficiency of the prediction.

[0051] Based on the load change data and in-depth load analysis according to the operating time sequence, a time series model is constructed. The load change data is carefully decomposed in time series to separate the trend component (such as the long-term growth trend of electricity or heat demand), seasonal component (such as the periodic fluctuation of heating load caused by seasonal changes) and random component (such as load changes caused by sudden factors in the short term). According to the characteristics and laws of these components, the appropriate time series model structure is selected, such as the autoregressive integrated moving average (ARIMA) model, the seasonal autoregressive integrated moving average (SARIMA) model, etc., and the order and parameters of the model are determined. By fitting and optimizing the historical load data, a time series model that can accurately describe the load change law is constructed. This model will serve as the core tool for predicting future loads, and the time series information in the historical data is used to infer the future load change trend.

[0052] The multiple load characteristics that have been screened and determined are synchronized to the constructed time series model for load forecasting, so as to obtain the load forecast results. The load characteristics are input into the time series model as input variables. The model calculates the load forecast values ​​at different time points in the future according to its internal algorithm and the learned load change law. These forecast values ​​cover the power load forecast and thermal load forecast of the cogeneration system, and present the expected changes in load in the future in a clear and intuitive data form. For example, the forecast results may show the specific values ​​of the peak and trough periods of power load every day in the next week, as well as the demand change trend of heating load in different time periods. These load forecast results will provide key decision-making basis for the operation and scheduling of the cogeneration system, help system managers make plans for equipment operation adjustment, energy storage and distribution in advance, and ensure that the system can achieve efficient and stable operation while meeting load demand.

[0053] In a possible implementation, step S500 further includes:

[0054] Step S510: Perform demand analysis based on multiple devices to obtain multiple device demand information, perform load fluctuation analysis based on device application scenarios and the multiple device demand information to obtain a load fluctuation coefficient, wherein the load fluctuation coefficient includes a load peak value and a load valley value.

[0055] Step S520: Capacity calculation is performed on multiple devices based on the load peak value and the load valley value combined with the multiple device demand information to obtain multiple device capacity information.

[0056] Step S530: The capacity information of the plurality of equipment is matched with the preset rated capacity and evaluated to generate the capacity matching result.

[0057] Specifically, first, a comprehensive demand analysis is carried out based on multiple devices. In-depth research is conducted on the working requirements of each device under different operating conditions, including the energy input requirements of the equipment (such as fuel type, fuel quantity requirements, etc.), output requirements (such as the power output power range of power generation equipment, heating temperature and flow requirements of heating equipment, etc.), operation stability requirements (such as the tolerance range of voltage and pressure fluctuations, etc.) and maintenance requirements (such as the regular maintenance cycle of equipment, the frequency of replacement of wearing parts, etc.), so as to obtain multiple equipment demand information. Then, according to the equipment application scenario, these equipment demand information are combined with the load changes in actual operation to conduct load fluctuation analysis. Considering the load change rules in different scenarios (such as the peak and off-season of industrial production, the peak and trough periods of residential electricity and heat consumption, etc.), the load fluctuation coefficient is calculated, where the load peak represents the maximum load demand borne by the system in a specific scenario, and the load valley is the minimum load demand. These parameters intuitively reflect the degree of load fluctuation under different circumstances, providing a key basis for subsequent equipment capacity calculations.

[0058] Based on the load peak and load valley values ​​calculated previously, and combined with the demand information of multiple devices, accurate capacity calculations are performed for multiple devices. For power generation equipment, the maximum power generation capacity it should have is determined based on the load peak to ensure stable power supply during peak demand. At the same time, the minimum operating capacity of the equipment is reasonably planned with reference to the load valley value and equipment operating efficiency to avoid inefficient operation of the equipment under low load. The heating equipment calculates the equipment capacity that meets the heating requirements in different scenarios based on the peak and valley values ​​of the heating load and the changing law of heating demand. By comprehensively considering factors such as the energy conversion efficiency of the equipment, the ability of the equipment to work together, and the expected future load growth, multiple equipment capacity information is obtained. This information clarifies the optimal capacity configuration required for each device in the cogeneration system to meet the load fluctuation demand.

[0059] The calculated multiple equipment capacity information is matched and evaluated with the preset rated capacity. The preset rated capacity is the theoretical capacity value of the equipment set based on the industry standard. The degree of match between the two is evaluated by comparing the actual calculated equipment capacity information with the preset rated capacity. If the equipment capacity information is close to the preset rated capacity or within a reasonable matching range, it means that the equipment capacity configuration is relatively reasonable; on the contrary, if there is a large deviation, further analysis of the reasons may be caused by improper equipment selection, inaccurate load forecasting, or changes in system operation requirements. Based on the matching evaluation results, the capacity matching results are generated. The results record in detail the matching of each equipment capacity with the preset rated capacity, providing an important reference for the subsequent formulation of equipment operation scheduling strategies and optimization of system operation, which helps to ensure that the cogeneration system operates in an efficient and stable state and achieves reasonable utilization of energy and supply and demand balance.

[0060] In a possible implementation, step S600 further includes:

[0061] Step S610: Set the test target of the simulation test according to the multi-device collaborative operation suggestions.

[0062] Step S620: Data extraction is performed on the multi-device collaborative operation suggestions and determine the data set to be tested.

[0063] Step S630: Build a simulation environment, run tests on the data set to be tested according to the test objectives and combines the simulation environment, and generate multiple test record data.

[0064] Step S640: The plurality of test record data is serialized according to the run time sequence to generate the run test results.

[0065] Specifically, the simulation test goal is set according to the multi-device collaborative operation suggestions. The goal is closely centered around the key performance indicators of system operation, such as energy efficiency, equipment operation stability, pollutant emission levels, and reliability of thermal power supply. For example, a specific percentage improvement target for energy efficiency under specific working conditions is set, or an optimization target for equipment operation stability indicators (such as power fluctuation range, temperature change range, etc.) is set to ensure that the test goal is consistent with the overall optimization direction of the system, providing clear direction guidance for subsequent tests.

[0066] Data extraction operations are carried out for the suggestions for the coordinated operation of multiple devices, and key information such as equipment operating parameters, control strategies, and load distribution plans are mined from the suggestions, and this information is organized into a data set to be tested. This data set comprehensively covers data from all aspects of the coordinated operation of multiple devices, such as the power setting values ​​of each power generation device at different time periods, the heating flow and temperature settings of the heating equipment, and the energy conversion and transfer parameters between devices, providing the necessary data support for accurately simulating actual operation conditions.

[0067] We set out to build a simulation environment based on the actual architecture and operating principles of the cogeneration system, including equipment models (such as accurate models of steam turbines, boilers, generators, etc.), energy supply models (fuel supply systems, grid access models, etc.), load demand models (simulating changes in electricity and heat demand for different types of users), and environmental impact models (considering the impact of environmental factors such as temperature and humidity on system operation). In the built simulation environment, we conduct operation tests on the test data set in accordance with the pre-set test objectives and combined with the characteristics of the environment. During the test, the simulation system simulates the coordinated operation of multiple devices in strict accordance with the parameter settings and control strategies in the data set, records detailed data on equipment operation status, energy conversion and consumption, load supply, and other aspects, and generates multiple test record data, which truly reflects the system's operating performance under given collaborative operation suggestions.

[0068] The generated multiple test record data are serialized according to the operating sequence, and the data recorded at different time points during the test are arranged and integrated in order to form a complete operation test result. The result clearly presents the operating dynamics of the system during the entire test cycle in the form of a time series, including key information such as the equipment startup sequence, power change process, and load supply stability. It intuitively demonstrates the implementation effect of the multi-device collaborative operation suggestion in the simulation environment, providing a direct and comprehensive data basis for the subsequent evaluation and optimization of the suggestion, which will help to further improve the performance and efficiency of the multi-device collaborative operation of the cogeneration system.

[0069] In a possible implementation, step S600 further includes:

[0070] Step S650: Coordinate the operation test results according to the multi-device collaborative operation suggestions, and generate the judgment results.

[0071] Step S660: Evaluate the multi-device collaborative operation suggestions based on the determination results, perform optimization analysis based on the evaluation results, and determine multiple improvement optimization data.

[0072] Step S670: Use the multiple improved optimization data as an index, synchronize to the multi-device collaborative operation suggestions for traversal replacement, and obtain the multi-device collaborative operation optimization suggestions.

[0073] Specifically, the operation test results are collaboratively judged based on the collaborative operation suggestions for multiple devices. Carefully compare the actual operating status of each device in the test results with the ideal status preset in the collaborative operation suggestions to check whether the coordination between the devices meets expectations. For example, observe whether the energy transfer between the power generation equipment and the heating equipment is smooth, whether the start and stop sequence and time of the equipment meet the optimization strategy, and whether the load distribution is balanced and reasonable. Through comprehensive comparative analysis, a judgment result is generated, which clearly points out the execution effect of the collaborative operation suggestions in the actual test, including which aspects perform well and meet expectations, and which parts have deviations or problems.

[0074] According to the judgment results, the suggestions for the coordinated operation of multiple devices are evaluated in depth. Based on the various indicators and problem feedback in the judgment results, comprehensive considerations are made from multiple angles such as the overall system performance, energy utilization efficiency, and equipment operation reliability. For the parts with good performance, experience is summarized and its rationality in the optimization plan is confirmed; for the parts with problems, the reasons are analyzed in depth, involving factors such as improper equipment parameter settings, inaccurate control strategies, and incomplete consideration of actual operating conditions. Then, optimization analysis is carried out for these problems to determine multiple improvement optimization data. These data include adjustment values ​​for equipment operating parameters (such as output power adjustment of power generation equipment, temperature setting optimization value of heating equipment, etc.), improvement directions of control strategies (such as optimizing the coordinated control logic between equipment, adjusting load distribution algorithms, etc.), and measures to enhance the adaptability of operating conditions (such as formulating more flexible operation plans based on the load characteristics of different seasons or time periods).

[0075] The determined multiple improved optimization data are used as indexes and synchronized to the collaborative operation suggestions for multiple devices for traversal and replacement. Following the guidance of the index, the corresponding parts are found in the collaborative operation suggestions and data updates and strategy adjustments are made. For the parts involving equipment parameters, the original values ​​are replaced with optimized parameter values; for the control strategy-related content, the corresponding logic and algorithms are modified according to the improvement direction; for the operating condition adaptability measures, they are integrated into the overall operation suggestions. After such a traversal and replacement process, the optimization suggestions for the collaborative operation of multiple devices are obtained. This optimization suggestion combines the feedback of the test results and the results of the optimization analysis, and can more effectively guide the collaborative operation of multiple devices in the cogeneration system, improve the overall performance, energy utilization efficiency and operational reliability of the system, and achieve a more optimized operating state.

[0076] In a possible implementation, step S660 further includes:

[0077] Step S661: Determine whether the operation test result is greater than or equal to the expected operation threshold.

[0078] Step S662: If the operation test result is less than the expected operation threshold, the operation test result is evaluated to generate the evaluation result, and the evaluation result includes a collaborative operation score.

[0079] Step S663: Based on the collaborative operation score, a traceability analysis and evaluation is performed on the multi-device collaborative operation suggestion to obtain multiple data analysis results.

[0080] Step S664: Identify improvements to multiple devices according to the multiple data analysis results, and build a collaborative improvement space for the devices.

[0081] Step S665: Map the running test results to the equipment collaborative improvement space for configuration to obtain the multiple improvement optimization data.

[0082] Specifically, the operation test results are compared with the expected operation thresholds. The expected operation thresholds are the critical values ​​of key performance indicators pre-set according to system design requirements, performance goals, and industry standards, covering quantitative standards in energy conversion efficiency, equipment operation stability, pollutant emission compliance levels, thermal power supply reliability, etc. For example, the expected threshold of energy conversion efficiency is set to a specific percentage, and the allowable threshold range of equipment power fluctuations is set. By comparing the corresponding indicators in the operation test results with these expected thresholds, it is determined whether the test results meet the basic requirements of the system.

[0083] It is found that the operation test results are less than the expected operation threshold, indicating that the system has not achieved the expected performance under the current multi-device collaborative operation recommendations. At this time, it is necessary to conduct a comprehensive evaluation of the operation test results and generate evaluation results, which include collaborative operation scores. The collaborative operation score is a quantitative indicator that comprehensively reflects the effect of multi-device collaborative operation. It is based on the analysis and weighted calculation of multiple key parameters in the test results. For example, different weights are assigned to factors such as energy utilization efficiency, equipment failure rate, and load response timeliness, and an overall score is calculated based on their actual performance in the test results. This score can intuitively reflect the pros and cons of the current collaborative operation of the system and provide an important basis for subsequent traceability analysis.

[0084] Based on the collaborative operation score, the suggestions for collaborative operation of multiple devices are traced back and analyzed to find out the root causes of the substandard system performance, thereby obtaining multiple data analysis results. By deeply exploring the relationship between the equipment operation data reflected behind the score, the problems in the collaborative cooperation between the equipment, the effectiveness of the control strategy, the rationality of the equipment parameter settings, etc. are analyzed. For example, if the low collaborative operation score is caused by the imbalance of energy matching between the power generation equipment and the heating equipment, the data analysis results will point out in detail the specific problems such as the loss points in the energy transfer process and the incoordination of the equipment operation parameters.

[0085] Based on the results of multiple data analyses, multiple devices are improved and identified to build a clear equipment collaborative improvement space. Based on the analyzed problems, the optimization direction and potential of each device in collaborative operation are determined. For example, a power generation device may have room for improvement in power adjustment range and response speed, and a heating device may need to be improved in heating temperature stability and heat distribution uniformity. These aspects that can be improved are integrated to form a multi-dimensional equipment collaborative improvement space covering equipment operation parameter adjustment, control strategy optimization, and improvement of collaborative relationships between equipment, providing a clear direction and scope for subsequent optimization configuration.

[0086] The operation test results are mapped to the equipment collaborative improvement space for configuration to obtain multiple improvement optimization data. In this process, the specific improvement value is calculated based on the actual performance of each indicator in the operation test results, combined with the optimization direction and range determined in the equipment collaborative improvement space. For example, in the case of low energy conversion efficiency, by analyzing the parameter adjustment range related to energy conversion in the equipment collaborative improvement space, combined with the actual energy input and output data in the test results, the specific improvement optimization data such as the fuel supply optimization amount of the power generation equipment and the heat exchange efficiency improvement target value of the heating equipment are determined. These data will be directly used for the optimization adjustment of the multi-device collaborative operation recommendations, so that the system gradually approaches the optimal operating state and realizes the efficient, stable and sustainable operation of the cogeneration system.

[0087] Embodiment 2 is based on the same inventive concept as the method for cogeneration capacity coordination optimization of multiple devices in the above embodiment. Figure 2 As shown, the present application provides a multi-device capacity collaborative optimization system for cogeneration of heat and power, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. The system includes:

[0088] The initial historical operation data acquisition module 10 performs multi-dimensional data scheduling on multiple devices based on the cogeneration system to obtain multiple initial historical operation data.

[0089] The historical operation data set generation module 20 is used to perform data cleaning processing on the multiple initial historical operation data to generate a historical operation data set.

[0090] The load forecasting result acquisition module 30 performs load forecasting on a plurality of devices based on the historical operation data set to obtain a load forecasting result for the cogeneration system.

[0091] The operation scheduling strategy formulation module 40 is used to perform operation analysis based on the load forecast results in combination with multiple equipment capacity parameters to formulate a multi-equipment operation scheduling strategy.

[0092] The collaborative operation suggestion generation module 50 performs device capacity matching based on multiple devices to obtain capacity matching results, executes the multi-device operation scheduling strategy according to the capacity matching results, performs collaborative analysis on multiple devices, and generates multi-device collaborative operation suggestions.

[0093] The optimization suggestion acquisition module 60 is used to perform simulation tests according to the multi-device collaborative operation suggestions, generate operation test results, optimize the multi-device collaborative operation suggestions according to the operation test results, and obtain multi-device collaborative operation optimization suggestions.

[0094] Furthermore, the historical operation data set generation module 20 further includes:

[0095] A target conversion data format generating unit is used to convert the format of the plurality of initial historical operation data to generate a target conversion data format.

[0096] The unit for determining data to be processed is used to traverse and identify the multiple initial historical operation data according to the target conversion data format, and determine multiple data to be processed, wherein the multiple data to be processed include missing data to be processed, abnormal data to be processed, and duplicate data to be processed.

[0097] A first processed data generating unit is configured to fill in the plurality of initial historical operation data according to the missing data to be processed to generate first processed data.

[0098] The second processed data generating unit is used to perform correction processing on the plurality of initial historical operation data according to the abnormal data to be processed to generate second processed data.

[0099] A third processed data generating unit is used to perform padding processing on the plurality of initial historical operation data according to the duplicate data to be processed to generate third processed data.

[0100] A data integration unit, wherein the data integration unit is used to integrate the first processed data, the second processed data, and the third processed data to generate the historical operation data set.

[0101] Furthermore, the load forecasting result acquisition module 30 further includes:

[0102] The device operation feature acquisition unit extracts features of a plurality of devices based on the historical operation data to obtain a plurality of device operation features.

[0103] A load characteristic determination unit is used to screen the plurality of equipment operation characteristics according to the load change data by using correlation analysis to determine a plurality of load characteristics.

[0104] A time series model building unit is used to perform load analysis according to the load change data and the operating time sequence to build a time series model.

[0105] A load forecasting result acquisition unit is used to synchronize the multiple load characteristics to the time series model to perform load forecasting and obtain the load forecasting result.

[0106] Furthermore, the collaborative operation suggestion generating module 50 further includes:

[0107] A load fluctuation coefficient acquisition unit, wherein the load fluctuation coefficient is obtained by performing demand analysis based on multiple devices to obtain multiple device demand information, performing load fluctuation analysis based on device application scenarios and combining the multiple device demand information to obtain the load fluctuation coefficient, wherein the load fluctuation coefficient includes load peak value and load valley value.

[0108] The device capacity information acquisition unit calculates the capacity of multiple devices based on the load peak value, the load valley value and the multiple device demand information to obtain multiple device capacity information.

[0109] A capacity matching result generating unit is used to perform matching evaluation on the plurality of equipment capacity information and preset rated capacity to generate the capacity matching result.

[0110] Furthermore, the optimization suggestion acquisition module 60 further includes:

[0111] A test target setting unit, wherein the test target setting unit is used to set a test target for a simulation test according to the multi-device collaborative operation suggestion.

[0112] A unit for determining a data set to be tested, wherein the data set to be tested is used to extract data from the multi-device collaborative operation suggestion and determine the data set to be tested.

[0113] A test record data generating unit is used to build a simulation environment, perform a running test on the data set to be tested according to the test target and in combination with the simulation environment, and generate a plurality of test record data.

[0114] A running test result generating unit is used to serialize the plurality of test record data according to the running sequence to generate the running test result.

[0115] Furthermore, the optimization suggestion acquisition module 60 further includes:

[0116] A determination result generating unit, wherein the determination result is used to make a collaborative determination on the operation test result according to the multi-device collaborative operation suggestion to generate a determination result.

[0117] An improved optimization data determination unit is used to evaluate the multi-device collaborative operation suggestion according to the determination result, perform optimization analysis according to the evaluation result, and determine multiple improved optimization data.

[0118] A collaborative operation optimization suggestion acquisition unit is used to use the multiple improvement optimization data as indexes, synchronize them to the multi-device collaborative operation suggestions for traversal and replacement, and obtain the multi-device collaborative operation optimization suggestions.

[0119] Furthermore, the improved optimization data determination unit also includes:

[0120] An operation test result judgment unit is used to judge whether the operation test result is greater than or equal to an expected operation threshold.

[0121] An evaluation result generating unit, wherein the evaluation result generating unit is used to evaluate the operation test result and generate the evaluation result if the operation test result is less than the expected operation threshold, wherein the evaluation result includes a collaborative operation score.

[0122] A data analysis result acquisition unit is configured to perform a traceability analysis and evaluation on the multi-device collaborative operation suggestion based on the collaborative operation score to obtain a plurality of data analysis results.

[0123] A collaborative improvement space construction unit is used to identify improvements on multiple devices according to the multiple data analysis results and construct a collaborative improvement space for the devices.

[0124] A collaborative improvement space configuration unit is used to map the operation test results to the equipment collaborative improvement space for configuration, so as to obtain the multiple improvement optimization data.

[0125] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0126] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0127] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for collaborative optimization of multi-equipment capacity for cogeneration of heat and power, characterized in that: The method comprises: Perform multi-dimensional data scheduling on multiple devices based on the cogeneration system to obtain multiple initial historical operation data; Performing data cleaning processing on the multiple initial historical operation data to generate a historical operation data set; Perform load forecasting on multiple devices based on the historical operation data set to obtain a load forecasting result for the cogeneration system; Performing operation analysis based on the load forecast results combined with multiple equipment capacity parameters to formulate a multi-equipment operation scheduling strategy; Perform device capacity matching based on multiple devices to obtain a capacity matching result, execute the multi-device operation scheduling strategy according to the capacity matching result to perform collaborative analysis on the multiple devices, and generate a multi-device collaborative operation suggestion; A simulation test is performed according to the multi-device collaborative operation suggestion to generate an operation test result, and the multi-device collaborative operation suggestion is optimized according to the operation test result to obtain a multi-device collaborative operation optimization suggestion.

2. The method for cogeneration multi-device capacity collaborative optimization according to claim 1, characterized in that: Performing data cleaning processing on the plurality of initial historical operation data to generate a historical operation data set, the method comprising: Convert the format of the plurality of initial historical operation data to generate a target conversion data format; Traversing and identifying the plurality of initial historical operation data according to the target conversion data format, and determining a plurality of data to be processed, wherein the plurality of data to be processed includes missing data to be processed, abnormal data to be processed, and duplicate data to be processed; Filling the plurality of initial historical operation data according to the missing data to be processed to generate first processed data; Performing correction processing on the plurality of initial historical operation data according to the abnormal data to be processed to generate second processed data; Performing padding processing on the plurality of initial historical operation data according to the to-be-processed duplicate data to generate third processed data; The first processed data, the second processed data, and the third processed data are integrated to generate the historical operation data set.

3. The method for cogeneration multi-device capacity collaborative optimization according to claim 1, characterized in that: Based on the historical operation data set, load forecasting is performed on multiple devices to obtain a load forecast result of the cogeneration system, and the method includes: Extracting features of multiple devices based on the historical operation data to obtain multiple device operation features; Using correlation analysis to screen the multiple equipment operation characteristics according to the load change data to determine multiple load characteristics; Perform load analysis according to the load change data and the operating time sequence to build a time series model; The multiple load characteristics are synchronized to the time series model to perform load forecasting and obtain the load forecasting result.

4. The method for cogeneration multi-device capacity collaborative optimization according to claim 1, characterized in that: Device capacity matching is performed based on multiple devices to obtain a capacity matching result, and the method includes: Performing demand analysis based on multiple devices to obtain multiple device demand information, performing load fluctuation analysis based on device application scenarios and combining the multiple device demand information to obtain a load fluctuation coefficient, wherein the load fluctuation coefficient includes a load peak value and a load valley value; Based on the load peak value, the load valley value and the multiple device demand information, capacity calculation is performed on multiple devices to obtain multiple device capacity information; The plurality of equipment capacity information is matched and evaluated with the preset rated capacity to generate the capacity matching result.

5. The method for cogeneration multi-device capacity collaborative optimization according to claim 3, characterized in that: Perform simulation test according to the multi-device collaborative operation suggestion to generate operation test results, the method comprising: Setting a test target for the simulation test according to the multi-device collaborative operation suggestion; Extracting data for the multi-device collaborative operation suggestion to determine a data set to be tested; Building a simulation environment, and performing a running test on the data set to be tested according to the test target and the simulation environment, to generate a plurality of test record data; The plurality of test record data are serialized according to the running sequence to generate the running test result.

6. The method for cogeneration multi-device capacity collaborative optimization according to claim 1, characterized in that: The multi-device collaborative operation suggestion is optimized according to the operation test result to obtain the multi-device collaborative operation optimization suggestion, the method comprising: Coordinated determination of the operation test results according to the multi-device coordinated operation suggestion to generate a determination result; Evaluate the multi-device collaborative operation suggestion according to the determination result, perform optimization analysis according to the evaluation result, and determine a plurality of improvement optimization data; The multiple improved optimization data are used as indexes and synchronized to the multi-device collaborative operation suggestions for traversal and replacement to obtain the multi-device collaborative operation optimization suggestions.

7. The method for cogeneration multi-device capacity collaborative optimization according to claim 6, characterized in that: The multi-device collaborative operation suggestion is evaluated according to the determination result, and optimization analysis is performed according to the evaluation result to determine a plurality of improvement optimization data, the method comprising: Determine whether the operation test result is greater than or equal to an expected operation threshold; If the operation test result is less than the expected operation threshold, the operation test result is evaluated to generate the evaluation result, wherein the evaluation result includes a collaborative operation score; Performing a traceability analysis and evaluation on the multi-device collaborative operation suggestion based on the collaborative operation score to obtain multiple data analysis results; Identify improvements for multiple devices according to the multiple data analysis results, and build a collaborative improvement space for the devices; The operation test results are mapped to the equipment collaborative improvement space for configuration to obtain the multiple improvement optimization data.

8. A multi-equipment capacity collaborative optimization system for cogeneration, characterized in that: The system is used to implement the method for collaborative optimization of multi-equipment capacity of cogeneration according to any one of claims 1 to 7, and the system comprises: An initial historical operation data acquisition module, wherein the initial historical operation data acquisition module performs multi-dimensional data scheduling on multiple devices based on the cogeneration system to obtain multiple initial historical operation data; A historical operation data set generation module, the historical operation data set generation module is used to perform data cleaning processing on the multiple initial historical operation data to generate a historical operation data set; A load forecasting result acquisition module, wherein the load forecasting result acquisition module performs load forecasting on multiple devices based on the historical operation data set to obtain a load forecasting result of a cogeneration system; An operation scheduling strategy formulation module, wherein the operation scheduling strategy formulation module is used to perform operation analysis based on the load forecast result in combination with multiple equipment capacity parameters to formulate a multi-equipment operation scheduling strategy; A collaborative operation suggestion generation module, wherein the collaborative operation suggestion generation module performs device capacity matching based on multiple devices to obtain a capacity matching result, executes the multi-device operation scheduling strategy according to the capacity matching result to perform collaborative analysis on multiple devices, and generates a multi-device collaborative operation suggestion; An optimization suggestion acquisition module is used to perform simulation tests according to the multi-device collaborative operation suggestions, generate operation test results, optimize the multi-device collaborative operation suggestions according to the operation test results, and obtain multi-device collaborative operation optimization suggestions.

Images