Energy efficiency evaluation method and optimization strategy for distributed integrated energy system

Abstract

The invention discloses an energy efficiency evaluation method and optimization strategy for a distributed integrated energy system. The method comprises the steps of data acquisition and preprocessing, preliminary energy efficiency calibration and evaluation, dynamic feedback adjustment, system state analysis and evaluation result output and transmission. By introducing a dynamic feedback mechanism and a nonlinear optimization strategy, the system can calibrate and adjust the multi-dimensional energy efficiency index in real time, so that the comprehensive utilization rate of energy is improved, the power heat ratio is reduced, and the power-cooling ratio is optimized. The strategy module further realizes self-adaptive optimization, eliminates low-efficiency bottlenecks, and ensures the overall improvement of the system performance. The system is reasonable in structure, remarkable in optimization effect and suitable for energy efficiency evaluation and management of various distributed energy systems.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management and optimization, and specifically to an energy efficiency evaluation method and optimization strategy for a distributed integrated energy system. Background Art

[0002] At present, distributed integrated energy systems face many challenges in the process of energy utilization and scheduling. First, there is parallel utilization of multiple energy forms such as electricity, heat, and cold in the system, but the existing energy efficiency evaluation methods are usually limited to the analysis of a single indicator or a single energy form, and it is difficult to comprehensively reflect the overall energy efficiency level of the system. Secondly, with the dynamic changes in environmental conditions (such as fluctuations in temperature and humidity), the energy efficiency status of the system will also change, but traditional evaluation methods often lack sensitivity and adaptability to real-time changes, resulting in energy efficiency evaluation results lagging behind actual conditions. In addition, traditional optimization strategies lack nonlinear adjustment and priority optimization of multi-dimensional energy efficiency indicators, making it difficult to effectively solve bottleneck problems in system operation, thereby limiting the improvement of the overall performance of the system.

[0003] Therefore, there is an urgent need for a new method that can comprehensively evaluate multi-dimensional energy efficiency, realize dynamic feedback adjustment, and perform nonlinear optimization to improve the energy utilization efficiency and operational adaptability of the system. Summary of the invention

[0004] The purpose of the present invention is to provide an energy efficiency evaluation method and optimization strategy for a distributed integrated energy system. The method solves the shortcomings of the existing system in multidimensional indicator evaluation, real-time adaptive adjustment and bottleneck optimization by introducing multidimensional energy efficiency evaluation, dynamic feedback mechanism and nonlinear optimization strategy, and can improve the overall performance and energy utilization efficiency of the system under complex environmental conditions.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for evaluating energy efficiency of a distributed integrated energy system, comprising the following steps:

[0006] S1. Data acquisition and preprocessing: The sensors of the data acquisition module in the system collect the operating parameters of power generation, heat output, cooling load, fuel consumption, ambient temperature and humidity in real time; the collected raw data are cleaned, filtered and standardized to generate a standardized measurement data set for subsequent algorithm input;

[0007] S2, preliminary energy efficiency calibration and evaluation algorithm: The input data is the standardized data set generated by S1; the preliminary energy efficiency calibration and evaluation algorithm performs basic calibration on the input data, corrects the measurement error, and calculates the multi-dimensional indicators of energy efficiency evaluation. The output results of the algorithm include comprehensive energy utilization rate, power-to-heat ratio, and electric-to-cooling ratio;

[0008] S3, dynamic feedback adjustment of evaluation results: based on the error information in the evaluation results generated by S2, the sensor acquisition parameters are adjusted through a dynamic feedback adjustment algorithm; the adjusted parameters are used as the data acquisition input of S1;

[0009] S4, system status analysis: The input data is the multi-dimensional energy efficiency index generated by S2 and the feedback adjustment results of S3; the system status analysis algorithm is used to analyze and identify the efficient operation status and bottleneck problems of the system, and provide overall evaluation results and improvement suggestions for the subsequent steps of the system performance;

[0010] S5, output and transfer of evaluation results: Integrate the multi-dimensional energy efficiency evaluation results generated by S2 and the system status analysis results of S4 into the final evaluation results; transfer the results to the strategy module through the data interface within the system to further optimize the basic input of the steps and the final performance evaluation.

[0011] Preferably, S1 comprises the following sub-steps:

[0012] S1-1. Multi-source data acquisition: Use power sensors, heat flow meters, cooling sensors, gas flow meters and environmental sensors to collect power generation power, heat output, cooling load, fuel consumption, ambient temperature and humidity operating parameters in real time and generate original data sets; S1-2. Data preprocessing: Clean and denoise the original data collected by S1-1 to eliminate invalid data; standardize the processed data through normalization operations to generate a standardized data set; S1-3. Error identification and calibration: Based on the standardized data set, identify the errors caused by measurement equipment deviations or environmental changes, and correct the standardized data through the calibration model to generate a corrected standardized measurement data set.

[0013] Preferably, S2 comprises the following sub-steps:

[0014] S2-1, Error calibration: Based on the corrected standardized data set generated by S1-3, the input data is further adjusted through the error calibration model; S2-2, Multi-dimensional energy efficiency index calculation: Calculate the energy efficiency index of the calibration results of S2-1, including comprehensive energy utilization rate, power-to-heat ratio and electric-to-cooling ratio; S2-3, Evaluation result generation: Output the multi-dimensional energy efficiency index results of S2-2, and the results serve as the input of S3.

[0015] Preferably, S3 comprises the following sub-steps:

[0016] S3-1, error information acquisition: compare the multi-dimensional energy efficiency index results of S2-3 with the preset target value, extract the error data, where the error amplitude E i and direction Δ i Defined as:

[0017] in is the i-th energy efficiency index actually measured, is the target indicator value; S3-2, dynamic feedback model construction: based on the error information of S3-1, a dynamic feedback model is established to adjust the sensor acquisition parameters. The specific adjustment formula is:

[0018] in and is the sampling frequency of the sensor, and is the sensor weight, k f and k ω is the feedback coefficient; S3-3, parameter optimization feedback: the sensor parameters adjusted in S3-2 are fed back to the data acquisition module of S1 and used for the next round of data acquisition to form a closed-loop feedback mechanism.

[0019] Preferably, S4 comprises the following sub-steps:

[0020] S4-1, multi-dimensional energy efficiency index input: input the multi-dimensional energy efficiency index of S2-3 and the feedback adjustment result of S3-3 as the input of S4-2; S4-2, system status evaluation model construction: based on the input of S4-1, establish the system status evaluation model and calculate the comprehensive performance score P of the system s , the specific calculation formula is:

[0021] in, is the adjusted i-th energy efficiency index, ω i is the corresponding weight, and α is the nonlinear adjustment coefficient; S4-3, state analysis result generation: Based on the comprehensive performance score of S4-2, identify the efficient operation area and the inefficient bottleneck area, and output the system state analysis result.

[0022] Preferably, S5 comprises the following sub-steps:

[0023] S5-1, integration of evaluation results: integrating the multi-dimensional energy efficiency indicators of S2-3 and the system status analysis results of S4-3 into the final comprehensive evaluation results; S5-2, construction of nonlinear combination model: optimizing the integration results of S5-1 through the nonlinear combination model, the specific formula is: in, is the i-th energy efficiency index after integration, and β is the nonlinear weight adjustment parameter; S5-3, evaluation result transfer: the final comprehensive evaluation result in S5-2 is transferred to the strategy module through the data interface for basic input of subsequent optimization steps.

[0024] An energy efficiency evaluation optimization strategy for a distributed integrated energy system includes the following steps:

[0025] S7-1, optimization target setting: Based on the comprehensive evaluation results of S5, the optimization targets are set through the strategy module. The optimization targets include improving the comprehensive utilization rate of energy, reducing the power-to-heat ratio, and optimizing the electric-to-cooling ratio index. The optimization target input is the basis for subsequent dynamic parameter adjustment and nonlinear optimization.

[0026] S7-2, dynamic parameter adjustment strategy: Based on the feedback adjustment results of S3, the strategy module further optimizes the weight and sampling frequency of sensor acquisition parameters, using a dynamic adjustment coefficient k opt The correction formula is: Where E res is the residual error, To optimize the sampling frequency, the strategy module adjusts the sampling parameters in real time;

[0027] S7-3, Goal achievement verification: Verify the optimized multi-dimensional energy efficiency indicators through the strategy module to ensure that each indicator reaches the set optimization goal.

[0028] Preferably, the dynamic parameter adjustment strategy in S7-2 further includes:

[0029] S8-1, nonlinear adjustment strategy: The strategy module applies nonlinear functions to dynamically adjust the multi-dimensional energy efficiency indicators, using an exponential adjustment function, the formula of which is: in, is the optimized energy efficiency index, γ is the nonlinear adjustment coefficient, which is dynamically calculated by the strategy module;

[0030] S8-2, Adaptive strategy update: The strategy module adaptively adjusts the acquisition parameters and the weights of the feedback model based on the optimization results of S8-1, so that the optimization process continues to adapt to new operating conditions.

[0031] Preferably, the method comprises the following steps:

[0032] S9-1, energy efficiency index priority adjustment strategy: According to the system status analysis results of S4, the energy efficiency index is given priority through the strategy module, and the priority weighted function is used for calculation. The formula is: in, is the weight after priority adjustment, λ is the priority adjustment coefficient, P i Prioritize energy efficiency indicators;

[0033] 9-2. Bottleneck elimination strategy: The strategy module optimizes the inefficient bottlenecks identified in S4-3 and improves the energy efficiency of inefficient areas by adjusting acquisition parameters and model weights.

[0034] Preferably, the following steps are included: S10-1, comprehensive performance evaluation strategy: Based on the nonlinear combination result of S5-2, the energy efficiency evaluation result is comprehensively evaluated through the strategy module, and a logarithmic amplification function is used, and the formula is: in, is the comprehensive performance evaluation result after optimization;

[0035] S10-2, strategy output and feedback: The comprehensive evaluation results of S10-1 are used as strategy output and transmitted to the next round of optimization module through the data interface of the strategy module for subsequent system optimization and evaluation cycles.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] 1. The present invention realizes the comprehensive evaluation of various energy forms (electricity, heat, and cooling) in the distributed integrated energy system by setting a multi-dimensional energy efficiency evaluation and preliminary calibration algorithm, thereby improving the accuracy of the energy efficiency evaluation and the overall performance of the system;

[0038] 2. By introducing a dynamic feedback adjustment mechanism, real-time feedback of energy efficiency evaluation results and adaptive adjustment of acquisition parameters are achieved, effectively improving the response speed and adaptability of the system under dynamic changes in environmental conditions;

[0039] 3. Adopting nonlinear optimization strategy, combining nonlinear function and priority weighting in the process of optimizing energy efficiency indicators, it realizes targeted optimization of system bottleneck problems and further improves energy utilization efficiency;

[0040] 4. The introduction of strategy modules and adaptive strategy updates ensure that the system can automatically adjust the optimization strategy under different operating conditions, thereby improving the intelligence and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of an energy efficiency evaluation method for a distributed integrated energy system according to the present invention;

[0042] Figure 2 This is a diagram of the multi-source data collection and preprocessing sub-steps of the present invention;

[0043] Figure 3 This is a flow chart of error identification and calibration of the present invention;

[0044] Figure 4 A dynamic feedback adjustment flow chart of the evaluation results of the present invention;

[0045] Figure 5 It is a flow chart of system status analysis of the present invention;

[0046] Figure 6 It is a flow chart of outputting and transmitting the evaluation results of the present invention;

[0047] Figure 7 This is a flow chart of optimization target setting and dynamic parameter adjustment of the present invention;

[0048] Figure 8 This is a flow chart of the nonlinear adjustment and adaptive strategy update of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] See also Figures 1 to 8 The present invention provides an energy efficiency evaluation method and optimization strategy for a distributed integrated energy system, wherein the first step is S1: data collection and preprocessing, which aims to provide an accurate and standardized data basis for subsequent energy efficiency evaluation and optimization algorithms through real-time collection, preprocessing and standardization of various operating parameters in the system.

[0051] S1. Data collection and preprocessing: This step includes three sub-steps: S1-1. Multi-source data collection, S1-2. Data preprocessing, and S1-3. Error identification and calibration. The specific implementation of each sub-step is as follows:

[0052] S1-1. Multi-source data collection: In the present invention, various types of sensors deployed in the data collection module of the system are used to collect different forms of energy data in real time. Specifically, it includes:

[0053] Power sensor: used to collect the power generation in the system to ensure accurate data input of power output; heat flow meter: used to collect heat output data and monitor the heat flow status of the system; cooling sensor: used to monitor the cooling load to ensure effective data acquisition of cooling output; gas flow meter: used to record fuel consumption data and accurately monitor the use of gas in the system; environmental sensor: including temperature and humidity sensors, which collect real-time data of ambient temperature and humidity to facilitate the consideration of environmental factors in the subsequent evaluation process.

[0054] The core of multi-source data acquisition is to achieve comprehensive coverage of various operating parameters in the system. These parameters are collected in real time and generate preliminary raw data sets. The raw data sets include not only output data in the form of electricity, heat, cold and other energy, but also changes in fuel consumption and environmental conditions. These data are collected at high frequency to ensure the real-time and comprehensiveness of the system, providing a basis for subsequent data processing and analysis.

[0055] S1-2, data preprocessing: After obtaining the original data, data preprocessing is performed to ensure the accuracy and consistency of the data. This sub-step includes the following specific operations: Data cleaning: Remove invalid values, missing values ​​and outliers in the original data. Invalid values ​​may come from sensor failure or data transmission errors, missing values ​​may be caused by temporary signal loss, and outliers may come from interference from the external environment or errors in the measuring equipment. Denoising: Use filtering algorithms or signal processing techniques to remove noise components in the data to make the data closer to the actual system state. For example, high-frequency noise signals are filtered out by a low-pass filter to retain key data related to energy efficiency evaluation. Data standardization: Normalize the cleaned and denoised data to convert different types of data into a unified standardized data format. For example, various energy parameters are converted into standardized data sets of unified dimensions through minimum-maximum normalization or Z-score normalization. This process ensures the consistency and comparability of data input to subsequent algorithms and provides standardized input data for energy efficiency evaluation algorithms.

[0056] S1-3, Error Identification and Calibration: In order to further improve the accuracy of data, the present invention adds error identification and calibration sub-steps on the basis of data standardization. The specific implementation is as follows:

[0057] Error identification: Based on the standardized data set, by analyzing the comparison between historical data and current data, errors caused by measurement equipment deviation or environmental changes can be identified. Error identification is achieved through a variety of methods, such as using a sliding window algorithm to identify abnormal data fluctuations, or determining the degree of data deviation by setting an error threshold.

[0058] Error calibration: Based on error identification, the standardized data is corrected by establishing a calibration model. For example, a linear regression model or Kalman filter algorithm is used to correct the error so that the standardized data is closer to the actual state of the system. The corrected data forms a corrected standardized measurement data set and serves as the input of subsequent algorithms.

[0059] Through the implementation of S1, the present invention can collect and process the multi-dimensional energy efficiency data in the system in real time and accurately, and provide reliable basic data support for energy efficiency evaluation and optimization through standardization and error calibration of multi-source data. Each sub-step in S1 is processed layer by layer to ensure the accuracy and consistency of the input data of the subsequent energy efficiency evaluation algorithm under multiple dimensions and conditions.

[0060] In the present invention, S2: Preliminary energy efficiency calibration and evaluation algorithm aims to perform more accurate energy efficiency evaluation and calibration on the standardized data set generated by S1. Through further error correction and calculation of multi-dimensional energy efficiency indicators, preliminary evaluation results of distributed integrated energy systems are provided.

[0061] S2, preliminary energy efficiency calibration and evaluation algorithm: S2 includes three sub-steps: S2-1, error calibration, S2-2, multi-dimensional energy efficiency index calculation, and S2-3, evaluation result generation. The specific implementation of each sub-step is as follows:

[0062] S2-1, error calibration: In the present invention, S2-1 performs further error calibration based on the corrected standardized data set generated by S1-3, aiming to ensure the accuracy and consistency of the input data. The specific implementation is as follows:

[0063] Identification of error sources: First, the corrected data set of S1-3 is further analyzed to identify potential error sources, including errors caused by sensor drift, environmental noise changes, measuring instrument aging, etc. Through statistical analysis and trend comparison methods, potential error patterns in the data can be determined.

[0064] Application of error calibration model: Based on the identified error pattern, the error calibration model is used to adjust the input data. The calibration model can use algorithms such as linear regression and Kalman filtering to perform targeted corrections for different error sources. For example, the linear regression model can correct the linear deviation caused by sensor drift; and the Kalman filter can dynamically correct the nonlinear error that changes over time.

[0065] Output of calibration results: The output of the calibration model is a further corrected standardized data set with higher accuracy and consistency, which serves as the input data basis for S2-2.

[0066] S2-2, multi-dimensional energy efficiency index calculation: In S2-2, multi-dimensional energy efficiency index calculation is performed on the error-calibrated data set. The specific implementation method is as follows:

[0067] Selection of energy efficiency indicators: Based on the characteristics of distributed integrated energy systems, comprehensive energy utilization rate, power-to-heat ratio (CHR) and power-to-cooling ratio (CCR) are selected as the main energy efficiency indicators. These indicators can fully reflect the utilization of electricity, heat, cooling and other energy forms in the system.

[0068] Calculation method of energy efficiency index, comprehensive energy utilization rate: Based on the input corrected data set, the comprehensive energy utilization rate is obtained by calculating the ratio of total energy input to total energy output of various energy forms in the system.

[0069] The formula is as follows: Comprehensive energy utilization rate = (total energy input / total effective energy output) × 100%; Power heat ratio (CHR): By calculating the ratio of electric energy output to heat energy output, it reflects the relative utilization of electric energy and heat energy in the system. The formula is as follows: CHR = heat energy output / electric energy output; Electricity cooling ratio (CCR): Calculate the ratio of electric energy output to cooling energy load to evaluate the utilization efficiency of electric energy and cooling energy. The formula is as follows: CCR = electric energy output / cooling energy load; Output of calculation results: The calculation results of multi-dimensional energy efficiency indicators form a preliminary evaluation data set for the system, which includes the specific values ​​of comprehensive energy utilization rate, power heat ratio and electric cooling ratio, which are used to evaluate the overall energy efficiency level of the system.

[0070] S2-3, generation of evaluation results: S2-3 organizes and outputs the multi-dimensional energy efficiency indicators obtained in S2-2. The specific implementation methods are as follows; Integration of evaluation results: The various energy efficiency indicators calculated by S2-2 are comprehensively organized to form a preliminary energy efficiency evaluation result set for the system. These evaluation results include not only the specific values ​​of each energy efficiency indicator, but also the corresponding evaluation time and environmental conditions information to facilitate subsequent dynamic feedback and optimization. Formatted output of results: The preliminary evaluation results are output in the form of structured data to ensure that subsequent steps can be quickly read and referenced when performing dynamic feedback adjustments and strategy optimization. These results will serve as the input basis for S3 to further improve the accuracy and adaptability of the overall energy efficiency evaluation of the system.

[0071] Through the implementation of S2, the present invention can realize the preliminary energy efficiency evaluation of the distributed integrated energy system based on the S1 data preprocessing. S2 ensures the accuracy, comprehensiveness and real-time performance of the evaluation results through error calibration and multi-dimensional energy efficiency index calculation. This step not only provides important basic data support for subsequent dynamic feedback adjustment and optimization, but also can quickly reflect the energy efficiency changes of the system under complex environmental conditions, which is convenient for subsequent adaptive adjustment.

[0072] In the present invention, S3: dynamic feedback adjustment of evaluation results aims to utilize the error information in the multi-dimensional energy efficiency evaluation results generated by S2 to adjust the sensor acquisition parameters in real time through a dynamic feedback model, thereby optimizing the accuracy and adaptability of the next round of data acquisition.

[0073] S3, dynamic feedback adjustment of evaluation results, the specific implementation of S3 is divided into three sub-steps: S3-1, error information acquisition, S3-2, dynamic feedback model construction, and S3-3, parameter optimization feedback. The specific implementation methods of each sub-step are as follows:

[0074] S3-1. Obtaining error information: In the present invention, the error data is extracted by comparing the multi-dimensional energy efficiency index results of S2 with the preset target values. The specific implementation is as follows:

[0075] Error definition: Compare the multi-dimensional energy efficiency index results with the preset targets one by one and calculate the error margin E i and direction Δ i The specific formula is: in The actual measured energy efficiency index i is collected by multi-source sensors in the system and is the data after multi-dimensional energy efficiency index calculation and error calibration by S2. It comes from the real-time data input in the energy efficiency evaluation process;

[0076] It is the target indicator value, which is set based on the optimization goal during system design or the statistical analysis results of historical data. Its source can be traced back to the initial optimization goal of the system, or determined by the set parameters in the strategy module; the error margin indicates the deviation of the indicator, and the direction is used to indicate the positive or negative deviation;

[0077] S3-2, dynamic feedback model construction: after obtaining the error information, the sensor acquisition parameters are adjusted through the dynamic feedback model. The specific implementation is as follows:

[0078] Application of feedback model: According to the error information obtained in S3-1, the dynamic feedback model is activated to correct the sampling frequency and weight of the sensor. The specific adjustment formula is:

[0079] in and They are the new sampling frequency and old sampling frequency of the sensor, which are the original sampling frequencies of the sensor in the previous round of acquisition and are derived from the sensor configuration records of the system;

[0080] k f It is a feedback coefficient, which is used to adjust the sampling frequency and the adjustment range of the weight. The setting of this coefficient is based on the analysis of historical data and the response requirements of the system, and can be obtained through experimental calibration or statistical analysis of historical data. The feedback model makes targeted adjustments to the sensor's acquisition parameters according to the error conditions of different energy efficiency indicators to ensure that the data acquisition process has stronger adaptability to changes in system status. This formula dynamically adjusts the sampling frequency by comprehensively considering the error average of all energy efficiency indicators to improve the sensor's ability to respond to energy efficiency changes. The reduction or increase of the sampling frequency depends on the direction and size of the error, ensuring the real-time adaptability of the system. Compared with the traditional fixed sampling frequency, the sampling frequency adjustment of the present invention has higher flexibility and adaptability, and can maintain high acquisition accuracy and energy efficiency evaluation accuracy when the system status changes rapidly.

[0081] Weight adjustment formula: in and is the sensor weight, which is the original weight of the sensor in the previous round of acquisition and comes from the sensor weight configuration file of the system; k ω : is the weight adjustment coefficient, which controls the adjustment ratio of the weight. The source of this coefficient is similar to the feedback coefficient, and can be set through historical data and the performance requirements of the system; this formula adjusts the weight of the sensor according to the specific errors of each energy efficiency indicator to highlight the focus on indicators with larger errors, while reducing the collection weight of indicators with smaller errors, and optimizing the overall collection strategy. Compared with the traditional fixed weight collection method, the dynamic weight adjustment mechanism of the present invention can allocate system resources more effectively, making the collection of key energy efficiency indicators more accurate, and improving the overall evaluation accuracy and stability of the system.

[0082] S3-3, parameter optimization feedback: When feeding back the adjusted parameters to the data acquisition module of S1:

[0083] Sampling frequency Hequan Source: These parameters are generated through the dynamic feedback model of S3-2, and their rationality is based on the aforementioned feedback control logic and experimental verification. Closed-loop feedback mechanism: The optimized parameters are applied in the next round of data collection to achieve adaptive adjustment of sensors and dynamic data collection. This feedback closed-loop mechanism ensures the traceability of parameters and the continuous optimization of adjustment effects.

[0084] In the present invention, S4: system status analysis aims to comprehensively analyze the multi-dimensional energy efficiency indicators generated by S2 and the feedback adjustment results of S3, identify the efficient operation status and potential bottlenecks of the system, and provide guidance for the subsequent optimization of system performance.

[0085] S4, system status analysis: S4 includes three sub-steps: S4-1, multi-dimensional energy efficiency index input, S4-2, system status evaluation model construction, S4-3, status analysis result generation. The specific implementation is as follows: S4-1, multi-dimensional energy efficiency index input: In the first step of S4, the system needs to receive the multi-dimensional energy efficiency index from S2-3 and the feedback adjustment result of S3-3 as input data. The specific implementation of this step is as follows:

[0086] Multi-dimensional energy efficiency index input: Energy efficiency indicators include key indicators such as comprehensive energy utilization rate, power-to-heat ratio and electric-to-cooling ratio, which are derived from the multi-dimensional energy efficiency calculation results of S2. These indicators are further adjusted to reflect the feedback adjustment effect of S3. Feedback adjustment result input: The feedback adjustment result of S3 contains dynamic optimization information of sensor parameters, which is used to assist in identifying the real-time status of the system and is used together with energy efficiency indicators as the basic data for system status analysis.

[0087] S4-2, system status evaluation model construction: Based on the input of multi-dimensional energy efficiency indicators and feedback adjustment results, S4-2 constructs a system status evaluation model to perform comprehensive performance scoring (P s ) calculation. The specific implementation is as follows: Application of system status evaluation model: This model performs weighted calculation on the input multi-dimensional energy efficiency indicators and combines nonlinear adjustment parameters to comprehensively evaluate system performance. The model calculation formula is: Where: i The corresponding weight of the energy efficiency index comes from the historical data analysis of the system and the weight setting in the strategy module. The weight is calculated by the strategy module, and the specific setting is based on the system's evaluation results of the importance of different energy efficiency indicators;

[0088] is the adjusted i-th energy efficiency index, which comes from the feedback adjustment result of S3 and is a dynamic optimization based on the energy efficiency calculation result of S2;

[0089] α is a nonlinear adjustment coefficient, which is based on the sensitivity analysis results of system state changes. Its function is to adjust the nonlinear effects of different energy efficiency indicators to ensure the accuracy and rationality of the calculation results. This formula comprehensively considers the weighted values ​​and nonlinear adjustment factors of multidimensional energy efficiency indicators, so that the performance evaluation results of the system can more accurately reflect the actual status and mutual influence of energy efficiency indicators; compared with the traditional linear weighted evaluation method, the evaluation model of the present invention introduces a nonlinear adjustment coefficient, so that the system status evaluation results can more flexibly reflect the complex correlation of energy efficiency indicators, thereby improving the accuracy of system status analysis;

[0090] S4-3, state analysis result generation: After completing the calculation of the system state evaluation model, S4-3 generates the state analysis result and outputs the overall performance evaluation of the system. The specific implementation method is as follows; State analysis result generation: Based on the comprehensive performance score of S4-2, identify the efficient operation area and inefficient bottleneck area of ​​the system. The system state analysis result includes an overall evaluation of the system performance and specific analysis results of each energy efficiency indicator.

[0091] The status analysis results are output in the form of structured data, including performance scores and identified bottleneck areas. At the same time, specific improvement suggestions are given based on the analysis results to provide guidance for subsequent optimization strategies.

[0092] Implementation effect of S4: Through the implementation of S4, the present invention can comprehensively and accurately evaluate the operating status of the distributed integrated energy system, identify the efficient operating areas and potential bottlenecks of the system, and provide targeted improvement suggestions. This system status analysis not only enhances the accuracy and comprehensiveness of energy efficiency evaluation, but also provides a scientific basis for subsequent optimization strategies.

[0093] In the present invention, S5: output and transmission of evaluation results is intended to integrate the multi-dimensional energy efficiency evaluation results of S2 and the system status analysis results of S4 to form a final comprehensive evaluation result, and transmit the result to the strategy module through the data interface within the system to provide basic input for subsequent optimization steps.

[0094] S5. Output and delivery of evaluation results

[0095] S5 includes three sub-steps: S5-1, integration of evaluation results, S5-2, construction of nonlinear combination model, and S5-3, transmission of evaluation results. The specific implementation method is as follows; S5-1, integration of evaluation results: In the first step of S5, the multidimensional energy efficiency evaluation results of S2-3 are integrated with the system status analysis results of S4-3 to form the final comprehensive evaluation results of the system. The specific implementation method is as follows; Multidimensional energy efficiency evaluation results: The evaluation results from S2-3 cover the preliminary calculation results of key energy efficiency indicators such as comprehensive energy utilization rate, power-to-heat ratio and electric-to-cooling ratio. System status analysis results: The system status analysis results from S4-3 contain information on efficient operating status and potential bottleneck areas. These results are used to optimize the weight setting of the evaluation and the input of the nonlinear combination model. Result integration process: During the integration process, the multidimensional energy efficiency evaluation results and the system status analysis results are weighted and matched to ensure that all indicators can be reasonably input into the nonlinear combination model in subsequent steps.

[0096] S5-2, nonlinear combination model construction: In S5-2, the integration results of S5-1 are further optimized and calculated through the nonlinear combination model to generate the final comprehensive evaluation value. The specific implementation is as follows:

[0097] Application of nonlinear combination model: This model calculates the final comprehensive performance evaluation value P of the system by nonlinearly weighting and combining the integration results. final The calculation formula of the model is: Where: i The corresponding weight of the energy efficiency index comes from the optimization calculation of the strategy module and the weight analysis of historical data. Its setting basis is the importance of different indicators in the multi-dimensional energy efficiency evaluation results to ensure the rationality of the weight setting;

[0098] is the i-th energy efficiency index after integration, including the final adjustment value of comprehensive energy utilization rate, power-to-heat ratio and electric-to-cooling ratio, which is the data integrated and optimized by S5-1;

[0099] β is a nonlinear weight adjustment parameter, which is set based on the results of system status analysis and nonlinear impact analysis of historical performance data. Its function is to adjust the weight distribution of different energy efficiency indicators in the comprehensive performance evaluation, making the evaluation results more flexible and accurate; this formula can more accurately reflect the comprehensive performance status of the system through the nonlinear combination of the integrated results. The application of logarithmic functions can adjust and amplify the impact of each energy efficiency indicator, making the final evaluation results of the system more reasonable and comprehensive;

[0100] S5-3, evaluation result transmission: After completing the calculation of the final comprehensive performance evaluation, S5-3 is responsible for transmitting the evaluation results to the strategy module to provide basic input for subsequent optimization steps. The specific implementation method is as follows; The way of transmitting the evaluation results: The final comprehensive performance evaluation results are transmitted to the strategy module through the data interface within the system. The transmitted data is in a structured format to ensure that the results can be quickly read and analyzed by the strategy module. The results transmitted to the strategy module will be used for the next optimization step, including dynamic feedback adjustment, adaptive optimization and strategy update, etc., to provide data support for further performance improvement of the system.

[0101] In the present invention, steps S7 to S10 involve the specific implementation of the optimization strategy, including steps such as optimization target setting, dynamic parameter adjustment, energy efficiency index priority optimization, bottleneck elimination and comprehensive performance evaluation.

[0102] S7, Optimization target setting and dynamic parameter adjustment: The implementation of S7 includes three sub-steps: S7-1, optimization target setting, S7-2, dynamic parameter adjustment strategy, and S7-3, target achievement verification.

[0103] S7-1. Optimization target setting: Input basis: Based on the comprehensive evaluation results of S5, the optimization targets are set through the strategy module, including improving the comprehensive energy utilization rate, reducing the power-to-heat ratio, and optimizing the electric-to-cooling ratio. Optimization input: The setting of targets serves as the basis for subsequent dynamic parameter adjustment and nonlinear optimization. Algorithm logic: The setting of optimization targets is to perform weighted analysis on various energy efficiency indicators through the strategy module to ensure that the priorities of different indicators in the optimization are reasonable.

[0104] S7-2, Dynamic parameter adjustment strategy: Adjustment logic: Based on the feedback adjustment results of S3, the strategy module further optimizes the sensor parameters. Specifically, the dynamic adjustment coefficient k opt To make corrections, the formula is:

[0105] is the optimized sampling frequency; E res is the residual error; coefficient k opt Determined according to the system's historical error adjustment strategy to ensure the rationality and traceability of the dynamic adjustment process;

[0106] S7-3. Verification of target achievement: Verification mechanism: Verify the optimized multi-dimensional energy efficiency indicators through the strategy module to ensure that each indicator reaches the set optimization target.

[0107] S8, nonlinear adjustment and adaptive strategy update: S8 further refines the dynamic parameter adjustment strategy of S7-2 and is divided into two sub-steps: S8-1, nonlinear adjustment strategy and S8-2, adaptive strategy update.

[0108] S8-1. Nonlinear adjustment strategy: Nonlinear adjustment model: Dynamically adjust the multi-dimensional energy efficiency indicators by applying nonlinear functions through the strategy module. The formula is: is the optimized energy efficiency index; γ is the nonlinear adjustment coefficient, which comes from the dynamic calculation of the strategy module. Compared with the traditional linear adjustment, the nonlinear model can more flexibly cope with the complex changes of multi-dimensional energy efficiency indicators and improve the accuracy of the optimization effect.

[0109] S8-2, Adaptive strategy update: Update logic: Based on the optimization results of S8-1, the strategy module adaptively adjusts the sensor parameters and feedback weights to ensure that the optimization process continues to adapt under the new operating conditions.

[0110] S9, energy efficiency index priority adjustment and bottleneck elimination: The implementation of S9 includes two sub-steps: S9-1, energy efficiency index priority adjustment strategy and S9-2, bottleneck elimination strategy.

[0111] S9-1. Energy efficiency index priority adjustment strategy: Priority adjustment model: According to the system status analysis results of S4, the energy efficiency index is given priority through the strategy module, and the priority weighted function is used for calculation. The formula is: is the weight after priority adjustment, and λ is the priority adjustment coefficient, which comes from the optimization analysis of each indicator by the strategy module.

[0112] S9-2, bottleneck elimination strategy: Bottleneck optimization: Optimize the inefficient bottlenecks identified in S4-3, improve the energy efficiency of the bottleneck area by adjusting the acquisition parameters and model weights, and ensure the improvement of system performance.

[0113] S10, comprehensive performance evaluation and feedback loop: S10 includes two sub-steps: S10-1, comprehensive performance evaluation strategy and S10-2, strategy output and feedback.

[0114] S10-1. Comprehensive performance evaluation strategy: Comprehensive evaluation model: Based on the nonlinear combination results of S5-2, the energy efficiency evaluation results are comprehensively evaluated through the strategy module, using a logarithmic amplification function, and the formula is: in, is the optimized comprehensive performance evaluation result; through the logarithmic amplification function, the model can enhance the nonlinear influence of different indicators on the final evaluation result during the evaluation process and improve the comprehensive evaluation accuracy of the system;

[0115] S10-2, strategy output and feedback: Feedback mechanism: The comprehensive evaluation results of S10-1 are used as strategy output and passed to the next round of optimization module through the data interface of the strategy module for subsequent optimization and evaluation cycles.

[0116] Embodiment 1: The present invention aims at the problems of inaccurate multi-source energy efficiency evaluation, untimely feedback adjustment, and delayed response of optimization strategy faced by distributed integrated energy systems in practical applications, and proposes an energy efficiency evaluation method and optimization strategy. The technical innovation of the invention is that through multi-dimensional energy efficiency evaluation, dynamic feedback adjustment and nonlinear combination optimization, accurate evaluation and real-time optimization of system energy efficiency are achieved, which can adapt to the operation requirements under different environmental conditions.

[0117] This embodiment aims to demonstrate the high efficiency energy efficiency evaluation and optimization capabilities of the present invention in practical applications through specific evaluation and optimization steps, and at the same time verify the application effects and relative advantages of the present invention in different situations through detailed comparative experiments. Through this embodiment, one can more intuitively understand the comprehensive performance of the present invention in improving the accuracy of energy efficiency evaluation, shortening feedback response time, and improving optimization effects.

[0118] In a typical distributed integrated energy system, this embodiment is applied to the real-time evaluation and optimization of various energy forms such as electric energy, thermal energy, and cold energy, and the system operation parameters are collected through intelligent sensors, and the multi-dimensional energy efficiency evaluation algorithm and dynamic optimization strategy of the present invention are used to achieve all-round optimization of the system. Data acquisition and preprocessing: The data acquisition module collects parameters such as power generation power, thermal energy output, cold energy load, fuel consumption, ambient temperature and humidity in real time, and cleans and standardizes the collected data. Energy efficiency evaluation and dynamic feedback adjustment: According to the multi-dimensional energy efficiency evaluation results, the efficient operation area and inefficient bottleneck area of ​​the system are identified, and the sensor acquisition parameters and sampling frequency are optimized through the dynamic feedback adjustment algorithm. Nonlinear combination and comprehensive performance optimization: Using the nonlinear combination model, the evaluation results are weighted and optimized to generate the final comprehensive performance evaluation value, and the optimization suggestions are output. Strategy adjustment and adaptive optimization: According to the comprehensive performance evaluation results, the system acquisition parameters and feedback weights are adjusted in real time to adapt to the dynamically changing system state.

[0119] Application scenarios: Integrated energy management system for large industrial parks: Using the optimization strategy of the present invention, efficient evaluation and real-time optimization can be achieved in large-scale, multi-energy integrated systems. Distributed energy supply system in urban areas: In this scenario, the present invention can be used to improve regional energy supply efficiency, reduce energy consumption costs, and optimize the comprehensive utilization efficiency of different energy forms. Energy efficiency management system for commercial buildings: Applying this invention in commercial buildings can achieve real-time monitoring and optimization of electricity, heat, and cooling energy in the building, improving overall energy efficiency.

[0120] In order to verify the performance advantages of the present invention, a detailed comparative experiment was designed to compare the present invention with three mainstream energy efficiency evaluation methods: method A (evaluation method based on static energy efficiency model), method B (regression evaluation method based on historical data analysis) and method C (rule evaluation method based on fuzzy logic). The comparative experiment covers multiple evaluation items, including 9 core indicators such as evaluation accuracy, response time, and optimization efficiency.

[0121] Experimental setup: Experimental conditions: The test was conducted in the same distributed integrated energy system environment, with the system configuration and acquisition parameters kept consistent to ensure the fairness of the comparative experiment. Experimental indicators: The core indicators of the test include: evaluation accuracy; feedback response time; comprehensive optimization efficiency; improvement of comprehensive energy utilization; power-to-heat ratio optimization; power-to-cooling ratio optimization; data stability; error correction effect; and adaptive capability. The comparative experimental results are as follows:

[0122]

[0123]

[0124] Through comparative experiments, it can be seen that the present invention performs well in multiple core indicators such as evaluation accuracy, feedback response time, and optimization efficiency, fully demonstrating the application effect and advantages of the present invention in distributed integrated energy systems. The invention is not only applicable to distributed energy supply systems in large industrial parks and urban areas, but can also be promoted and applied to energy efficiency management of commercial buildings.

[0125] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating energy efficiency of a distributed integrated energy system, characterized in that: The following steps are involved: S1. Data acquisition and preprocessing: The sensors of the data acquisition module in the system collect the operating parameters of power generation, heat output, cooling load, fuel consumption, ambient temperature and humidity in real time; the collected raw data are cleaned, filtered and standardized to generate a standardized measurement data set for subsequent algorithm input; S2, preliminary energy efficiency calibration and evaluation algorithm: The input data is the standardized data set generated by S1; the preliminary energy efficiency calibration and evaluation algorithm performs basic calibration on the input data, corrects the measurement error, and calculates the multi-dimensional indicators of energy efficiency evaluation. The output results of the algorithm include comprehensive energy utilization rate, power-to-heat ratio, and electric-to-cooling ratio; S3, dynamic feedback adjustment of evaluation results: based on the error information in the evaluation results generated by S2, the sensor acquisition parameters are adjusted through a dynamic feedback adjustment algorithm; the adjusted parameters are used as the data acquisition input of S1; S4, system status analysis: the input data is the multi-dimensional energy efficiency index generated by S2 and the feedback adjustment results of S3; Through the system status analysis algorithm, the system's efficient operation status and bottleneck problems are identified, and the overall evaluation results and improvement suggestions of the system performance are provided for the subsequent steps; S5, output and transfer of evaluation results: Integrate the multi-dimensional energy efficiency evaluation results generated by S2 and the system status analysis results of S4 into the final evaluation results; The results are passed to the strategy module through the data interface within the system to further optimize the basic input of the steps and the final performance evaluation.

2. The energy efficiency evaluation method of a distributed integrated energy system according to claim 1, characterized in that: S1 includes the following sub-steps: S1-1. Multi-source data collection: Use power sensors, heat flow meters, cooling sensors, gas flow meters and environmental sensors to collect power generation, heat output, cooling load, fuel consumption, ambient temperature and humidity operating parameters in real time and generate original data sets; S1-2, data preprocessing: clean and denoise the raw data collected in S1-1 to remove invalid data; standardize the processed data through normalization operation to generate a standardized data set; S1-3. Error identification and calibration: Based on the standardized data set, identify the errors caused by measurement equipment deviation or environmental changes, and correct the standardized data through the calibration model to generate a corrected standardized measurement data set.

3. The energy efficiency evaluation method of a distributed integrated energy system according to claim 1, characterized in that: The S2 comprises the following sub-steps: S2-1, Error calibration: Based on the corrected standardized data set generated by S1-3, the input data is further adjusted through the error calibration model; S2-2, multi-dimensional energy efficiency index calculation: Calculate the energy efficiency index based on the calibration results of S2-1, including comprehensive energy utilization rate, power-to-heat ratio and electric-to-cooling ratio; S2-3. Generation of evaluation results: Output the multi-dimensional energy efficiency index results of S2-2.

4. The energy efficiency evaluation method of a distributed integrated energy system according to claim 1, characterized in that: The S3 comprises the following sub-steps: S3-1, error information acquisition: compare the multi-dimensional energy efficiency index results of S2-3 with the preset target value, extract the error data, where the error amplitude E i and direction Δ i Defined as: in is the i-th energy efficiency index actually measured, is the target indicator value; S3-2, dynamic feedback model construction: Based on the error information of S3-1, a dynamic feedback model is established to adjust the sensor acquisition parameters. The specific adjustment formula is: in and is the sampling frequency of the sensor, and is the sensor weight, k f is the feedback coefficient; S3-3, parameter optimization feedback: The sensor parameters adjusted in S3-2 are fed back to the data acquisition module of S1 and used for the next round of data acquisition, forming a closed-loop feedback mechanism.

5. The energy efficiency evaluation method of a distributed integrated energy system according to claim 1, characterized in that: The S4 comprises the following sub-steps: S4-1, multi-dimensional energy efficiency index input: input the multi-dimensional energy efficiency index of S2-3 and the feedback adjustment result of S3-3; S4-2, System status evaluation model construction: Based on the input of S4-1, establish the system status evaluation model and calculate the system's comprehensive performance score P s , the specific calculation formula is: in, is the adjusted i-th energy efficiency index, ω i is the corresponding weight, α is the nonlinear adjustment coefficient; S4-3, status analysis result generation: Based on the comprehensive performance score of S4-2, identify the efficient operation area and the inefficient bottleneck area, and output the system status analysis results.

6. The energy efficiency evaluation method of a distributed integrated energy system according to claim 1, characterized in that: The S5 comprises the following sub-steps: S5-1, integration of evaluation results: Integrate the multi-dimensional energy efficiency indicators of S2-3 and the system status analysis results of S4-3 into the final comprehensive evaluation results; S5-2. Construction of nonlinear combination model: The integration results of S5-1 are optimized and calculated through the nonlinear combination model. The specific formula is: in, is the i-th energy efficiency index after integration, β is the nonlinear weight adjustment parameter; S5-3. Evaluation result transfer: The final comprehensive evaluation result in S5-2 is transferred to the strategy module through the data interface, which is used as the basic input for subsequent optimization steps.

7. An energy efficiency evaluation optimization strategy for a distributed integrated energy system, applied to an energy efficiency evaluation method for a distributed integrated energy system according to any one of claims 1 to 6, characterized in that: The following steps are involved: S7-1, optimization target setting: Based on the comprehensive evaluation results of S5, the optimization targets are set through the strategy module. The optimization targets include improving the comprehensive utilization rate of energy, reducing the power-to-heat ratio, and optimizing the electric-to-cooling ratio index. The optimization target input is the basis for subsequent dynamic parameter adjustment and nonlinear optimization. S7-2, dynamic parameter adjustment strategy: Based on the feedback adjustment results of S3, the strategy module further optimizes the weight and sampling frequency of sensor acquisition parameters, using a dynamic adjustment coefficient k opt The correction formula is: Where E res is the residual error, To optimize the sampling frequency, the strategy module adjusts the sampling parameters in real time; S7-3, Goal achievement verification: Verify the optimized multi-dimensional energy efficiency indicators through the strategy module to ensure that each indicator reaches the set optimization goal.

8. The energy efficiency evaluation optimization strategy of a distributed integrated energy system according to claim 7 is characterized by: The dynamic parameter adjustment strategy in S7-2 also includes: S8-1, nonlinear adjustment strategy: The strategy module applies nonlinear functions to dynamically adjust the multi-dimensional energy efficiency indicators, using an exponential adjustment function, the formula of which is: in, is the optimized energy efficiency index, γ is the nonlinear adjustment coefficient, which is dynamically calculated by the strategy module; S8-2, Adaptive strategy update: The strategy module adaptively adjusts the acquisition parameters and the weights of the feedback model based on the optimization results of S8-1, so that the optimization process continues to adapt to new operating conditions.

9. The energy efficiency evaluation optimization strategy of a distributed integrated energy system according to claim 7 is characterized by: The following steps are involved: S9-1, energy efficiency index priority adjustment strategy: According to the system status analysis results of S4, the energy efficiency index is given priority through the strategy module, and the priority weighted function is used for calculation. The formula is: in, is the weight after priority adjustment, λ is the priority adjustment coefficient, P i Prioritize energy efficiency indicators; 9-2. Bottleneck elimination strategy: The strategy module optimizes the inefficient bottlenecks identified in S4-3 and improves the energy efficiency of inefficient areas by adjusting acquisition parameters and model weights.

10. The energy efficiency evaluation optimization strategy of a distributed integrated energy system according to claim 7, characterized in that: The following steps are involved: S10-1, comprehensive performance evaluation strategy: Based on the nonlinear combination results of S5-2, the energy efficiency evaluation results are comprehensively evaluated through the strategy module, using a logarithmic amplification function, the formula is: in, is the comprehensive performance evaluation result after optimization; S10-2, strategy output and feedback: The comprehensive evaluation results of S10-1 are used as strategy output and transmitted to the next round of optimization module through the data interface of the strategy module for subsequent system optimization and evaluation cycles.

Images