Power saving accounting method based on historical power consumption and equipment operation information

Abstract

The application relates to the technical field of energy management, and discloses a power saving calculation method based on historical power consumption and equipment operation information, which comprises the following steps: obtaining typical load change modes, power consumption distribution difference coefficients, operation efficiency coefficients of each power consumption equipment and start-stop influence factor matrices according to historical power consumption data and historical associated equipment operation information, inputting the power saving calculation model, and outputting a power saving scheme; based on the power saving scheme, simulating the historical power consumption data and the historical associated equipment operation information, generating a benchmark power consumption, and obtaining a predicted power saving amount according to the difference between the benchmark power consumption and the historical power consumption; obtaining a deviation rate and an abnormal equipment identifier after the power saving scheme is implemented, and generating a power saving calculation evaluation report. The application can provide accurate basis for the power saving decision of an enterprise, effectively solves the problems that the existing power saving calculation method is not accurate, the equipment operation information is not fully considered, and multi-source data integration is insufficient, and helps the enterprise to better realize energy saving and consumption reduction and sustainable development.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, and in particular to a method for calculating energy savings based on historical electricity consumption and equipment operation information. Background Technology

[0002] In the field of energy management, energy saving accounting is of great significance for enterprises to reduce operating costs and achieve sustainable development. However, existing energy saving accounting methods have several shortcomings. On the one hand, traditional methods often rely solely on simple electricity consumption data, failing to fully explore the deeper patterns hidden within historical electricity data, such as trends in electricity load changes and differences in electricity distribution across different time periods, resulting in inaccurate energy saving calculations. On the other hand, most methods do not adequately consider equipment operating information. Factors such as the operating efficiency, power factor, and start-up / shutdown times of different equipment have a significant impact on electricity consumption, but existing accounting methods often overlook this crucial information, making it difficult to accurately assess the effectiveness of energy saving. Furthermore, existing technologies lack the ability to integrate multi-source data and conduct comprehensive analysis, failing to establish effective models to comprehensively measure the actual effectiveness of energy-saving measures. This hinders enterprises' energy-saving decision-making and limits their further development in energy conservation and consumption reduction.

[0003] Therefore, there is an urgent need to provide a technical solution to address the above problems. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method for calculating energy-saving costs based on historical electricity consumption and equipment operation information.

[0005] Firstly, the present invention provides a method for calculating energy savings based on historical electricity consumption and equipment operation information. The technical solution of this method is as follows:

[0006] Acquire historical electricity consumption data and historical associated equipment operation information within the target period; wherein, the historical electricity consumption data includes: historical electricity load sequence and historical time period electricity distribution of all electrical equipment, and the historical associated equipment operation information includes: historical efficiency parameters, historical power factor and historical start and stop timestamp set of each electrical equipment;

[0007] The historical electricity load sequence is decomposed into time series and typical load change patterns are identified through clustering algorithms. The electricity distribution difference coefficient of the historical period is determined. The historical efficiency parameters and historical power factors of each electrical device are normalized and weighted and summed to obtain the operating efficiency coefficient of each electrical device. The start-stop influence factor matrix of the corresponding electrical device is constructed based on the historical start-stop timestamp set of each electrical device.

[0008] The typical load change pattern, the electricity distribution difference coefficient, the operating efficiency coefficient of each electrical device, and the start-stop influence factor matrix are input into the target energy-saving calculation model to output an energy-saving scheme; wherein, the energy-saving scheme includes: system-level electricity consumption period optimization interval and power adjustment threshold for each electrical device;

[0009] Based on the energy-saving scheme, simulation calculations are performed on the historical electricity consumption data and the historical associated equipment operation information to generate a baseline electricity consumption. Based on the difference between the baseline electricity consumption and the historical electricity consumption corresponding to the historical electricity load sequence, the predicted electricity saving is obtained.

[0010] After implementing the energy-saving scheme, obtain real-time power consumption data and real-time associated equipment operation information, calculate the actual power saving based on the real-time power consumption corresponding to the real-time power consumption data and the benchmark power consumption, determine the deviation rate between the actual power saving and the predicted power saving, generate abnormal equipment identifiers based on the real-time associated equipment operation information, and form an energy-saving accounting and evaluation report containing the deviation rate and the abnormal equipment identifiers.

[0011] The beneficial effects of the energy-saving calculation method based on historical electricity consumption and equipment operation information of the present invention are as follows:

[0012] The method of this invention can provide accurate basis for enterprises' energy-saving decisions, effectively solving the problems of inaccurate existing energy-saving calculation methods, insufficient consideration of equipment operation information, and lack of integration of multi-source data, thus helping enterprises to better achieve energy conservation, consumption reduction and sustainable development.

[0013] Based on the above scheme, the energy-saving calculation method of the present invention based on historical electricity consumption and equipment operation information can be further improved as follows.

[0014] In one optional approach, the step of acquiring historical electricity consumption data and associated equipment operation information within the target period further includes:

[0015] According to the predicted collection frequency, acquire the historical electricity consumption data and the operation information of the associated equipment within the target period;

[0016] Among them, the first in the target period Historical electricity load at any given time The expression is: The first period within the target period Historical electricity consumption distribution for each time period The expression is: ; Indicates the first The electrical equipment in the target period of the first Power at any moment , This represents the total number of sampling points within the target period. This indicates the total number of electrical devices.

[0017] In an optional embodiment, the step of performing time-series decomposition of the historical electricity load sequence and identifying typical load change patterns using a clustering algorithm further includes:

[0018] The historical electricity load sequence is decomposed into time series, trend components are extracted, and typical load change patterns in the trend components are identified by clustering algorithm;

[0019] The typical load change patterns include: peak-valley fluctuation pattern, step-up pattern, and stable operation pattern; the electricity load sequence of the cluster centers in the peak-valley fluctuation pattern shows periodic high-low alternation, the electricity load sequence of the cluster centers in the step-up pattern increases monotonically and the difference between adjacent time points is constant, and the electricity load sequence of the cluster centers in the stable operation pattern is within the target fluctuation range.

[0020] In one alternative approach, the step of determining the electricity distribution difference coefficient for the historical time period further includes:

[0021] Based on the historical electricity consumption distribution, a regression model is constructed, and the difference coefficient of electricity consumption distribution in different time periods is quantified based on the regression model.

[0022] The expression for the regression model is as follows: ; Represents the intercept term. Indicates the first The time period type, Indicates the first The average temperature over a period of time Indicates the first Production plan intensity for each time period , and These represent the regression coefficients for the corresponding features. Represents the residual;

[0023] The expression for the electricity consumption distribution difference coefficient for each time period is as follows: , ; Indicates the first The electricity distribution difference coefficient corresponding to each characteristic.

[0024] In one alternative approach, the first The expression for the operating efficiency coefficient of an electrical device is:

[0025]

[0026] In the formula, Indicates the first The operating efficiency coefficient of each electrical device , Indicates the first The average standardized value of the historical power factor of each electrical device. Indicates the first Standardized values ​​of historical efficiency parameters for each electrical device;

[0027] No. The expression for the start-up and shutdown impact factor matrix of individual electrical equipment is as follows: ; Indicates the first Matrix of factors influencing the start-up and shutdown of individual electrical equipment Total number of time periods This indicates the correlation between the impact weight of start / stop frequency and load change; the impact weight of start / stop frequency The expression is: The correlation of the load change The expression is: ; Indicates the first The electrical equipment in the first Number of starts and stops during each time period Indicates the first Start-stop status indication function for each electrical device ; Indicates the first The start time of the next start-stop cycle Indicates the first The stopping time of the next start / stop; .

[0028] In one alternative approach, the target energy-saving calculation model is a pre-trained random forest model. The step of inputting the typical load change pattern, the electricity distribution difference coefficient, the operating efficiency coefficient of each electrical device, and the start-stop influence factor matrix into the target energy-saving calculation model and outputting the energy-saving scheme further includes:

[0029] Construct the input feature vector for each electrical device at different time periods. ; Indicates the first Load change pattern of each time period Cluster center values, Indicates the first The first time period The electricity distribution difference coefficient corresponding to each characteristic;

[0030] The input feature vectors corresponding to each electrical device at different time periods are input into the trained random forest model to generate the energy-saving scheme that includes the system-level power consumption time period optimization interval and the power adjustment threshold of each electrical device;

[0031] Among them, the system-level power consumption period optimization interval The expression is: ; , ;

[0032] Among them, the Power adjustment threshold for individual electrical devices The expression is: ; For the first The rated power of each electrical device.

[0033] In an optional approach, the step of simulating and calculating the historical electricity consumption data and the historical associated equipment operation information based on the energy-saving scheme to generate a baseline electricity consumption further includes:

[0034] According to the Power adjustment threshold for individual electrical devices , for the The historical power of each electrical device is corrected to obtain the first... The corrected power of each electrical device is calculated until the corrected power of each device is obtained, and its expression is: ; Indicates the first The electrical equipment in the first Historical power at any given moment;

[0035] The electricity load during periods within the target period that do not belong to the system-level electricity consumption period optimization interval is transferred to the system-level electricity consumption period optimization interval to generate an optimized electricity load sequence. Its expression is:

[0036]

[0037] In the formula, ; This represents the load transfer weighting coefficient, indicating the proportion of load transferred from non-optimal periods to optimal periods. Represents the first non-optimized time period Historical electricity load at any given time ;

[0038] According to the optimized power load sequence Calculate the baseline power consumption. Its expression is:

[0039]

[0040] The step of obtaining the predicted energy saving based on the difference between the baseline energy consumption and the historical energy consumption corresponding to the historical energy consumption data further includes:

[0041] Calculate the historical electricity consumption based on the historical electricity load sequence. Its expression is:

[0042]

[0043] The predicted energy saving is determined based on the difference between the historical energy consumption and the baseline energy consumption, and its expression is as follows:

[0044]

[0045] In the formula, This indicates the predicted energy saving.

[0046] In one optional approach, the step of calculating the actual energy saving based on the real-time energy consumption corresponding to the real-time energy consumption data and the baseline energy consumption further includes:

[0047] Based on the real-time electricity load sequence in the real-time electricity consumption data, the real-time electricity consumption is calculated, and its expression is as follows:

[0048]

[0049] In the formula, ; Indicates the first The first electrical device in the current cycle Power at any given moment; This indicates the real-time power consumption. This represents the total number of sampling points within the current period;

[0050] The actual energy saving is determined based on the difference between the baseline energy consumption and the real-time energy consumption, and its expression is as follows:

[0051]

[0052] In the formula, This indicates the actual amount of electricity saved.

[0053] In an optional approach, the steps of determining the deviation rate between the predicted energy saving and the actual energy saving, generating an abnormal device identifier based on the real-time associated device operation information, and forming an energy saving accounting and evaluation report containing the deviation rate and the abnormal device identifier, further include:

[0054] The deviation rate is calculated based on the actual energy saving and the predicted energy saving, and its expression is as follows:

[0055]

[0056] In the formula, This represents the deviation rate;

[0057] The abnormal equipment is identified by marking the electrical equipment with abnormal real-time power factor or abnormal real-time start / stop timestamp set in the real-time associated equipment operation information, and an abnormal equipment identifier is generated.

[0058] Secondly, the present invention provides an energy-saving accounting system based on historical electricity consumption and equipment operation information. The technical solution of the system is as follows:

[0059] The acquisition module is used to acquire historical electricity consumption data and historical associated equipment operation information within a target period; wherein, the historical electricity consumption data includes: historical electricity load sequence and historical time period electricity distribution of all electrical equipment, and the historical associated equipment operation information includes: historical efficiency parameters, historical power factor and historical start and stop timestamp set of each electrical equipment;

[0060] The processing module is used to perform time-series decomposition on the historical electricity load sequence and identify typical load change patterns through clustering algorithms, and determine the electricity distribution difference coefficient of the electricity distribution in the historical period; normalize the historical efficiency parameters and historical power factors of each electrical device and perform weighted summation to obtain the operating efficiency coefficient of each electrical device, and construct the start-stop influence factor matrix of the corresponding electrical device based on the historical start-stop timestamp set of each electrical device;

[0061] The output module is used to input the typical load change pattern, the electricity distribution difference coefficient, the operating efficiency coefficient of each electrical device, and the start-stop influence factor matrix into the target energy-saving calculation model, and output the energy-saving scheme; wherein, the energy-saving scheme includes: system-level electricity consumption period optimization interval and power adjustment threshold for each electrical device;

[0062] The calculation module is used to perform simulation calculations on the historical electricity consumption data and the historical associated equipment operation information based on the power saving scheme, generate a baseline electricity consumption, and obtain the predicted electricity saving based on the difference between the baseline electricity consumption and the historical electricity consumption corresponding to the historical electricity load sequence.

[0063] The evaluation module is used to acquire real-time electricity consumption data and real-time associated equipment operation information after the implementation of the power saving scheme, calculate the actual power saving based on the real-time electricity consumption corresponding to the real-time electricity consumption and the benchmark electricity consumption, determine the deviation rate between the actual power saving and the predicted power saving, and generate abnormal equipment identifiers based on the real-time associated equipment operation information to form a power saving accounting evaluation report containing the deviation rate and the abnormal equipment identifiers.

[0064] The beneficial effects of the energy-saving accounting system based on historical electricity consumption and equipment operation information of the present invention are as follows:

[0065] The system of this invention provides accurate basis for enterprises' energy-saving decisions, effectively solving the problems of inaccurate existing energy-saving calculation methods, insufficient consideration of equipment operation information, and lack of integration of multi-source data, thus helping enterprises to better achieve energy conservation, emission reduction, and sustainable development.

[0066] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0067] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0068] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0069] Figure 1 This is a flowchart illustrating an embodiment of the energy-saving calculation method based on historical electricity consumption and equipment operation information according to the present invention.

[0070] Figure 2 This is a schematic diagram of an embodiment of the energy-saving accounting system based on historical electricity consumption and equipment operation information of the present invention. Detailed Implementation

[0071] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0072] Figure 1 This diagram illustrates a flowchart of an embodiment of a power-saving calculation method based on historical electricity consumption and equipment operation information provided by the present invention. Figure 1 As shown, it includes the following steps:

[0073] S1. Obtain historical electricity consumption data and historical related equipment operation information within the target period.

[0074] The historical electricity consumption data includes: the historical electricity load sequence and historical time period distribution of all electrical equipment. The historical associated equipment operation information includes: the historical efficiency parameters, historical power factor and historical start-stop timestamp set of each electrical equipment.

[0075] The target period is a historical period measured in weeks or months, with clearly defined start and end times. Data is recorded at a fixed collection frequency (e.g., every 15 minutes, adjustable as needed) to ensure the integrity and comparability of the time-series data. The historical power load sequence refers to the sequence data of the system-level total power arranged chronologically; each data point corresponds to the sum of the instantaneous power of all equipment at a sampling time, used to analyze the temporal variation patterns of the overall power load. Historical time-period power distribution refers to the proportion of electricity consumption to total electricity consumption in different time periods (e.g., divided by hours) within the target period. Historical efficiency parameters refer to the rated operating efficiency values ​​of electrical equipment within the target period, typically obtained based on the nameplate parameters or historical measured data, used to quantify the energy conversion efficiency of electrical equipment under ideal conditions. Historical power factor refers to the power factor values ​​of electrical equipment at different time points within the target period, reflecting the ratio of active power to apparent power during equipment operation, used to assess the dynamic changes in energy utilization efficiency. The historical start-stop timestamp set refers to the start-up and stop times of electrical equipment within the target period. It is used to analyze the impact of the start-stop behavior of electrical equipment on the system load and to support the optimization of start-stop strategies.

[0076] S2. Perform time-series decomposition on the historical electricity load sequence and identify typical load change patterns through clustering algorithms, and determine the electricity distribution difference coefficient of the historical period; normalize the historical efficiency parameters and historical power factors of each electrical device and perform weighted summation to obtain the operating efficiency coefficient of each electrical device, and construct the start-stop influence factor matrix of the corresponding electrical device based on the historical start-stop timestamp set of each electrical device.

[0077] Typical load variation patterns include: peak-valley fluctuation pattern, stepped increase pattern, and stable operation pattern. The electricity load sequence of the cluster centers in the peak-valley fluctuation pattern exhibits periodic high-low alternation; the electricity load sequence of the cluster centers in the stepped increase pattern is monotonically increasing with a constant difference between adjacent time points; and the electricity load sequence of the cluster centers in the stable operation pattern is within the target fluctuation range. The electricity distribution difference coefficient refers to the weight of the influence of external factors (such as time period type, temperature, and production plan) on the electricity consumption of a time period, quantified through a regression model. The larger the electricity distribution difference coefficient, the more significant the regulatory effect of that factor on electricity distribution, and it is used to guide the optimization of time period priority ranking. The operating efficiency coefficient is an energy efficiency evaluation index generated by combining the static efficiency parameters and dynamic power factor of electrical equipment; it reflects the actual operating energy efficiency level of the equipment through normalization of efficiency parameters and weighted summation of dynamic power factor values, and is used for power threshold optimization. The start-stop influence factor matrix is ​​the correlation matrix between the start-stop behavior of electrical equipment and system load fluctuations.

[0078] S3. Input the typical load change pattern, the power consumption distribution difference coefficient, the operating efficiency coefficient of each electrical device and the start-stop influence factor matrix into the target power saving calculation model, and output the power saving scheme.

[0079] The energy-saving scheme includes: system-level power consumption period optimization intervals and power adjustment thresholds for each electrical device.

[0080] S4. Based on the energy-saving scheme, perform simulation calculations on the historical electricity consumption data and the historical associated equipment operation information to generate a baseline electricity consumption, and obtain the predicted energy saving based on the difference between the baseline electricity consumption and the historical electricity consumption corresponding to the historical electricity load sequence.

[0081] S5. Obtain real-time power consumption data and real-time associated equipment operation information after implementing the power saving scheme, and calculate the actual power saving based on the real-time power consumption corresponding to the real-time power consumption data and the benchmark power consumption, and determine the deviation rate between the actual power saving and the predicted power saving, and generate abnormal equipment identifiers based on the real-time associated equipment operation information, forming a power saving accounting and evaluation report containing the deviation rate and the abnormal equipment identifiers.

[0082] The technical solution in this embodiment integrates historical electricity consumption data and equipment operation information to construct a multi-source data fusion-based energy-saving calculation model. It outputs an energy-saving scheme that includes system-level electricity consumption period optimization and equipment-level power adjustment, and generates an energy-saving assessment report based on simulation and actual data comparison. This method significantly improves the accuracy of energy-saving calculations by dynamically quantifying the impact of equipment efficiency, power factor, and start-up / shutdown behavior on electricity consumption. It solves the problems of insufficient data utilization and isolated analysis of equipment characteristics in traditional methods, while also ensuring the verifiability of energy-saving strategies. This provides enterprises with closed-loop energy-saving decision support, helping them scientifically reduce energy costs and promote sustainable development.

[0083] In one optional approach, the step of acquiring historical electricity consumption data and associated equipment operation information within the target period further includes:

[0084] According to the predicted collection frequency, the historical electricity consumption data and the operation information of the associated equipment within the target period are obtained.

[0085] Specifically, when acquiring historical electricity consumption data and related equipment operation information, it is necessary to synchronously collect historical electricity load sequences and historical time period electricity distributions according to a preset collection frequency. To achieve data alignment, and A unified timestamp needs to be bound. During data alignment, if data is missing at a certain point in time, linear interpolation is used to complete it. .

[0086] Among them, the first in the target period Historical electricity load at any given time The expression is: The first period within the target cycle Historical electricity consumption distribution for each time period The expression is . ; Indicates the first The first electrical device within the target period Power at any moment , This represents the total number of sampling points within the target period. This indicates the total number of electrical devices.

[0087] For example, if the target period is from 00:00 to 23:45 on a certain day, and the data collection frequency is 15 minutes per time, then... Suppose there are three electrical devices, located at... The historical electricity loads at the time (00:00) were 8kW, 12kW, and 18kW respectively. .when The time (08:00-09:00) includes 4 sampling points (33, 34, 35, 36); if , ,but .

[0088] The aforementioned optional technical solutions further acquire system-level load and sub-equipment parameters synchronously through a preset acquisition frequency, ensuring strict alignment of historical electricity consumption data and equipment operation information in the time dimension, and avoiding the loss of correlation caused by asynchronous data. System-level load calculation and time-period distribution statistics provide reliable input for subsequent cluster analysis and difference coefficient modeling, supporting the mining of multi-granularity electricity consumption patterns, while laying the foundation for the normalization processing of equipment-level parameters, enhancing the consistency of data throughout the entire process, and thus improving the robustness of energy-saving strategies.

[0089] In an optional embodiment, the step of performing time-series decomposition of the historical electricity load sequence and identifying typical load change patterns using a clustering algorithm further includes:

[0090] The historical electricity load sequence is decomposed into time series, trend components are extracted, and typical load change patterns in the trend components are identified by clustering algorithm.

[0091] The time-series decomposition uses the Seasonal-Trend Decomposition using Loess (STL) method by default, which decomposes historical electricity load sequences. Decomposed into trend components Periodic components and residual components The formula is: Trend components are calculated using the sliding window averaging method. ; Indicates the window length. The default clustering algorithm is K-means clustering; set the number of clusters. Cluster center is The distance metric is calculated using Euclidean distance. Cluster centers representing peak-valley fluctuation patterns Cluster centers representing a ladder-like ascending pattern Cluster centers representing stable operating patterns.

[0092] It should be noted that trend components Smoothness requirements must be met, such as a sliding window duration of 168 hours, covering a one-week cycle. In addition to K-means clustering, DBSCAN (density clustering) can also be used to address non-spherical data distribution problems.

[0093] The aforementioned optional technical solutions further employ time-series decomposition to extract load trend components and combine them with clustering algorithms to identify typical load patterns (peak-valley fluctuations, stepped increases, and stable operation), effectively eliminating noise interference and accurately capturing long-term variation patterns of electricity load. Through pattern classification definitions, intuitive basis is provided for time-period optimization strategies. For example, in peak-valley fluctuation patterns, priority can be given to adjusting high-load periods, while in stable modes, equipment operating parameters can be optimized. This allows for the development of differentiated energy-saving measures for different load characteristics, improving the adaptability and effectiveness of the strategies.

[0094] In one alternative approach, the step of determining the electricity distribution difference coefficient for the historical time period further includes:

[0095] Based on the historical electricity consumption distribution, a regression model is constructed, and the difference coefficient of electricity consumption distribution in different time periods is quantified based on the regression model.

[0096] The expression for the regression model is as follows: ; Represents the intercept term. Indicates the first The time period type, Indicates the first The average temperature over a period of time Indicates the first Production plan intensity for each time period , and These represent the regression coefficients for the corresponding features. Represents the residual.

[0097] The expression for the electricity consumption distribution difference coefficient for each time period is as follows: , ; Indicates the first The electricity distribution difference coefficient corresponding to each characteristic.

[0098] It should be noted that interaction terms can be introduced into the regression model to enhance interpretability. The modified model is as follows: ; This represents the combined effect of time period type and temperature (e.g., a surge in electricity consumption on hot workdays). The expression for the electricity consumption distribution difference coefficient for each time period is modified as follows: .

[0099] The aforementioned optional technical solutions further quantify the impact weights of external factors (time period type, temperature, production plan) on electricity consumption distribution by constructing regression models, generating difference coefficients to reflect the control priorities of each factor. These difference coefficients guide the dynamic selection of optimization time periods, such as electricity shifting during high-temperature periods or peak production periods, avoiding strategy biases caused by relying solely on empirical rules. Simultaneously, they provide quantitative basis for multi-objective collaborative optimization, enhancing the scientific rigor and interpretability of energy-saving solutions.

[0100] In one alternative approach, the first The expression for the operating efficiency coefficient of an electrical device is:

[0101]

[0102] In the formula, Indicates the first The operating efficiency coefficient of each electrical device , Indicates the first The average standardized value of the historical power factor of each electrical device. Indicates the first Standardized values ​​of historical efficiency parameters for each electrical device. Assume... , , , ,but .

[0103] No. The expression for the start-up and shutdown impact factor matrix of individual electrical equipment is as follows: ; Indicates the first Matrix of factors influencing the start-up and shutdown of individual electrical equipment Total number of time periods This indicates the correlation between the impact weight of start / stop frequency and load change; the impact weight of start / stop frequency The expression is: The correlation of the load change The expression is: ; Indicates the first The electrical equipment in the first Number of starts and stops during each time period Indicates the first Start-stop status indication function for each electrical device ; Indicates the first The start time of the next start-stop cycle Indicates the first The stopping time of the next start / stop; Assuming the first electrical device starts up twice and stops once during the 8th time period (08:00-09:00), then If the historical electricity load sequence for the 8th time period is: 40kW, 42kW, 45kW, 43kW; then .

[0104] It should be noted that, among the above optional methods, the Pearson correlation coefficient can be used instead of cosine similarity, i.e. ; Indicates the first The electrical equipment in the first Average start / stop status over a period of time This represents the average load gradient.

[0105] The aforementioned optional technical solutions further quantify the actual energy efficiency level of equipment through normalization and weighted calculation, providing precise input for power threshold optimization; the start-stop influencing factor matrix correlates the start-stop frequency of equipment with system load fluctuations, identifies highly correlated equipment, and optimizes its start-stop strategies, such as reducing the impact of frequent start-stops on the power grid. The combination of these two approaches achieves the dual goals of improving equipment-level energy efficiency and stabilizing system-level load, overcoming the limitation of traditional methods where equipment and system optimization are disconnected.

[0106] In one alternative approach, the target energy-saving calculation model is a pre-trained random forest model. The step of inputting the typical load change pattern, the electricity distribution difference coefficient, the operating efficiency coefficient of each electrical device, and the start-stop influence factor matrix into the target energy-saving calculation model and outputting the energy-saving scheme further includes:

[0107] Construct the input feature vector for each electrical device at different time periods. ; Indicates the first Load change pattern of each time period Cluster center values, Indicates the first The first time period The electricity distribution difference coefficient corresponding to each characteristic;

[0108] The input feature vectors corresponding to each electrical device at different time periods are input into the trained random forest model to generate the energy-saving scheme that includes the system-level power consumption time period optimization interval and the power adjustment threshold of each electrical device.

[0109] Among them, the system-level power consumption period optimization interval The expression is: ; , .

[0110] Among them, the Power adjustment threshold for individual electrical devices The expression is: ; For the first The rated power of each electrical device.

[0111] In the above optional methods, the target energy-saving calculation model can be replaced by an LSTM neural network, and the output features of the LSTM neural network are: The corresponding time-series data is output as a range that includes system-level power consumption period optimization intervals. Power adjustment threshold for each electrical device A power-saving solution. LSTM neural networks can utilize temporal dependencies to improve multi-step prediction accuracy.

[0112] The aforementioned optional technical solutions further integrate load patterns, difference coefficients, and equipment parameters to generate system-level time-period optimization intervals and equipment-level power thresholds, ensuring that the energy-saving strategy takes into account both global coordination and individual adaptation. The time-period optimization interval selects low-impact periods through weighted selection using difference coefficients, reducing electricity costs; the power thresholds, combined with efficiency coefficients, dynamically constrain equipment peak power to avoid overload losses. This model enhances the correlation analysis capabilities of multi-source data through machine learning, significantly improving the generalization and feasibility of the strategy.

[0113] In an optional approach, the step of simulating and calculating the historical electricity consumption data and the historical associated equipment operation information based on the energy-saving scheme to generate a baseline electricity consumption further includes:

[0114] According to the Power adjustment threshold for individual electrical devices , for the The historical power of each electrical device is corrected to obtain the first... The corrected power of each electrical device is calculated until the corrected power of each device is obtained, and its expression is: ; Indicates the first The electrical equipment in the first Historical power at any given moment.

[0115] The electricity load during periods within the target period that do not belong to the system-level electricity consumption period optimization interval is transferred to the system-level electricity consumption period optimization interval to generate an optimized electricity load sequence. Its expression is:

[0116]

[0117] In the formula, ; This represents the load transfer weighting coefficient, indicating the proportion of load transferred from non-optimal periods to optimal periods. Represents the first non-optimized time period Historical electricity load at any given time .

[0118] According to the optimized power load sequence Calculate the baseline power consumption. Its expression is:

[0119]

[0120] The step of obtaining the predicted energy saving based on the difference between the baseline energy consumption and the historical energy consumption corresponding to the historical energy consumption data further includes:

[0121] Calculate the historical electricity consumption based on the historical electricity load sequence. Its expression is:

[0122]

[0123] The predicted energy saving is determined based on the difference between the historical energy consumption and the baseline energy consumption, and its expression is as follows:

[0124]

[0125] In the formula, This indicates the predicted energy saving.

[0126] The aforementioned optional technical solutions further generate a baseline electricity consumption by correcting historical power consumption to within a threshold and transferring load from non-optimized periods to the optimized range according to correlation, accurately simulating the theoretical electricity consumption scenario after the implementation of energy-saving measures. The difference between the baseline electricity consumption and historical data directly reflects the theoretical energy-saving potential, providing a reliable baseline for effect prediction. The load transfer rule is dynamically allocated based on start-stop influencing factors, ensuring load conservation and conforming to actual operating constraints, avoiding simulation distortion, and thus improving the confidence of the prediction results.

[0127] In one optional approach, the step of calculating the actual energy saving based on the real-time energy consumption corresponding to the real-time energy consumption data and the baseline energy consumption further includes:

[0128] Based on the real-time electricity load sequence in the real-time electricity consumption data, the real-time electricity consumption is calculated, and its expression is as follows:

[0129]

[0130] In the formula, ; Indicates the first The first electrical device in the current cycle Power at any given moment; This indicates the real-time power consumption. This represents the total number of sampling points within the current period;

[0131] The actual energy saving is determined based on the difference between the baseline energy consumption and the real-time energy consumption, and its expression is as follows:

[0132]

[0133] In the formula, This indicates the actual amount of electricity saved.

[0134] The aforementioned optional technical solutions further calculate the actual power saving by comparing real-time power consumption with the benchmark value, and dynamically evaluate the deviation rate by combining the predicted value, thereby achieving closed-loop monitoring of the power saving effect; triggering alarms by exceeding the deviation rate limit indicates abnormal strategy execution or changes in external conditions, supporting rapid adjustments; and eliminating errors caused by inconsistent time ranges by strictly relying on time-series aligned load data in the calculation of actual power saving, ensuring that the evaluation results truly reflect the effectiveness of power saving measures, and providing enterprises with traceable optimization basis.

[0135] In an optional approach, the steps of determining the deviation rate between the predicted energy saving and the actual energy saving, generating an abnormal device identifier based on the real-time associated device operation information, and forming an energy saving accounting and evaluation report containing the deviation rate and the abnormal device identifier, further include:

[0136] The deviation rate is calculated based on the actual energy saving and the predicted energy saving, and its expression is as follows:

[0137]

[0138] In the formula, This indicates the deviation rate; when the deviation rate is greater than the threshold, an early warning message is output.

[0139] The abnormal equipment is identified by marking the electrical equipment with abnormal real-time power factor or abnormal real-time start / stop timestamp set in the real-time associated equipment operation information, and an abnormal equipment identifier is generated.

[0140] It should be noted that the real-time efficiency parameters in the real-time associated device operation information are usually static attributes and will not change significantly, so they are not included in the anomaly flag.

[0141] The real-time power factor anomaly detection process is as follows: For the first... For each electrical device, calculate the standard deviation of the real-time power factor fluctuation. ; Indicates the first The standard deviation of the real-time power factor fluctuation of individual electrical devices. Indicates the first Real-time power factor of each electrical device Indicates the first The average real-time power factor of each electrical device; if Then for the first Each electrical device is identified and marked as having an abnormal real-time power factor. The default value is 0.2, but it can be set according to the actual situation. No restrictions are set here.

[0142] The process of detecting anomalies in the real-time start / stop timestamp set is as follows: For the first... For each electrical device, the number of real-time start-stop cycles within the current period is counted. ;like Then for the first Each electrical device is identified and marked as an anomaly in the real-time start / stop timestamp set. This represents the tolerance factor, which defaults to 1.5. However, it can be set according to actual conditions, and there are no restrictions here.

[0143] It should be noted that when the real-time power factor or real-time start-stop timestamp set of a certain electrical device is abnormal, the electrical device will be identified.

[0144] The aforementioned optional technical solutions further generate abnormal equipment identifiers by detecting real-time power factor fluctuations and excessive start-stop frequencies, accurately locating faulty or inefficient equipment, such as capacitor failure or control logic anomalies. The abnormal identifiers are linked to deviation rate alarms, forming a closed-loop feedback mechanism that helps enterprises quickly respond to changes in equipment status, preventing single-device problems from dragging down overall energy-saving effects, and improving operational efficiency and system reliability.

[0145] Figure 2 This diagram illustrates a structural schematic of an embodiment of an energy-saving accounting system based on historical electricity consumption and equipment operation information provided by the present invention. Figure 2 As shown, the system includes:

[0146] The acquisition module 210 is used to acquire historical electricity consumption data and historical associated equipment operation information within a target period; wherein, the historical electricity consumption data includes: historical electricity load sequence and historical time period electricity distribution of all electrical equipment, and the historical associated equipment operation information includes: historical efficiency parameters, historical power factor and historical start and stop timestamp set of each electrical equipment;

[0147] The processing module 220 is used to perform time-series decomposition on the historical power load sequence and identify typical load change patterns through clustering algorithms, and determine the power distribution difference coefficient of the power distribution in the historical period; normalize the historical efficiency parameters and historical power factors of each electrical device and perform weighted summation to obtain the operating efficiency coefficient of each electrical device, and construct the start-stop influence factor matrix of the corresponding electrical device based on the historical start-stop timestamp set of each electrical device;

[0148] The output module 230 is used to input the typical load change pattern, the power consumption distribution difference coefficient, the operating efficiency coefficient of each electrical device and the start-stop influence factor matrix into the target power saving calculation model, and output the power saving scheme; wherein, the power saving scheme includes: system-level power consumption period optimization interval and power adjustment threshold for each electrical device;

[0149] The calculation module 240 is used to perform simulation calculations on the historical electricity consumption data and the historical associated equipment operation information based on the power saving scheme, generate a baseline electricity consumption, and obtain the predicted electricity saving based on the difference between the baseline electricity consumption and the historical electricity consumption corresponding to the historical electricity load sequence.

[0150] The evaluation module 250 is used to acquire real-time power consumption data and real-time associated equipment operation information after the implementation of the power saving scheme, calculate the actual power saving based on the real-time power consumption corresponding to the real-time power consumption data and the benchmark power consumption, determine the deviation rate between the actual power saving and the predicted power saving, and generate abnormal equipment identifiers based on the real-time associated equipment operation information to form a power saving accounting evaluation report containing the deviation rate and the abnormal equipment identifiers.

[0151] The technical solution of this embodiment can provide accurate basis for enterprises' energy-saving decisions, effectively solve the problems of inaccurate existing energy-saving calculation methods, insufficient consideration of equipment operation information, and lack of integration of multi-source data, and help enterprises better achieve energy conservation, consumption reduction and sustainable development.

[0152] Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0153] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0154] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0155] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for calculating energy savings based on historical electricity consumption and equipment operation information, characterized in that, The method includes: Acquire historical electricity consumption data and historical associated equipment operation information within the target period; wherein, the historical electricity consumption data includes: historical electricity load sequence and historical time period electricity distribution of all electrical equipment, and the historical associated equipment operation information includes: historical efficiency parameters, historical power factor and historical start and stop timestamp set of each electrical equipment; The historical electricity load sequence is decomposed into time series and typical load change patterns are identified through clustering algorithms. The electricity distribution difference coefficient of the historical period is determined. The historical efficiency parameters and historical power factors of each electrical device are normalized and weighted and summed to obtain the operating efficiency coefficient of each electrical device. The start-stop influence factor matrix of the corresponding electrical device is constructed based on the historical start-stop timestamp set of each electrical device. The typical load change pattern, the electricity distribution difference coefficient, the operating efficiency coefficient of each electrical device, and the start-stop influence factor matrix are input into the target energy-saving calculation model to output an energy-saving scheme; wherein, the energy-saving scheme includes: system-level electricity consumption period optimization interval and power adjustment threshold for each electrical device; Based on the energy-saving scheme, simulation calculations are performed on the historical electricity consumption data and the historical associated equipment operation information to generate a baseline electricity consumption. Based on the difference between the baseline electricity consumption and the historical electricity consumption corresponding to the historical electricity load sequence, the predicted electricity saving is obtained. After implementing the energy-saving scheme, obtain real-time power consumption data and real-time associated equipment operation information, calculate the actual power saving based on the real-time power consumption corresponding to the real-time power consumption data and the benchmark power consumption, determine the deviation rate between the actual power saving and the predicted power saving, generate abnormal equipment identifiers based on the real-time associated equipment operation information, and form an energy-saving accounting and evaluation report containing the deviation rate and the abnormal equipment identifiers.

2. The energy-saving calculation method based on historical electricity consumption and equipment operation information according to claim 1, characterized in that, The step of obtaining historical electricity consumption data and associated equipment operation information within the target period further includes: According to the predicted collection frequency, acquire the historical electricity consumption data and the operation information of the associated equipment within the target period; Among them, the first in the target period Historical electricity load at any given time The expression is: The first period within the target period Historical electricity consumption distribution for each time period The expression is: ; Indicates the first The electrical equipment in the target period of the first Power at any moment , This represents the total number of sampling points within the target period. This indicates the total number of electrical devices.

3. The energy-saving calculation method based on historical electricity consumption and equipment operation information according to claim 2, characterized in that, The step of performing time-series decomposition of the historical electricity load sequence and identifying typical load change patterns using a clustering algorithm further includes: The historical electricity load sequence is decomposed into time series, trend components are extracted, and typical load change patterns in the trend components are identified by clustering algorithm. The typical load change patterns include: peak-valley fluctuation pattern, stepped increase pattern, and stable operation pattern; the electricity load sequence of the cluster centers in the peak-valley fluctuation pattern shows periodic high-low alternation, the electricity load sequence of the cluster centers in the stepped increase pattern increases monotonically and the difference between adjacent time points is constant, and the electricity load sequence of the cluster centers in the stable operation pattern is within the target fluctuation range.

4. The energy-saving calculation method based on historical electricity consumption and equipment operation information according to claim 3, characterized in that, The step of determining the electricity distribution difference coefficient for the historical period further includes: Based on the historical electricity consumption distribution, a regression model is constructed, and the difference coefficient of electricity consumption distribution in different time periods is quantified based on the regression model. The expression for the regression model is as follows: ; Represents the intercept term. Indicates the first The time period type, Indicates the first The average temperature over a period of time Indicates the first Production plan intensity for each time period , and These represent the regression coefficients for the corresponding features. Represents the residual; The expression for the electricity consumption distribution difference coefficient for each time period is as follows: , ; Indicates the first The electricity distribution difference coefficient corresponding to each characteristic.

5. The energy-saving calculation method based on historical electricity consumption and equipment operation information according to claim 4, characterized in that, No. The expression for the operating efficiency coefficient of an electrical device is: In the formula, Indicates the first The operating efficiency coefficient of each electrical device , Indicates the first The average standardized value of the historical power factor of each electrical device. Indicates the first Standardized values ​​of historical efficiency parameters for each electrical device; No. The expression for the start-up and shutdown impact factor matrix of individual electrical equipment is as follows: ; Indicates the first Matrix of start-up and shutdown factors for individual electrical equipment Total number of time periods This indicates the correlation between the impact weight of start / stop frequency and load change; the impact weight of start / stop frequency The expression is: The correlation of the load change The expression is: ; Indicates the first The electrical equipment in the first Number of starts and stops during each time period Indicates the first Start / stop status indication function for each electrical device ; Indicates the first The start time of the next start-stop cycle Indicates the first The stopping time of the next start / stop; .

6. The energy-saving calculation method based on historical electricity consumption and equipment operation information according to claim 5, characterized in that, The target energy-saving calculation model is a pre-trained random forest model. The step of inputting the typical load change pattern, the electricity consumption distribution difference coefficient, the operating efficiency coefficient of each electrical device, and the start-stop influence factor matrix into the target energy-saving calculation model and outputting the energy-saving scheme further includes: Construct the input feature vector for each electrical device at different time periods. ; Indicates the first Load change pattern of each time period Cluster center values, Indicates the first The first time period The electricity distribution difference coefficient corresponding to each characteristic; The input feature vectors corresponding to each electrical device at different time periods are input into the trained random forest model to generate the energy-saving scheme that includes the system-level power consumption time period optimization interval and the power adjustment threshold of each electrical device; Among them, the system-level power consumption period optimization interval The expression is: ; , ; Among them, the Power adjustment threshold for individual electrical devices The expression is: ; For the first The rated power of each electrical device.

7. The energy-saving calculation method based on historical electricity consumption and equipment operation information according to claim 6, characterized in that, The step of simulating and calculating the historical electricity consumption data and the historical associated equipment operation information based on the energy-saving scheme to generate a baseline electricity consumption further includes: According to the Power adjustment threshold for individual electrical devices , for the The historical power of each electrical device is corrected to obtain the first... The corrected power of each electrical device is calculated until the corrected power of each device is obtained, and its expression is: ; Indicates the first The electrical equipment in the first Historical power at any given moment; The electricity load during periods within the target period that do not belong to the system-level electricity consumption period optimization interval is transferred to the system-level electricity consumption period optimization interval to generate an optimized electricity load sequence. Its expression is: In the formula, ; This represents the load transfer weighting coefficient, indicating the proportion of load transferred from non-optimal periods to optimal periods. Represents the first non-optimized time period Historical electricity load at any given time ; According to the optimized power load sequence Calculate the baseline power consumption. Its expression is: The step of obtaining the predicted energy saving based on the difference between the baseline energy consumption and the historical energy consumption corresponding to the historical energy consumption data further includes: Calculate the historical electricity consumption based on the historical electricity load sequence. Its expression is: The predicted energy saving is determined based on the difference between the historical energy consumption and the baseline energy consumption, and its expression is as follows: In the formula, This indicates the predicted energy saving.

8. The energy-saving calculation method based on historical electricity consumption and equipment operation information according to claim 7, characterized in that, The step of calculating the actual energy saving based on the real-time energy consumption corresponding to the real-time energy consumption data and the baseline energy consumption further includes: Based on the real-time electricity load sequence in the real-time electricity consumption data, the real-time electricity consumption is calculated, and its expression is as follows: In the formula, ; Indicates the first The first electrical device in the current cycle Power at any given moment; This indicates the real-time power consumption. This represents the total number of sampling points within the current period; The actual energy saving is determined based on the difference between the baseline energy consumption and the real-time energy consumption, and its expression is as follows: In the formula, This indicates the actual amount of electricity saved.

9. The energy-saving calculation method based on historical electricity consumption and equipment operation information according to claim 8, characterized in that, The steps of determining the deviation rate between the predicted energy saving and the actual energy saving, generating an abnormal device identifier based on the real-time associated device operation information, and forming an energy saving accounting and evaluation report containing the deviation rate and the abnormal device identifier, further include: The deviation rate is calculated based on the actual energy saving and the predicted energy saving, and its expression is as follows: In the formula, This represents the deviation rate; The abnormal equipment is identified by marking the electrical equipment with abnormal real-time power factor or abnormal real-time start / stop timestamp set in the real-time associated equipment operation information, and an abnormal equipment identifier is generated.

10. A power-saving accounting system based on historical electricity consumption and equipment operation information, characterized in that, The system includes: The acquisition module is used to acquire historical electricity consumption data and historical associated equipment operation information within a target period; wherein, the historical electricity consumption data includes: historical electricity load sequence and historical time period electricity distribution of all electrical equipment, and the historical associated equipment operation information includes: historical efficiency parameters, historical power factor and historical start and stop timestamp set of each electrical equipment; The processing module is used to perform time-series decomposition of the historical electricity load sequence and identify typical load change patterns through clustering algorithms, and determine the electricity distribution difference coefficient of the electricity distribution in the historical period; normalize the historical efficiency parameters and historical power factors of each electrical device and perform weighted summation to obtain the operating efficiency coefficient of each electrical device, and construct the start-stop influence factor matrix of the corresponding electrical device based on the historical start-stop timestamp set of each electrical device; The output module is used to input the typical load change pattern, the electricity distribution difference coefficient, the operating efficiency coefficient of each electrical device, and the start-stop influence factor matrix into the target energy-saving calculation model, and output the energy-saving scheme; wherein, the energy-saving scheme includes: system-level electricity consumption period optimization interval and power adjustment threshold for each electrical device; The calculation module is used to perform simulation calculations on the historical electricity consumption data and the historical associated equipment operation information based on the power saving scheme, generate a baseline electricity consumption, and obtain the predicted electricity saving based on the difference between the baseline electricity consumption and the historical electricity consumption corresponding to the historical electricity load sequence. The evaluation module is used to acquire real-time electricity consumption data and real-time associated equipment operation information after the implementation of the power saving scheme, calculate the actual power saving based on the real-time electricity consumption corresponding to the real-time electricity consumption and the benchmark electricity consumption, determine the deviation rate between the actual power saving and the predicted power saving, and generate abnormal equipment identifiers based on the real-time associated equipment operation information to form a power saving accounting evaluation report containing the deviation rate and the abnormal equipment identifiers.

Images