User power consumption double-track simulation and influence quantification method, device, equipment and medium

Abstract

This application provides a method, device, equipment, and medium for dual-track simulation and impact quantification of user electricity consumption. It can load and process historical electricity consumption data covering all users in one go, achieving a global and unbiased grasp of the impact of electricity parameter adjustments, providing a reliable data foundation for decision-making. Through tensor-based multidimensional electricity consumption data and a parallel computing architecture, the computation process that previously required sequential, household-by-household calculations is transformed into matrix operations that can be executed in parallel on large-scale computing clusters. This shortens the computation time for the target electricity consumption result vector and the baseline electricity consumption result vector, improving the efficiency and agility of decision-making in quantifying the impact of electricity parameter adjustments. Household-by-household differential quantification analysis can accurately quantify the impact of electricity parameter adjustments on each user. Combined with user profile attribute data, it quantifies the impact of electricity parameter adjustments on multiple dimensions of different users, and visualization provides a more intuitive display of the quantified impact range and degree.

Description

Technical Field

[0001] This application relates to the field of power system simulation technology, and in particular to a method, device, equipment and medium for dual-track simulation and influence quantification of user power consumption. Background Technology

[0002] Adjustments to electricity system parameters directly impact the economic interests of tens of millions of electricity users. Any reform of the electricity consumption mechanism, such as adjustments to time-of-use pricing, changes to tiered pricing thresholds, alterations to basic electricity fee calculation methods, or revisions to power factor assessment standards, will have differentiated and non-linear systemic impacts on users with different electricity consumption characteristics. Current methods for quantifying the impact (such as sampling statistics, business system-based testing, and general analysis tools) suffer from problems such as large sampling errors, slow calculation speeds, limited analytical dimensions, and an inability to achieve accurate pre-assessment. Summary of the Invention

[0003] In view of this, the purpose of this application is to propose a dual-track simulation and impact quantification method, device, equipment and medium for user electricity consumption, which performs parallel calculations and results comparisons using historical electricity consumption data of all users, and quickly and accurately quantifies the scope and degree of impact on each user before adjusting electricity consumption parameters.

[0004] To achieve the above objectives, this application provides a method for dual-track simulation and impact quantification of user electricity consumption, including:

[0005] Historical electricity consumption data of all users are loaded from the power business system, and the historical electricity consumption data is constructed into a standardized multi-dimensional electricity consumption data tensor; The current rule engine of the power business system is mapped to a benchmark electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor. The multidimensional electricity consumption data tensor and the benchmark electricity consumption mask tensor are multiplied element by element and then summed to obtain the benchmark electricity consumption result vector. The preset power consumption parameter configuration file is mapped to a target power consumption mask tensor with the same dimension as the multidimensional power consumption data tensor. The multidimensional power consumption data tensor and the target power consumption mask tensor are multiplied element by element and then summed to obtain the target power consumption result vector. Based on the target electricity consumption result vector and the benchmark electricity consumption result vector, a household-by-household difference quantitative analysis is performed to obtain the user-level electricity consumption change vector; Based on the baseline electricity consumption result vector, a multidimensional impact analysis is performed according to the user profile attribute data of the power business system and the user-level electricity consumption change vector to obtain multidimensional impact data. The multidimensional impact data is then statistically analyzed and visualized to obtain an impact distribution image.

[0006] Based on the same inventive concept, this application also provides a dual-track simulation and impact quantification device for user electricity consumption, comprising: The multidimensional electricity consumption tensor construction module is configured to: load historical electricity consumption data of all users from the power business system, and construct the historical electricity consumption data into a standardized multidimensional electricity consumption tensor; The benchmark electricity consumption result determination module is configured to: map the current rule engine of the power business system to a benchmark electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor, and sum the elements of the multidimensional electricity consumption data tensor and the benchmark electricity consumption mask tensor to obtain the benchmark electricity consumption result vector; The target electricity consumption result determination module is configured to: map a preset electricity consumption parameter configuration file to a target electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor; multiply the multidimensional electricity consumption data tensor and the target electricity consumption mask tensor element by element and then sum them to obtain the target electricity consumption result vector. The electricity consumption result difference analysis module is configured to: perform household-by-household difference quantification analysis based on the target electricity consumption result vector and the benchmark electricity consumption result vector to obtain the user-level electricity consumption change vector; The electricity consumption result impact analysis module is configured to: based on the baseline electricity consumption result vector, perform multidimensional impact analysis according to the user profile attribute data of the power business system and the user-level electricity consumption change vector to obtain multidimensional impact data, and perform statistical analysis and visualization processing on the multidimensional impact data to obtain an impact distribution image.

[0007] Based on the same inventive concept, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described above when executing the computer program.

[0008] Based on the same inventive concept, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing a computer to perform the method described above.

[0009] As can be seen from the above, the user electricity consumption dual-track simulation and impact quantification method, device, equipment, and medium provided in this application load historical electricity consumption data of all users from the power business system and construct the historical electricity consumption data into a standardized multi-dimensional electricity consumption data tensor; map the current rule engine of the power business system into a benchmark electricity consumption mask tensor with the same dimension as the multi-dimensional electricity consumption data tensor; multiply the multi-dimensional electricity consumption data tensor and the benchmark electricity consumption mask tensor element-wise and then sum them to obtain the benchmark electricity consumption result vector; and map the preset electricity consumption parameter configuration file into the multi-dimensional electricity consumption data tensor. Based on the target electricity consumption mask tensor with the same tensor dimension, the multidimensional electricity consumption data tensor and the target electricity consumption mask tensor are multiplied element-wise and then summed to obtain the target electricity consumption result vector. A household-by-household difference quantification analysis is then performed based on the target electricity consumption result vector and the baseline electricity consumption result vector to obtain the user-level electricity consumption change vector. Using the baseline electricity consumption result vector as a basis, multidimensional impact analysis is performed based on the user profile attribute data and user-level electricity consumption change vector from the power business system to obtain multidimensional impact data. Statistical analysis and visualization processing are then performed on this multidimensional impact data to obtain an impact distribution image. By loading and processing historical electricity consumption data covering all users at once, the analysis results are ensured to have no information loss or sampling error. It can accurately capture the impact on long-tail users with special electricity consumption behaviors, achieving a global and unbiased grasp of the impact of electricity parameter adjustments, providing a reliable data foundation for decision-making. Through the tensor-quantified multidimensional electricity consumption data tensor and parallel computing architecture, the original household-by-household, serial, iterative calculation process is transformed into matrix operations that can be executed in parallel on large-scale computing clusters. This reduces the computation time for target and baseline electricity consumption result vectors, improving the efficiency and agility of decision-making in quantifying the impact of electricity parameter adjustments. Household-by-household differential quantitative analysis can accurately quantify the impact of electricity parameter adjustments on each user. By combining user profile attribute data, it quantifies the impact of electricity parameter adjustments on multiple dimensions of different users. Visualizing this multi-dimensional impact data provides a more intuitive display of the quantified scope and extent of the impact. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart of the user power consumption dual-track simulation and impact quantification method in an embodiment of this application; Figure 2 This is a schematic diagram of the dual-track simulation calculation in an embodiment of this application; Figure 3This is a schematic diagram of the dual-track simulation and influence quantification device for user electricity consumption in an embodiment of this application; Figure 4 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0013] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0014] In this article, it is important to understand that any number of elements in the accompanying figures is for illustrative purposes and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0015] Based on the above background description, the following situations also exist in the related technologies: Evaluation methods based on sampling statistics in related technologies suffer from problems such as overgeneralization and significant errors. Sampling statistics employ a statistical inference approach that draws conclusions from limited data, which has fundamental flaws. This is because electricity users' consumption behaviors are highly heterogeneous and exhibit a long-tail distribution (i.e., a few users may have very specific consumption patterns). The sampling frame cannot cover all types of users, leading to a systematic underestimation or complete omission of the impact of special user groups. Sampling errors are unavoidable; inferring the whole from local data inevitably results in sampling errors, failing to provide accurate assessments down to each individual household and thus hindering refined decision-making.

[0016] The testing and verification model for marketing-based business systems in related technologies suffers from problems such as post-event verification and low efficiency. Using systems designed for business processing for data analysis results in poor scenario adaptability. Furthermore, it cannot perform pre-event simulation, requiring analysis of the impact of new data collected after power consumption parameters are adjusted, which constitutes post-event verification and cannot predict the impact before the adjusted power consumption parameters are applied, leading to significant time lag.

[0017] Marketing-based business systems suffer from computational performance bottlenecks. To ensure transaction consistency and high concurrency, these systems typically employ serial computation for each user. When processing the full dataset of tens of millions of users, a single settlement can take hours or even tens of hours, completely failing to meet the rapid iteration requirements for real-time comparison and immediate feedback of multiple options during the quantification process.

[0018] Simple analysis methods based on general-purpose analysis tools (such as Excel and BI) in related technologies suffer from insufficient capabilities and difficulty in expansion. The computing power and data capacity of general-purpose analysis tools cannot meet the needs of massive power data analysis. Tools such as Excel are limited by single-machine memory and single-threaded computing. When faced with multi-dimensional time-series data from millions of users, they are prone to memory overflow, lag, or unresponsiveness, and cannot complete full calculations.

[0019] General-purpose analytics tools are weak at handling complex rules. Business intelligence (BI) tools excel at querying and visualization, but their underlying relational databases are inefficient for electricity consumption calculation scenarios that require complex rule nesting and household-by-household condition judgments. They are equally ill-suited for large-scale, high-performance simulation tasks.

[0020] It can be seen that the relevant technologies have significant shortcomings in terms of data integrity, computational timeliness, analytical dimensions, and application scenarios.

[0021] The user electricity consumption dual-track simulation and impact quantification method, device, equipment, and medium provided in this application's embodiments load and process historical electricity consumption data covering all users in one go, ensuring no information loss or sampling error in the analysis results. It accurately captures the impact on long-tail users with unique electricity consumption behaviors, achieving a global and unbiased grasp of the impact of electricity parameter adjustments, providing a reliable data foundation for decision-making. By converting all users' historical electricity consumption data into a multi-dimensional electricity consumption data tensor and employing a parallel computing architecture to calculate the electricity consumption results before and after parameter adjustments, the original household-by-household, serial, iterative calculation process is transformed into matrix operations that can be executed in parallel on a large-scale computing cluster. This shortens the calculation time for the target electricity consumption result vector and the baseline electricity consumption result vector, improving the decision-making efficiency and agility of quantifying the impact of electricity parameter adjustments. Household-by-household differential quantification analysis can accurately quantify the impact of electricity parameter adjustments on each user. Combined with user profile attribute data, it quantifies the impact of electricity parameter adjustments on multiple dimensions of different users. By visualizing the multi-dimensional impact data, it more intuitively displays the scope and degree of the quantified impact.

[0022] The following describes in detail, with reference to the accompanying drawings, the user power consumption dual-track simulation and influence quantification method provided by the embodiments of this application.

[0023] In some embodiments, such as Figure 1 As shown, a dual-track simulation and impact quantification method for user electricity consumption includes steps 101-105.

[0024] Step 101: Load historical electricity consumption data of all users from the power business system and construct the historical electricity consumption data into a standardized multi-dimensional electricity consumption data tensor.

[0025] In practice, defining the multidimensional electricity consumption data tensor is crucial for providing a standardized and structured data foundation for subsequent high-speed, unbiased dual-track simulation calculations. This is achieved by abandoning sampling, processing the entire dataset, and transforming it into a tensor data structure suitable for parallel computing.

[0026] In some embodiments, historical electricity consumption data is constructed into a standardized multidimensional electricity consumption data tensor, including: Determine each user's user identification code based on historical electricity consumption data; The total number of time periods is determined based on the preset analysis cycle and the extraction duration of historical electricity consumption data, and a unique time period number is assigned to each time period based on the total number of time periods. Determine electricity consumption characteristics and electricity consumption from historical electricity consumption data based on user identification code and time period sequence number; A location index is constructed based on the user's identification code, time period number, and electricity consumption characteristics. The electricity consumption is determined as the value of the electricity consumption data element corresponding to the location index, resulting in a multidimensional electricity consumption data tensor.

[0027] In practice, the first step is to obtain historical electricity consumption data for all registered users within a specified analysis period (such as the previous calendar month) from the power business system (e.g., power marketing business system, data warehouse, or big data platform). This historical electricity consumption data mainly includes two categories: first, time-series electricity consumption data, which includes user identification (user ID code), precise timestamps, and the corresponding active power value at the metering point, typically collected every 15 minutes or hour; second, user profile attribute data, which records the static characteristics of each user, such as industry classification code, voltage level, power supply unit, and electricity consumption category (residential, general commercial and industrial, industrial, etc.).

[0028] Then, the critical data preprocessing and tensor construction processes are performed.

[0029] Data preprocessing includes: 1) Data cleaning. Identifying and processing outliers in the raw data (e.g., negative electricity consumption, significant outliers due to metering or communication failures), and using interpolation and other techniques to appropriately complete missing data. 2) Time series alignment. Mapping the electricity consumption time series of all users onto a standard time axis. For example, if the analysis period is one month, with 15-minute intervals, a series containing 2880 consecutive time periods is constructed, and each time period is assigned a unique time period number (1 to 2880), ensuring that the data of each user covers the exact same set of time periods, laying the foundation for dimensional consistency for subsequent matrix operations.

[0030] After preprocessing, the tensor construction phase begins. A three-dimensional, multi-dimensional electricity consumption data tensor K ∈ R^(U×T×F) is constructed. Where: U (User Dimension): Represents the total number of users, which may reach tens of millions or hundreds of millions.

[0031] T (Time Dimension): Represents the total number of time periods within the analysis period (e.g., 2880).

[0032] F (Electricity Consumption Characteristics): Represents the electricity consumption characteristics extracted from historical electricity consumption data and related to electricity price calculation rules. These characteristics are dynamically defined according to electricity consumption configuration parameters and typically include: total electricity consumption, peak electricity consumption, average electricity consumption, valley electricity consumption, and maximum demand electricity consumption.

[0033] The value of each element k[u, t, f] in the multidimensional electricity consumption data tensor K is determined by the following rules: The user index u is mapped to the user dimension based on the user's identification code; the time period index t is mapped to the time dimension based on the time period; and the electricity consumption feature index f is mapped to the feature dimension based on the feature type. Then, the specific electricity consumption (usually in kilowatt-hours, kWh) of the corresponding user u under time period t and feature item f is determined as the value of that position index. This value is the value of element k[u, t, f]. Therefore, k[u, t, f] represents the specific value of the f-th electricity consumption feature of the u-th user in the t-th time period. For example, assuming f=1 represents the total electricity consumption, K[100, 288, 1]=15.6 indicates that the user with user index 100 has a total electricity consumption feature value of 15.6 kWh in the time period with time period number 288. Given that f=2 represents peak electricity consumption, K[100, 288,2] = 15.6 indicates that for user index 100, the peak electricity consumption characteristic value is 15.6 kWh during the time period with time period number 288.

[0034] Simultaneously, a mapping table between user identification codes and tensor user dimension index u is established and persistently stored, enabling accurate backtracking of calculation results to specific user entities. By tensorizing historical electricity consumption data, massive and heterogeneous historical electricity consumption data can be transformed into a well-structured, dimensionally unified multidimensional data tensor, providing support for subsequent implementation of dual-track simulation based on large-scale parallel matrix operations.

[0035] Step 102: Map the current rule engine of the power business system to a baseline electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor. Multiply the multidimensional electricity consumption data tensor and the baseline electricity consumption mask tensor element by element and sum them to obtain the baseline electricity consumption result vector.

[0036] In specific implementation, such as Figure 2 As shown, the goal of the baseline electricity consumption simulation based on the current rule engine in the dual-track simulation is to simulate the electricity expenditure of all users under the currently executing electricity configuration parameters, in order to establish a baseline for comparative analysis. The core of the electricity consumption simulation based on the current rule engine is to transform the fixed current rule engine into a computable baseline electricity consumption mask tensor, and then perform element-wise multiplication and summation operations on the baseline electricity consumption mask tensor and the electricity consumption data tensor to obtain a baseline electricity consumption result vector representing the electricity expenditure.

[0037] The current rules engine's electricity consumption simulation calls the previous rules engine already built into the power business system. The current rules engine is a software module that encapsulates all currently valid electricity consumption configuration parameters (electricity pricing rules).

[0038] The key to current rule engine-based electricity consumption simulation lies in generating a baseline electricity consumption mask tensor M_old. This baseline electricity consumption mask tensor has the exact same dimensions (U×T×F) as the multidimensional electricity consumption data tensor K. The process of generating the baseline electricity consumption mask tensor essentially involves encoding electricity consumption configuration parameters (such as time-of-use pricing periods and prices, tiered pricing thresholds and unit prices, basic electricity fee calculation methods, power factor assessment standards, etc.) into each element of the tensor. For each location index (u, t, f) in the multidimensional electricity consumption data tensor K, based on the baseline rule engine, and combining the user attribute corresponding to the location index (associated through the user index u), the time period attribute (determined by the time period index t to identify peak, flat, or valley periods), and the electricity consumption feature index f (representing the type of electricity consumption feature, such as peak electricity consumption, valley electricity consumption, etc.), a corresponding first electricity consumption unit coefficient (i.e., the first unit price) is calculated. For example, if the electricity consumption feature f=2 represents peak electricity consumption, and the time period t is located in the peak time period, then the reference electricity consumption mask element m_old[u, t, f] corresponding to the location index (u, t, f) is assigned the first electricity consumption unit coefficient (also known as the first unit electricity price) of the peak time period.

[0039] After generating the baseline electricity consumption mask tensor M_old, parallel computation is performed. The computation process is described as tensor operation: F_old = Σ(K ⊙ M_old). Here, ⊙ represents element-wise multiplication, meaning that for each position index (u, t, f), the electricity consumption k[u, t, f] is multiplied by the corresponding first electricity consumption unit coefficient m_old[u, t, f] to obtain the first time-period electricity resource amount (time-period electricity expenditure) generated by user u under time period t and electricity consumption feature f. The operator "Σ" represents summation and reduction, that is, for each user u, the first time-period electricity resource amounts calculated for all time periods and all electricity consumption features are summed to obtain the first user's total electricity resource amount (total user electricity expenditure). Finally, the output is a baseline electricity consumption result vector F_old with dimension U×1, where the value of its u-th element is the first user's total electricity resource amount (total user electricity expenditure) under the current rule engine. The multiplication operation of K ⊙ M_old is executed in parallel in memory, enabling second-level simulation of electricity charges for tens of millions of users.

[0040] Step 103: Map the preset power consumption parameter configuration file to a target power consumption mask tensor with the same dimension as the multidimensional power consumption data tensor. Multiply the multidimensional power consumption data tensor and the target power consumption mask tensor element by element and sum them to obtain the target power consumption result vector.

[0041] In specific implementation, such as Figure 2 As shown, the goal of the target-side electricity consumption simulation in the dual-track simulation, based on the preset electricity consumption parameter configuration file, is to simulate the electricity expenditure of all users under the new electricity consumption configuration parameters that have not been implemented, so as to establish a dynamic input for comparative analysis.

[0042] It receives external input of electricity consumption parameter configuration files. The input format can be a structured standard configuration file or a text document written in natural language. The input is processed through a natural language parsing and rule parameterization module. If the input electricity consumption parameter configuration file is a text document, key elements are automatically extracted using natural language processing technology, such as the new time-of-use pricing period divisions, the new electricity prices for each period, the new tiered pricing levels, and the new basic electricity price, and then converted into a machine-readable structured rule description file.

[0043] For example, the input electricity consumption parameter configuration file is a text document (e.g., PDF / Word document). Natural language processing techniques (such as named entity recognition and key information extraction) are used to automatically parse the text and extract key elements. For example, it can recognize text describing "peak hours: 10:00-12:00, 14:00-19:00, electricity price is 1.2" and extract key elements such as the time period and electricity price. It can also identify the thresholds and corresponding prices for tiered electricity pricing. It can also identify basic billing methods (e.g., by capacity) and unit prices. The extracted target elements are then converted into a structured rule description file (e.g., JSON / XML). This rule description file is a machine-readable file.

[0044] Then, based on the parsed rule description file, a new rule engine is dynamically generated. The new rule engine is a computation module with the same structure as the current rule engine but entirely new parameters. Based on the new rule engine, following the exact same generation logic as generating the baseline electricity consumption mask tensor, a target electricity consumption mask tensor M_new with the same dimensions as the multidimensional electricity consumption data tensor K is generated. Each element m_new[u, t, f] in M_new is calculated based on the new rule engine.

[0045] For each location index (u, t, f) in the multidimensional electricity consumption data tensor K, according to the new rule engine, a corresponding second electricity consumption unit coefficient (i.e., the second unit electricity price) is calculated by combining the user attribute corresponding to the location index (associated through the user index u), the time period attribute (determined by the time period index t to belong to peak, flat, or valley periods), and the electricity consumption feature index f (representing the electricity consumption feature type, such as peak electricity consumption, valley electricity consumption, etc.). For example, if the electricity consumption feature f=2 represents peak electricity consumption, and the time period t is located in the peak period, then the target electricity consumption mask element m_new[u, t, f] corresponding to the location index (u, t, f) is assigned the second electricity consumption unit coefficient (also called the second unit electricity price) for the peak period.

[0046] After generating the baseline electricity consumption mask tensor M_new, parallel computation is performed. The computation process is described as tensor operation: F_new = Σ(K ⊙ M_new). Here, ⊙ represents element-wise multiplication, meaning that for each location index (u, t, f), the electricity consumption k[u, t, f] is multiplied by the corresponding second electricity consumption unit coefficient m_new[u, t, f] to obtain the second-period electricity resource amount (period electricity expenditure) generated by user u under time period t and electricity consumption feature f. For each user u, the second-period electricity resource amounts calculated for all time periods and all electricity consumption features are summed to obtain the second user's total electricity resource amount (total user electricity expenditure). Finally, the output is a baseline electricity consumption result vector F_new with dimension U×1, where the value of the u-th element is the second user's total electricity resource amount (total user electricity expenditure) under the electricity parameter configuration file. The multiplication operation of K ⊙ M_new is executed in parallel in memory, enabling second-level simulation of electricity charges for tens of millions of users.

[0047] The baseline simulation based on the current rule engine and the target simulation based on a preset electricity consumption parameter configuration file perform identical parallel dual-track calculations. The multidimensional electricity consumption data tensor K used in both simulations (baseline and target) is exactly the same, ensuring that the input data for both simulations is completely consistent. The only variable is the rule engine (reflected in the difference between M_old and M_new). The final output target electricity consumption result vector F_new has its u-th element representing the total electricity resource consumption (total electricity expenditure) of user u under the preset electricity consumption parameter configuration file. The parallel dual-track simulation using the same data and two sets of rules creates the prerequisite for subsequent accurate difference analysis.

[0048] Step 104: Perform a household-by-household difference quantification analysis based on the target electricity consumption result vector and the baseline electricity consumption result vector to obtain the user-level electricity consumption change vector.

[0049] In practice, the goal of household-by-household differential quantitative analysis is to compare macroscopic parameter configurations and accurately apply them to each micro-user, calculate the specific changes in each user's electricity consumption data, and thus complete the key transformation from simulation to impact mapping.

[0050] A refined, household-by-household difference quantification analysis was performed on the baseline electricity consumption result vector F_old and the target electricity consumption result vector F_new. The core operation of the analysis was element-by-element vector subtraction. For each user index u (from 1 to U), the electricity consumption difference element Δf[u] = f_new[u] - f_old[u] was calculated. The calculation results for all users constituted a user-level electricity consumption change vector ΔF = F_new - F_old, with the same dimension U×1. The user-level electricity consumption change vector ΔF is the sole data source for all subsequent statistical analyses. This allows the analysis granularity to be refined from the user group to each individual user, truly achieving traceability of the impact to a single user, and providing a complete data foundation for mining macro-statistical patterns from micro-data.

[0051] Step 105: Based on the baseline electricity consumption result vector, conduct multidimensional impact analysis according to the user profile attribute data and user-level electricity consumption change vector of the power business system to obtain multidimensional impact data, and perform statistical analysis and visualization processing on the multidimensional impact data to obtain the impact distribution image.

[0052] In practice, the goal of dimensional impact analysis is to conduct in-depth mining and multi-dimensional aggregation of user-level differential data, extracting massive amounts of individual change information into key dimensions such as the scale of impact, group profile, and degree of impact that decision-makers can intuitively understand, and presenting them in a visual form.

[0053] In some embodiments, multidimensional impact data includes impact scale data, user distribution data, impact magnitude data, and impact degree data; based on the baseline electricity consumption result vector, multidimensional impact analysis is performed according to the user profile attribute data and user-level electricity consumption change vector of the power business system to obtain multidimensional impact data, including: The elements are classified according to their values ​​in the user-level electricity consumption change vector to obtain element type data; The scale of influence is determined based on the total number of elements and the number of elements representing different types of electricity consumption differences within the element type data. By associating user profile attribute data with user indexes of different types of electricity consumption difference elements in the element type data, user distribution data can be obtained. The ratio of the user-level electricity consumption change vector to the baseline electricity consumption result vector is used to determine the proportional change vector, and the impact amplitude data is determined based on the preset statistical interval and the proportional change vector. Mathematical analysis is performed on the element values ​​of the user-level electricity consumption change vector to obtain data on the degree of impact.

[0054] Specifically, element type data is obtained by classifying the elements based on their values ​​in the user-level electricity consumption change vector, including: In response to an element taking a negative value, the corresponding electricity consumption difference element is classified as a reduced electricity consumption difference element. In response to an element taking a positive value, the corresponding electricity consumption difference element is classified as an incremental electricity consumption difference element. In response to an element taking a value of zero, the corresponding electricity consumption difference element is classified as a stable electricity consumption difference element. In response to the completion of the classification of all electricity consumption difference elements in the user-level electricity consumption change vector, the element type data is obtained.

[0055] In practice, the following four dimensions of quantitative analysis are performed using the user-level electricity consumption change vector ΔF, the baseline electricity consumption result vector F_old, and user profile attribute data as input: First, elements are classified based on the signs of the electricity consumption difference elements in ΔF. Each element Δf[u] in the user-level electricity consumption change vector ΔF has a clear physical meaning and numerical attribute. The absolute value of Δf[u] represents the change in electricity expenditure data caused by the adjustment of electricity consumption parameters for user u. The signs of Δf[u] also have different meanings. If Δf[u] > 0, it indicates that the user's electricity expenditure has increased, and this electricity consumption difference element is marked as an incremental electricity consumption difference element. If Δf[u] < 0, it indicates that the user's electricity expenditure has decreased, and this electricity consumption difference element is marked as a decreasing electricity consumption difference element. If Δf[u] = 0, it indicates that the user's electricity expenditure has not been affected, and this electricity consumption difference element is marked as a stable electricity consumption difference element with no impact. The number of incremental, decreasing, and stable electricity consumption difference elements is counted to obtain element type data.

[0056] Impact Scale Analysis: Based on element type data, the number of elements for incremental, decreasing, and stable electricity consumption differences is statistically analyzed, and their respective proportions are calculated. The number and proportion of elements of different types directly reflect the degree of impact of electricity parameter adjustments. Impact scale data includes the number of elements of each type and their percentage of the total number of elements. The coverage of the impact of electricity parameter adjustments is usually visually displayed using a pie chart or ring chart. User distribution data. Affected User Group Identification: User indexes marked as incremental or decreasing electricity consumption difference elements in the element type data are linked to the user profile database. Then, statistics are performed by grouping according to dimensions such as industry, region, voltage level, and electricity capacity. The resulting series of cross-statistical tables constitute the user distribution data. This user distribution data accurately answers the question of which users are affected by the electricity parameter adjustments, forming a group profile of affected users. The user distribution is typically visualized using a pie chart or ring chart.

[0057] Impact Analysis: Calculate the electricity cost change ratio vector R = ΔF / F_old. Then analyze the distribution of R, for example, by counting the number and percentage of users whose change falls within the ranges of "<-10%", "-10%~0", "0", "0~10%", ">10%", etc., to obtain the impact magnitude data. The distribution of different change magnitudes is usually visually displayed using a pie chart or ring chart.

[0058] Mathematical analysis involves calculating statistical indicators such as average change per household, total change, median change percentage, and 90th quantile change percentage to obtain impact data. This impact data answers the question of the magnitude of the impact of electricity parameter adjustments and identifies users who may face significant disruptions.

[0059] The impact data from different dimensions are integrated to form structured multidimensional impact data. This multidimensional impact data is then transformed into intuitive graphs and reports: pie charts or ring charts are generated to visually display the scale and proportion of users with increased revenue, reduced expenditure, and no impact. Histograms are generated to show the distribution of the proportion R of changes in electricity expenditure, clearly presenting the concentration and dispersion trends of the degree of impact. Key statistical indicators (such as changes in total electricity expenditure, changes per household, and maximum increase) are centrally displayed on an interactive dashboard.

[0060] The visualization interface offers multi-dimensional cross-filtering and interactive functions, allowing decision-makers to click on specific areas of the chart (such as "Manufacturing - Income-Increasing Users") to view a detailed list of affected users. It also supports exporting analysis results and detailed data as standardized reports or data files. This completes a closed loop from data to information to decision support, providing comprehensive, quantitative, and visualized evidence for the formulation, evaluation, and optimization of new electricity consumption parameters.

[0061] In summary, the dual-track simulation and impact quantification method for user electricity consumption provided in this application can load and process historical electricity consumption data covering all users at once, ensuring that the analysis results are free of information loss and sampling errors. It can accurately capture the impact on long-tail users with unique electricity consumption behaviors, achieving a global and unbiased grasp of the impact of electricity parameter adjustments, providing a reliable data foundation for decision-making. By converting the historical electricity consumption data of all users into a multi-dimensional electricity consumption data tensor and employing a parallel computing architecture to calculate the electricity consumption results before and after the adjustment of electricity parameters, the original calculation process, which required sequential iterations for each user, is transformed into matrix operations that can be executed in parallel on a large-scale computing cluster. This shortens the calculation time for the target electricity consumption result vector and the baseline electricity consumption result vector, improving the decision-making efficiency and agility of quantifying the impact of electricity parameter adjustments. The user-specific differential quantification analysis can accurately quantify the impact of electricity parameter adjustments on each user. Combined with user profile attribute data, it quantifies the impact of electricity parameter adjustments on multiple dimensions of different users. By visualizing the multi-dimensional impact data, it more intuitively displays the scope and degree of the quantified impact.

[0062] In some embodiments, mapping the current rule engine of the power business system to a baseline electricity consumption mask tensor with the same dimensions as the multidimensional electricity consumption data tensor includes: Determine the position index that is the same as the electricity consumption data element in the multidimensional electricity consumption data tensor; Determine the feature type of the electricity consumption feature in the location index; The first electricity consumption unit coefficient corresponding to the feature type is determined based on the current rule engine. The first power consumption unit coefficient is determined as the value of the reference power consumption mask element corresponding to the position index, thus obtaining the reference power consumption mask tensor.

[0063] In practice, firstly, a location index is determined that is identical to each electricity consumption data element (i.e., k[u, t, f]) in the multidimensional electricity consumption data tensor K. This location index is a triple (u, t, f), which uniquely identifies a location of user u, time period t, and electricity consumption feature f.

[0064] Then, for each location index, determine the feature type to which its electricity consumption feature f belongs. For example, electricity consumption feature f=1 corresponds to the total electricity consumption feature, electricity consumption feature f=2 corresponds to the peak electricity consumption feature, electricity consumption feature f=3 corresponds to the valley electricity consumption feature, and electricity consumption feature f=4 corresponds to the maximum demand electricity consumption feature.

[0065] Next, based on the current rule engine (EBCL_old) which encapsulates the current electricity consumption configuration parameters, the first electricity consumption unit coefficient corresponding to the feature type f of the current location index is determined. This first electricity consumption unit coefficient is a concrete manifestation of the electricity billing rules. For example, if the electricity consumption feature f is peak-hour electricity consumption, and time period t is defined as the peak period, then the first electricity consumption unit coefficient is the peak-hour electricity price. If tiered pricing is involved, the tier to which user u belongs needs to be determined based on the user's cumulative electricity consumption up to time period t, thereby determining the corresponding tiered electricity price as the first electricity consumption unit coefficient.

[0066] Finally, the calculated first electricity consumption unit coefficient is used as the value of the baseline electricity consumption mask element at the same index (u, t, f) as the multidimensional electricity consumption data tensor K, i.e., m_old[u, t, f] = first electricity consumption unit coefficient. After traversing all indexes, a baseline electricity consumption mask tensor M_old is generated that is completely consistent with the dimensions (U×T×F) of the multidimensional electricity consumption data tensor K. The baseline electricity consumption mask tensor M_old contains pricing coefficients applicable to each micro-electricity consumption scenario.

[0067] In some embodiments, the reference electricity consumption result vector is obtained by summing the element-wise multiplications of the multidimensional electricity consumption data tensor and the reference electricity consumption mask tensor, including: Based on the location index, determine the mutually matching associated reference power consumption mask element and the first associated power consumption data element in the multidimensional power consumption data tensor and the reference power consumption mask tensor; Determine the first electricity consumption unit coefficient in the associated reference electricity consumption mask element, and determine the first electricity consumption corresponding to the first electricity consumption unit coefficient in the first associated electricity consumption data element; The product of the first electricity consumption and the first electricity consumption unit coefficient is determined as the electricity resource quantity for the first time period, and the sum of the first electricity resource quantities for all time periods corresponding to the same user identification code is determined as the total electricity resource quantity for the first user. Using the user identification code in the location index as the user index, the total electricity consumption of the first user is determined as the benchmark electricity consumption result element corresponding to the user index, thus obtaining the benchmark electricity consumption result vector.

[0068] In practice, firstly, based on the same position index (u, t, f), mutually matching associated element pairs are determined in the multidimensional electricity consumption data tensor K and the reference electricity consumption mask tensor M_old. That is, for the index (u, t, f), the associated reference electricity consumption mask element is m_old[u, t, f], and the first associated electricity consumption data element is k[u, t, f].

[0069] Then, the values ​​of the associated reference power consumption mask element m_old[u, t, f] are used as the first power consumption unit coefficient, and the values ​​of the first associated power consumption data element k[u, t, f] are used as the corresponding first power consumption.

[0070] Next, the product of the first electricity consumption and the first electricity consumption unit coefficient is calculated. The physical meaning of this product is the electricity expenditure of user u in time period t due to electricity consumption characteristic f, which is expressed as the electricity resource quantity of the first time period.

[0071] Then, for the same user u, the electricity resource amount calculated for the first time period over all time periods t (t=1 to T) and all electricity consumption characteristics f (f=1 to F) is summed. This sum represents the total electricity cost that user u should pay throughout the entire analysis period under the current rule engine, and is expressed as the total electricity resource amount of the first user.

[0072] Finally, based on the user index u, the total electricity consumption of the first user is used as the value of the u-th element (i.e., the benchmark electricity consumption element) in the benchmark electricity consumption result vector F_old. By taking the values ​​of the elements corresponding to all user indices u (u=1 to U), the benchmark electricity consumption result vector F_old with dimension U×1 can be obtained. This calculation process is transformed into efficient tensor operations in the system: F_old = Σ(K ⊙ M_old), where ⊙ represents element-wise multiplication (Hadamard product), and Σ represents summation and reduction along the time dimension T and the feature dimension F. This operation can be completed at high speed in an environment that supports parallel computing.

[0073] In some embodiments, mapping a preset electricity consumption parameter configuration file to a target electricity consumption mask tensor with the same dimensions as the multidimensional electricity consumption data tensor includes: Determine the location index that is the same as the electricity consumption data element in the multidimensional electricity consumption data tensor, and determine the feature type of the electricity consumption feature in the location index; Target elements are extracted from the electricity parameter configuration file using natural language processing, and these target elements are converted into a structured rule description file. The rule description file is read according to the pre-set calculation logic template to obtain a new rule engine; The new rule engine determines the second electricity consumption unit coefficient corresponding to the feature type; The second power consumption unit coefficient is determined as the value of the target power consumption mask element corresponding to the position index, thus obtaining the target power consumption mask tensor.

[0074] In practice, firstly, the location index (u, t, f) that is the same as the electricity consumption data element in the multidimensional electricity consumption data tensor K is determined, and the feature type of the electricity consumption feature f in the location index is determined.

[0075] The system then receives a power consumption parameter configuration file, which can be a structured configuration file or a text document described in natural language. If the input is a text document, the system automatically extracts the target elements using natural language processing technology. These target elements include, but are not limited to: the new time-of-use pricing period division and prices for each period, the new tiered pricing thresholds and prices, the new basic electricity charge calculation method and unit price, and the new power factor assessment standards. The extracted target elements are then converted into a structured rule description file (such as JSON or XML format).

[0076] Then, the generated structured rule description file is read, and the pre-set calculation logic template is dynamically configured according to the file content, thereby instantiating a new rule engine (EBCL_new).

[0077] Then, based on the new rule engine, and combined with the feature type f corresponding to the location index (u, t, f), as well as user attributes, time period attributes, and other conditions, the corresponding second electricity consumption unit coefficient is determined. This process is the same as the baseline calculation process, but the new rule engine is used.

[0078] Finally, the determined second electricity consumption unit coefficient is used as the element value of the target electricity consumption mask tensor M_new at the same index (u, t, f) as the multi-electricity consumption data tensor K, i.e., m_new[u, t, f] = second electricity consumption unit coefficient. This generates a target electricity consumption mask tensor M_new that has the same dimensions (U×T×F) as the electricity consumption data tensor T.

[0079] In some embodiments, the target electricity consumption result vector is obtained by summing the element-wise multiplications of the multidimensional electricity consumption data tensor and the target electricity consumption mask tensor, including: Based on the location index, determine the mutually matching associated target power consumption mask elements and the second associated power consumption data elements in the multidimensional power consumption data tensor and the target power consumption mask tensor; Determine the second electricity consumption unit coefficient in the associated target electricity consumption mask element, and determine the second electricity consumption corresponding to the second electricity consumption unit coefficient in the second associated electricity consumption data element; The product of the second electricity consumption and the second electricity consumption unit coefficient is determined as the electricity resource quantity for the second time period, and the sum of the second electricity resource quantities for all time periods corresponding to the same user identification code is determined as the total electricity resource quantity for the second user. Using the user identification code in the location index as the user index, the total electricity consumption of the second user is determined as the target electricity consumption result element corresponding to the user index, thus obtaining the target electricity consumption result vector.

[0080] In practice, the calculation logic of the target power consumption result vector is completely symmetrical with that of the baseline power consumption result vector, but the target power consumption mask tensor M_new is used.

[0081] First, based on the same position index (u, t, f), mutually matching associated element pairs are determined in the multidimensional electricity consumption data tensor K and the target electricity consumption mask tensor M_new. That is, the associated target electricity consumption mask element is m_new[u, t, f], and the second associated electricity consumption data element is k[u, t, f].

[0082] Then, the park value of the associated target electricity mask element m_new[u, t, f] is determined as the second electricity unit coefficient, and the element value of the second associated electricity data element k[u, t, f] is determined as the corresponding second electricity consumption.

[0083] Then, the product of the second electricity consumption and the second electricity consumption unit coefficient is calculated to obtain the itemized electricity fee amount generated by user u in time period t due to electricity consumption characteristic f under the target policy, which is the electricity resource amount in the second time period.

[0084] Then, for the same user u, the electricity resource amount calculated for the second time period based on all time periods t and all electricity consumption characteristics f is summed to obtain the total electricity cost that user u should pay throughout the entire analysis period under the new rule engine, which is represented as the total electricity resource amount of the second user.

[0085] Finally, based on the user index u, the total electricity consumption of the second user is used as the value of the u-th element (i.e., the target electricity consumption element) in the target electricity consumption result vector F_new. Calculating the values ​​of all elements yields the target electricity consumption result vector F_new with dimension U×1. The expression for the target electricity consumption result vector F_new is: F_new = Σ(K⊙M_new). The two simulations use the exact same multidimensional electricity consumption data tensor K, ensuring the comparability of the results.

[0086] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0087] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] Based on the same inventive concept, and corresponding to any of the above embodiments, this application also provides a dual-track simulation and influence quantification device for user electricity consumption.

[0089] refer to Figure 3 The user electricity consumption dual-track simulation and impact quantification device includes: The multidimensional electricity consumption tensor construction module 10 is configured to: load historical electricity consumption data of all users from the power business system and construct the historical electricity consumption data into a standardized multidimensional electricity consumption tensor; The benchmark electricity consumption result determination module 20 is configured to: map the current rule engine of the power business system to a benchmark electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor, and sum the multidimensional electricity consumption data tensor and the benchmark electricity consumption mask tensor element by element to obtain the benchmark electricity consumption result vector. The target electricity consumption result determination module 30 is configured to: map the preset electricity consumption parameter configuration file to a target electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor, and sum the multidimensional electricity consumption data tensor and the target electricity consumption mask tensor element by element to obtain the target electricity consumption result vector; The electricity consumption result difference analysis module 40 is configured to: perform household-by-household difference quantitative analysis based on the target electricity consumption result vector and the benchmark electricity consumption result vector to obtain the user-level electricity consumption change vector; The electricity consumption result impact analysis module 50 is configured to: based on the baseline electricity consumption result vector, perform multi-dimensional impact analysis according to the user profile attribute data and user-level electricity consumption change vector of the power business system, obtain multi-dimensional impact data, and perform statistical analysis and visualization processing on the multi-dimensional impact data to obtain an impact distribution image.

[0090] In some embodiments, the multidimensional power consumption tensor construction module 10 is further configured to: Determine each user's user identification code based on historical electricity consumption data; The total number of time periods is determined based on the preset analysis cycle and the extraction duration of historical electricity consumption data, and a unique time period number is assigned to each time period based on the total number of time periods. Determine electricity consumption characteristics and electricity consumption from historical electricity consumption data based on user identification code and time period sequence number; A location index is constructed based on the user's identification code, time period number, and electricity consumption characteristics. The electricity consumption is determined as the value of the electricity consumption data element corresponding to the location index, resulting in a multidimensional electricity consumption data tensor.

[0091] In some embodiments, the baseline power consumption determination module 20 is further configured to: Determine the position index that is the same as the electricity consumption data element in the multidimensional electricity consumption data tensor; Determine the feature type of the electricity consumption feature in the location index; The first electricity consumption unit coefficient corresponding to the feature type is determined based on the current rule engine. The first power consumption unit coefficient is determined as the value of the reference power consumption mask element corresponding to the position index, thus obtaining the reference power consumption mask tensor.

[0092] In some embodiments, the baseline power consumption determination module 20 is further configured to: Based on the location index, determine the mutually matching associated reference power consumption mask element and the first associated power consumption data element in the multidimensional power consumption data tensor and the reference power consumption mask tensor; Determine the first electricity consumption unit coefficient in the associated reference electricity consumption mask element, and determine the first electricity consumption corresponding to the first electricity consumption unit coefficient in the first associated electricity consumption data element; The product of the first electricity consumption and the first electricity consumption unit coefficient is determined as the electricity resource quantity for the first time period, and the sum of the first electricity resource quantities for all time periods corresponding to the same user identification code is determined as the total electricity resource quantity for the first user. Using the user identification code in the location index as the user index, the total electricity consumption of the first user is determined as the benchmark electricity consumption result element corresponding to the user index, thus obtaining the benchmark electricity consumption result vector.

[0093] In some embodiments, the target electricity consumption result determination module 30 is further configured to: Determine the location index that is the same as the electricity consumption data element in the multidimensional electricity consumption data tensor, and determine the feature type of the electricity consumption feature in the location index; Target elements are extracted from the electricity parameter configuration file using natural language processing, and these target elements are converted into a structured rule description file. The rule description file is read according to the pre-set calculation logic template to obtain a new rule engine; The new rule engine determines the second electricity consumption unit coefficient corresponding to the feature type; The second power consumption unit coefficient is determined as the value of the target power consumption mask element corresponding to the position index, thus obtaining the target power consumption mask tensor.

[0094] In some embodiments, the target electricity consumption result determination module 30 is further configured to: Based on the location index, determine the mutually matching associated target power consumption mask elements and the second associated power consumption data elements in the multidimensional power consumption data tensor and the target power consumption mask tensor; Determine the second electricity consumption unit coefficient in the associated target electricity consumption mask element, and determine the second electricity consumption corresponding to the second electricity consumption unit coefficient in the second associated electricity consumption data element; The product of the second electricity consumption and the second electricity consumption unit coefficient is determined as the electricity resource quantity for the second time period, and the sum of the second electricity resource quantities for all time periods corresponding to the same user identification code is determined as the total electricity resource quantity for the second user. Using the user identification code in the location index as the user index, the total electricity consumption of the second user is determined as the target electricity consumption result element corresponding to the user index, thus obtaining the target electricity consumption result vector.

[0095] In some embodiments, the multidimensional impact data includes impact scale data, user distribution data, impact magnitude data, and impact degree data; the electricity consumption outcome impact analysis module 50 is further configured to: The elements are classified according to their values ​​in the user-level electricity consumption change vector to obtain element type data; The scale of influence is determined based on the total number of elements and the number of elements representing different types of electricity consumption differences within the element type data. By associating user profile attribute data with user indexes of different types of electricity consumption difference elements in the element type data, user distribution data can be obtained. The ratio of the user-level electricity consumption change vector to the baseline electricity consumption result vector is used to determine the proportional change vector, and the impact amplitude data is determined based on the preset statistical interval and the proportional change vector. Mathematical analysis is performed on the element values ​​of the user-level electricity consumption change vector to obtain data on the degree of impact.

[0096] In some embodiments, the electricity consumption result impact analysis module 50 is further configured to: In response to an element taking a negative value, the corresponding electricity consumption difference element is classified as a reduced electricity consumption difference element. In response to an element taking a positive value, the corresponding electricity consumption difference element is classified as an incremental electricity consumption difference element. In response to an element taking a value of zero, the corresponding electricity consumption difference element is classified as a stable electricity consumption difference element. In response to the completion of the classification of all electricity consumption difference elements in the user-level electricity consumption change vector, the element type data is obtained.

[0097] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.

[0098] The apparatus in the above embodiments is used to implement the corresponding user electricity dual-track simulation and influence quantification method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0099] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the user power consumption dual-track simulation and influence quantification method described in any of the above embodiments.

[0100] Figure 4 This embodiment illustrates a more specific hardware structure of an electronic device. The device may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0101] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0102] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0103] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0104] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0105] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0106] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0107] The electronic devices described above are used to implement the corresponding user power consumption dual-track simulation and impact quantification methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0108] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to execute the user power consumption dual-track simulation and impact quantification method as described in any of the above embodiments.

[0109] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0110] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the user electricity dual-track simulation and influence quantification method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0111] It is understood that before using the technical solutions of the various embodiments in this application, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0112] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations described in this application.

[0113] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0114] It is understood that the above notification and user authorization process is merely illustrative and does not limit the implementation of this application. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this application.

[0115] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application is limited to these examples; under the concept of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in detail for the sake of brevity.

[0116] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0117] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0118] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the claims of this application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A dual-track simulation and impact quantification method for user electricity consumption, characterized in that, include: Historical electricity consumption data of all users are loaded from the power business system, and the historical electricity consumption data is constructed into a standardized multi-dimensional electricity consumption data tensor; The current rule engine of the power business system is mapped to a benchmark electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor. The multidimensional electricity consumption data tensor and the benchmark electricity consumption mask tensor are multiplied element by element and then summed to obtain the benchmark electricity consumption result vector. The preset power consumption parameter configuration file is mapped to a target power consumption mask tensor with the same dimension as the multidimensional power consumption data tensor. The multidimensional power consumption data tensor and the target power consumption mask tensor are multiplied element by element and then summed to obtain the target power consumption result vector. Based on the target electricity consumption result vector and the benchmark electricity consumption result vector, a household-by-household difference quantitative analysis is performed to obtain the user-level electricity consumption change vector; Based on the baseline electricity consumption result vector, a multidimensional impact analysis is performed according to the user profile attribute data of the power business system and the user-level electricity consumption change vector to obtain multidimensional impact data. The multidimensional impact data is then statistically analyzed and visualized to obtain an impact distribution image.

2. The user electricity consumption dual-track simulation and impact quantification method according to claim 1, characterized in that, The step of constructing the historical electricity consumption data into a standardized multidimensional electricity consumption data tensor includes: Determine each user's user identification code based on the historical electricity consumption data; The total number of time periods is determined based on the preset analysis period and the extraction duration of the historical electricity consumption data, and a unique time period number is assigned to each time period based on the total number of time periods. Based on the user identification code and the time period number, the electricity consumption characteristics and electricity consumption are determined from the historical electricity consumption data; A location index is constructed based on the user identification code, the time period number, and the electricity consumption characteristics. The electricity consumption is determined as the value of the electricity consumption data element corresponding to the location index, thereby obtaining the multidimensional electricity consumption data tensor.

3. The user electricity consumption dual-track simulation and impact quantification method according to claim 1, characterized in that, The step of mapping the current rule engine of the power business system to a baseline electricity consumption mask tensor with the same dimensions as the multi-dimensional electricity consumption data tensor includes: Determine the position index that is the same as the electricity consumption data element in the multidimensional electricity consumption data tensor; Determine the feature type of the electricity consumption feature in the location index; The first electricity consumption unit coefficient corresponding to the feature type is determined based on the current rule engine. The first power consumption unit coefficient is determined as the value of the reference power consumption mask element corresponding to the location index, and the reference power consumption mask tensor is obtained.

4. The user electricity consumption dual-track simulation and impact quantification method according to claim 1, characterized in that, The step of summing the element-wise multiplications of the multidimensional electricity consumption data tensor and the baseline electricity consumption mask tensor to obtain the baseline electricity consumption result vector includes: Based on the location index, a mutually matching associated reference power consumption mask element and a first associated power consumption data element are determined in the multidimensional power consumption data tensor and the reference power consumption mask tensor; A first power consumption unit coefficient is determined in the associated reference power consumption mask element, and a first power consumption corresponding to the first power consumption unit coefficient is determined in the first associated power consumption data element; The product of the first electricity consumption and the first electricity consumption unit coefficient is determined as the electricity resource quantity for the first time period, and the sum of the first electricity resource quantities for all time periods corresponding to the same user identification code is determined as the total electricity resource quantity for the first user. Using the user identification code in the location index as the user index, the total electricity consumption of the first user is determined as the benchmark electricity consumption result element corresponding to the user index, thus obtaining the benchmark electricity consumption result vector.

5. The user electricity consumption dual-track simulation and impact quantification method according to claim 1, characterized in that, The step of mapping the preset electricity consumption parameter configuration file to a target electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor includes: Determine the location index that is the same as the electricity consumption data element of the multidimensional electricity consumption data tensor, and determine the feature type of the electricity consumption feature in the location index; The target elements in the power consumption parameter configuration file are extracted using natural language processing, and the target elements are converted into a structured rule description file. The rule description file is read according to the pre-set calculation logic template to obtain a new rule engine; The new rule engine determines the second electricity consumption unit coefficient corresponding to the feature type. The second power consumption unit coefficient is determined as the value of the target power consumption mask element corresponding to the location index, thus obtaining the target power consumption mask tensor.

6. The user electricity consumption dual-track simulation and impact quantification method according to claim 1, characterized in that, The step of summing the element-wise multiplications of the multidimensional electricity consumption data tensor and the target electricity consumption mask tensor to obtain the target electricity consumption result vector includes: Based on the location index, mutually matching associated target power consumption mask elements and second associated power consumption data elements are determined in the multidimensional power consumption data tensor and the target power consumption mask tensor; A second electricity consumption unit coefficient is determined in the associated target electricity consumption mask element, and a second electricity consumption corresponding to the second electricity consumption unit coefficient is determined in the second associated electricity consumption data element; The product of the second electricity consumption and the second electricity consumption unit coefficient is determined as the electricity resource quantity for the second time period, and the sum of the second electricity resource quantities for all time periods corresponding to the same user identification code is determined as the total electricity resource quantity for the second user. Using the user identification code in the location index as the user index, the total electricity consumption of the second user is determined as the target electricity consumption result element corresponding to the user index, thus obtaining the target electricity consumption result vector.

7. The user electricity consumption dual-track simulation and impact quantification method according to claim 1, characterized in that, The multidimensional impact data includes impact scale data, user distribution data, impact magnitude data, and impact degree data; based on the benchmark electricity consumption result vector, multidimensional impact analysis is performed according to the user profile attribute data of the power business system and the user-level electricity consumption change vector to obtain multidimensional impact data, including: Based on the element values ​​of the electricity consumption difference elements in the user-level electricity consumption change vector, the elements are classified to obtain element type data; The impact scale data is determined based on the total number of elements and the number of elements of different types of electricity consumption difference elements in the element type data; The user distribution data is obtained by associating the user profile attribute data with the user index of different types of electricity consumption difference elements in the element type data; The ratio of the user-level electricity consumption change vector to the baseline electricity consumption result vector is used to determine the proportional change vector, and the influence amplitude data is determined based on the preset statistical interval and the proportional change vector. Mathematical analysis is performed on the element values ​​of the user-level electricity consumption change vector to obtain the impact level data.

8. The user electricity consumption dual-track simulation and impact quantification method according to claim 7, characterized in that, The element classification based on the element values ​​of the electricity consumption difference elements in the user-level electricity consumption change vector yields element type data, including: In response to the element taking a negative value, the corresponding electricity consumption difference element is classified as a reduced electricity consumption difference element. In response to the element taking a positive value, the corresponding electricity consumption difference element is classified as an incremental electricity consumption difference element. In response to the element taking a value of zero, the corresponding electricity consumption difference element is classified as a stable electricity consumption difference element. In response to the completion of the classification of all electricity consumption difference elements in the user-level electricity consumption change vector, the element type data is obtained.

9. A dual-track simulation and influence quantification device for user electricity consumption, characterized in that, include: The multidimensional electricity consumption tensor construction module is configured to: load historical electricity consumption data of all users from the power business system, and construct the historical electricity consumption data into a standardized multidimensional electricity consumption tensor; The benchmark electricity consumption result determination module is configured to: map the current rule engine of the power business system to a benchmark electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor, and sum the elements of the multidimensional electricity consumption data tensor and the benchmark electricity consumption mask tensor to obtain the benchmark electricity consumption result vector; The target electricity consumption result determination module is configured to: map a preset electricity consumption parameter configuration file to a target electricity consumption mask tensor with the same dimension as the multidimensional electricity consumption data tensor; multiply the multidimensional electricity consumption data tensor and the target electricity consumption mask tensor element by element and then sum them to obtain the target electricity consumption result vector. The electricity consumption result difference analysis module is configured to: perform household-by-household difference quantification analysis based on the target electricity consumption result vector and the benchmark electricity consumption result vector to obtain the user-level electricity consumption change vector; The electricity consumption result impact analysis module is configured to: based on the baseline electricity consumption result vector, perform multidimensional impact analysis according to the user profile attribute data of the power business system and the user-level electricity consumption change vector to obtain multidimensional impact data, and perform statistical analysis and visualization processing on the multidimensional impact data to obtain an impact distribution image.

10. The dual-track simulation and influence quantification device for user electricity consumption according to claim 9, characterized in that, The multidimensional power consumption tensor construction module is also configured as follows: Determine each user's user identification code based on the historical electricity consumption data; The total number of time periods is determined based on the preset analysis period and the extraction duration of the historical electricity consumption data, and a unique time period number is assigned to each time period based on the total number of time periods. Based on the user identification code and the time period number, the electricity consumption characteristics and electricity consumption are determined from the historical electricity consumption data; A location index is constructed based on the user identification code, the time period number, and the electricity consumption characteristics. The electricity consumption is determined as the value of the electricity consumption data element corresponding to the location index, thereby obtaining the multidimensional electricity consumption data tensor.

11. The dual-track simulation and influence quantification device for user electricity consumption according to claim 9, characterized in that, The benchmark electricity consumption result determination module is further configured to: Determine the position index that is the same as the electricity consumption data element in the multidimensional electricity consumption data tensor; Determine the feature type of the electricity consumption feature in the location index; The first electricity consumption unit coefficient corresponding to the feature type is determined based on the current rule engine. The first power consumption unit coefficient is determined as the value of the reference power consumption mask element corresponding to the location index, and the reference power consumption mask tensor is obtained.

12. The dual-track simulation and influence quantification device for user electricity consumption according to claim 9, characterized in that, The benchmark electricity consumption result determination module is further configured to: Based on the location index, a mutually matching associated reference power consumption mask element and a first associated power consumption data element are determined in the multidimensional power consumption data tensor and the reference power consumption mask tensor; A first power consumption unit coefficient is determined in the associated reference power consumption mask element, and a first power consumption corresponding to the first power consumption unit coefficient is determined in the first associated power consumption data element; The product of the first electricity consumption and the first electricity consumption unit coefficient is determined as the electricity resource quantity for the first time period, and the sum of the first electricity resource quantities for all time periods corresponding to the same user identification code is determined as the total electricity resource quantity for the first user. Using the user identification code in the location index as the user index, the total electricity consumption of the first user is determined as the benchmark electricity consumption result element corresponding to the user index, thus obtaining the benchmark electricity consumption result vector.

13. The dual-track simulation and influence quantification device for user electricity consumption according to claim 9, characterized in that, The target electricity consumption result determination module is further configured to: Determine the location index that is the same as the electricity consumption data element of the multidimensional electricity consumption data tensor, and determine the feature type of the electricity consumption feature in the location index; The target elements in the power consumption parameter configuration file are extracted using natural language processing, and the target elements are converted into a structured rule description file. The rule description file is read according to the pre-set calculation logic template to obtain a new rule engine; The new rule engine determines the second electricity consumption unit coefficient corresponding to the feature type. The second power consumption unit coefficient is determined as the value of the target power consumption mask element corresponding to the location index, thus obtaining the target power consumption mask tensor.

14. The dual-track simulation and influence quantification device for user electricity consumption according to claim 9, characterized in that, The target electricity consumption result determination module is further configured to: Based on the location index, mutually matching associated target power consumption mask elements and second associated power consumption data elements are determined in the multidimensional power consumption data tensor and the target power consumption mask tensor; A second electricity consumption unit coefficient is determined in the associated target electricity consumption mask element, and a second electricity consumption corresponding to the second electricity consumption unit coefficient is determined in the second associated electricity consumption data element; The product of the second electricity consumption and the second electricity consumption unit coefficient is determined as the electricity resource quantity for the second time period, and the sum of the second electricity resource quantities for all time periods corresponding to the same user identification code is determined as the total electricity resource quantity for the second user. Using the user identification code in the location index as the user index, the total electricity consumption of the second user is determined as the target electricity consumption result element corresponding to the user index, thus obtaining the target electricity consumption result vector.

15. The dual-track simulation and influence quantification device for user electricity consumption according to claim 9, characterized in that, The multidimensional impact data includes impact scale data, user distribution data, impact magnitude data, and impact degree data; the electricity consumption result impact analysis module is also configured to: Based on the element values ​​of the electricity consumption difference elements in the user-level electricity consumption change vector, the elements are classified to obtain element type data; The impact scale data is determined based on the total number of elements and the number of elements of different types of electricity consumption difference elements in the element type data; The user distribution data is obtained by associating the user profile attribute data with the user index of different types of electricity consumption difference elements in the element type data; The ratio of the user-level electricity consumption change vector to the baseline electricity consumption result vector is used to determine the proportional change vector, and the influence amplitude data is determined based on the preset statistical interval and the proportional change vector. Mathematical analysis is performed on the element values ​​of the user-level electricity consumption change vector to obtain the impact level data.

16. The dual-track simulation and influence quantification device for user electricity consumption according to claim 15, characterized in that, The electricity consumption result impact analysis module is also configured to: In response to the element taking a negative value, the corresponding electricity consumption difference element is classified as a reduced electricity consumption difference element. In response to the element taking a positive value, the corresponding electricity consumption difference element is classified as an incremental electricity consumption difference element. In response to the element taking a value of zero, the corresponding electricity consumption difference element is classified as a stable electricity consumption difference element. In response to the completion of the classification of all electricity consumption difference elements in the user-level electricity consumption change vector, the element type data is obtained.

17. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 8.

Images