Energy efficiency optimization management method and system for power terminal users

Abstract

The invention discloses an energy efficiency optimization management method and system for power terminal users, and relates to the technical field of energy management. The method comprises the following steps: acquiring a power utilization data set; synchronizing to a time sequence prediction channel to carry out power consumption prediction on a power terminal user, and determining a plurality of power demand prediction data; determining a plurality of power utilization behavior modes; performing power utilization analysis, and formulating a first power utilization management strategy; simulating execution of the first power consumption management strategy to perform multi-target feedback, generating a feedback response data set, dynamically adjusting the first power consumption management strategy, determining a power consumption optimization management strategy, and performing self-adaptive optimization management of power consumption energy efficiency on a power terminal user. The technical problem that in the prior art, power terminal user energy efficiency management lacks real-time adjustment capacity is solved, self-adaptive optimization management is achieved by constructing a power utilization collection network, a time sequence prediction channel and a dynamic adjustment strategy, and the technical effect of improving the power utilization efficiency of power terminal users is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and in particular to an energy efficiency optimization management method and system for power terminal users. Background Art

[0002] With the continuous growth of global energy demand and the increasing awareness of environmental protection, energy management has become the focus of attention from all walks of life. Especially in the field of electricity, how to use electricity resources efficiently and sustainably has become an important direction for the development of the power industry and related technologies. Traditional power management often focuses on the dispatching and operation of the power grid, while the energy efficiency management of power end users is relatively neglected. However, as the main group of electricity consumers, the power consumption behavior and energy efficiency level of power end users directly affect the operating efficiency and energy utilization efficiency of the entire power system. In addition, traditional energy management is mostly based on fixed rules and models, lacks flexibility and real-time performance, and is difficult to effectively respond to complex and changing power consumption behaviors and demands. Summary of the invention

[0003] The present application provides an energy efficiency optimization management method and system for power terminal users, which solves the technical problem that the energy efficiency management of power terminal users in the prior art lacks real-time adjustment capability.

[0004] In view of the above problems, the present application provides an energy efficiency optimization management method and system for power terminal users.

[0005] In a first aspect of the present application, there is provided an energy efficiency optimization management method for power terminal users, the method comprising: A power consumption collection network is constructed based on multiple sensor devices, and real-time sensing of power terminal users is performed through the power consumption collection network to obtain power terminal users' power consumption data sets; a time series prediction channel is constructed, and the power consumption data sets are synchronized to the time series prediction channel to perform power consumption predictions on power terminal users and determine multiple power demand prediction data; power consumption is identified based on the multiple power demand prediction data to determine multiple power consumption behavior patterns; power consumption is analyzed according to the multiple power consumption behavior patterns to formulate a first power consumption management strategy; the first power consumption management strategy is simulated for multi-objective feedback to generate a feedback response data set, and the first power consumption management strategy is dynamically adjusted according to the feedback response data set to determine a power consumption optimization management strategy to perform adaptive optimization management of power consumption energy efficiency for power terminal users.

[0006] The second aspect of the present application provides an energy efficiency optimization management system for power terminal users, the system comprising: A data acquisition module, the data acquisition module is used to build an electricity consumption acquisition network based on multiple sensor devices, and to perform real-time sensing of power terminal users through the power consumption acquisition network to obtain power terminal users' electricity consumption data sets; a prediction module, the prediction module is used to build a time series prediction channel, synchronize the power consumption data sets to the time series prediction channel to predict power consumption for power terminal users, and determine multiple power demand prediction data; an identification module, the identification module is used to identify power consumption based on the multiple power demand prediction data, and determine multiple power consumption behavior patterns; an analysis module, the analysis module is used to perform power consumption analysis according to the multiple power consumption behavior patterns, and formulate a first power consumption management strategy; a management module, the management module is used to simulate the execution of the first power consumption management strategy for multi-objective feedback, generate a feedback response data set, dynamically adjust the first power consumption management strategy according to the feedback response data set, determine the power consumption optimization management strategy, and perform adaptive optimization management of power consumption energy efficiency for power terminal users.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, a power consumption collection network is constructed based on multiple sensing devices, and real-time sensing of power terminal users is performed through the power consumption collection network to obtain power consumption data sets of power terminal users. Next, a time series prediction channel is constructed, and the power consumption data set is synchronized to the time series prediction channel to predict power consumption for power terminal users, and multiple power demand prediction data are determined. Further, power consumption is identified based on multiple power demand prediction data, and multiple power consumption behavior patterns are determined. Then, power consumption analysis is performed according to multiple power consumption behavior patterns, and a first power consumption management strategy is formulated. Finally, the first power consumption management strategy is simulated and executed for multi-objective feedback, a feedback response data set is generated, and the first power consumption management strategy is dynamically adjusted according to the feedback response data set, and the power consumption optimization management strategy is determined, and the power consumption energy efficiency of power terminal users is adaptively optimized. The technical problem that the energy efficiency management of power terminal users lacks real-time adjustment capability in the prior art is solved. By constructing a power consumption collection network, a time series prediction channel and a dynamic adjustment strategy, adaptive optimization management is realized, and the technical effect of improving the power consumption efficiency of power terminal users is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1A schematic flow chart of an energy efficiency optimization management method for power terminal users provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the structure of an energy efficiency optimization management system for power terminal users provided in an embodiment of the present application.

[0011] Explanation of the accompanying drawings: data collection module 11, prediction module 12, identification module 13, analysis module 14, management module 15. DETAILED DESCRIPTION

[0012] The present application solves the technical problem in the prior art that energy efficiency management of power terminal users lacks real-time adjustment capability by providing an energy efficiency optimization management method and system for power terminal users.

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0014] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0015] Embodiment 1, as Figure 1 As shown, the present application provides an energy efficiency optimization management method for power terminal users, wherein the method includes: A power consumption collection network is constructed based on multiple sensor devices, and power terminal users are sensed in real time through the power consumption collection network to obtain power consumption data sets of the power terminal users.

[0016] According to the power consumption characteristics and monitoring needs of power terminal users, select appropriate sensor equipment, such as smart meters, current sensors, voltage sensors, power factor sensors, etc.; in the power consumption system of power terminal users, deploy sensor equipment at key locations, such as distribution boxes, input terminals of major electrical equipment, etc.; connect these sensor devices through wired or wireless methods (such as Wi-Fi, LoRa, NB-IoT, etc.) to form a power consumption collection network with wide coverage and stable data transmission. Use the power consumption collection network to collect power consumption data of power terminal users in real time, including current, voltage, power factor, power consumption, etc., to obtain the power consumption data set of power terminal users.

[0017] A time series prediction channel is constructed, and the power consumption data set is synchronized to the time series prediction channel to perform power consumption prediction for power terminal users, and determine multiple power demand prediction data.

[0018] Useful features are extracted from electricity consumption data, such as the periodicity, trend, and seasonality of the time series. According to the characteristics of electricity consumption data and forecast demand, the time series forecasting model such as LSTM (Long Short-Term Memory Network) is trained using historical electricity consumption data. After the training is completed, a time series forecasting channel is obtained. The electricity consumption data set is input into the time series forecasting channel. The time series forecasting channel calculates future electricity demand forecast data based on the input data and outputs multiple electricity demand forecast data.

[0019] Furthermore, the power consumption data set is synchronized to the time series prediction channel to perform power consumption prediction on power terminal users, and a plurality of power demand prediction data are determined, the method comprising: The electricity consumption data set is time-aligned according to the data collection frequency to obtain multiple electricity consumption alignment data; fluctuation analysis is performed based on the multiple electricity consumption alignment data to draw an electricity consumption trend chart; the electricity consumption trend chart is traversed and difference comparison is performed in combination with the multiple electricity consumption alignment data to obtain multiple electricity consumption fluctuation data and multiple electricity consumption stability data; short-term prediction is performed on the multiple electricity consumption alignment data according to the multiple electricity consumption fluctuation data to generate a short-term electricity demand prediction data set; long-term prediction is performed on the multiple electricity consumption alignment data according to the multiple electricity consumption stability data to generate a long-term electricity demand prediction data set; the short-term electricity demand prediction data set is integrated with the long-term electricity demand prediction data set to determine the multiple electricity demand prediction data.

[0020] Specifically, the electricity consumption data set is time-aligned according to the data collection frequency (such as every hour, every minute, etc.) to ensure that all data points are on the same time axis, thereby obtaining multiple electricity consumption aligned data; based on multiple electricity consumption aligned data, an electricity consumption trend chart is drawn, and the electricity consumption trend chart intuitively reflects the electricity consumption habits and changing trends of electricity consumption of power terminal users; the electricity consumption trend chart is traversed, and a difference comparison is performed in combination with multiple electricity consumption aligned data. By comparing the differences in electricity consumption at adjacent time points, electricity consumption fluctuation data and electricity consumption stability data are identified. Electricity consumption fluctuation data represent data points where electricity consumption changes significantly in a short period of time, and electricity consumption stability data represent data points where electricity consumption remains relatively stable for a long period of time; based on multiple electricity consumption fluctuation data, a time series suitable for short-term fluctuation prediction is used. Models (such as the short-term version of the ARIMA model, LSTM, etc.) are used to make short-term predictions on multiple aligned electricity consumption data to generate a short-term electricity demand forecast data set. The short-term electricity demand forecast data set reflects the changes in electricity demand in the short future period (such as the next few hours or a day); based on multiple stable electricity consumption data, time series models suitable for long-term trend forecasting (such as linear regression, the long-term version of the SARIMA model, etc.) are used to make long-term predictions on multiple aligned electricity consumption data to generate a long-term electricity demand forecast data set. The long-term electricity demand forecast data set reflects the electricity demand trend in the longer future period (such as the next week or a month); the short-term electricity demand forecast data set is integrated with the long-term electricity demand forecast data set to obtain multiple electricity demand forecast data.

[0021] Power consumption is identified based on the multiple power demand forecast data to determine multiple power consumption behavior patterns.

[0022] Key features are extracted from the power demand forecast data, such as peak power consumption, valley power consumption, and power consumption volatility. Clustering algorithms (such as K-means and DBSCAN) are used to cluster the features to form multiple power consumption behavior patterns.

[0023] Furthermore, the method of identifying power consumption based on the plurality of power demand forecast data and determining a plurality of power consumption behavior patterns includes: Based on the short-term electricity demand forecast data set, cluster analysis is performed on the multiple electricity demand forecast data to determine multiple short-term electricity forecast clustering clusters; based on the long-term electricity demand forecast data set, cluster analysis is performed on the multiple electricity demand forecast data to determine multiple long-term electricity forecast clustering clusters; feature analysis is performed on the multiple electricity demand forecast data according to the multiple short-term electricity forecast clustering clusters to determine multiple short-term electricity features; feature analysis is performed on the multiple electricity demand forecast data according to the multiple long-term electricity forecast clustering clusters to determine multiple long-term electricity features; based on the multiple short-term electricity features, the multiple short-term electricity forecast clustering clusters are traversed to identify electricity consumption and generate electricity fluctuation labels; based on the multiple long-term electricity features, the multiple long-term electricity forecast clustering clusters are traversed to identify electricity consumption and generate electricity stability labels; using the electricity fluctuation labels and the electricity stability labels as indexes, the multiple electricity demand forecast data are traversed to perform electricity consumption pattern analysis to determine the multiple electricity consumption behavior patterns.

[0024] Specifically, based on the short-term electricity demand forecast data set, a cluster analysis is performed on multiple electricity demand forecast data, and a clustering algorithm (such as K-means, hierarchical clustering, etc.) is used to classify similar short-term electricity demand forecast data into the same cluster cluster to form multiple short-term electricity forecast cluster clusters; similarly, based on the long-term electricity demand forecast data set, a cluster analysis is performed on multiple electricity demand forecast data to form multiple long-term electricity forecast cluster clusters; for each short-term electricity forecast cluster cluster, a feature analysis is performed to extract the common features of the electricity demand forecast data within the short-term electricity forecast cluster cluster, such as the volatility of electricity consumption, peak and valley periods, and periodicity, to form multiple short-term electricity features; for each long-term electricity forecast cluster cluster, a similar feature analysis is performed to extract the long-term trend features of the electricity demand forecast data within the long-term electricity forecast cluster cluster, such as The growth rate and seasonal changes of electricity consumption are used to form multiple long-term electricity characteristics; based on multiple short-term electricity characteristics, each short-term electricity forecast cluster is traversed to identify electricity consumption, and according to the volatility of electricity consumption and other related characteristics, an electricity fluctuation label is generated for the electricity demand forecast data within the short-term electricity forecast cluster, that is, the typical electricity consumption behavior pattern of the short-term electricity forecast cluster is determined; based on multiple long-term electricity characteristics, each long-term electricity forecast cluster is traversed to perform similar electricity consumption identification, and according to the stability of electricity consumption and long-term trend characteristics, an electricity stability label is generated for the electricity demand forecast data within the long-term electricity forecast cluster, that is, the typical electricity consumption behavior pattern of the long-term electricity forecast cluster is determined; using the electricity fluctuation label and the electricity stability label as indexes, all electricity demand forecast data are traversed to determine multiple electricity consumption behavior patterns.

[0025] Furthermore, the power consumption fluctuation tag and the power consumption stability tag are used as indexes, the plurality of power demand forecast data are traversed to perform power consumption pattern analysis, and a plurality of power consumption behavior patterns are determined. The method includes: Based on the power consumption fluctuation label as an index, the multiple power demand forecast data are traversed to perform calculations to obtain multiple fluctuation coefficients; based on the power consumption stability label as an index, the multiple power demand forecast data are traversed to perform calculations to obtain multiple stability coefficients; power consumption analysis is performed according to the multiple fluctuation coefficients to determine power consumption fluctuation characteristics; power consumption analysis is performed according to the multiple stability coefficients to determine power consumption stability characteristics; power consumption patterns of power terminal users are analyzed according to the power consumption fluctuation characteristics and the power consumption stability characteristics to obtain the multiple power consumption behavior patterns.

[0026] Specifically, based on the power fluctuation label as an index, multiple power demand forecast data are traversed, and for each data point with the power fluctuation label, its fluctuation coefficient is calculated. The fluctuation coefficient can reflect the volatility of power demand, which can usually be obtained by analyzing the power fluctuation characteristics of the power demand forecast data in the short term, and dividing the maximum power consumption by the minimum power consumption; based on the power stability label as an index, multiple power demand forecast data are traversed, and for each data point with the power stability label, its stability coefficient is calculated. The stability coefficient can reflect the stability of power demand, which can be obtained by analyzing the power stability characteristics of the power demand forecast data in the short term, and dividing the standard deviation by the average power consumption; according to the calculated multiple fluctuation coefficients, Analyze the characteristics of electricity consumption fluctuation, which may include the distribution of fluctuation coefficient, peak period of fluctuation, periodicity of fluctuation, etc.; analyze the characteristics of electricity consumption stability based on the calculated multiple stability coefficients, which may include the average value of the stability coefficient, the changing trend of the stability coefficient, the stable time period, etc.; combine the characteristics of electricity consumption fluctuation with the characteristics of electricity consumption stability, conduct a comprehensive analysis of the electricity consumption patterns of power terminal users, and determine multiple electricity consumption behavior patterns based on the results of the comprehensive electricity consumption characteristics analysis. These patterns may include peak electricity consumption patterns (high volatility, low stability), valley electricity consumption patterns (low volatility, high stability), seasonal electricity consumption patterns (stability varies with the seasons), periodic electricity consumption patterns (volatility is periodic), etc.

[0027] Power consumption analysis is performed according to the multiple power consumption behavior patterns, and a first power consumption management strategy is formulated.

[0028] Based on the electricity consumption behavior pattern, the electricity consumption of power terminal users is deeply analyzed, including electricity consumption habits, electricity efficiency, etc. For example, for peak electricity consumption patterns, it is necessary to determine its peak time period, peak power consumption and possible triggering factors (such as weekdays, holidays, weather conditions, etc.); according to the analysis results, the first electricity consumption management strategy is formulated. For example, for peak electricity consumption patterns, a staggered electricity consumption plan can be formulated to encourage users to use electricity during non-peak hours, or to balance the electricity demand during peak hours by installing energy storage equipment; for off-peak electricity consumption patterns, the operating time of power equipment can be optimized to ensure that high-energy consumption activities are carried out during periods with lower electricity rates; for electricity consumption patterns with periodic characteristics, a periodic electricity consumption plan can be formulated, such as adjusting the operating strategy of power equipment according to the difference in electricity consumption between weekdays and weekends.

[0029] The first power management strategy is simulated to perform multi-objective feedback, a feedback response data set is generated, the first power management strategy is dynamically adjusted according to the feedback response data set, the power optimization management strategy is determined, and adaptive optimization management of power energy efficiency is performed on power terminal users.

[0030] The first power management strategy is simulated and executed in a virtual environment to observe its impact on the power consumption of power terminal users; multiple target feedback data are collected during the simulation execution process, such as power cost, power efficiency, etc.; according to the feedback response data set, the first power management strategy is dynamically adjusted, such as adjusting the power plan, increasing the use of energy storage equipment, optimizing equipment operating parameters, etc., to form a more optimized power optimization management strategy; the power optimization management strategy is implemented among actual power terminal users, and the power consumption of power terminal users is continuously monitored through the power collection network. According to the monitoring results and new power consumption behavior patterns, the power optimization management strategy is continuously adaptively adjusted and optimized.

[0031] Furthermore, the method of simulating and executing the first power management strategy to perform multi-objective feedback and generate a feedback response data set includes: Based on the short-term electricity demand forecast data set and the long-term electricity demand forecast data set, a power usage scenario analysis is performed to construct a plurality of simulated power usage scenario parameters; the first power usage management strategy is executed according to the plurality of simulated power usage scenario parameters to record power usage and obtain a power usage simulation record log; a plurality of power usage targets are set, and response evaluation is performed on the plurality of power usage targets according to the power usage simulation record log, and the feedback response data set is determined according to the evaluation results.

[0032] Specifically, the short-term electricity demand forecast data set is integrated with the long-term electricity demand forecast data set to obtain comprehensive electricity demand forecast information; based on the integrated electricity demand forecast data, electricity consumption scenario analysis is performed, including identifying electricity demand characteristics under different time periods, different weather conditions, and different economic activity levels; according to the results of the electricity consumption scenario analysis, multiple simulated electricity consumption scenario parameters are constructed, and these parameters should cover different electricity demand patterns, peak electricity consumption periods, electricity consumption fluctuations, etc., to simulate the real electricity consumption environment; the first electricity consumption management strategy is deployed in the simulated environment, and simulated execution is performed according to the constructed multiple simulated electricity consumption scenario parameters; during the strategy execution process, the electricity consumption data under each simulated electricity consumption scenario is recorded in detail, including Including electricity consumption, electricity consumption time, electricity consumption equipment, etc., these data will form an electricity consumption simulation record log; according to the actual needs and management goals of power terminal users, set multiple electricity consumption goals, including electricity bill savings, energy utilization efficiency improvement, carbon emission reduction, etc.; based on the electricity consumption simulation record log, respond to the set multiple electricity consumption goals and evaluate them, including calculating key indicators such as electricity bill savings rate, energy utilization efficiency improvement rate, carbon emission reduction, and evaluate the performance of the first electricity consumption management strategy in different simulated electricity consumption scenarios; integrate and analyze the results of the response evaluation to form a feedback response data set, which contains the electricity consumption target response in each simulated electricity consumption scenario, as well as the performance data of the first electricity consumption management strategy in different scenarios.

[0033] Furthermore, a plurality of power consumption targets are set, and response evaluation is performed on the plurality of power consumption targets according to the power consumption simulation record log, and the method includes: Perform electricity consumption impact analysis based on the electricity consumption simulation record log, set multiple electricity consumption targets, and the multiple electricity consumption targets have multiple weight coefficients; perform feedback responses to the multiple electricity consumption targets according to the multiple weight coefficients in combination with the electricity consumption simulation record log, and generate multiple feedback response data; set multiple feedback targets for the multiple electricity consumption targets based on the multiple feedback response data; and perform response evaluation on the multiple electricity consumption targets according to the multiple feedback targets to generate the evaluation results.

[0034] Specifically, an electricity consumption impact analysis is performed based on the electricity consumption simulation record log, including analyzing the impact of different electricity consumption behaviors on key indicators such as electricity charges, energy utilization efficiency, and carbon emissions, as well as the changes in these impacts in different time periods and different electricity consumption scenarios; based on the results of the electricity consumption impact analysis, multiple electricity consumption targets are set, and these targets should cover multiple aspects such as electricity cost savings, energy utilization efficiency improvement, and carbon emission reduction; at the same time, a weight coefficient is set for each electricity consumption target to reflect its importance and priority in the overall electricity consumption management; according to the set weight coefficient, combined with the electricity consumption simulation record log, feedback response calculations are performed on multiple electricity consumption targets, including calculating the actual response value of each target in different electricity consumption scenarios, and the difference between these response values ​​and the target set values; based on the feedback response data, multiple feedback targets are set for each electricity consumption target, and these feedback targets should reflect the expected improvement effect that can be achieved by adjusting the electricity management strategy in different electricity consumption scenarios; according to the set multiple feedback targets, response evaluations are performed on multiple electricity consumption targets, including calculating the difference between the actual response value of each electricity consumption target in different electricity consumption scenarios and the feedback target value, and the impact of these differences on the overall electricity consumption management effect.

[0035] Furthermore, dynamically adjusting the first power management strategy according to the feedback response data set to determine the power optimization management strategy includes: Based on the feedback response data set, random extraction is performed to determine a first feedback target; the first power management strategy is traversed according to the first feedback target to make a response judgment; when there is no response to the first feedback target in the first power management strategy, a first optimization instruction is generated, and the first power management strategy is dynamically adjusted through the first optimization instruction to obtain a second power management strategy; the second power management strategy is traversed according to the second feedback target to make a response judgment; when there is no response to the second feedback target in the second power management strategy, a second optimization instruction is generated, and the second power management strategy is dynamically adjusted through the second optimization instruction, thereby iterating until the feedback target in the feedback response data set is traversed and stopped, the power management strategy is continuously iteratively optimized, and the power optimization management strategy is output.

[0036] Specifically, based on the feedback response data set, a feedback target is randomly extracted as the first feedback target; according to the extracted first feedback target, the first power management strategy is traversed to make a response judgment, that is, to check whether there are clear measures for the feedback target in the first power management strategy; when there is no direct response to the first feedback target in the first power management strategy, it means that the strategy is insufficient or needs to be improved in this aspect. At this time, a first optimization instruction should be generated, which should contain specific suggestions or measures for dynamic adjustment of the strategy; according to the first optimization instruction, the first power management strategy is dynamically adjusted to obtain the second power management strategy. After obtaining the second power management strategy, the second feedback target is extracted for traversal and response judgment in the same way; when there is no direct response to the second feedback target in the second power management strategy, the second optimization instruction is also generated and dynamically adjusted; when all feedback targets are traversed and the corresponding strategy adjustments and optimizations are made, it is considered that the iterative optimization process of the power management strategy has been completed, and the final power management strategy is output as the power optimization management strategy.

[0037] In summary, the embodiments of the present application have at least the following technical effects: First, a power consumption collection network is constructed based on multiple sensing devices, and real-time sensing of power terminal users is performed through the power consumption collection network to obtain power consumption data sets of power terminal users. Next, a time series prediction channel is constructed, and the power consumption data set is synchronized to the time series prediction channel to predict power consumption for power terminal users, and multiple power demand prediction data are determined. Further, power consumption is identified based on multiple power demand prediction data, and multiple power consumption behavior patterns are determined. Then, power consumption analysis is performed according to multiple power consumption behavior patterns, and a first power consumption management strategy is formulated. Finally, the first power consumption management strategy is simulated and executed for multi-objective feedback, a feedback response data set is generated, and the first power consumption management strategy is dynamically adjusted according to the feedback response data set, and the power consumption optimization management strategy is determined, and the power consumption energy efficiency of power terminal users is adaptively optimized. The technical problem that the energy efficiency management of power terminal users lacks real-time adjustment capability in the prior art is solved. By constructing a power consumption collection network, a time series prediction channel and a dynamic adjustment strategy, adaptive optimization management is realized, and the technical effect of improving the power consumption efficiency of power terminal users is achieved.

[0038] Embodiment 2 is based on the same inventive concept as the energy efficiency optimization management method for power terminal users in the above embodiment. Figure 2 As shown, the present application provides an energy efficiency optimization management system for power terminal users, wherein the system includes: A data acquisition module 11, the data acquisition module 11 is used to build an electricity consumption collection network based on multiple sensor devices, and to perform real-time sensing of power terminal users through the power consumption collection network to obtain power terminal users' electricity consumption data sets; a prediction module 12, the prediction module 12 is used to build a time series prediction channel, synchronize the power consumption data set to the time series prediction channel to predict power consumption for power terminal users, and determine multiple power demand prediction data; an identification module 13, the identification module 13 is used to identify power consumption based on the multiple power demand prediction data, and determine multiple power consumption behavior patterns; an analysis module 14, the analysis module 14 is used to perform power consumption analysis according to the multiple power consumption behavior patterns, and formulate a first power consumption management strategy; a management module 15, the management module 15 is used to simulate the execution of the first power consumption management strategy for multi-objective feedback, generate a feedback response data set, dynamically adjust the first power consumption management strategy according to the feedback response data set, determine the power consumption optimization management strategy, and perform adaptive optimization management of power consumption energy efficiency for power terminal users.

[0039] Furthermore, the prediction module 12 is used to perform the following method: The electricity consumption data set is time-aligned according to the data collection frequency to obtain multiple electricity consumption alignment data; fluctuation analysis is performed based on the multiple electricity consumption alignment data to draw an electricity consumption trend chart; the electricity consumption trend chart is traversed and difference comparison is performed in combination with the multiple electricity consumption alignment data to obtain multiple electricity consumption fluctuation data and multiple electricity consumption stability data; short-term prediction is performed on the multiple electricity consumption alignment data according to the multiple electricity consumption fluctuation data to generate a short-term electricity demand prediction data set; long-term prediction is performed on the multiple electricity consumption alignment data according to the multiple electricity consumption stability data to generate a long-term electricity demand prediction data set; the short-term electricity demand prediction data set is integrated with the long-term electricity demand prediction data set to determine the multiple electricity demand prediction data.

[0040] Furthermore, the identification module 13 is used to execute the following method: Based on the short-term electricity demand forecast data set, cluster analysis is performed on the multiple electricity demand forecast data to determine multiple short-term electricity forecast clustering clusters; based on the long-term electricity demand forecast data set, cluster analysis is performed on the multiple electricity demand forecast data to determine multiple long-term electricity forecast clustering clusters; feature analysis is performed on the multiple electricity demand forecast data according to the multiple short-term electricity forecast clustering clusters to determine multiple short-term electricity features; feature analysis is performed on the multiple electricity demand forecast data according to the multiple long-term electricity forecast clustering clusters to determine multiple long-term electricity features; based on the multiple short-term electricity features, the multiple short-term electricity forecast clustering clusters are traversed to identify electricity consumption and generate electricity fluctuation labels; based on the multiple long-term electricity features, the multiple long-term electricity forecast clustering clusters are traversed to identify electricity consumption and generate electricity stability labels; using the electricity fluctuation labels and the electricity stability labels as indexes, the multiple electricity demand forecast data are traversed to perform electricity consumption pattern analysis to determine the multiple electricity consumption behavior patterns.

[0041] Furthermore, the identification module 13 is used to execute the following method: Based on the power consumption fluctuation label as an index, the multiple power demand forecast data are traversed to perform calculations to obtain multiple fluctuation coefficients; based on the power consumption stability label as an index, the multiple power demand forecast data are traversed to perform calculations to obtain multiple stability coefficients; power consumption analysis is performed according to the multiple fluctuation coefficients to determine power consumption fluctuation characteristics; power consumption analysis is performed according to the multiple stability coefficients to determine power consumption stability characteristics; power consumption patterns of power terminal users are analyzed according to the power consumption fluctuation characteristics and the power consumption stability characteristics to obtain the multiple power consumption behavior patterns.

[0042] Furthermore, the management module 15 is used to execute the following method: Based on the short-term electricity demand forecast data set and the long-term electricity demand forecast data set, a power usage scenario analysis is performed to construct a plurality of simulated power usage scenario parameters; the first power usage management strategy is executed according to the plurality of simulated power usage scenario parameters to record power usage and obtain a power usage simulation record log; a plurality of power usage targets are set, and response evaluation is performed on the plurality of power usage targets according to the power usage simulation record log, and the feedback response data set is determined according to the evaluation results.

[0043] Furthermore, the management module 15 is used to execute the following method: Perform electricity consumption impact analysis based on the electricity consumption simulation record log, set multiple electricity consumption targets, and the multiple electricity consumption targets have multiple weight coefficients; perform feedback responses to the multiple electricity consumption targets according to the multiple weight coefficients in combination with the electricity consumption simulation record log, and generate multiple feedback response data; set multiple feedback targets for the multiple electricity consumption targets based on the multiple feedback response data; and perform response evaluation on the multiple electricity consumption targets according to the multiple feedback targets to generate the evaluation results.

[0044] Furthermore, the management module 15 is used to execute the following method: Based on the feedback response data set, random extraction is performed to determine a first feedback target; the first power management strategy is traversed according to the first feedback target to make a response judgment; when there is no response to the first feedback target in the first power management strategy, a first optimization instruction is generated, and the first power management strategy is dynamically adjusted through the first optimization instruction to obtain a second power management strategy; the second power management strategy is traversed according to the second feedback target to make a response judgment; when there is no response to the second feedback target in the second power management strategy, a second optimization instruction is generated, and the second power management strategy is dynamically adjusted through the second optimization instruction, thereby iterating until the feedback target in the feedback response data set is traversed and stopped, the power management strategy is continuously iteratively optimized, and the power optimization management strategy is output.

[0045] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0046] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0047] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An energy efficiency optimization management method for power terminal users, characterized in that: The method comprises: Building an electricity consumption collection network based on multiple sensor devices, performing real-time sensing on power terminal users through the electricity consumption collection network, and obtaining power consumption data sets of power terminal users; Constructing a time series prediction channel, synchronizing the power consumption data set to the time series prediction channel to perform power consumption prediction on power terminal users, and determining a plurality of power demand prediction data; Identify electricity consumption based on the multiple electricity demand forecast data to determine multiple electricity consumption behavior patterns; Performing power consumption analysis according to the plurality of power consumption behavior patterns and formulating a first power consumption management strategy; The first power management strategy is simulated to perform multi-objective feedback, a feedback response data set is generated, the first power management strategy is dynamically adjusted according to the feedback response data set, the power optimization management strategy is determined, and adaptive optimization management of power energy efficiency is performed on power terminal users.

2. The energy efficiency optimization management method for power terminal users according to claim 1, characterized in that: The power consumption data set is synchronized to the time series prediction channel to perform power consumption prediction on power terminal users, and a plurality of power demand prediction data are determined, the method comprising: Time-aligning the electricity consumption data set according to the data collection frequency to obtain a plurality of electricity consumption aligned data; Perform fluctuation analysis based on the plurality of electricity usage alignment data and draw an electricity usage trend graph; Traversing the power consumption trend graph and performing difference comparison in combination with the plurality of power consumption alignment data, to obtain a plurality of power consumption fluctuation data and a plurality of power consumption stability data; Performing short-term forecasting on the plurality of electricity usage alignment data according to the plurality of electricity usage fluctuation data to generate a short-term electricity demand forecasting data set; Performing long-term prediction on the plurality of electricity usage alignment data according to the plurality of electricity usage stability data to generate a long-term electricity demand prediction data set; The short-term electricity demand forecast data set and the long-term electricity demand forecast data set are integrated to determine the plurality of electricity demand forecast data.

3. The energy efficiency optimization management method for power terminal users according to claim 2, characterized in that: Based on the plurality of power demand forecast data, power consumption identification is performed to determine a plurality of power consumption behavior patterns, the method comprising: Based on the short-term electricity demand forecast data set, cluster analysis is performed on the plurality of electricity demand forecast data to determine a plurality of short-term electricity forecast clusters; Based on the long-term electricity demand forecast data set, cluster analysis is performed on the plurality of electricity demand forecast data to determine a plurality of long-term electricity forecast clusters; Performing feature analysis on the plurality of power demand forecast data according to the plurality of power short-term forecast clusters to determine a plurality of power short-term features; Performing feature analysis on the plurality of power demand forecast data according to the plurality of power long-term forecast clusters to determine a plurality of power long-term features; Based on the multiple short-term power features, the multiple short-term power forecast clusters are traversed to identify power consumption and generate a power consumption fluctuation label; Based on the multiple long-term power characteristics, the multiple long-term power prediction clusters are traversed to identify power consumption and generate a power consumption stability label; The power consumption fluctuation tag and the power consumption stability tag are used as indexes, the multiple power demand forecast data are traversed to perform power consumption pattern analysis, and the multiple power consumption behavior patterns are determined.

4. The energy efficiency optimization management method for power terminal users according to claim 3, characterized in that: The power consumption fluctuation tag and the power consumption stability tag are used as indexes, the plurality of power demand forecast data are traversed to perform power consumption pattern analysis, and a plurality of power consumption behavior patterns are determined, the method comprising: Based on the power consumption fluctuation tag as an index, traverse the plurality of power demand forecast data to perform calculations to obtain a plurality of fluctuation coefficients; Based on the power consumption stability tag as an index, traverse the plurality of power demand forecast data to perform calculations to obtain a plurality of stability coefficients; Performing power consumption analysis according to the multiple fluctuation coefficients to determine power consumption fluctuation characteristics; Performing power consumption analysis according to the multiple stability coefficients to determine power consumption stability characteristics; The power consumption patterns of power terminal users are analyzed according to the power consumption fluctuation characteristics and the power consumption stability characteristics to obtain the multiple power consumption behavior patterns.

5. The energy efficiency optimization management method for power terminal users according to claim 2, characterized in that: The method of simulating and executing the first power management strategy to perform multi-objective feedback and generate a feedback response data set includes: Performing power usage scenario analysis based on the short-term power demand forecast data set and the long-term power demand forecast data set, and constructing multiple simulated power usage scenario parameters; Executing the first power consumption management strategy to record power consumption according to the multiple simulated power consumption scenario parameters to obtain a power consumption simulation record log; A plurality of electricity consumption targets are set, response evaluation is performed on the plurality of electricity consumption targets according to the electricity consumption simulation record log, and the feedback response data set is determined according to the evaluation result.

6. The energy efficiency optimization management method for power terminal users according to claim 5, characterized in that: Setting a plurality of power consumption targets, and performing response evaluation on the plurality of power consumption targets according to the power consumption simulation record log, the method comprising: Performing power consumption impact analysis according to the power consumption simulation record log, setting multiple power consumption targets, wherein the multiple power consumption targets have multiple weight coefficients; Performing feedback responses to the multiple power consumption targets according to the multiple weight coefficients combined with the power consumption simulation record log to generate multiple feedback response data; setting a plurality of feedback targets for the plurality of power usage targets based on the plurality of feedback response data; The plurality of power consumption targets are evaluated for response according to the plurality of feedback targets to generate the evaluation result.

7. The energy efficiency optimization management method for power terminal users according to claim 1, characterized in that: The first power management strategy is dynamically adjusted according to the feedback response data set to determine a power optimization management strategy, the method comprising: Performing random extraction based on the feedback response data set to determine a first feedback target; Traversing the first power management strategy according to the first feedback target to make a response determination; When there is no response to the first feedback target in the first power management strategy, generating a first optimization instruction, dynamically adjusting the first power management strategy through the first optimization instruction, and obtaining a second power management strategy; Traversing the second power management strategy according to the second feedback target to make a response determination; When there is no response to the second feedback target in the second power management strategy, a second optimization instruction is generated, and the second power management strategy is dynamically adjusted through the second optimization instruction, thereby iterating until the feedback targets in the feedback response data set are traversed and the power management strategy is continuously iterated and optimized to output the power optimization management strategy.

8. An energy efficiency optimization management system for power terminal users, characterized in that: The system is used to implement the energy efficiency optimization management method for power terminal users according to any one of claims 1 to 7, and comprises: A data collection module, wherein the data collection module is used to construct an electricity consumption collection network based on multiple sensor devices, and to perform real-time sensing of power terminal users through the power consumption collection network to obtain power consumption data sets of power terminal users; A prediction module, the prediction module is used to construct a time series prediction channel, synchronize the power consumption data set to the time series prediction channel to perform power consumption prediction on power terminal users, and determine multiple power demand prediction data; an identification module, the identification module being used to identify power consumption based on the plurality of power demand forecast data and determine a plurality of power consumption behavior patterns; An analysis module, the analysis module being used to perform power consumption analysis according to the multiple power consumption behavior patterns and formulate a first power consumption management strategy; A management module, the management module is used to simulate the execution of the first power management strategy for multi-objective feedback, generate a feedback response data set, dynamically adjust the first power management strategy according to the feedback response data set, determine the power optimization management strategy, and perform adaptive optimization management of power energy efficiency for power terminal users.

Images