Public building-oriented mixed time scale demand side resource feature construction method, system and equipment and medium

Abstract

The invention discloses a public building-oriented mixed time scale demand side resource feature construction method, system and device, and a medium. The method comprises the steps of collecting first load data of a to-be-analyzed public building in different operation periods through a power utilization monitoring terminal; comprehensively considering the time scale difference and the multi-dimensional attribute of the building electrical load, and extracting a description type feature, a ratio type feature and a peak period refinement feature through the first load data; and fusing the description type features, the ratio type features and the peak period refinement features to obtain a first comprehensive feature set so as to comprehensively represent the load operation rule and the demand side resource features of the public building. According to the method, the load operation rule and the flexible regulation and control characteristics of the public building under different time scales can be comprehensively described, and a refined data support is provided for peak regulation potential evaluation and demand response strategy formulation of the building load.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building energy data analysis and load feature extraction, and particularly relates to a hybrid time scale demand side resource feature construction method, system, equipment and medium for public buildings. BACKGROUND

[0002] With the continuous improvement of smart energy systems and building energy efficiency management, public buildings, as an important part of urban electricity consumption, their load characteristics and demand side resource potential are attracting widespread attention. Public buildings have large electricity consumption, relatively stable operation mode, and good demand response and load regulation potential. Accurate and comprehensive construction of public building load characteristics is the basis for realizing flexible load management, peak regulation capacity assessment and optimized demand response strategy. However, the current load feature extraction method for public buildings generally has the problems of coarse granularity and single structure. Traditional methods mostly rely on single features such as daily maximum load, average load, peak-valley difference, lack of in-depth mining of different time scales, different load structures and high load period details, and are difficult to fully reflect the dynamic change rule and regulation capacity of building load. In addition, some existing methods ignore the detailed description of peak load characteristics, and cannot accurately identify the operation characteristics and potential regulation space of buildings in high load period, which restricts the effective use of demand side resources.

[0003] Therefore, it is urgent to propose a method of combining multi-time scale and multi-dimensional feature information to systematically construct demand side resource features of public buildings, fully improve the integrity and accuracy of building load feature expression, and help effective mining and scientific management of public building flexible load. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a hybrid time scale demand side resource feature construction method, system, equipment and medium for public buildings, which solves the problems of single feature and coarse granularity in traditional public building load feature extraction methods, and realizes comprehensive and accurate characterization of public building load characteristics.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a hybrid time scale demand side resource feature construction method for public buildings, comprising:

[0008] acquiring first load data of the public building to be analyzed in different operation periods by the power monitoring terminal;

[0009] The time scale difference and multi-dimensional attributes of the building electricity load are comprehensively considered, and the first load data is used to extract description type features, ratio type features, and peak period refinement features;

[0010] The description type features, the ratio type features, and the peak period refinement features are fused to obtain a first comprehensive feature set, so as to comprehensively represent the load operation law and the demand side resource characteristics of the public building.

[0011] As a preferred scheme of the public building-oriented mixed time scale demand side resource feature construction method, wherein: the first determination is performed according to the actual load of the building to obtain the peak period time period, and the first determination includes:

[0012] When the load value of a time period in the first load data is greater than the first all-day maximum load threshold of the public building or greater than the first daily average load threshold of the public building, the time period is determined as the peak period time period.

[0013] As a preferred scheme of the public building-oriented mixed time scale demand side resource feature construction method, wherein: the first comprehensive feature set is obtained by:

[0014] Based on the description type features, the building electricity basic load profile is formed, based on the ratio type features, the internal structure relationship of the load is analyzed, and based on the peak period refinement features, the dynamic change characteristics of the high load period are focused;

[0015] By fusing the description type features, the ratio type features, and the peak period refinement features, the first comprehensive feature set is obtained, so as to comprehensively represent the load operation law and the demand side resource characteristics of the public building.

[0016] As a preferred scheme of the public building-oriented mixed time scale demand side resource feature construction method, wherein: the first load data is collected by:

[0017] Non-intrusive monitoring equipment is deployed at a public building total electricity meter or a building energy management system;

[0018] The first load data of the public building to be analyzed on a typical operation day is collected in real time at a first time resolution.

[0019] As a preferred scheme of the public building-oriented mixed time scale demand side resource feature construction method, wherein: the extraction of the description type features includes:

[0020] The description type features reflecting the overall load level and change range of the building are extracted by statistical analysis of the first load data of the public building, and the description type features include the daily maximum load, the daily minimum load, the daily average load, and the daily peak valley difference.

[0021] Among them, the daily maximum load is used to measure the peak power of building electricity, the daily minimum load is used to measure the basic load level of the building in the lowest running state, the daily average load is used to reflect the whole building load level throughout the day, and the daily peak valley difference is used to evaluate the load fluctuation amplitude.

[0022] The beneficial effects of the preferred technical solution are: by fusing the load characteristic information of multiple time scales, the limitations of traditional single feature structure are broken through, and the comprehensiveness and fineness of building load feature description are significantly improved.

[0023] As a preferred scheme of the mixed time scale demand side resource feature construction method for public buildings provided by the application, wherein: the extraction of the ratio type feature includes:

[0024] By statistically analyzing the first load data of the public building, the ratio type feature reflecting the load structure and relative change law is extracted, and the ratio type feature includes daily load rate, peak period load rate, valley period load rate, daily peak valley difference rate and daily maximum load utilization hours;

[0025] Among them, the daily load rate is used to reflect the overall stability of building load, the peak period load rate and the valley period load rate measure the load level of the high load period and the low load period respectively, the daily peak valley difference rate is used to quantify the load fluctuation intensity, and the daily maximum load utilization hours are used to measure the time utilization efficiency and load persistence of building electricity, which assists in judging the load optimization capability of the building.

[0026] As a preferred scheme of the mixed time scale demand side resource feature construction method for public buildings provided by the application, wherein: the extraction of the peak period refined feature includes:

[0027] The peak period refined feature reflecting the internal load change feature of the high load period is extracted in the peak period, and the peak period refined feature includes peak period maximum minimum load difference, peak period load standard deviation, peak period coefficient of variation and peak period load coefficient;

[0028] Among them, the peak period maximum minimum load difference directly reflects the load fluctuation range in the high load period, the peak period load standard deviation is used to quantify the dispersion degree of load in the peak period, reflect the load fluctuation intensity, the peak period coefficient of variation is used to evaluate the relative fluctuation level of load in the peak period of different buildings on the basis of eliminating the influence of building scale difference, and the peak period load coefficient is used to measure the proportion of peak period load fluctuation range relative to the maximum load.

[0029] The beneficial effects of the preferred technical solution are: effectively supplementing the dynamic information of load change in the high load period, enhancing the pertinence and accuracy of building load regulation and control capability analysis.

[0030] In a second aspect, the present application provides a hybrid time scale demand side resource feature construction system for public buildings, comprising:

[0031] A data acquisition module is configured to acquire first load data of the public building to be analyzed in different operation time periods through the power consumption monitoring terminal;

[0032] A feature extraction module is configured to comprehensively consider the time scale difference and multi-dimensional attributes of the building power consumption load, and extract description class features, ratio class features and peak period refinement features from the first load data;

[0033] An integrated feature representation module is configured to fuse the description class features, ratio class features and peak period refinement features to obtain a first integrated feature set, so as to comprehensively represent the load operation law and demand side resource characteristics of the public building.

[0034] In a third aspect, the present application provides an electronic device comprising a memory and a processor; the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the steps of the hybrid time scale demand side resource feature construction method for public buildings.

[0035] In a fourth aspect, the present application provides a computer readable storage medium storing computer executable instructions, which are executed by a processor to implement the steps of the hybrid time scale demand side resource feature construction method for public buildings.

[0036] Compared with the prior art, the present application has the following beneficial effects: the present application provides a hybrid time scale demand side resource feature construction method, system, device and medium for public buildings, which breaks through the limitation of traditional single feature structure by fusing multi-time scale load feature information, significantly improves the comprehensiveness and fineness of building load feature description, introduces peak period refinement features to effectively supplement the dynamic information of load changes in high load periods, and enhances the pertinence and accuracy of building load regulation and control capability analysis; the overall feature construction method has clear structure and strong adaptability, and is suitable for demand side resource feature extraction and flexible load management of various public buildings, which provides reliable technical support for public buildings to participate in demand response, load optimization and differentiated regulation strategy formulation, and has good engineering application value and promotion prospect. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0038] Figure 1 The overall flow logic diagram of the public building-oriented mixed time scale demand side resource feature construction method is shown in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present application.

[0040] Embodiment 1, reference Figure 1 For an embodiment of the present application, a public building-oriented mixed time scale demand side resource feature construction method is provided, as shown in Figure 1 and specifically comprising the following steps:

[0041] S100: collecting first load data of a public building to be analyzed in different operation periods through a power consumption monitoring terminal;

[0042] S200: comprehensively considering the time scale difference and multi-dimensional attributes of building power load, extracting description type features, ratio type features and peak period refinement features through the first load data;

[0043] S300: fusing the description type features, ratio type features and peak period refinement features to obtain a first comprehensive feature set, so as to comprehensively represent the load operation law and demand side resource characteristics of the public building;

[0044] It should be noted that, in order to solve the problems of single feature and coarse granularity in the traditional public building load feature extraction method, and to realize comprehensive and accurate representation of the load characteristics of the public building, the above steps S100-S300 fuse the load feature information of multiple time scales, break through the limitation of the traditional single feature structure, and significantly improve the comprehensiveness and fineness of the building load feature description. The peak period refinement features are introduced to effectively supplement the dynamic information of the load change in the high load period, and enhance the pertinence and accuracy of the building load regulation and control ability analysis. The overall feature construction method has clear structure and strong adaptability, and is suitable for demand side resource feature extraction and flexible load management of various public buildings, and provides reliable technical support for public buildings to participate in demand response, load optimization and differentiated regulation strategy formulation, and has good engineering application value and promotion prospect.

[0045] Embodiment 2, based on the previous embodiment, the present embodiment provides a specific implementation of the public building-oriented mixed time scale demand side resource feature construction method, which is used to illustrate the technical means used in the method.

[0046] In this embodiment of the application, the above step S100, which involves collecting the first load data of the public building to be analyzed during different operating periods through an electricity monitoring terminal, includes:

[0047] Deploy non-intrusive monitoring devices at the main electricity meter or building energy management system of public buildings;

[0048] The system collects first load data of the public building to be analyzed on a typical operating day in real time at the highest time resolution.

[0049] Specifically, in this embodiment, the first load data is the hourly electricity load data of the building during a typical operating day, expressed as: P(t)={P1,P2,...,P N}, where P(t) represents the load value of the building at time step t, and N is the total number of sampling points per day;

[0050] Specifically, the data covers the building 24 hours a day, and the first time resolution of the data is set according to actual needs, preferably common granularities such as 5 minutes, 15 minutes or 1 hour, to ensure data integrity and accuracy.

[0051] In an optional embodiment, the initial time resolution can be flexibly set according to the specific application scenario and monitoring accuracy requirements. For example, for scenarios requiring detailed analysis of short-term load fluctuations (such as studies on the start-up and shutdown characteristics of air conditioning systems), a high-precision sampling of 1 minute can be used; while for scenarios such as long-term energy efficiency assessment or load trend analysis, a moderate resolution of 30 minutes can be selected to balance the amount of data and the analysis requirements.

[0052] It should be noted that step S100 above collects the first load data of the public building through the electricity monitoring terminal, realizing all-time, multi-dimensional monitoring of the building's electricity consumption behavior. The use of non-invasive monitoring equipment ensures the integrity of data collection while avoiding interference with the building's normal electricity use. By flexibly setting the sampling time resolution, load data of appropriate granularity can be obtained according to the needs of different application scenarios, providing a reliable data foundation for subsequent feature extraction.

[0053] In this embodiment of the application, step S200, which comprehensively considers the time-scale differences and multi-dimensional attributes of building electricity load, extracts descriptive features, ratio features, and peak-period refinement features from the first load data, including the following sub-steps B1 to B4:

[0054] In B1: the extraction of descriptive class features includes:

[0055] By statistically analyzing the primary load data of public buildings, descriptive features reflecting the overall load level and range of variation of the buildings are extracted. These descriptive features include daily maximum load, daily minimum load, daily average load, and daily peak-to-valley difference. Among them, daily maximum load is used to measure the peak power consumption capacity of the building, daily minimum load is used to measure the basic load level of the building under the lowest operating conditions, daily average load is used to reflect the overall load level of the building throughout the day, and daily peak-to-valley difference is used to assess the load fluctuation range. The larger this indicator is, the more obvious the peak-to-valley characteristics of the building load are, and the greater the adjustment space it has.

[0056] Specifically, the maximum daily load is expressed as: P max =max{P(t)};

[0057] Specifically, the daily minimum load is expressed as: P min =min{P(t)};

[0058] Specifically, the daily average load is expressed as:

[0059] Specifically, the daily peak-to-valley difference is expressed as: D peak-valley =P max -P min .

[0060] In B2: the extraction of ratio-type features includes:

[0061] By statistically analyzing the primary load data of public buildings, ratio-based features reflecting the load structure and relative change patterns are extracted. These features include daily load factor, peak load factor, valley load factor, daily peak-valley difference rate, and daily maximum load utilization hours. Among them, the daily load factor reflects the overall stability of the building load; the closer the value is to 1, the more stable the load. The peak load factor and valley load factor measure the load levels during high and low load periods, respectively. Their comparison with the overall load level helps to assess the adjustability of the building load. The daily peak-valley difference rate quantifies the intensity of load fluctuations, and the daily maximum load utilization hours measure the time utilization efficiency and load continuity of building electricity, assisting in judging the building's load optimization capabilities.

[0062] Specifically, the daily load factor is expressed as:

[0063] Specifically, the daily peak-to-valley difference rate is expressed as:

[0064] Specifically, the daily maximum load utilization hours are expressed as follows:

[0065] Among them, E total This represents the total daily electricity consumption, reflecting the load utilization efficiency.

[0066] In B3: The peak time period is determined by the first judgment based on the actual load of the building;

[0067] Specifically, the first determination step includes: when the load value of a certain time period in the first load data is greater than the first full-day maximum load threshold of the public building, or greater than the first daily average load threshold of the public building, it is determined to be a peak period.

[0068] Specifically, in this embodiment, the first full-day maximum load threshold is 80% of the building's daily maximum load, and the first daily average load threshold is 1.35 times the building's daily average load.

[0069] In an optional embodiment, the threshold can also be dynamically adjusted according to actual needs, for example, by using a sliding window to calculate the moving average load and introducing a seasonal factor (e.g., 1.4 times in summer and 1.3 times in winter), or by setting it differently according to building type. Simultaneously, time-segmentation strategies and duration conditions can be combined to improve the accuracy and adaptability of the judgment.

[0070] It should be noted that the selection of the first full-day maximum load threshold and the first daily average load threshold is mainly based on the statistical distribution characteristics of building load. The 80% peak load threshold can effectively capture significant peak periods, while the 1.35 times daily average load threshold corresponds to the range of mean + 1σ in the normal distribution, covering about 85% of the normal load.

[0071] In an optional embodiment, the first determination step can also be based on a quantile-based statistical distribution method. First, the load data of the building over the past 30 days is statistically analyzed, and the probability distribution of the hourly load value is calculated. The 85th quantile of the load value distribution is selected as the peak period determination threshold. During real-time monitoring, when the load value at three consecutive sampling points exceeds this quantile threshold, the peak period is determined to have begun. When the load value falls below the 75th quantile and remains below it for 30 minutes, the peak period is determined to have ended.

[0072] In another optional embodiment, the first determination step can also be a dynamic determination method based on the load change rate, using the average load of the building in the same period of the past 7 days as the benchmark value; the deviation rate between the current load and the benchmark value is calculated in real time; when the following conditions are met simultaneously: deviation rate ≥ 40%, absolute load value > 1.2 times the daily average load, peak period determination is triggered; the conditions are verified every 5 minutes during the peak period, until the conditions are not met after 2 consecutive tests.

[0073] In B4: the extraction of peak refinement features includes:

[0074] Within the peak period, refined peak period features reflecting the load variation characteristics within the high load period are extracted. These refined peak period features include the difference between the maximum and minimum peak loads, the standard deviation of the peak load, the peak load coefficient of variation, and the peak load coefficient.

[0075] Among them, the difference between the maximum and minimum loads during peak periods directly reflects the range of load fluctuations during high-load periods, revealing the dynamic characteristics of peak loads; the standard deviation of peak loads is used to quantify the degree of load dispersion during peak periods, reflecting the severity of load fluctuations; the coefficient of variation during peak periods is used to assess the relative fluctuation level of loads of different buildings during peak periods after eliminating the influence of differences in building size; and the peak load coefficient is used to measure the proportion of the peak load fluctuation range relative to the maximum load, revealing load stability and assisting in judging the building's adjustment flexibility during high-load periods.

[0076] Specifically, suppose there are M sampling points during the peak period, and the load value is: P peak ={P1,P2,…,P M};

[0077] Specifically, the difference between the maximum and minimum load during peak periods is expressed as: D peak-max-min =max{P peak}-min{P peak};

[0078] Specifically, the standard deviation of peak load is expressed as:

[0079] in, This represents the average load during peak periods; a larger standard deviation indicates more severe fluctuations.

[0080] Specifically, the peak period coefficient of variation is expressed as:

[0081] Specifically, the peak load factor is expressed as:

[0082] It should be noted that step S200 above objectively reflects the basic load characteristics of a building by extracting descriptive features such as daily maximum load and daily minimum load; it deeply reveals the internal structural relationships of the load by calculating ratio features such as daily load rate and peak-valley difference rate; and it accurately captures the dynamic change patterns of high-load periods by extracting refined features for peak periods. This overcomes the limitations of traditional single-feature analysis and achieves a three-dimensional representation of building load characteristics.

[0083] In this embodiment of the application, step S300 above integrates descriptive features, ratio features, and peak period refinement features to obtain a first comprehensive feature set, which comprehensively characterizes the load operation patterns and demand-side resource characteristics of public buildings, including:

[0084] Based on descriptive features, the basic load profile of building electricity consumption is formed to understand its basic load level and fluctuation range; based on ratio features, the internal structural relationship of the load is analyzed to evaluate load stability and utilization efficiency; based on peak period refinement features, the dynamic change characteristics of high load periods are focused.

[0085] By integrating descriptive features, ratio features, and peak period refinement features, a first comprehensive feature set is obtained to fully characterize the load operation patterns and demand-side resource characteristics of public buildings.

[0086] In an optional embodiment, the first comprehensive feature set can also be obtained using a feature-weighted fusion method. First, correlation analysis and expert scoring are performed on descriptive features (such as daily maximum load and daily peak-to-valley difference), ratio features (such as daily load factor and peak-to-valley difference rate), and peak-period refinement features (such as peak-period variation coefficient and load standard deviation) to quantify the contribution of each type of feature to the load characteristic representation. Based on the evaluation results, weights are assigned to each type of feature using the analytic hierarchy process (AHP) or entropy weighting method. For example, peak-period refinement features may be given higher weights because they reflect key control periods. Each feature is multiplied by its weight and then linearly superimposed to generate the comprehensive feature set.

[0087] In another optional embodiment, the first comprehensive feature set can also be obtained using principal component analysis (PCA). Descriptive, ratio, and peak-period refined features are Z-score standardized to eliminate dimensional differences. The correlation between features is analyzed, and the covariance matrix is ​​calculated to determine the principal component orientation. The top k principal components with a cumulative contribution rate ≥ 85% are selected, and the original multidimensional features are projected into a low-dimensional space. The dimensionality-reduced principal components are used as the new feature set, balancing information integrity and computational efficiency.

[0088] It should be noted that the method provided in this embodiment is applicable to the analysis of the electricity load characteristics of various public buildings, and is particularly suitable for the following application scenarios: on the one hand, it can be used for accurate assessment of the load regulation capability at the building level, and help identify building types with good peak-shaving potential; on the other hand, it can serve the formulation and optimization of building participation demand response strategies, and improve the flexibility and adjustability of building loads; at the same time, it can also provide a data foundation and theoretical support for the classification management and differentiated load management strategies of public buildings, and has good engineering application value and promotion prospects.

[0089] It should be noted that step S300 not only preserves the independent information value of various features, but also, through the synergistic effect between features, fully presents the static characteristics and dynamic variation patterns of building loads. This supports more accurate load characteristic analysis, peak-shaving potential assessment, and demand response strategy formulation, providing a scientific basis for building energy management.

[0090] Example 3: This example provides a hybrid time-scale demand-side resource characteristic construction system for public buildings, including:

[0091] The data acquisition module is used to collect the first load data of the public building to be analyzed during different operating periods through the power consumption monitoring terminal;

[0092] The feature extraction module is used to comprehensively consider the time scale differences and multi-dimensional attributes of building electricity load, and extract descriptive features, ratio features and peak period refinement features from the first load data.

[0093] The comprehensive feature representation module is used to integrate descriptive features, ratio features, and peak period refinement features to obtain the first comprehensive feature set, so as to comprehensively represent the load operation pattern and demand-side resource characteristics of public buildings.

[0094] It should be noted that the technical solution of the hybrid time-scale demand-side resource feature construction system for public buildings is based on the same concept as the technical solution of the hybrid time-scale demand-side resource feature construction method for public buildings described above. For details not described in detail in the technical solution of the hybrid time-scale demand-side resource feature construction system for public buildings in this embodiment, please refer to the description of the technical solution of the hybrid time-scale demand-side resource feature construction method for public buildings described above.

[0095] The above-mentioned unit modules can be embedded in the processor of the electronic device in hardware form or independent of it, or they can be stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of the above modules.

[0096] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for constructing demand-side resource characteristics for public buildings using a hybrid timescale. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0097] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method proposed in the above embodiments.

[0098] The storage medium proposed in this embodiment belongs to the same inventive concept as the method proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0099] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute the method of the embodiments of the present invention.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for constructing demand-side resource characteristics for public buildings using a hybrid timescale, characterized in that: include: The first load data of the public building to be analyzed is collected through the power consumption monitoring terminal during different operating periods. Taking into account the time scale differences and multidimensional attributes of building electricity load, descriptive features, ratio features, and peak period refinement features are extracted from the first load data. The descriptive features, ratio features, and peak period refinement features are fused together to obtain the first comprehensive feature set, which comprehensively characterizes the load operation pattern and demand-side resource characteristics of public buildings.

2. The method for constructing demand-side resource characteristics for public buildings using a hybrid time scale as described in claim 1, characterized in that, The peak time period is determined by a first determination based on the actual load of the building. The first determination includes: When the load value in the first load data for a certain period of time is greater than the first maximum daily load threshold of the public building, or greater than the first average daily load threshold of the public building, it is determined to be a peak period.

3. The method for constructing demand-side resource characteristics for public buildings using a hybrid time scale as described in claim 2, characterized in that, The acquisition of the first comprehensive feature set includes: Based on the descriptive features, a basic load profile for building electricity consumption is formed; based on the ratio features, the internal structural relationship of the load is analyzed; and based on the peak period refinement features, the dynamic change characteristics of high load periods are focused. By integrating the descriptive features, ratio features, and peak period refinement features, a first comprehensive feature set is obtained to fully characterize the load operation patterns and demand-side resource characteristics of public buildings.

4. The method for constructing demand-side resource characteristics for public buildings using a hybrid time scale as described in claim 1, characterized in that, The acquisition of the first load data includes: Deploy non-intrusive monitoring devices at the main electricity meter or building energy management system of public buildings; The system collects first load data of the public building to be analyzed on a typical operating day in real time at the highest time resolution.

5. The method for constructing demand-side resource characteristics for public buildings using a hybrid time scale as described in claim 4, characterized in that, The extraction of the descriptive features includes: By statistically analyzing the first load data of the public buildings, descriptive features reflecting the overall load level and range of change of the buildings are extracted. These descriptive features include daily maximum load, daily minimum load, daily average load, and daily peak-to-valley difference. Among them, the daily maximum load is used to measure the building's peak power capacity, the daily minimum load is used to measure the basic load level of the building under the lowest operating conditions, the daily average load is used to reflect the overall building's load level throughout the day, and the daily peak-to-valley difference is used to assess the load fluctuation range.

6. The method for constructing demand-side resource characteristics for public buildings using a hybrid timescale as described in claim 5, characterized in that, The extraction of the ratio-type features includes: By statistically analyzing the first load data of the public buildings, ratio-type features reflecting the load structure and relative change patterns are extracted. These ratio-type features include daily load rate, peak load rate, valley load rate, daily peak-valley difference rate, and daily maximum load utilization hours. The daily load factor is used to reflect the overall stability of the building load. The peak load factor and valley load factor measure the load level during high load periods and low load periods, respectively. The daily peak-valley difference rate is used to quantify the intensity of load fluctuations. The daily maximum load utilization hours are used to measure the time utilization efficiency and load continuity of building electricity consumption, and to help judge the building's load optimization capability.

7. The method for constructing demand-side resource characteristics for public buildings using a hybrid time scale as described in claim 6, characterized in that, The extraction of peak period refinement features includes: Within the peak period, refined peak period features reflecting load variation characteristics within high-load periods are extracted. These refined peak period features include the difference between the maximum and minimum peak loads, the standard deviation of peak loads, the coefficient of variation of peak loads, and the peak load coefficient. Among them, the difference between the maximum and minimum load during peak periods directly reflects the range of load fluctuations during high-load periods; the standard deviation of peak load is used to quantify the dispersion of load during peak periods and reflect the severity of load fluctuations; the coefficient of variation during peak periods is used to assess the relative fluctuation level of loads of different buildings during peak periods after eliminating the influence of differences in building size; and the peak load coefficient is used to measure the proportion of the peak load fluctuation range relative to the maximum load.

8. A system for constructing demand-side resource characteristics for public buildings using a hybrid timescale, employing the method for constructing demand-side resource characteristics for public buildings using a hybrid timescale as described in any one of claims 1 to 7, characterized in that... include: The data acquisition module is used to collect the first load data of the public building to be analyzed during different operating periods through the power consumption monitoring terminal; The feature extraction module is used to comprehensively consider the time scale differences and multi-dimensional attributes of building electricity load, and extract descriptive features, ratio features and peak period refinement features from the first load data. The comprehensive feature representation module is used to fuse the descriptive features, ratio features, and peak period refinement features to obtain the first comprehensive feature set, so as to comprehensively represent the load operation pattern and demand-side resource characteristics of public buildings.

9. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store computer-executable instructions, and when the processor executes the computer-executable instructions, it implements the steps of the method for constructing hybrid time-scale demand-side resource characteristics for public buildings as described in any one of claims 1 to 7.

10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the computer-executable instructions are executed by the processor, they implement the steps of the method for constructing hybrid time-scale demand-side resource characteristics for public buildings as described in any one of claims 1 to 7.

Images