Residential user-oriented comprehensive energy efficiency evaluation method, system, equipment and medium

Abstract

The invention provides a resident user-oriented comprehensive energy efficiency evaluation method, system and device and a medium. The method comprises the steps of obtaining values of indexes in an energy efficiency index set in a historical time period from historical energy efficiency data of a regional resident user group; the energy efficiency index set comprises equipment dynamic energy efficiency indexes; obtaining the weight of each index in the energy efficiency index set through a data envelope analysis-relaxation measure model; selecting a plurality of indexes corresponding to the residential users and the energy consumption equipment thereof from the energy efficiency index set as evaluation indexes, and performing weighted summation based on the weights of the evaluation indexes and the values of the evaluation indexes in the current time period to obtain a total energy efficiency score of the residential users in the current time period; according to the method and the system, the weight of the index can be dynamically adjusted along with time as time goes on so as to adapt to the index importance changing along with time, and the timeliness of an evaluation result is ensured; and through selection of evaluation indexes, adaptive adjustment can be carried out for different users during comprehensive energy efficiency evaluation, and the fairness of the result is enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of comprehensive energy efficiency evaluation of residential users, and specifically relates to a comprehensive energy efficiency evaluation method, system, equipment and medium for residential users. Background Art

[0002] In the context of increasingly severe global energy consumption and environmental problems, energy efficiency evaluation, as a key tool to promote energy conservation and environmental protection, is particularly important in terms of its scientificity and practicality. Although the data envelopment analysis (DEA) method has been widely used in the field of energy efficiency evaluation, especially in the context of environmental regulation, the existing technology still has some shortcomings:

[0003] First, most existing energy efficiency evaluation index systems are mainly aimed at large-scale buildings such as industrial, commercial or public buildings, while the energy efficiency evaluation of residential users lacks sufficient detail and accuracy. This has led to a relative lack of research on residential energy efficiency evaluation, which cannot accurately reflect the actual energy use and efficiency of residential users.

[0004] Secondly, existing technologies often set up different indicator systems for different user groups when evaluating energy efficiency. This fixed indicator system cannot flexibly respond to user needs and environmental changes, limiting the universality and flexibility of the evaluation method. In addition, the existing evaluation method cannot timely reflect the changes in the importance of indicators, thus affecting the accuracy and timeliness of the evaluation results.

[0005] In summary, the existing energy efficiency evaluation technology has obvious shortcomings in terms of the meticulousness, accuracy, timeliness and universality of residents' energy efficiency evaluation. Summary of the invention

[0006] In order to overcome the above-mentioned deficiencies of the prior art, the present invention proposes a comprehensive energy efficiency evaluation method for residential users, comprising:

[0007] Based on a pre-constructed energy efficiency index set of a regional residential user group, the value of each index in the energy efficiency index set in a historical period is obtained from the historical energy efficiency data of the regional residential user group; the energy efficiency index set includes the equipment dynamic energy efficiency index of each energy-consuming equipment in the regional residential user group;

[0008] Based on the values ​​of each of the indicators in the historical period and the set total energy efficiency score of the resident user group in the area, the weight of each of the indicators in the energy efficiency indicator set is obtained through a data envelopment analysis-relaxation measurement model;

[0009] Based on each residential user in the regional residential user group, selecting a number of indicators corresponding to the residential user and its energy-consuming equipment from the energy efficiency indicator set as evaluation indicators, and selecting a weight of each evaluation indicator from the weights of each indicator;

[0010] The value of each evaluation indicator in the current time period is obtained from the current energy efficiency data of the residential user group in the area, and a weighted sum is performed based on the weight of each evaluation indicator and the value of each evaluation indicator in the current time period to obtain the total energy efficiency score of the residential users in the current time period, wherein the time interval between the historical time period and the current time period does not exceed a preset time threshold.

[0011] Preferably, the energy efficiency index set is constructed by the following steps:

[0012] Based on the historical energy efficiency data of the residential user group in the area, determining the types of all energy-consuming devices in the residential user group in the area;

[0013] Determine, according to the type of each of the energy-consuming devices, a device dynamic energy efficiency index corresponding to each of the energy-consuming devices;

[0014] Based on the user static data in the historical energy efficiency data, the correlation between each user static data and the user energy efficiency is calculated by using the Spearman rank correlation coefficient, and the type of user static data with a correlation greater than a threshold is used as a user static indicator;

[0015] The energy efficiency indicator set is constructed based on the dynamic energy efficiency indicators of each device and the static indicators of each user.

[0016] Preferably, after determining the device dynamic energy efficiency index corresponding to each of the energy-consuming devices, the method further includes:

[0017] Based on each of the dynamic energy efficiency indicators of the equipment, and according to the historical energy efficiency data of the resident user group in the area, determining a number of subordinate influencing items that affect the value of the dynamic energy efficiency indicator of the equipment;

[0018] The subordinate impact items include one or more of the following:

[0019] Standard value item for daily usage time of equipment per population, standard value item for daily usage time of equipment per area, standard value item for equipment power consumption per population, standard value item for equipment power consumption per area, daily usage times of equipment item, and equipment activation condition item.

[0020] Preferably, the energy efficiency index set based on the pre-constructed regional resident user group, obtaining the value of each index in the energy efficiency index set in the historical period from the historical energy efficiency data of the regional resident user group, includes:

[0021] Based on each energy-consuming device, obtaining the values ​​of several subordinate impact items in a historical period and the values ​​of the static indicators of each user in a historical period from the historical energy efficiency data of the residential user group in the area;

[0022] Based on the equipment dynamic energy efficiency index of each of the energy-consuming equipment, the values ​​of several subordinate influencing items of the equipment dynamic energy efficiency index in the historical period are used as input, and the set equipment energy efficiency score of the equipment dynamic energy efficiency index is used as output to construct an equipment decision unit;

[0023] Adding slack variables to the equipment decision unit, and obtaining weights of several subordinate influencing items through a data envelopment analysis-slack measurement model;

[0024] Based on the weight of each of the subordinate influencing items and the value of each of the subordinate influencing items in the historical period, a weighted sum is performed to obtain the value of the equipment dynamic energy efficiency index of the energy-consuming equipment in the historical period.

[0025] Preferably, the weight of each indicator in the energy efficiency indicator set is obtained by using a data envelopment analysis-relaxation measurement model based on the value of each indicator in the historical period and the set total energy efficiency score of the regional resident user group, including:

[0026] The values ​​of the indicators in the historical period are used as input, and the set total energy efficiency score of the residential user group in the area is used as output to construct a decision unit; wherein the average total energy consumption of the residential user group in the area is used as the initial set total energy efficiency score;

[0027] A slack variable is added to the decision unit, and the weight of each indicator in the energy efficiency indicator set is obtained through a data envelopment analysis-relaxation measurement model.

[0028] Preferably, after obtaining the total energy efficiency score of the residential user in the current period, the method further includes:

[0029] The total energy efficiency scores of all residential users in the residential user group in the area in the current period are summed up and averaged to obtain the average value of the total energy efficiency score;

[0030] The average value of the total energy efficiency score is used as the set total energy efficiency score for the comprehensive energy efficiency evaluation in the next period to obtain a new set total energy efficiency score;

[0031] The weights of the indicators are updated according to the newly set total energy efficiency score to obtain new weights of the indicators;

[0032] Based on the new weights of the indicators and the values ​​of the evaluation indicators in the next time period, the total energy efficiency score of the residential user in the next time period is recalculated.

[0033] Preferably, the weighted summation based on the weight of each evaluation index and the value of each evaluation index in the current period to obtain the total energy efficiency score of the residential user in the current period includes:

[0034] Based on the quantifiability of each evaluation indicator, each of the indicators is divided into quantifiable indicators and non-quantifiable indicators;

[0035] Based on each of the quantifiable indicators, determining the positive and negative influence of the quantifiable indicator on the user's energy efficiency;

[0036] According to the positive and negative influence of the quantifiable indicator, the value of the quantifiable indicator in the current period is normalized to obtain the score of the quantifiable indicator in the current period;

[0037] Based on each of the non-quantifiable indicators, a value of the non-quantifiable indicator is obtained by a fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period;

[0038] Based on the weight of each evaluation indicator, the scores of each evaluation indicator in the current time period are weighted and summed to obtain the total energy efficiency score of the residential user in the current time period.

[0039] Preferably, the weighted summation based on the weight of each evaluation index and the value of each evaluation index in the current period to obtain the total energy efficiency score of the residential user in the current period includes:

[0040] Based on the quantifiability of each evaluation indicator, each of the indicators is divided into quantifiable indicators and non-quantifiable indicators;

[0041] Based on each of the quantifiable indicators, determining the positive and negative influence of the quantifiable indicator on the user's energy efficiency;

[0042] According to the positive and negative influence of the quantifiable indicator, the value of the quantifiable indicator in the current period is normalized to obtain the score of the quantifiable indicator in the current period;

[0043] Based on each of the non-quantifiable indicators, a value of the non-quantifiable indicator is obtained by a fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period;

[0044] Based on the weights of the evaluation indicators, weighted sum of the scores of the evaluation indicators in the current period is performed to obtain a weighted sum of the scores;

[0045] The scores of the evaluation indicators of the resident users in the current period are summed to obtain the sum of the scores of the current period; the scores of the evaluation indicators of the resident users in the historical period are summed to obtain the sum of the scores of the historical period, wherein the calculation method of the scores of the evaluation indicators of the historical period and the current period is the same;

[0046] Subtract the score sum of the current period from the score sum of the historical period to obtain the trend score of the resident user;

[0047] The weighted sum of the scores is superimposed on the user trend score, and the superimposed result is used as the total energy efficiency score of the residential user in the current time period.

[0048] Based on the same inventive concept, the present invention also provides a comprehensive energy efficiency evaluation system for residential users, including:

[0049] A data acquisition module, for acquiring the value of each indicator in the energy efficiency indicator set in a historical period from the historical energy efficiency data of the regional resident user group based on a pre-constructed energy efficiency indicator set of the regional resident user group; the energy efficiency indicator set includes the equipment dynamic energy efficiency indicator of each energy-consuming equipment in the regional resident user group;

[0050] A weight acquisition module, for obtaining the weight of each of the indicators in the energy efficiency indicator set through a data envelopment analysis-relaxation measurement model based on the value of each of the indicators in the historical period and the set total energy efficiency score of the regional resident user group;

[0051] An indicator selection module is used to select, based on each residential user in the regional residential user group, several indicators corresponding to the residential user and its energy-consuming equipment from the energy efficiency indicator set as evaluation indicators, and select the weight of each evaluation indicator from the weights of each indicator;

[0052] An evaluation module is used to obtain the value of each evaluation indicator in the current time period from the current energy efficiency data of the residential user group in the area, and perform weighted summation based on the weight of each evaluation indicator and the value of each evaluation indicator in the current time period to obtain the total energy efficiency score of the residential users in the current time period, wherein the time interval between the historical time period and the current time period does not exceed a preset time threshold.

[0053] Preferably, the data acquisition module is specifically used for:

[0054] Based on the historical energy efficiency data of the residential user group in the area, determining the types of all energy-consuming devices in the residential user group in the area;

[0055] Determine, according to the type of each of the energy-consuming devices, a device dynamic energy efficiency index corresponding to each of the energy-consuming devices;

[0056] Based on the user static data in the historical energy efficiency data, the correlation between each user static data and the user energy efficiency is calculated by using the Spearman rank correlation coefficient, and the type of user static data with a correlation greater than a threshold is used as a user static indicator;

[0057] The energy efficiency indicator set is constructed based on the dynamic energy efficiency indicators of each device and the static indicators of each user.

[0058] Preferably, the data acquisition module is further specifically used for:

[0059] Based on each of the dynamic energy efficiency indicators of the equipment, and according to the historical energy efficiency data of the resident user group in the area, determining a number of subordinate influencing items that affect the value of the dynamic energy efficiency indicator of the equipment;

[0060] The subordinate impact items include one or more of the following:

[0061] Standard value item for daily usage time of equipment per population, standard value item for daily usage time of equipment per area, standard value item for equipment power consumption per population, standard value item for equipment power consumption per area, daily usage times of equipment item, and equipment activation condition item.

[0062] Preferably, the data acquisition module is further specifically used for:

[0063] Based on each energy-consuming device, obtaining the values ​​of several subordinate impact items in a historical period and the values ​​of the static indicators of each user in a historical period from the historical energy efficiency data of the residential user group in the area;

[0064] Based on the equipment dynamic energy efficiency index of each of the energy-consuming equipment, the values ​​of several subordinate influencing items of the equipment dynamic energy efficiency index in the historical period are used as input, and the set equipment energy efficiency score of the equipment dynamic energy efficiency index is used as output to construct an equipment decision unit;

[0065] Adding slack variables to the equipment decision unit, and obtaining weights of several subordinate influencing items through a data envelopment analysis-slack measurement model;

[0066] Based on the weight of each of the subordinate influencing items and the value of each of the subordinate influencing items in the historical period, a weighted sum is performed to obtain the value of the equipment dynamic energy efficiency index of the energy-consuming equipment in the historical period.

[0067] Preferably, the weight acquisition module is specifically used for:

[0068] The values ​​of the indicators in the historical period are used as input, and the set total energy efficiency score of the residential user group in the area is used as output to construct a decision unit; wherein the average total energy consumption of the residential user group in the area is used as the initial set total energy efficiency score;

[0069] A slack variable is added to the decision unit, and the weight of each indicator in the energy efficiency indicator set is obtained through a data envelopment analysis-relaxation measurement model.

[0070] Preferably, the evaluation module is also used for:

[0071] The total energy efficiency scores of all residential users in the residential user group in the area in the current period are summed up and averaged to obtain the average value of the total energy efficiency score;

[0072] The average value of the total energy efficiency score is used as the set total energy efficiency score for the comprehensive energy efficiency evaluation in the next period to obtain a new set total energy efficiency score;

[0073] The weights of the indicators are updated according to the newly set total energy efficiency score to obtain new weights of the indicators;

[0074] Based on the new weights of the indicators and the values ​​of the evaluation indicators in the next time period, the total energy efficiency score of the residential user in the next time period is recalculated.

[0075] Preferably, the evaluation module is specifically used for:

[0076] Based on the quantifiability of each evaluation indicator, each of the indicators is divided into quantifiable indicators and non-quantifiable indicators;

[0077] Based on each of the quantifiable indicators, determining the positive and negative influence of the quantifiable indicator on the user's energy efficiency;

[0078] According to the positive and negative influence of the quantifiable indicator, the value of the quantifiable indicator in the current period is normalized to obtain the score of the quantifiable indicator in the current period;

[0079] Based on each of the non-quantifiable indicators, a value of the non-quantifiable indicator is obtained by a fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period;

[0080] Based on the weight of each evaluation indicator, the scores of each evaluation indicator in the current time period are weighted and summed to obtain the total energy efficiency score of the residential user in the current time period.

[0081] Preferably, the evaluation module is specifically used for:

[0082] Based on the quantifiability of each evaluation indicator, each of the indicators is divided into quantifiable indicators and non-quantifiable indicators;

[0083] Based on each of the quantifiable indicators, determining the positive and negative influence of the quantifiable indicator on the user's energy efficiency;

[0084] According to the positive and negative influence of the quantifiable indicator, the value of the quantifiable indicator in the current period is normalized to obtain the score of the quantifiable indicator in the current period;

[0085] Based on each of the non-quantifiable indicators, a value of the non-quantifiable indicator is obtained by a fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period;

[0086] Based on the weights of the evaluation indicators, weighted sum of the scores of the evaluation indicators in the current period is performed to obtain a weighted sum of the scores;

[0087] The scores of the evaluation indicators of the resident users in the current period are summed to obtain the sum of the scores of the current period; the scores of the evaluation indicators of the resident users in the historical period are summed to obtain the sum of the scores of the historical period, wherein the calculation method of the scores of the evaluation indicators of the historical period and the current period is the same;

[0088] Subtract the score sum of the current period from the score sum of the historical period to obtain the trend score of the resident user;

[0089] The weighted sum of the scores is superimposed on the user trend score, and the superimposed result is used as the total energy efficiency score of the residential user in the current time period.

[0090] Based on the same inventive concept, the present invention also provides a computer device, including: one or more processors;

[0091] A memory for storing one or more programs;

[0092] When the one or more programs are executed by the one or more processors, a comprehensive energy efficiency evaluation method for residential users as described above is implemented.

[0093] Based on the same inventive concept, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed, it implements the comprehensive energy efficiency evaluation method for residential users as described above.

[0094] Compared with the closest prior art, the present invention has the following beneficial effects:

[0095] The present invention provides a comprehensive energy efficiency evaluation method, system, device and medium for residential users, including an energy efficiency index set based on a pre-constructed regional residential user group, obtaining the value of each indicator in the energy efficiency index set in a historical period from the historical energy efficiency data of the regional residential user group; the energy efficiency index set includes the equipment dynamic energy efficiency index of each energy-consuming device in the regional residential user group; based on the value of each indicator in the historical period and the set total energy efficiency score of the regional residential user group, the weight of each indicator in the energy efficiency index set is obtained through a data envelopment analysis-relaxation measurement model; based on each residential user in the regional residential user group, a number of indicators corresponding to the residential user and its energy-consuming equipment are selected from the energy efficiency index set as evaluation indicators, and the weight of each evaluation indicator is selected from the weights of each evaluation indicator; the current energy efficiency data of the regional residential user group are obtained for each evaluation in the current period. The value of the indicator is weighted and summed based on the weight of each evaluation indicator and the value of each evaluation indicator in the current time period to obtain the total energy efficiency score of the residential user in the current time period, wherein the time interval between the historical time period and the current time period does not exceed the preset time threshold; the method and system calculate the weight of the indicator by using the value of the indicator in the historical time period, so that the weight of the indicator can be dynamically adjusted over time to adapt to the importance of the indicator that changes over time; this dynamic adjustment mechanism ensures that the evaluation method can flexibly respond to changes in the influence of different indicators and maintain the timeliness and adaptability of the evaluation results; in addition, through the selection of evaluation indicators, the comprehensive energy efficiency evaluation can be adaptively adjusted for different users to ensure that the scores of all residential users obtained based on the evaluation indicators are fair and reasonable. This adaptive adjustment not only improves the personalization of the evaluation process, but also enhances the fairness and credibility of the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Figure 1 A schematic diagram of a comprehensive energy efficiency evaluation method for residential users provided by the present invention;

[0097] Figure 2 A schematic diagram of an energy efficiency evaluation system architecture provided by the present invention;

[0098] Figure 3 A schematic diagram showing the relationship between the air conditioner activation temperature threshold, temperature and air conditioner energy consumption provided by the present invention;

[0099] Figure 4 A schematic diagram of a population standard value curve of air conditioning power consumption provided by the present invention;

[0100] Figure 5 A schematic diagram of the data envelopment analysis-relaxation measure model analysis process provided by the present invention;

[0101] Figure 6 A schematic diagram of the structure of a comprehensive energy efficiency evaluation system for residential users provided by the present invention;

[0102] Figure 7 The present invention provides a schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0103] The specific implementation modes of the present invention are further described in detail below with reference to the accompanying drawings.

[0104] Example 1

[0105] The present invention provides a comprehensive energy efficiency evaluation method for residential users, such as Figure 1 As shown, including:

[0106] S1. Based on the pre-constructed energy efficiency indicator set of the regional residential user group, the value of each indicator in the energy efficiency indicator set in the historical period is obtained from the historical energy efficiency data of the regional residential user group; the energy efficiency indicator set includes the equipment dynamic energy efficiency indicator of each energy-consuming equipment in the regional residential user group;

[0107] S2. Based on the values ​​of each indicator in the historical period and the set total energy efficiency score of the regional resident user group, the weights of each indicator in the energy efficiency indicator set are obtained through the data envelopment analysis-relaxation measurement model;

[0108] S3. Based on each residential user in the regional residential user group, select several indicators corresponding to the residential user and its energy-consuming equipment from the energy efficiency indicator set as evaluation indicators, and select the weight of each evaluation indicator from the weights of each indicator;

[0109] S4. Obtain the value of each evaluation index in the current period from the current energy efficiency data of the regional residential user group, perform weighted summation based on the weight of each evaluation index and the value of each evaluation index in the current period, and obtain the total energy efficiency score of the residential users in the current period, wherein the time interval between the historical period and the current period does not exceed the preset time threshold.

[0110] In this embodiment, after the total energy efficiency score of the residential user in the current period is obtained in the above S4, the following steps are also included:

[0111] The total energy efficiency scores of all residential users in the regional residential user group in the current period are summed up and averaged to obtain the average value of the total energy efficiency score;

[0112] The average value of the total energy efficiency score is used as the set total energy efficiency score for the comprehensive energy efficiency evaluation in the next period to obtain a new set total energy efficiency score;

[0113] Update the weight of each indicator according to the newly set total energy efficiency score to obtain a new weight of each indicator;

[0114] Based on the new weights of each indicator and the values ​​of each evaluation indicator in the next period, the total energy efficiency score of the residential user in the next period is recalculated.

[0115] Considering that most existing energy efficiency evaluation index systems are mainly aimed at large-scale buildings such as industrial, commercial or public buildings, the energy efficiency evaluation of residential users lacks sufficient detail and accuracy. This has led to a relatively insufficient research on residential energy efficiency evaluation, which cannot accurately reflect the actual energy use and efficiency of residential users. Secondly, the existing technology often sets up different index systems for different user groups when evaluating energy efficiency, and lacks a set of index systems that can adapt to the actual situation of users. This fixed index system cannot flexibly respond to user needs and environmental changes, which limits the universality and flexibility of the evaluation method. In addition, the importance of each indicator affecting energy efficiency may change over time, but the existing evaluation methods often cannot achieve dynamic adaptation and cannot timely reflect the changes in the importance of indicators, thus affecting the accuracy and timeliness of the evaluation results. In summary, the existing energy efficiency evaluation technology has obvious deficiencies in the detail of resident energy efficiency evaluation, the adaptability of the index system, and the dynamic adaptability of the evaluation method. In order to improve the scientificity and practicality of energy efficiency evaluation, it is necessary to develop more detailed, flexible and dynamically adaptable energy efficiency evaluation methods to more accurately reflect the energy efficiency of different user groups and provide more effective decision support for energy conservation and environmental protection. The present invention calculates the weight of the indicator by using the value of the indicator in the historical period. As time goes by, the total energy efficiency score set will also change accordingly, so that the weight of the indicator can be dynamically adjusted over time to adapt to the importance of the indicator that changes over time; this dynamic adjustment mechanism ensures that the evaluation method can flexibly respond to changes in the influence of different indicators and maintain the timeliness and adaptability of the evaluation results; in addition, through the selection of evaluation indicators, the comprehensive energy efficiency evaluation can be adaptively adjusted for different users to ensure that the scores of all residential users obtained based on the evaluation indicators are fair and reasonable. This adaptive adjustment not only improves the personalization of the evaluation process, but also enhances the fairness and credibility of the evaluation results.

[0116] The comprehensive energy efficiency evaluation method for residential users of the present invention is based on a comprehensive energy efficiency evaluation index system for residential users. The establishment process of the comprehensive energy efficiency evaluation index system for residential users is mainly divided into four steps: index selection, preprocessing, weight evaluation and scoring method design. Figure 2As shown in the figure, in terms of indicator selection, a multi-level evaluation index combining dynamic and static is adopted, which is divided into static index, dynamic index and trend index. The core part is the dynamic index. A set of secondary indicators is designed for each energy-consuming equipment for evaluation, and finally all indicators are summarized to obtain the user's comprehensive energy efficiency. The preprocessing mainly includes two steps: impact judgment and data normalization. The weight evaluation method uses the DEA-SBM (Data Envelopment Analysis based-Slack Based Measure) model for evaluation, and the scoring method uses multi-level fuzzy comprehensive evaluation.

[0117] Specifically, when selecting indicators, considering that the comprehensive energy efficiency of users is related to the basic background information of the user's family and the energy consumption of users during actual use, a multi-level evaluation indicator combining dynamic and static is adopted in the above S1, and static indicators (i.e., user static indicators) used to describe user static information and dynamic indicators (i.e., equipment dynamic energy efficiency indicators) reflecting user electricity usage habits are set up respectively, and energy efficiency evaluation is performed on each device of the user, so as to obtain more detailed and accurate evaluation results. The trend indicator (i.e., trend score) reflecting the trend of user energy efficiency changes does not involve the above indicator weight calculation.

[0118] Specifically, in this embodiment, when constructing the energy efficiency indicator set in the above S1, it may include:

[0119] Based on the historical energy efficiency data of the regional residential user group, determine the types of all energy-consuming devices in the regional residential user group;

[0120] According to the type of each energy-consuming device, determine the equipment dynamic energy efficiency index corresponding to each energy-consuming device;

[0121] Based on the user static data in the historical energy efficiency data, the correlation between each user static data and the user energy efficiency is calculated by the Spearman rank correlation coefficient, and the type of user static data with a correlation greater than a threshold is used as the user static indicator;

[0122] An energy efficiency indicator set is constructed based on the dynamic energy efficiency indicators of each device and the static indicators of each user.

[0123] In this embodiment, after determining the device dynamic energy efficiency index corresponding to each energy-consuming device, the following is further included:

[0124] Based on each device dynamic energy efficiency index, several subordinate influencing items that affect the value of the device dynamic energy efficiency index are determined according to the historical energy efficiency data of the regional residential user group;

[0125] Subordinate influence items include one or more of the following:

[0126] Standard value item for daily usage time of equipment per population, standard value item for daily usage time of equipment per area, standard value item for equipment power consumption per population, standard value item for equipment power consumption per area, daily usage times of equipment item, and equipment activation condition item.

[0127] For example, static indicators provide basic background information of the user's home, including house area, population, and detailed information of electrical equipment (equipment list), such as equipment category, quantity, power, and energy efficiency level. This information helps to assess the user's energy demand and energy usage structure.

[0128] Dynamic indicators focus on the energy consumption of users during actual use. By recording the usage time, usage frequency and power consumption of each device, we can understand the specific electricity usage behavior of users. Furthermore, considering the impact of family population and house area on energy consumption, the population standard value and area standard value are calculated for usage time and power consumption respectively, which helps to more accurately evaluate the energy efficiency of the family.

[0129] Since this method is data-driven, its specific implementation mainly depends on data analysis. The required data include: user data, such as the user's house area, family population, home address, home appliance equipment list (including equipment type, quantity, power, etc.); equipment usage history data, including the start and stop time, startup time, average power, power consumption, etc. of each device; meteorological data, including temperature, humidity and weather information in the user's area.

[0130] The data involved are analyzed. For user data, the Spearman rank correlation coefficient is used to calculate the correlation between each type of data and user energy efficiency, and a threshold is set. The part above the threshold is used as a static indicator, that is, factors that have a significant impact on user energy efficiency are used as static indicators, such as house area, family population, etc. The list of household appliances is also used as part of the static indicator, which includes secondary indicators such as the number and power of each type of equipment.

[0131] For dynamic indicators, each type of equipment is designed separately. Taking air conditioners as an example, the secondary indicators (i.e., lower-level influencing items) are designed to include: daily usage time, number of uses, power consumption, and air conditioner activation temperature threshold. When the ambient temperature reaches or exceeds the air conditioner activation temperature threshold, users tend to activate air conditioners, such as Figure 3 As shown, it shows the method of obtaining the secondary indicator of the air conditioner activation temperature threshold, and the relationship between the user's air conditioner energy consumption and the real-time temperature is counted. The temperature value corresponding to the point where the energy consumption starts to rise from 0 is the user's air conditioner activation temperature threshold.

[0132] The correlation analysis between the use time and power consumption of air conditioners and static indicators shows that the use time and power consumption of air conditioners are greatly affected by population and housing area. Therefore, the population standard value and area standard value are taken for the daily use time and power consumption, respectively. Figure 4 As shown in the figure, taking the population standard value of air conditioning power consumption as an example, the relationship between population and air conditioning power consumption is fitted by linear or nonlinear regression through historical data of different users to obtain the air conditioning energy consumption-population relationship model, and the air conditioning energy consumption value when the population is 1 is obtained as the population standard value of air conditioning power consumption. Since the use time and power consumption of air conditioners are not in simple positive proportion to the population and area, the actual relationship is obtained through linear or nonlinear fitting, and then the use time and power consumption per unit population and per unit area are estimated as part of the secondary indicators in the indicator system.

[0133] In recent years, the application of data envelopment analysis (DEA) in energy efficiency evaluation has been increasing, especially in the context of environmental regulation. At present, foreign literature research mainly focuses on the level of total factor energy efficiency under environmental regulation. The main results are Sueyoshi et al. and Yuan et al. Their models use the traditional DEA energy efficiency evaluation method to rank coal-fired power plants, but do not fully rank all decision-making units (DMUs). The Superefficiency model proposed by Andersen et al. can solve the ranking problem between effective DMUs. The super-efficiency model excludes the DMU from the set by borrowing the linear combination of the input and output of other DMUs. Borrow the linear combination of the input and output of other DMUs for replacement. In fact, when evaluating the efficiency of effective units, the model removes the constraint that the efficiency index is equal to 1, thereby obtaining an efficiency value greater than or equal to 1, which is called the super-efficiency value. Therefore, this method solves the same efficiency comparison analysis problem as the effective DMU and has no effect on the invalid decision-making unit. Therefore, the effective DMU can be ranked. Xu Zhiwei summarized the current status of research on production efficiency in energy and other industries under foreign environmental regulations. Margi et al. studied the relationship between the intensity of environmental noise regulation and the efficiency of the transportation industry in Italy through DEA ​​inefficiency decomposition, and found that strong regulation is conducive to improving efficiency. Li Xiaofei used the Bootstrap-DEA self-bootstrapping data envelopment analysis method to quantify the total factor energy efficiency of relevant provinces, and then explored the influencing factors of total factor energy efficiency. Wang et al. used the fuzzy comprehensive evaluation method to establish a comprehensive evaluation system for energy-saving and emission reduction technologies in tobacco enterprises. Jing et al. used a fuzzy multi-criteria decision-making model combining grey correlation analysis and combined weighting method to evaluate the combined heat and power system. Li et al. used the comprehensive analytic hierarchy process (AHP, Analytic Hierarchy Process) and fuzzy comprehensive evaluation method to evaluate the operating level of high-energy-consuming equipment.

[0134] Data envelopment analysis (DEA) is a mathematical method for evaluating production efficiency by determining the efficiency of a set of decision-making units (DMUs) to identify which units are efficient and which are inefficient. Unlike traditional production function analysis, DEA does not rely on a pre-set functional form, but uses linear programming to determine the most efficient production frontier. In DEA, the inputs and outputs of each decision-making unit are used to construct a multidimensional space where the efficient frontier is defined by those decision-making units that produce the maximum output for a given input. By comparing the distance of each unit from this frontier, its relative efficiency can be evaluated.

[0135] The DEA algorithm process usually includes the following steps: first, determine the input and output vectors of each decision-making unit; then, use linear programming to determine the effective production frontier, which usually involves solving a series of linear programming problems, each of which aims to maximize the efficiency of a specific decision-making unit; then, based on the results of linear programming, determine the efficiency score of each decision-making unit, with a decision-making unit with a score of 1 being on the effective frontier, and a decision-making unit with a score less than 1 being inside the frontier; finally, the analysis results can be used to identify the causes of inefficiency and propose improvement measures.

[0136] The advantages of DEA are its flexibility and applicability. It can handle situations with multiple inputs and outputs and does not require strict assumptions about the production process. In addition, DEA is able to provide specific suggestions on how to improve efficiency because it can identify which inputs need to be reduced or which outputs can be increased. However, DEA also has some limitations. For example, it is very sensitive to the quality of the data, and any errors or inconsistencies in the data may affect the accuracy of the evaluation results. In addition, DEA usually cannot provide a specific path on how to reach an efficient state from the current state. It provides more of a comparative benchmark for efficiency.

[0137] Taking into account the impact of slack variables and unexpected outputs, the DEA-SBM model adds slack variables SBM to the traditional DEA method. SBM is a non-radial efficiency evaluation method used in DEA. The advantage of this method is that it can directly identify and quantify the excess of input and the shortage of output. In the evaluation of production efficiency, we call the gap between input and output and the production frontier the slack value, which directly reflects the efficiency level of the decision-making unit.

[0138] Taking into account the impact of family population and housing area on energy consumption, the present invention adopts a bottom-up approach in the specific weight evaluation, defines the equipment dynamic energy efficiency index and the user static index as the first-level index, and defines the subordinate influence item as the second-level index. The weight of the second-level index is first evaluated to obtain the weight of the subordinate influence item, and then the corresponding first-level index value is obtained according to the weight of the subordinate influence item, and the first-level index with the second-level index is further weighted.

[0139] Specifically, in this embodiment, when obtaining the value of each indicator in the energy efficiency indicator set in the historical period in the above S1, it may include:

[0140] Based on each energy-consuming device, the values ​​of several subordinate influencing items and the values ​​of static indicators of each user in the historical period are obtained from the historical energy efficiency data of the regional residential user group; the value of each user static indicator is obtained according to the quantifiability of the user static indicator. For quantifiable user static indicators, their values ​​can be directly obtained from historical energy efficiency data; for non-quantifiable user static indicators, their values ​​need to be based on historical energy efficiency data and obtained according to fuzzy comprehensive algorithm;

[0141] Based on the equipment dynamic energy efficiency index of each energy-consuming equipment, the equipment decision unit is constructed by taking the values ​​of several subordinate influencing items of the equipment dynamic energy efficiency index in the historical period as input and taking the set equipment energy efficiency score of the equipment dynamic energy efficiency index as output;

[0142] Add slack variables to the equipment decision-making unit and obtain the weights of several subordinate influencing items through the data envelopment analysis-slack measurement model;

[0143] Based on the weight of each subordinate influencing item and the value of each subordinate influencing item in the historical period, a weighted sum is performed to obtain the value of the equipment dynamic energy efficiency index of the energy-consuming equipment in the historical period.

[0144] Among them, the total energy consumption value of the energy-consuming equipment is used as the initial setting equipment energy efficiency score, and the subsequent setting equipment energy efficiency score is based on the value of the equipment dynamic energy efficiency index obtained in the previous period as the setting equipment energy efficiency score of the current period, so that the weight of each subordinate influencing item can change over time;

[0145] Specifically, the DEA-SBM model analysis process is as follows: Figure 5As shown, first determine the goal of model evaluation. For this method, the goal of DEA-SBM model evaluation is the impact of various indicators of the comprehensive energy efficiency evaluation index system for residential users on the final score; secondly, select the decision unit. The decision unit of this method is the energy efficiency score of each device and the comprehensive energy efficiency score of the user; the input and output are the value of each indicator and the score result, respectively. After collecting multiple sets of input-output data, select the DEA model. This method uses the DEA-SBM model and adds slack variables to the traditional DEA model based on linear programming; finally, solve the calculation model to obtain the analysis and evaluation results, that is, the degree of influence of each input item on the output item.

[0146] Specifically, the secondary indicators include the equipment list in the static indicators and the relevant indicators of each type of equipment in the dynamic indicators. Take the air conditioner in the dynamic indicators as an example: First, construct the equipment decision unit (DMU) and name it air conditioner. Its input is the standard value of daily usage time population, standard value of daily usage time area, standard value of power consumption population, standard value of power consumption area, number of times of use, and air conditioner activation temperature threshold. The output value should be the user's air conditioner energy efficiency score, that is, the set equipment energy efficiency score. However, before the evaluation index system is established, the user's air conditioner energy efficiency score cannot be obtained. Because the energy efficiency of the air conditioner is proportional to the total energy consumption value of the air conditioner when the user's basic information remains unchanged, the total energy consumption value of the air conditioner is used as the output value when the equipment energy efficiency index value of the air conditioner is first obtained. As the influence of various indicators on the energy efficiency level of residential users will change over time, the weights should be adjusted dynamically. Each time the evaluation is performed, the score of each indicator and the final energy efficiency score are recorded, and the weight evaluation is re-performed by the above method every month through all the data of the month. Since the energy efficiency score data is available at this time, the total energy consumption is no longer used as the output instead of it.

[0147] Secondly, collect multiple sets of corresponding input-output values, add slack variables, and calculate them together with DMU through the DEA-SBM model to obtain the efficiency value of each type of input value, that is, the efficiency value of each type of subordinate influence item. The efficiency value reflects the degree of influence of each input on the output, and the value is 0-1. The closer to 1, the greater the influence. Since the sum of the efficiency values ​​obtained by the DEA-SBM model is not 1, the efficiency values ​​of all input items are normalized, and the result is the weight of the secondary indicator, that is, the weight of the subordinate influence item. For example, assuming that the efficiency values ​​of the three indicators are 0.4, 0.7, and 0.9 respectively, directly using them as the weights of the corresponding indicators will result in the sum of the weights of the three indicators not being 1, so normalization is performed, the above three efficiency values ​​are scaled proportionally, and their sum is stipulated to be 1, and the final weights of the three indicators are: 0.2, 0.35, and 0.45 respectively.

[0148] The first-level indicators include user information in static indicators, the score of the equipment list, and the energy efficiency score of each type of equipment in dynamic indicators. The weight evaluation is also carried out according to the above method.

[0149] In this embodiment, when obtaining the weights of each indicator in the energy efficiency indicator set, that is, each primary indicator in the above S2, it may include:

[0150] The values ​​of each indicator in the historical period are used as input, and the set total energy efficiency score of the regional residential user group is used as output to construct a decision unit; wherein the average total energy consumption of the regional residential user group is used as the initial set total energy efficiency score;

[0151] Slack variables are added to the decision-making unit, and the weights of each indicator in the energy efficiency index set are obtained through the data envelopment analysis-relaxation measurement model.

[0152] It should be noted that, taking the weight of the dynamic energy efficiency index of air-conditioning equipment as an example, this weight is applicable to all users in the regional residential user group, that is, the weight of each indicator is applicable to all users in the regional residential user group. If a special weight is set for each user, the scores of different users will not be comparable. Therefore, the same set of indicator weights should be used in the regional residential user group to reflect the energy efficiency of each residential user through the comparison of their comprehensive energy efficiency scores.

[0153] Specifically, the principle of the DEA-SBM model is as follows:

[0154] Assume there are n decision making units (DMUs), each with three vectors, and the input vector x∈R m , expected output vector y g ∈R S ; Among them, R m , R S are the input vector set and the expected output vector set, respectively, and m is the total number of input vectors; in this method, taking the weight of each indicator in the energy efficiency indicator set obtained by the data envelopment analysis-relaxation measurement model as an example, the input vector is the value of each indicator in the historical period, and the expected output vector is the set total energy efficiency score of the regional residential user group;

[0155] Define input matrix X and expected output matrix Y g X=(x ij )∈R m×n , Among them, x ij represents the i-th input used by the j-th decision unit, represents the rth expected output of the jth decision unit, i = 1, ..., m; j = 1, ..., n; r = 1, ..., S, S is the total number of expected output vectors, Rm×n Represents the input vector R from the first decision unit to the nth decision unit m The matrix composed of S×n Represents the matrix consisting of the expected output vectors from the 1st decision unit to the nth decision unit.

[0156] Based on the actual input-output, assuming X>0, Y g >0, the production possibility set is P, which is all the combinations of expected and undesired outputs produced by the inputs of n decision-making units, and can be defined as:

[0157] P={(x,y g )|x≥Xλ,y g ≥Y g λ,λ≥0};

[0158] Among them, P is the production possibility set, which represents all the combinations of expected and unexpected outputs that the decision-making unit can achieve under a given input combination, and λ is the weight vector.

[0159] The model of the SBM-desirable expected output of the jth DMU is as follows:

[0160]

[0161] Among them, ρ* is the efficiency value, λ is the weight vector, and x j is the input vector of the jth DMU, ​​x j ={x 1j ,...,x mj},S - is the input relaxation vector, and are the i-th and m-th elements of the input relaxation vector, S g is the expected output relaxation vector, is the rth element of the expected output relaxation vector; Represents the output vector of the jth decision unit;

[0162] For this method, there is only one expected output, so the SBM-desirable model is:

[0163]

[0164] When ρ*=1, that is, S - =0, S g =0, the decision unit is effective;

[0165] When ρ*<1, that is, S - , S gWhen at least one of them is not zero, the decision-making unit is invalid and the output of the input needs to be improved. At the same time, since the model is a nonlinear programming model, it can be converted into a linear programming model according to the Charnes-Cooper transformation method.

[0166] In terms of evaluation index preprocessing, it is mainly divided into two aspects: impact judgment and data normalization. Among them, impact judgment refers to the potential impact and relationship of evaluation indicators on the comprehensive energy efficiency of residential users. All selected quantifiable indicators are divided into two groups: indicators that have a positive impact on the goal of achieving higher energy efficiency for residential users and indicators that have a negative impact.

[0167] In order to understand whether an indicator is positively or negatively correlated with the comprehensive energy efficiency of residential users, the impact of each indicator on the comprehensive energy efficiency of residential users is evaluated by the following rule of thumb: If the added value of an indicator accelerates the improvement of the comprehensive energy efficiency of residential users, the indicator has a positive impact on the comprehensive energy efficiency of residential users. On the other hand, if the added value of an indicator hinders the improvement of the comprehensive energy efficiency of residential users, the indicator has a negative impact on the comprehensive energy efficiency of residential users. Classification according to the impact of indicators on the comprehensive energy efficiency of residential users is necessary because it determines the calculation method of data normalization in the subsequent steps.

[0168] For quantifiable evaluation indicators, the value obtained after the normalization process in the above preprocessing can be used as the score value of the indicator; for non-quantifiable evaluation indicators, such as the device list indicator in the user static indicator, the fuzzy comprehensive evaluation method is used for scoring.

[0169] Fuzzy comprehensive evaluation uses the principles of fuzzy mathematics to comprehensively process evaluation indicators through fuzzy logic, allowing evaluators to give scores under uncertain or ambiguous conditions, thereby better reflecting the true situation of the evaluation object. The advantage of this method is that it can handle the uncertainty and ambiguity in the evaluation process and improve the accuracy and reliability of the evaluation. At the same time, fuzzy comprehensive evaluation can also transform the evaluator's subjective judgment into a more objective evaluation result through fuzzy mathematical tools such as membership function, thereby enhancing the scientificity and fairness of the evaluation. Therefore, in a complex evaluation system, the fuzzy comprehensive evaluation method has become an important evaluation tool due to its flexibility and adaptability.

[0170] Fuzzy comprehensive evaluation is a comprehensive evaluation method based on fuzzy mathematics, which uses the principle of fuzzy relationship synthesis to quantify some factors with unclear boundaries and difficult to measure. The essence of the domain X' is the function of X'→[0,1]. The first step of fuzzy evaluation is to determine the membership function For qualitative indicators, the four levels of "very high (VH), high (H), normal (M), and low (L)" are first assigned values ​​of f(1) = 1.0, f(2) = 0.75, f(3) = 0.5, and f(4) = 0.25, respectively, where f(x') is the assignment function of the x'th level.

[0171] Then, the expert’s feedback is also converted into a fuzzy number y uv ,y uv =[d(1) uv ,d(2) uv ,d(3) uv ,d(4) uv ], where d(x') uv It refers to the proportion of experts of different levels, that is, the proportion of experts who are rated as the x'th level on the u'th evaluation factor for the v'th evaluation object, x'=1, 2, 3, 4.

[0172] Based on the weighted average method, the membership degree r of the vth evaluation object of the qualitative indicator on the uth evaluation factor is uv The calculation is as follows:

[0173] Among them, U is the total number of evaluation factors, and V is the total number of evaluation objects;

[0174] Then the fuzzy relationship matrix R is expressed as:

[0175]

[0176] In the formula, r UV is the membership degree of the Vth evaluation object on the Uth evaluation factor.

[0177] Next, the weight matrix W and the fuzzy relationship matrix R are combined with a suitable fuzzy operator to obtain the evaluation result vector B.

[0178]

[0179] Among them, b1...b V represents the evaluation results of the 1st to the Vth evaluation objects; w U represents the weight of the Uth evaluation factor;

[0180] Finally, the best evaluation result selected according to the maximum membership principle is expressed as:

[0181]

[0182] Among them, b k represents the kth element in the evaluation result vector B, and br represents the best evaluation result, that is, the item with the largest value in the evaluation result vector B.

[0183] Since the types and quantities of electrical equipment owned by different users are not the same, it is impossible to directly use the cumulative method to calculate the final energy efficiency score. Therefore, before executing S4, in the above S3, based on each residential user in the regional residential user group, several indicators corresponding to the residential user and its energy-consuming equipment are selected from the energy efficiency indicator set as evaluation indicators, and the weight of each evaluation indicator is selected from the weight of each indicator;

[0184] The evaluation indicators include user static indicators and several equipment dynamic energy efficiency indicators. For the selection of several equipment dynamic energy efficiency indicators, in order to adapt to the different equipment conditions of different users, when the evaluation indicators were initially designed, the dynamic indicator S d The dynamic energy efficiency index of all common residential electrical equipment, i.e., energy-consuming equipment, is designed. The initial dynamic index is called the benchmark index scoring set S base :

[0185] S base ={s1,s2,…,s n'};

[0186] Among them, n' is the total number of types of residential electrical equipment in the region, that is, the total number of types of common energy-consuming equipment on the market. These total categories can cover various types of energy-consuming equipment in the regional residential user group. The area in the regional residential user group is the station area, and s n' Score the indicators of n' categories of energy-consuming devices. For each user, in the benchmark indicator scoring set S base Filter out all devices included in the user's device list as the user's device energy efficiency index scoring set S user .

[0187]

[0188] Where m' is the total number of user equipment categories, s i' 、s j' 、s m' The index scores of energy-consuming equipment of categories i', j', and m' are respectively used. Then, the equipment energy efficiency index score set S user The weights of the corresponding indicators in are normalized and used as the final weights of several equipment dynamic energy efficiency indicators in the current period, and then subsequent weighted processing is performed.

[0189] In this embodiment, in the above S4, a weighted sum is performed based on the weight of each evaluation index and the value of each evaluation index in the current period to obtain the total energy efficiency score of the residential user in the current period, which may include:

[0190] Based on the quantifiability of each evaluation indicator, each indicator is divided into quantifiable indicators and non-quantifiable indicators;

[0191] Based on each quantifiable indicator, determine the positive and negative impact of the quantifiable indicator on user energy efficiency;

[0192] According to the positive and negative influence of the quantifiable indicators, the values ​​of the quantifiable indicators in the current period are normalized to obtain the scores of the quantifiable indicators in the current period;

[0193] Based on each non-quantifiable indicator, the value of the non-quantifiable indicator is obtained through the fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period;

[0194] Based on the weight of each evaluation indicator, the scores of each evaluation indicator in the current period are weighted and summed to obtain the total energy efficiency score of the residential user in the current period.

[0195] Specifically, for each quantifiable indicator in the energy efficiency indicator set, the impact is first judged and all indicators are divided into two categories: positive impact and negative impact. Then, the maximum-minimum normalization is performed to convert all different scales of the indicator into a common scale, so that all different indicators are comparable.

[0196] Among them, in order to eliminate the ambiguity of indicators and obtain more consistent results, data normalization is necessary. Data normalization converts all different scales of indicators into a common scale, making all different indicators comparable. Therefore, after data normalization, all indicators are compatible with a common comprehensive index.

[0197] Common data normalization methods include minimum-maximum normalization, Z-score normalization, decimal calibration normalization, unit norm normalization, Euclidean norm normalization, etc. This method adopts minimum-maximum normalization.

[0198] Min-max normalization is a simple and intuitive data preprocessing technique that can adjust the numerical range of data to a fixed interval, usually (0,1). In this way, it retains the distribution characteristics of the original data, including the skewness of the data, so that the dynamic range of the data is effectively compressed. The advantage of this method is its flexibility, which can easily scale the data to any desired range, and because it is easy to implement and understand, it is compatible with a variety of machine learning algorithms and mathematical models. In addition, min-max normalization is sensitive to the relative size relationship of the data, making the results easy to interpret.

[0199] For the positive impact indicators, the following formula is used for normalization:

[0200]

[0201] For the negative impact indicator, the following formula is used for normalization:

[0202]

[0203] in, It is a normalized indicator that has a positive impact on the comprehensive energy efficiency of residential users. N - It is a normalized index that has a negative impact on the comprehensive energy efficiency of residential users. act is the actual value of a certain indicator for a specific user, I max is the maximum value of a certain indicator among all users, I min It is the minimum value of a certain indicator among all users.

[0204] The above trend indicators are used to reflect the changing trend of user energy efficiency levels and encourage users to save energy. Superimposing the weighted sum of scores with the user trend score can make the total energy efficiency score better reflect the trend changes.

[0205] In another possible implementation, the above S4 may also include:

[0206] Based on the quantifiability of each evaluation indicator, each indicator is divided into quantifiable indicators and non-quantifiable indicators;

[0207] Based on each quantifiable indicator, determine the positive and negative impact of the quantifiable indicator on user energy efficiency;

[0208] According to the positive and negative influence of the quantifiable indicators, the values ​​of the quantifiable indicators in the current period are normalized to obtain the scores of the quantifiable indicators in the current period;

[0209] Based on each non-quantifiable indicator, the value of the non-quantifiable indicator is obtained through the fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period;

[0210] Based on the weight of each evaluation indicator, the scores of each evaluation indicator in the current period are weighted and summed to obtain the weighted sum of the scores;

[0211] The scores of the evaluation indicators of the resident users in the current period are summed up to obtain the sum of the scores of the current period; the scores of the evaluation indicators of the resident users in the historical period are summed up to obtain the sum of the scores of the historical period, wherein the calculation method of the scores of the evaluation indicators of the historical period and the current period is the same;

[0212] Subtract the score sum of the current period from the score sum of the historical period to obtain the trend score of the resident user;

[0213] The weighted sum of the scores is superimposed with the user trend score, and the superimposed result is used as the total energy efficiency score of the residential user in the current period.

[0214] For example, the time interval between the historical period and the current period does not exceed the preset time threshold, where the preset time threshold is a monthly interval or a daily interval. For the trend index, i.e., the trend score, the sum of the user's static index and dynamic index scores for this month (or today) is used, and the sum of the static index and dynamic index scores for the previous month (or previous day) is subtracted, and then scaled by a preset multiple to represent the user's energy-saving trend. If the index is a positive number, it means that this month is more economical than last month, otherwise it means that this month is more wasteful than last month.

[0215] In this method, the user's total energy efficiency score S is composed of the static score S s , Dynamic Rating S d and trend score S t The dynamic scoring part is composed of a set of secondary evaluation indicators designed for each user's device. Since the types and quantities of electrical equipment owned by different users are different, the final energy efficiency score cannot be calculated directly by the cumulative method.

[0216] Therefore, before executing S4, in the above S3, based on each residential user in the regional residential user group, several indicators corresponding to the residential user and its energy-consuming equipment are selected from the energy efficiency indicator set as evaluation indicators, and the weight of each evaluation indicator is selected from the weights of each indicator;

[0217] Specifically, the equipment energy efficiency index scoring set S obtained above is used user , for the equipment energy efficiency index scoring set S user The weights of the corresponding indicators in the normalized process are used to obtain the final weights of several equipment dynamic energy efficiency indicators in the current period, and then compared with the static score S s Calculate the weighted sum and finally add it to the trend score S t By adding them together, we can get the user's total energy efficiency score S, which is expressed as:

[0218]

[0219] Among them, w userI is the weight of the index of the energy-consuming equipment of category I corresponding to the user's equipment energy efficiency index scoring set, I = i', j', ..., m', w b ase k is the weight of the index of the k-category energy-consuming equipment corresponding to the benchmark index scoring set, k = 1,...,n', w baseI is the weight of the indicator of energy-consuming equipment in category I corresponding to the benchmark indicator scoring set, is the sum of the weights of all indicators in the user's equipment energy efficiency indicator score set, w s is the weight of the static indicator, S userIThe index scores of energy-consuming equipment in category I in the user's equipment energy efficiency index scoring set. The adaptive evaluation index system thus obtained does not change the proportional relationship between the importance of each index, so it can achieve a fair and just evaluation effect for different users.

[0220] It should be noted that the calculation formula for the above user's total energy efficiency score S assumes that there is only one static indicator. When there are multiple static indicators, the weighted calculation of the static score is calculated in accordance with the weighted calculation form of the dynamic score.

[0221] In summary, in order to solve the problem that the accuracy, timeliness and universality of the existing comprehensive energy efficiency evaluation are not ideal, this method fully considers the electricity consumption characteristics of residential users. Compared with commercial buildings and industrial buildings, residential users have a smaller scale of electricity consumption, and their electricity usage habits have a more significant impact on energy efficiency. Therefore, in terms of indicator selection, this method adopts a more in-depth and detailed strategy, designed for residential users, and adopts a multi-level evaluation index combining dynamic and static. It not only focuses on overall energy consumption, but also expands the perspective to every device used by users in daily life, and evaluates the energy efficiency of each device of regional users, so as to obtain more detailed and accurate evaluation results. This method establishes a comprehensive set of secondary evaluation indicators for each device, which can carefully reflect the user's electricity usage habits. By collecting and analyzing the user's equipment usage data, the user's energy efficiency is accurately evaluated, ensuring the accuracy and reliability of the evaluation results.

[0222] This method is designed with dynamic weight adjustment. During the evaluation process, the system will record the score data of each indicator in real time, which will then be used to dynamically adjust the indicator weight to adapt to the changing importance of the indicator over time. This dynamic adjustment mechanism ensures that the evaluation system can flexibly respond to changes in the influence of different indicators and maintain the timeliness and adaptability of the evaluation results;

[0223] This method also designs a set of adaptive index adjustment methods to meet the personalized needs of different users. By selecting several evaluation indicators from the energy efficiency index set, the indicators that users do not have are eliminated, and the weights of the evaluation indicators are re-normalized to ensure that the evaluation index system is fair and reasonable for all users. This adaptive adjustment not only improves the personalization of the evaluation, but also enhances the fairness and credibility of the evaluation results.

[0224] This method is suitable for the evaluation of the comprehensive energy efficiency of residential households, especially in the face of different regions, different climatic conditions, and different living habits. It can more accurately reflect the actual situation of household energy consumption. This method is particularly suitable for areas that require personalized energy management strategies, such as densely populated urban areas, rural areas, or areas with significant seasonal changes. By dynamically adjusting the evaluation indicators, residents can be more effectively guided to save and optimize energy use, thereby achieving the goal of energy conservation and emission reduction without reducing the quality of life. In addition, this indicator system and evaluation method are also suitable for policymakers and energy management agencies to help them better understand residents' energy use patterns and formulate more scientific and reasonable energy policies and incentives.

[0225] Example 2

[0226] Based on the same inventive concept, the present invention also provides a comprehensive energy efficiency evaluation system for residential users, such as Figure 6 As shown, including:

[0227] A data acquisition module is used to obtain the value of each indicator in the energy efficiency indicator set in the historical period from the historical energy efficiency data of the regional resident user group based on the pre-constructed energy efficiency indicator set of the regional resident user group; the energy efficiency indicator set includes the equipment dynamic energy efficiency indicator of each energy-consuming equipment in the regional resident user group;

[0228] The weight acquisition module is used to obtain the weight of each indicator in the energy efficiency indicator set through the data envelopment analysis-relaxation measurement model based on the value of each indicator in the historical period and the set total energy efficiency score of the regional resident user group;

[0229] An indicator selection module is used to select, based on each residential user in the regional residential user group, several indicators corresponding to the residential user and its energy-consuming equipment from the energy efficiency indicator set as evaluation indicators, and to select the weight of each evaluation indicator from the weights of each indicator;

[0230] The evaluation module is used to obtain the value of each evaluation indicator in the current period from the current energy efficiency data of the regional residential user group, and perform weighted summation based on the weight of each evaluation indicator and the value of each evaluation indicator in the current period to obtain the total energy efficiency score of the residential users in the current period, wherein the time interval between the historical period and the current period does not exceed the preset time threshold.

[0231] In this embodiment, the data acquisition module is specifically used for:

[0232] Based on the historical energy efficiency data of the regional residential user group, determine the types of all energy-consuming devices in the regional residential user group;

[0233] According to the type of each energy-consuming device, determine the equipment dynamic energy efficiency index corresponding to each energy-consuming device;

[0234] Based on the user static data in the historical energy efficiency data, the correlation between each user static data and the user energy efficiency is calculated by the Spearman rank correlation coefficient, and the type of user static data with a correlation greater than a threshold is used as the user static indicator;

[0235] An energy efficiency indicator set is constructed based on the dynamic energy efficiency indicators of each device and the static indicators of each user.

[0236] In this embodiment, the data acquisition module is also specifically used for:

[0237] Based on each device dynamic energy efficiency index, several subordinate influencing items that affect the value of the device dynamic energy efficiency index are determined according to the historical energy efficiency data of the regional residential user group;

[0238] Subordinate influence items include one or more of the following:

[0239] Standard value item for daily usage time of equipment per population, standard value item for daily usage time of equipment per area, standard value item for equipment power consumption per population, standard value item for equipment power consumption per area, daily usage times of equipment item, and equipment activation condition item.

[0240] In this embodiment, the data acquisition module is also specifically used for:

[0241] Based on each energy-consuming device, the values ​​of several subordinate influencing items and the values ​​of static indicators of each user in the historical period are obtained from the historical energy efficiency data of the regional residential user group;

[0242] Based on the equipment dynamic energy efficiency index of each energy-consuming equipment, the equipment decision unit is constructed by taking the values ​​of several subordinate influencing items of the equipment dynamic energy efficiency index in the historical period as input and taking the set equipment energy efficiency score of the equipment dynamic energy efficiency index as output;

[0243] Add slack variables to the equipment decision-making unit and obtain the weights of several subordinate influencing items through the data envelopment analysis-slack measurement model;

[0244] Based on the weight of each subordinate influencing item and the value of each subordinate influencing item in the historical period, a weighted sum is performed to obtain the value of the equipment dynamic energy efficiency index of the energy-consuming equipment in the historical period.

[0245] In this embodiment, the weight acquisition module is specifically used for:

[0246] The values ​​of each indicator in the historical period are used as input, and the set total energy efficiency score of the regional residential user group is used as output to construct a decision unit; wherein the average total energy consumption of the regional residential user group is used as the initial set total energy efficiency score;

[0247] Slack variables are added to the decision-making unit, and the weights of each indicator in the energy efficiency index set are obtained through the data envelopment analysis-relaxation measurement model.

[0248] In this embodiment, the evaluation module is also used for:

[0249] The total energy efficiency scores of all residential users in the regional residential user group in the current period are summed up and averaged to obtain the average value of the total energy efficiency score;

[0250] The average value of the total energy efficiency score is used as the set total energy efficiency score for the comprehensive energy efficiency evaluation in the next period to obtain a new set total energy efficiency score;

[0251] Update the weight of each indicator according to the newly set total energy efficiency score to obtain a new weight of each indicator;

[0252] Based on the new weights of each indicator and the values ​​of each evaluation indicator in the next period, the total energy efficiency score of the residential user in the next period is recalculated.

[0253] In this embodiment, the evaluation module is specifically used for:

[0254] Based on the quantifiability of each evaluation indicator, each indicator is divided into quantifiable indicators and non-quantifiable indicators;

[0255] Based on each quantifiable indicator, determine the positive and negative impact of the quantifiable indicator on user energy efficiency;

[0256] According to the positive and negative influence of the quantifiable indicators, the values ​​of the quantifiable indicators in the current period are normalized to obtain the scores of the quantifiable indicators in the current period;

[0257] Based on each non-quantifiable indicator, the value of the non-quantifiable indicator is obtained through the fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period;

[0258] Based on the weight of each evaluation indicator, the scores of each evaluation indicator in the current period are weighted and summed to obtain the total energy efficiency score of the residential user in the current period.

[0259] In this embodiment, the evaluation module is specifically used for:

[0260] Based on the quantifiability of each evaluation indicator, each indicator is divided into quantifiable indicators and non-quantifiable indicators;

[0261] Based on each quantifiable indicator, determine the positive and negative impact of the quantifiable indicator on user energy efficiency;

[0262] According to the positive and negative influence of the quantifiable indicators, the values ​​of the quantifiable indicators in the current period are normalized to obtain the scores of the quantifiable indicators in the current period;

[0263] Based on each non-quantifiable indicator, the value of the non-quantifiable indicator is obtained through the fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period;

[0264] Based on the weight of each evaluation indicator, the scores of each evaluation indicator in the current period are weighted and summed to obtain the weighted sum of the scores;

[0265] The scores of the evaluation indicators of the resident users in the current period are summed up to obtain the sum of the scores of the current period; the scores of the evaluation indicators of the resident users in the historical period are summed up to obtain the sum of the scores of the historical period, wherein the calculation method of the scores of the evaluation indicators of the historical period and the current period is the same;

[0266] Subtract the score sum of the current period from the score sum of the historical period to obtain the trend score of the resident user;

[0267] The weighted sum of the scores is superimposed with the user trend score, and the superimposed result is used as the total energy efficiency score of the residential user in the current period.

[0268] Example 3

[0269] like Figure 7 As shown, the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and / or modified when the instructions are executed.

[0270] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement the corresponding method flow or corresponding functions, so as to realize the steps of a comprehensive energy efficiency evaluation method for residential users in the above embodiment.

[0271] Example 4

[0272] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It can be understood that the storage medium here can include both built-in storage media in electronic devices and, of course, extended storage media supported by electronic devices. The storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a comprehensive energy efficiency evaluation system for residential users in the above embodiment.

[0273] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0274] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0275] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0276] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0277] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the application, but these changes, modifications or equivalent substitutions are all within the protection scope of the claims of the present invention.

Claims

1. A comprehensive energy efficiency evaluation method for residential users, characterized in that: include: Based on a pre-constructed energy efficiency index set of a regional residential user group, the value of each index in the energy efficiency index set in a historical period is obtained from the historical energy efficiency data of the regional residential user group; the energy efficiency index set includes the equipment dynamic energy efficiency index of each energy-consuming equipment in the regional residential user group; Based on the values ​​of each of the indicators in the historical period and the set total energy efficiency score of the resident user group in the area, the weight of each of the indicators in the energy efficiency indicator set is obtained through a data envelopment analysis-relaxation measurement model; Based on each residential user in the regional residential user group, selecting a number of indicators corresponding to the residential user and its energy-consuming equipment from the energy efficiency indicator set as evaluation indicators, and selecting a weight of each evaluation indicator from the weights of each indicator; The value of each evaluation indicator in the current time period is obtained from the current energy efficiency data of the residential user group in the area, and a weighted sum is performed based on the weight of each evaluation indicator and the value of each evaluation indicator in the current time period to obtain the total energy efficiency score of the residential users in the current time period, wherein the time interval between the historical time period and the current time period does not exceed a preset time threshold.

2. The method according to claim 1, characterized in that The energy efficiency indicator set is constructed by the following steps: Based on the historical energy efficiency data of the residential user group in the area, determining the types of all energy-consuming devices in the residential user group in the area; Determine, according to the type of each of the energy-consuming devices, a device dynamic energy efficiency index corresponding to each of the energy-consuming devices; Based on the user static data in the historical energy efficiency data, the correlation between each user static data and the user energy efficiency is calculated by using the Spearman rank correlation coefficient, and the type of user static data with a correlation greater than a threshold is used as a user static indicator; The energy efficiency indicator set is constructed based on the dynamic energy efficiency indicators of each device and the static indicators of each user.

3. The method according to claim 2, characterized in that After determining the device dynamic energy efficiency index corresponding to each of the energy-consuming devices, the method further includes: Based on each of the dynamic energy efficiency indicators of the equipment, and according to the historical energy efficiency data of the resident user group in the area, determining a number of subordinate influencing items that affect the value of the dynamic energy efficiency indicator of the equipment; The subordinate impact items include one or more of the following: Standard value item for daily usage time of equipment per population, standard value item for daily usage time of equipment per area, standard value item for equipment power consumption per population, standard value item for equipment power consumption per area, daily usage times of equipment item, and equipment activation condition item.

4. The method according to claim 3, characterized in that The energy efficiency indicator set based on the pre-constructed regional residential user group, obtaining the value of each indicator in the energy efficiency indicator set in the historical period from the historical energy efficiency data of the regional residential user group, includes: Based on each energy-consuming device, obtaining the values ​​of several subordinate impact items in a historical period and the values ​​of the static indicators of each user in a historical period from the historical energy efficiency data of the residential user group in the area; Based on the equipment dynamic energy efficiency index of each of the energy-consuming equipment, the values ​​of several subordinate influencing items of the equipment dynamic energy efficiency index in the historical period are used as input, and the set equipment energy efficiency score of the equipment dynamic energy efficiency index is used as output to construct an equipment decision unit; Adding slack variables to the equipment decision unit, and obtaining weights of several subordinate influencing items through a data envelopment analysis-slack measurement model; Based on the weight of each of the subordinate influencing items and the value of each of the subordinate influencing items in the historical period, a weighted sum is performed to obtain the value of the equipment dynamic energy efficiency index of the energy-consuming equipment in the historical period.

5. The method according to claim 1 or 2, characterized in that: The weight of each indicator in the energy efficiency indicator set is obtained by using a data envelopment analysis-relaxation measurement model based on the value of each indicator in the historical period and the set total energy efficiency score of the regional resident user group, including: The values ​​of the indicators in the historical period are used as input, and the set total energy efficiency score of the residential user group in the area is used as output to construct a decision unit; wherein the average total energy consumption of the residential user group in the area is used as the initial set total energy efficiency score; A slack variable is added to the decision unit, and the weight of each indicator in the energy efficiency indicator set is obtained through a data envelopment analysis-relaxation measurement model.

6. The method according to claim 5, characterized in that After obtaining the total energy efficiency score of the residential user in the current period, the method further includes: The total energy efficiency scores of all residential users in the residential user group in the area in the current period are summed up and averaged to obtain the average value of the total energy efficiency score; The average value of the total energy efficiency score is used as the set total energy efficiency score for the comprehensive energy efficiency evaluation in the next period to obtain a new set total energy efficiency score; The weights of the indicators are updated according to the newly set total energy efficiency score to obtain new weights of the indicators; Based on the new weights of the indicators and the values ​​of the evaluation indicators in the next time period, the total energy efficiency score of the residential user in the next time period is recalculated.

7. The method according to claim 1 or 2, characterized in that: The weighted summation based on the weight of each evaluation index and the value of each evaluation index in the current period is performed to obtain the total energy efficiency score of the residential user in the current period, including: Based on the quantifiability of each evaluation indicator, each of the indicators is divided into quantifiable indicators and non-quantifiable indicators; Based on each of the quantifiable indicators, determining the positive and negative influence of the quantifiable indicator on the user's energy efficiency; According to the positive and negative influence of the quantifiable indicator, the value of the quantifiable indicator in the current period is normalized to obtain the score of the quantifiable indicator in the current period; Based on each of the non-quantifiable indicators, a value of the non-quantifiable indicator is obtained by a fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period; Based on the weight of each evaluation indicator, the scores of each evaluation indicator in the current time period are weighted and summed to obtain the total energy efficiency score of the residential user in the current time period.

8. The method according to claim 1 or 2, characterized in that: The weighted summation based on the weight of each evaluation index and the value of each evaluation index in the current period is performed to obtain the total energy efficiency score of the residential user in the current period, including: Based on the quantifiability of each evaluation indicator, each of the indicators is divided into quantifiable indicators and non-quantifiable indicators; Based on each of the quantifiable indicators, determining the positive and negative influence of the quantifiable indicator on the user's energy efficiency; According to the positive and negative influence of the quantifiable indicator, the value of the quantifiable indicator in the current period is normalized to obtain the score of the quantifiable indicator in the current period; Based on each of the non-quantifiable indicators, a value of the non-quantifiable indicator is obtained by a fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period; Based on the weights of the evaluation indicators, weighted sum of the scores of the evaluation indicators in the current period is performed to obtain a weighted sum of the scores; The scores of the evaluation indicators of the resident users in the current period are summed to obtain the sum of the scores of the current period; the scores of the evaluation indicators of the resident users in the historical period are summed to obtain the sum of the scores of the historical period, wherein the calculation method of the scores of the evaluation indicators of the historical period and the current period is the same; Subtract the score sum of the current period from the score sum of the historical period to obtain the trend score of the resident user; The weighted sum of the scores is superimposed on the user trend score, and the superimposed result is used as the total energy efficiency score of the residential user in the current time period.

9. A comprehensive energy efficiency evaluation system for residential users, characterized in that: include: A data acquisition module, for acquiring the value of each indicator in the energy efficiency indicator set in a historical period from the historical energy efficiency data of the regional resident user group based on a pre-constructed energy efficiency indicator set of the regional resident user group; the energy efficiency indicator set includes the equipment dynamic energy efficiency indicator of each energy-consuming equipment in the regional resident user group; A weight acquisition module, for obtaining the weight of each of the indicators in the energy efficiency indicator set through a data envelopment analysis-relaxation measurement model based on the value of each of the indicators in the historical period and the set total energy efficiency score of the regional resident user group; An indicator selection module is used to select, based on each residential user in the regional residential user group, several indicators corresponding to the residential user and its energy-consuming equipment from the energy efficiency indicator set as evaluation indicators, and select the weight of each evaluation indicator from the weights of each indicator; An evaluation module is used to obtain the value of each evaluation indicator in the current time period from the current energy efficiency data of the residential user group in the area, and perform weighted summation based on the weight of each evaluation indicator and the value of each evaluation indicator in the current time period to obtain the total energy efficiency score of the residential users in the current time period, wherein the time interval between the historical time period and the current time period does not exceed a preset time threshold.

10. The system according to claim 9, characterized in that The data acquisition module is specifically used for: Based on the historical energy efficiency data of the residential user group in the area, determining the types of all energy-consuming devices in the residential user group in the area; Determine, according to the type of each of the energy-consuming devices, a device dynamic energy efficiency index corresponding to each of the energy-consuming devices; Based on the user static data in the historical energy efficiency data, the correlation between each user static data and the user energy efficiency is calculated by using the Spearman rank correlation coefficient, and the type of user static data with a correlation greater than a threshold is used as a user static indicator; The energy efficiency indicator set is constructed based on the dynamic energy efficiency indicators of each device and the static indicators of each user.

11. The system according to claim 10, characterized in that The data acquisition module is also specifically used for: Based on each of the dynamic energy efficiency indicators of the equipment, and according to the historical energy efficiency data of the resident user group in the area, determining a number of subordinate influencing items that affect the value of the dynamic energy efficiency indicator of the equipment; The subordinate impact items include one or more of the following: Standard value item for daily usage time of equipment per population, standard value item for daily usage time of equipment per area, standard value item for equipment power consumption per population, standard value item for equipment power consumption per area, daily usage times of equipment item, and equipment activation condition item.

12. The system according to claim 11, characterized in that The data acquisition module is also specifically used for: Based on each energy-consuming device, obtaining the values ​​of several subordinate impact items in a historical period and the values ​​of the static indicators of each user in a historical period from the historical energy efficiency data of the residential user group in the area; Based on the equipment dynamic energy efficiency index of each of the energy-consuming equipment, the values ​​of several subordinate influencing items of the equipment dynamic energy efficiency index in the historical period are used as input, and the set equipment energy efficiency score of the equipment dynamic energy efficiency index is used as output to construct an equipment decision unit; Adding slack variables to the equipment decision unit, and obtaining weights of several subordinate influencing items through a data envelopment analysis-slack measurement model; Based on the weight of each of the subordinate influencing items and the value of each of the subordinate influencing items in the historical period, a weighted sum is performed to obtain the value of the equipment dynamic energy efficiency index of the energy-consuming equipment in the historical period.

13. The system according to claim 9 or 10, characterized in that The weight acquisition module is specifically used for: The values ​​of the indicators in the historical period are used as input, and the set total energy efficiency score of the residential user group in the area is used as output to construct a decision unit; wherein the average total energy consumption of the residential user group in the area is used as the initial set total energy efficiency score; A slack variable is added to the decision unit, and the weight of each indicator in the energy efficiency indicator set is obtained through a data envelopment analysis-relaxation measurement model.

14. The system of claim 13, wherein: The evaluation module is also used to: The total energy efficiency scores of all residential users in the residential user group in the area in the current period are summed up and averaged to obtain the average value of the total energy efficiency score; The average value of the total energy efficiency score is used as the set total energy efficiency score for the comprehensive energy efficiency evaluation in the next period to obtain a new set total energy efficiency score; The weights of the indicators are updated according to the newly set total energy efficiency score to obtain new weights of the indicators; Based on the new weights of the indicators and the values ​​of the evaluation indicators in the next time period, the total energy efficiency score of the residential user in the next time period is recalculated.

15. The system according to claim 9 or 10, characterized in that The evaluation module is specifically used for: Based on the quantifiability of each evaluation indicator, each of the indicators is divided into quantifiable indicators and non-quantifiable indicators; Based on each of the quantifiable indicators, determining the positive and negative influence of the quantifiable indicator on the user's energy efficiency; According to the positive and negative influence of the quantifiable indicator, the value of the quantifiable indicator in the current period is normalized to obtain the score of the quantifiable indicator in the current period; Based on each of the non-quantifiable indicators, a value of the non-quantifiable indicator is obtained by a fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period; Based on the weight of each evaluation indicator, the scores of each evaluation indicator in the current time period are weighted and summed to obtain the total energy efficiency score of the residential user in the current time period.

16. The system according to claim 9 or 10, characterized in that The evaluation module is specifically used for: Based on the quantifiability of each evaluation indicator, each of the indicators is divided into quantifiable indicators and non-quantifiable indicators; Based on each of the quantifiable indicators, determining the positive and negative influence of the quantifiable indicator on the user's energy efficiency; According to the positive and negative influence of the quantifiable indicator, the value of the quantifiable indicator in the current period is normalized to obtain the score of the quantifiable indicator in the current period; Based on each of the non-quantifiable indicators, a value of the non-quantifiable indicator is obtained by a fuzzy comprehensive evaluation method, and the value of the non-quantifiable indicator is used as the score of the non-quantifiable indicator in the current period; Based on the weights of the evaluation indicators, weighted sum of the scores of the evaluation indicators in the current period is performed to obtain a weighted sum of the scores; The scores of the evaluation indicators of the resident users in the current period are summed to obtain the sum of the scores of the current period; the scores of the evaluation indicators of the resident users in the historical period are summed to obtain the sum of the scores of the historical period, wherein the calculation method of the scores of the evaluation indicators of the historical period and the current period is the same; Subtract the score sum of the current period from the score sum of the historical period to obtain the trend score of the resident user; The weighted sum of the scores is superimposed on the user trend score, and the superimposed result is used as the total energy efficiency score of the residential user in the current time period.

17. An electronic device, characterized in that: include: at least one processor and memory; The memory and the processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, a comprehensive energy efficiency evaluation method for residential users as described in any one of claims 1 to 8 is implemented.

18. A readable storage medium, characterized in that: An execution program is stored thereon, and when the execution program is executed, a comprehensive energy efficiency evaluation method for residential users as described in any one of claims 1 to 8 is implemented.

Images