A method, device and terminal device for load estimation based on user portrait

Abstract

The present application is applicable to the technical field of integrated energy systems, and provides a method, device and terminal equipment for load estimation based on user portraits, the method comprising: obtaining the annual load curve and load estimation value of the target user; decomposing the annual load curve according to multiple load fluctuation frequencies to obtain multiple load fluctuation frequency characteristic components; clustering analysis of multiple load fluctuation frequency characteristic components to obtain multiple cluster center curves; obtaining a daily load characteristic curve based on multiple cluster center curves; obtaining daily loads at multiple times according to the daily load characteristic curve and load estimation value; and obtaining estimated daily loads at multiple times by Monte Carlo calculation of daily loads at multiple times. The present application determines the "user portrait" in the integrated energy system, clarifies the user load type and change characteristics, and enables the integrated energy system to be targeted in selection, sizing and optimal scheduling.

Description

Technical Field

[0001] The present application belongs to the technical field of integrated energy systems, and in particular, relates to a load estimation method, apparatus and terminal device based on user portraits. Background Art

[0002] Since the 21st century, my country's social and economic development has been rapid, the total energy demand has increased dramatically, and the contradiction between energy supply and demand has become increasingly prominent. Improving the comprehensive efficiency of energy utilization, exploring ways to utilize renewable energy, and strengthening the level of consumption of new energy have become the inevitable choices for the future development of my country's energy sector.

[0003] In this context, the Integrated Energy System (IES) has emerged as a new energy ecosystem that integrates energy production, transmission and consumption, with demand as the core, integrating solar energy, wind energy, geothermal energy and fossil energy in the region through digitalization and informatization. The Integrated Energy System effectively emphasizes the coordinated optimization of various energy subsystems in various links of energy utilization, realizes the complementary advantages of multiple energy sources, taps into the ability of users to participate in comprehensive demand response, improves the efficiency of comprehensive energy utilization, and effectively solves the problem of relative independence and loose coupling between traditional energy subsystems.

[0004] However, integrated energy systems often include multiple types of loads, such as industrial, commercial, and residential. Different types of loads are affected by different factors and show different change characteristics and laws, which leads to low efficiency of integrated energy systems and great waste of resources. Therefore, it is urgent to find a method to profile users, clarify the types of user loads and change characteristics, so that the integrated energy system can be targeted in selection, capacity determination, and optimal scheduling. Summary of the invention

[0005] In order to overcome the problems existing in the related art, the embodiments of the present application provide a load estimation method, system and terminal device based on user portrait.

[0006] This application is implemented through the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a load estimation method based on user profile, including:

[0008] Obtain the target user's annual load curve and load estimate;

[0009] Decompose the annual load curve according to various load fluctuation frequencies to obtain various load fluctuation frequency characteristic components;

[0010] Cluster analysis is performed on various load fluctuation frequency characteristic components to obtain multiple cluster center curves;

[0011] Based on multiple cluster center curves, the daily load characteristic curve is obtained;

[0012] According to the daily load characteristic curve and load estimation, the daily load at multiple times is obtained;

[0013] The daily load at multiple times is calculated by Monte Carlo and the estimated daily load at multiple times is obtained.

[0014] In a possible implementation of the first aspect, the annual load curve is decomposed according to multiple load fluctuation frequencies to obtain multiple load fluctuation frequency characteristic components, including:

[0015] The annual load curve is decomposed by discrete wavelet transform to obtain various load fluctuation frequency characteristic components;

[0016] Among them, the various load fluctuation frequencies include: stable fluctuation frequency, periodic fluctuation frequency and accidental fluctuation frequency; the various load fluctuation frequency characteristic components include: stable fluctuation frequency characteristic component, periodic fluctuation frequency characteristic component and accidental fluctuation frequency characteristic component.

[0017] In a possible implementation manner of the first aspect, Haar wavelet is selected as a wavelet basis function of discrete wavelet transform.

[0018] In a possible implementation of the first aspect, cluster analysis is performed on multiple load fluctuation frequency characteristic components to obtain multiple cluster center curves, including:

[0019] Cluster analysis is performed on various load fluctuation frequency characteristic components using a fast density peak clustering algorithm based on improved KNN to obtain multiple cluster center curves.

[0020] Among them, the cluster center curve is divided into stable frequency component cluster curve, periodic frequency component cluster curve and accidental frequency component cluster curve according to the load fluctuation frequency characteristic components.

[0021] In a possible implementation manner of the first aspect, a fast density peak clustering algorithm improved based on KNN includes:

[0022] Data selection steps:

[0023] Selecting a target component as a sample for cluster analysis, the target component is any one of a stable fluctuation frequency characteristic component, a periodic fluctuation frequency characteristic component and an accidental fluctuation frequency characteristic component;

[0024] Cluster analysis preparation steps:

[0025] Calculate any sample x i The Euclidean distance d(x i , x j); Arrange the Euclidean distance d(x) in ascending order i , x j ), then the sample with the kth Euclidean distance is NN k (x i );

[0026] Cluster analysis calculation steps:

[0027] Calculate x i The k nearest neighbors of are expressed as:

[0028] KNN(x i )={j∈X|d(x i , x j )≤d(x i , N.N. k (x i ))}

[0029] Using KNN(x i ) Calculate x i The local density The expression is:

[0030]

[0031] In the formula, N is the number of samples, p is the percentage of the number of samples N, K = p × N; it can be seen that K is determined by the parameter p, The larger the value, the greater the i The greater the local density;

[0032] According to the local density Calculating KNN distance The expression is:

[0033]

[0034] In the formula, KNN distance is the NN of this sample and its kth sample k (x i )’s distance;

[0035] The load fluctuation frequency characteristic components that simultaneously exceed the local density Threshold and KNN distance The data with the value of the tick is determined as the cluster center; among them, the decision variable of the cluster center The expression is: In the formula, It follows a long-tail distribution;

[0036] Cluster analysis results steps:

[0037] According to the data of the cluster center, the clustering curve corresponding to the target component is obtained, which is recorded as TLPA or TLP Di .

[0038] In a possible implementation of the first aspect, a daily load characteristic curve is obtained based on multiple cluster center curves, including:

[0039] pass

[0040]

[0041] Multiple cluster center curves are reconstructed to obtain the daily load characteristic curve.

[0042] In a possible implementation of the first aspect, obtaining daily loads at multiple times according to the daily load characteristic curve and the load estimate includes:

[0043] Determine the daily load at multiple times according to the product of the load ratio at multiple times in the daily load characteristic curve and the load estimate;

[0044] The load estimate is determined based on the population or land area of ​​the target users and the load index value, and the load index value includes the power load estimate and the cooling and heating load estimate;

[0045] The power load estimate is determined using the load density method, and the expression is:

[0046]

[0047] In the formula, To estimate the annual or monthly electricity consumption of target users, is the estimated target user population or land area, is the electricity density, which is the average electricity consumption per person or per land area;

[0048] The estimated values ​​of cooling and heating loads include: estimated values ​​of building demand load, estimated values ​​of domestic hot water load and estimated values ​​of industrial heat load;

[0049] The building demand load estimate is the building air conditioning load, expressed as:

[0050]

[0051] Where W q is the cooling load of air conditioning, E q is the air conditioning cooling index, W a is the air conditioning heat load, E a is the air conditioning thermal index, G k The floor area of ​​the building being air-conditioned;

[0052] The estimated domestic hot water load is the bathing water load, expressed as:

[0053]

[0054] In the formula, Q max is the maximum load of domestic hot water, Q a is the average heat load of domestic hot water, D h is the hourly variation coefficient; q w is the domestic hot water index, A is the total building area;

[0055] The estimated industrial heat load is the steam load, expressed as:

[0056] L=dcR

[0057] In the formula, L is the amount of steam required by the industry; d is the steam consumption index of the industrial building; c is the floor area of ​​the industrial building, and R is the volume ratio of the industrial building.

[0058] In a possible implementation of the first aspect, the daily loads at multiple moments are calculated by Monte Carlo to obtain the estimated daily loads at multiple moments, including:

[0059] Steps to build a random probability model:

[0060] Obtain the distribution parameters of daily loads at multiple times as random variables and establish a Monte Carlo model;

[0061] Steps to determine risk variables and probability distribution:

[0062] In fuzzy multi-attribute decision making, I i (X) is a risk variable, which is a discrete random variable sample value determined by the membership function. In the Monte Carlo simulation, there are n risk variables. For a single daily load at multiple moments, U is a discontinuous value. 1 、u 2 、…、u n , and u 1 <u 2 <…<u n , I i The expressions of the probability density function (p) and distribution function (F) of (X) are as follows:

[0063] p(μ i )=p{U=μ i}

[0064]

[0065] Steps to get an estimate:

[0066] According to I iThe probability distribution of (X) generates random numbers and derives the distribution of the target variable. For any discrete time variable, the expression of the sampling method of discrete distribution is as follows:

[0067]

[0068] Where U F is the corresponding transformation probability of the random number, ξ is an interval random number, through random sampling, according to U F Get the corresponding I i (X), through N times of random sampling, the estimated daily load at multiple times is obtained.

[0069] In a second aspect, an embodiment of the present application provides a load estimation device based on user profile, including:

[0070] An acquisition module is used to obtain the annual load curve and load estimate of the target user;

[0071] The curve decomposition module is used to decompose the annual load curve according to various load fluctuation frequencies to obtain various load fluctuation frequency characteristic components;

[0072] Cluster analysis module, used to perform cluster analysis on various load fluctuation frequency characteristic components to obtain multiple cluster center curves;

[0073] A combination module is used to obtain a daily load characteristic curve based on multiple cluster center curves;

[0074] The estimation module obtains the daily load at multiple times according to the daily load characteristic curve and the load estimation value, and obtains the estimated daily load at multiple times by Monte Carlo calculation.

[0075] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a load estimation method based on user profile as described in any one of the first aspects is implemented.

[0076] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for load estimation based on user portrait as described in any one of the first aspects is implemented.

[0077] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes a load estimation method based on user profile as described in any one of the above-mentioned first aspects.

[0078] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0079] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0080] In the embodiment of the present application, a discrete wavelet transform is adopted to decompose the target user's annual load curve according to various load fluctuation frequencies, and various load fluctuation frequency characteristic components are extracted. Then, based on the fast density peak clustering algorithm improved by KNN, a cluster analysis is performed on the various load fluctuation frequency characteristic components to obtain multiple cluster center curves, and the multiple cluster center curves are reconstructed to obtain the daily load characteristic curve. The daily load characteristic curve and the load estimation value are combined to obtain the daily load at multiple times. Finally, the daily load at multiple times is calculated by the Monte Carlo algorithm, and the estimated daily load at multiple times is finally obtained.

[0081] The daily load of the target users in the integrated energy system of this application is accurately estimated, the "profile" of the target users in the integrated energy system is determined, and the load type and change characteristics of the target users are clarified, which can make the integrated energy system targeted in selection, sizing and optimal scheduling.

[0082] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0084] Figure 1 It is a flowchart of a load estimation method based on user portrait provided by an embodiment of the present application;

[0085] Figure 2 This is a full-year electricity load curve diagram provided by an embodiment of the present application;

[0086] Figure 3 This is a full-year heat load curve diagram provided by an embodiment of the present application;

[0087] Figure 4 is a cooling load curve for the whole year provided in an embodiment of the present application;

[0088] Figure 5 It is a component diagram of the stable fluctuation frequency characteristics of the electric load throughout the year provided by an embodiment of the present application;

[0089] Figure 6 It is a frequency characteristic component diagram of the annual electric load period fluctuation provided by an embodiment of the present application;

[0090] Figure 7 It is a component diagram of the frequency characteristic of the occasional fluctuation of the electric load throughout the year provided by an embodiment of the present application;

[0091] Figure 8 is a cluster center curve diagram of stable fluctuation frequency components provided in an embodiment of the present application;

[0092] Fig. 9 It is a cluster center curve diagram of periodic fluctuation frequency components provided in an embodiment of the present application;

[0093] Fig.10 is a cluster center curve diagram of the accidental fluctuation frequency component provided in an embodiment of the present application;

[0094] Fig.11 is a daily load characteristic curve diagram provided in an embodiment of the present application;

[0095] Fig.12 It is a flow chart of a fast density peak clustering algorithm based on KNN improvement provided in an embodiment of the present application;

[0096] Fig.13 It is a schematic diagram of a flow chart of calculating daily loads at multiple times by Monte Carlo method provided in an embodiment of the present application;

[0097] Fig.14 It is a structural schematic diagram of a load estimation device based on user portrait provided in an embodiment of the present application;

[0098] Fig.15 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0099] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0100] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0101] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0102] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0103] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0104] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0105] In recent years, energy storage technology has been rapidly improved, renewable energy power generation technology has been gradually improved, and new Internet technologies have been widely used in power systems, providing technical guarantees for the interconnection of various energy sources. People have begun to study the coupling relationship between energy supply and energy demand, pay attention to the flow of data information in the energy system, and explore ways to achieve comprehensive energy utilization. In this context, the Integrated Energy System (IES) has emerged as a new energy ecosystem that integrates energy production, transmission, and consumption, with demand as the core, integrating solar energy, wind energy, geothermal energy, and fossil energy in the region through digitalization and informatization. The integrated energy system not only greatly reduces the consumption of fossil energy, optimizes the energy structure, but also reduces the dependence of today's society on traditional fossil energy. The integrated energy system effectively emphasizes the coordinated optimization of various energy subsystems in various links of energy utilization, realizes the complementary advantages of multiple energy sources, taps the ability of users to participate in comprehensive demand response, and improves the efficiency of comprehensive energy utilization. It effectively solves the problems of relative independence and loose coupling between traditional energy subsystems, and is one of the important strategies to solve the current dilemma of China's energy system.

[0106] However, integrated energy systems often include multiple types of loads, such as industrial, commercial, and residential. Different types of loads are affected by different factors and exhibit different changing characteristics and laws, resulting in low efficiency of the integrated energy system and a huge waste of resources.

[0107] Based on the above problems, a load estimation method based on user portrait in the embodiment of the present application is carried out from two aspects: on the one hand, based on the annual load curve of the target user, cluster analysis is performed according to its load characteristics to construct an accurate typical load curve of the target user; on the other hand, the load of the target user is estimated through a mathematical model by combining the typical load curve and the load estimation index. The specific method is: using discrete wavelet transform, decomposing the annual load curve of the target user according to multiple load fluctuation frequencies, extracting multiple load fluctuation frequency characteristic components, and then based on the KNN improved fast density peak clustering algorithm, cluster analysis is performed on multiple load fluctuation frequency characteristic components to obtain multiple cluster center curves, reconstructing multiple cluster center curves to obtain daily load characteristic curves, combining daily load characteristic curves and load estimation values ​​to obtain daily loads at multiple times, and finally calculating the daily loads at multiple times through the Monte Carlo algorithm, and finally obtaining the estimated daily loads at multiple times.

[0108] Figure 1 is a schematic flow chart of a method for load estimation based on user portraits provided in an embodiment of the present application, with reference to Figure 1 , the method is described in detail as follows:

[0109] In step 101, the annual load curve and load estimate of the target user are obtained.

[0110] In a possible implementation, the target user's annual load curve is generated after the target user's annual load data is sorted and converted, and the target user's annual load data is obtained from the relevant energy supply agency. The annual load curve includes the annual electricity load curve, the annual heat load curve and the annual cooling load curve.

[0111] For example, refer to Figure 2 Annual electricity load curve, Figure 3 Annual heat load curve and Figure 4 Cooling load curve for the whole year.

[0112] In a possible implementation, the load estimate is the product of the population or land area of ​​the target users and the load index value, wherein the load estimate includes: power load estimate and cooling and heating load estimate.

[0113] Optionally, the population size or land area of ​​the target users may be obtained from relevant institutions, the Internet or other channels, and the load index value may have different indices for different industries or buildings.

[0114] For example, Table 1 shows the air conditioning load index values.

[0115] Table 1

[0116] Building Types <![CDATA[Cold index E q > <![CDATA[Thermal index E a > Movie Theater 150-200 115-140 Hospital 70-100 90-120 stadium 140-200 130-190 Shops, exhibition halls 125-180 100-120 Office 80-110 80-100 Hotels and guesthouses 80-110 90-120

[0117] Table 2 shows the indicators of domestic hot water

[0118] Table 2

[0119]

[0120] Table 3 shows the steam consumption index values ​​of industrial buildings

[0121] Table 3

[0122]

[0123] In step 102, the annual load curve is decomposed according to various load fluctuation frequencies to obtain various load fluctuation frequency characteristic components.

[0124] In a possible implementation, the load fluctuation frequency is determined according to the load characteristics of the target user. In this application, the load characteristics of the target user are divided into randomness, periodicity and trend. According to the load characteristics of the target user, the load fluctuation frequency is divided into stable fluctuation frequency, periodic fluctuation frequency and occasional fluctuation frequency.

[0125] Furthermore, the obtained load fluctuation frequency characteristic components are divided into: stable fluctuation frequency characteristic components, periodic fluctuation frequency characteristic components and occasional fluctuation frequency characteristic components.

[0126] Optionally, discrete wavelet transform is used to decompose the annual load curve, and Haar wavelet is selected as the mother wavelet of discrete wavelet transform.

[0127] For example, taking the electric load of the target user as an example, the electric load characteristic curve is decomposed by discrete wavelet transform to extract the characteristic components of the electric load data. Figure 5 The component diagram of stable fluctuation frequency characteristics of electric load throughout the year, Figure 6 The frequency characteristic component diagram of the annual electric load cycle fluctuation, Figure 7 Component diagram of frequency characteristics of accidental fluctuations in electric load throughout the year.

[0128] According to the characteristics of the data, this step uses Haar wavelet as the mother wavelet of discrete wavelet transform to decompose the data, extract the main information such as random terms, periodic terms and trend terms in the load data, obtain the characteristics of different load fluctuation frequency scales of the load curve, and analyze the characteristics at different scales. This can comprehensively characterize the user's electricity consumption behavior from multiple angles and significantly reduce the computational complexity of cluster analysis.

[0129] In step 103, cluster analysis is performed on the multiple load fluctuation frequency characteristic components to obtain multiple cluster center curves.

[0130] Electricity consumption behavior analysis is an important part of power big data research and the basis for research and work such as load forecasting, demand-side response, grid planning, economic operation, rate setting, and energy efficiency improvement.

[0131] In a possible implementation, multiple load fluctuation frequency characteristic components are taken as input and clustered respectively.

[0132] Optionally, a fast density peak clustering algorithm based on KNN improvement is used to perform cluster analysis on various load fluctuation frequency characteristic components, refer to Fig.12 Flowchart of the fast density peak clustering algorithm improved based on KNN.

[0133] In step 1031, data selection:

[0134] Any one of the stable fluctuation frequency characteristic components, periodic fluctuation frequency characteristic components and accidental fluctuation frequency characteristic components is selected as a sample for cluster analysis.

[0135] In step 1032, cluster analysis preparation:

[0136] Calculate any sample x iThe Euclidean distance d(x i , x j ); Arrange the Euclidean distance d(x) in ascending order i , x j ), then the sample with the kth Euclidean distance is NN k (x i ).

[0137] In step 1033, cluster analysis calculates:

[0138] Calculate x i The k nearest neighbors of are expressed as:

[0139] KNN(x i )={j∈X|d(x i , x j )≤d(x i , N.N. k (x i ))}

[0140] Using KNN(x i ) Calculate x i The local density The expression is:

[0141]

[0142] In the formula, N is the number of samples, p is the percentage of the number of samples N, K = p × N; it can be seen that K is determined by the parameter p, The larger the value, the greater the i The greater the local density;

[0143] According to the local density Calculating KNN distance The expression is:

[0144]

[0145] In the formula, KNN distance is the NN of this sample and its kth sample k (x i )’s distance;

[0146] The load fluctuation frequency characteristic components that simultaneously exceed the local density Threshold and KNN distance The data of the threshold is determined as the cluster center; among them, the decision variable of the cluster center The expression is: In the formula, It follows a long-tail distribution.

[0147] In step 1034, cluster analysis results:

[0148] According to the data of the cluster center, the clustering curve corresponding to the target component is obtained, which is recorded as TLP A or TLP Di .

[0149] For example, taking the electric load as an example, the clustering curve obtained from step 1031 to step 1034 is shown in FIG. Figure 8 Stable fluctuation frequency component cluster center curve, Fig. 9 The cluster center curve of the periodic fluctuation frequency component and Fig.10 Cluster center curve of random fluctuation frequency component.

[0150] In step 103, based on the improvement of the local density and distance definitions in the fast density peak based on the KNN concept, in view of the deficiency of the original algorithm that relies on manual identification of possible cluster centers in the decision graph, the cluster center is automatically selected using the outward statistical test method, and good results are obtained in the data classification of single users and users in different industries.

[0151] In step 104, a daily load characteristic curve is obtained based on the plurality of cluster center curves.

[0152] Get multiple cluster center curves TLP A or TLP Di Reconstruct the typical load curve through the expression:

[0153]

[0154] Multiple cluster center curves are reconstructed to obtain the daily load characteristic curve.

[0155] In this step, the typical load curve is obtained to analyze the electricity consumption behavior, and the results are analyzed and interpreted in combination with the power business and actual conditions, so as to provide targeted energy-saving and peak-shifting suggestions for the integrated energy system.

[0156] For example, taking the electric load as an example, based on the above cluster analysis results, the typical load curve of the target user is reconstructed by clustering the centers of the three types of electric load fluctuation frequency characteristic components, and the daily load characteristic curve can be obtained. Fig.11 Daily load characteristic curve.

[0157] from Fig.11 It can be seen that the first load peak occurs at 9-12 o'clock, the second peak occurs at 14-16 o'clock, and the third load peak occurs at around 18 o'clock. Combined with the user's profile information, comprehensive consideration of the user's electricity consumption characteristics, type, and external market, environment, season and other factors, corresponding energy conservation or participation in power demand response implementation suggestions can be given:

[0158] The load regulation methods based on power demand response are mainly divided into rigid control methods and flexible regulation methods. The rigid control method generally directly shuts down all or part of the power-consuming equipment. The biggest advantages of this method are simple method, rapid response, effective execution, and determined load limit capacity. The flexible regulation method adjusts the output of the load by changing the operating mode, operating parameters, operating mode, etc. of a single or multiple power-consuming equipment to achieve the purpose of partial load reduction.

[0159] Take a shopping mall as an example. The main controllable load equipment in this mall includes chiller load, lighting load, refrigeration (cooling) water pump and cooling tower fan. Among them, chillers account for the largest proportion, about 40%. The main control method for air-conditioning related loads is direct control (flexible) adjustment, and the control preparation and resumption of operation time can reach minutes. The lighting load and some cooling tower fans adopt direct control (rigid) control, and the control preparation and resumption of operation time can reach seconds. The adjustable proportion of air-conditioning loads is about 20%, and the adjustable proportion of lighting loads is about 10%.

[0160] According to the analysis of the daily load characteristic curve, the adjustable load ratio of the shopping mall is about 30%. The load regulation situation is detailed in Table 4.

[0161] Table 4

[0162]

[0163] In step 105, daily loads at multiple moments are obtained according to the daily load characteristic curve and the load estimation value.

[0164] Step 101 has been roughly described, and the load estimate is the product of the population or land area of ​​the target user and the load index value. The load estimate includes: power load estimate and cooling and heating load estimate. Here, the power load estimate and cooling and heating load estimate are further described.

[0165] In some embodiments, the power load estimate is determined using a load density method, expressed as:

[0166]

[0167] In the formula, To estimate the annual or monthly electricity consumption of target users, is the estimated target user population or land area, It is the electricity density, that is, the average electricity consumption per person or per land area.

[0168] In some embodiments, the cooling and heating load estimates include: a building demand load estimate, a domestic hot water load estimate, and an industrial heat load estimate;

[0169] Optionally, the building demand load estimate is the building air conditioning load, expressed as:

[0170]

[0171] Where W q is the cooling load of air conditioning, E q is the air conditioning cooling index, W a is the air conditioning heat load, E a is the air conditioning thermal index, G k is the building area of ​​the air-conditioned building. The air-conditioning load index values ​​are shown in Table 1.

[0172] Optionally, the domestic hot water load is estimated as the bathing water load, expressed as:

[0173]

[0174] In the formula, Q max is the maximum load of domestic hot water, Q a is the average heat load of domestic hot water, D h is the hourly variation coefficient; q w is the domestic hot water index, and A is the total building area. The domestic hot water index values ​​are shown in Table 2.

[0175] Optionally, the industrial heat load is estimated as steam load, expressed as:

[0176] L=dcR

[0177] In the formula, L is the amount of steam required by the industry; d is the steam consumption index of industrial buildings; c is the floor area of ​​industrial buildings, and R is the volume ratio of industrial buildings. The steam consumption index values ​​of industrial buildings are shown in Table 3.

[0178] In this step, the maximum load values ​​of different buildings can be obtained through the load estimation index value and the population or land area of ​​the target users. Combined with the daily load characteristic curve, the daily load of the target users at multiple times can be calculated.

[0179] In step 106, the daily loads at the multiple moments are calculated by Monte Carlo to obtain the estimated daily loads at the multiple moments.

[0180] In some embodiments, based on the above calculation results, the daily load at multiple times can be calculated by Monte Carlo method to obtain the estimated daily load of the target user at multiple times. Fig.13 The flow chart of calculating the daily load at multiple times by Monte Carlo method is as follows:

[0181] In step 1061, a random probability model is established:

[0182] Obtain the distribution parameters of daily load at different times as random variables and establish a Monte Carlo model;

[0183] In step 1062, the risk variables and probability distributions are determined:

[0184] In fuzzy multi-attribute decision making, I i (X) is a risk variable, which is a discrete random variable sample value determined by the membership function. In the Monte Carlo simulation, there are n risk variables. For a single daily load at different times, U is a discontinuous value. 1 、u 2 、…、u n , and U 1 <U 2 <···<u n , I i The expressions of the probability density function (p) and distribution function (F) of (X) are as follows:

[0185] p(μ i )=p{U=μ i}

[0186]

[0187] In step 1063, an estimated value is obtained:

[0188] According to I i The probability distribution of (X) generates random numbers and derives the distribution of the target variable. For any discrete time variable, the expression of the sampling method of discrete distribution is as follows:

[0189]

[0190] Where U F is the corresponding transformation probability of the random number, ξ is an interval random number, through random sampling, according to U F Get the corresponding I i (X), through N times of random sampling, the estimated daily load at different times is obtained.

[0191] Optionally, during the load estimation process, the Monte Carlo method may be used to randomly sample daily loads at multiple times based on the distribution functions and set parameters of different influencing factors to obtain estimated daily loads at different multiple times.

[0192] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0193] Corresponding to the load estimation method based on user portrait described in the above embodiment, Fig.14 A structural block diagram of a load estimation device based on user portrait provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0194] See also Fig.14 A load estimation device based on user portrait in an embodiment of the present application may include: an acquisition module 201, a curve decomposition module 202, a cluster analysis module 203, a combination module 204 and an estimation module 205.

[0195] The acquisition module 201 is used to obtain the target user's annual load curve and load estimate. The curve decomposition module 202 is used to decompose the annual load curve according to the load fluctuation frequency to obtain multiple load fluctuation frequency characteristic components. The cluster analysis module 203 is used to perform cluster analysis on multiple load fluctuation frequency characteristic components to obtain multiple cluster center curves. The combination module 204 is used to obtain the daily load characteristic curve based on multiple cluster center curves. The estimation module 205 is used to obtain the daily load at multiple times based on the daily load characteristic curve and the load estimate, and to estimate the daily load at multiple times by Monte Carlo calculation of the daily load at multiple times.

[0196] In some embodiments, the acquisition module 201 is used to obtain the annual load curve of the target user, including: the annual electricity load curve, the annual heat load curve and the annual cooling load curve.

[0197] Optionally, the acquisition module 201 is further used to acquire load estimates, including power load estimates, cooling and heating load estimates, and load index values. The load index values ​​include air conditioning load index values, domestic hot water index values, and industrial building gas consumption index values.

[0198] In some embodiments, the curve decomposition module 202 is used to: decompose the annual load curve using discrete wavelet transform to obtain multiple load fluctuation frequency characteristic components. The multiple load fluctuation frequencies include: stable fluctuation frequency, periodic fluctuation frequency and occasional fluctuation frequency; the multiple load fluctuation frequency characteristic components include: stable fluctuation frequency characteristic component, periodic fluctuation frequency characteristic component and occasional fluctuation frequency characteristic component.

[0199] Optionally, the curve decomposition module 202 is further used for: discrete wavelet transform uses Haar wavelet as wavelet basis function.

[0200] In some embodiments, the cluster analysis module 203 is used to perform cluster analysis on multiple load fluctuation frequency characteristic components using a fast density peak clustering algorithm based on KNN improvement to obtain multiple cluster center curves. The cluster center curves can be divided into stable frequency component cluster curves, periodic frequency component cluster curves, and accidental frequency component cluster curves according to the load fluctuation frequency characteristic components.

[0201] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0202] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0203] The present application also provides a terminal device, see Fig.15 The terminal device 300 may include: at least one processor 310, a memory 320, and a computer program stored in the memory 320 and executable on the at least one processor 310, wherein the processor 310 implements the steps in any of the above-mentioned method embodiments when executing the computer program, for example Figure 1 Steps 101 to 106 in the illustrated embodiment. Alternatively, when the processor 310 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Fig.14 Functions of modules 201 to 205 are shown.

[0204] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 320, and executed by the processor 310 to complete the present application. The one or more modules / units may be a series of computer program segments that can complete specific functions, and the program segments are used to describe the execution process of the computer program in the terminal device 300.

[0205] Those skilled in the art will understand that Fig.15 It is only an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, buses, etc.

[0206] The processor 310 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. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0207] The memory 320 may be an internal storage unit of the terminal device, or an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. The memory 320 is used to store the computer program and other programs and data required by the terminal device. The memory 320 may also be used to temporarily store data that has been output or is to be output.

[0208] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0209] The method for user profiling of a comprehensive energy efficiency system provided in the embodiment of the present application can be applied to terminal devices such as computers, wearable devices, vehicle-mounted devices, tablet computers, laptops, netbooks, personal digital assistants (PDAs), augmented reality (AR) / virtual reality (VR) devices, and mobile phones. The embodiment of the present application does not impose any restrictions on the specific type of terminal devices.

[0210] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps in each embodiment of the method for realizing the user profiling of the comprehensive energy efficiency system.

[0211] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal implements the steps in each embodiment of the method for realizing user profiling of the comprehensive energy efficiency system.

[0212] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0213] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0214] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0215] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0216] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0217] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A load estimation method based on user portrait, which is characterized by: include: Obtain the target user's annual load curve and load estimate; Decomposing the annual load curve according to various load fluctuation frequencies to obtain various load fluctuation frequency characteristic components; Performing cluster analysis on the multiple load fluctuation frequency characteristic components to obtain multiple cluster center curves; Based on the plurality of cluster center curves, a daily load characteristic curve is obtained; According to the daily load characteristic curve and the load estimation value, obtaining the daily load at multiple times; Calculate the daily loads at the multiple moments by Monte Carlo to obtain the estimated daily loads at the multiple moments; Wherein, obtaining the daily load at multiple times according to the daily load characteristic curve and the load estimation value includes: Determine the daily loads at the multiple moments according to the product of the load ratios at the multiple moments in the daily load characteristic curve and the load estimate; The load estimation value is determined based on the population or land area of ​​the target users and the load index value, and the load estimation value includes the power load estimation value and the cooling and heating load estimation value; The power load estimate is determined by the load density method, and the expression is: In the formula, To estimate the annual or monthly electricity consumption of target users, is the estimated target user population or land area, is the electricity density, which is the average electricity consumption per person or per land area; The estimated cold and hot loads include: estimated building demand load, estimated domestic hot water load and estimated industrial heat load; The building demand load estimate is the building air conditioning load, expressed as: Where W q is the cooling load of air conditioning, E q is the air conditioning cooling index, W a is the air conditioning heat load, E a is the air conditioning thermal index, G k The floor area of ​​the building being air-conditioned; The estimated value of the domestic hot water load is the bathing water load, and the expression is: In the formula, Q max is the maximum load of domestic hot water, Q a is the average heat load of domestic hot water, D h is the hourly variation coefficient; q w is the domestic hot water index, A is the total building area; The industrial heat load estimate is the steam load, expressed as: L=dcR In the formula, L is the amount of steam required by the industry; d is the steam consumption index of the industrial building; c is the floor area of ​​the industrial building, and R is the volume ratio of the industrial building.

2. A method for load estimation based on user profile according to claim 1, characterized in that: Decomposing the annual load curve according to multiple load fluctuation frequencies to obtain multiple load fluctuation frequency characteristic components includes: Decomposing the annual load curve by discrete wavelet transform to obtain multiple load fluctuation frequency characteristic components; Wherein, the multiple load fluctuation frequencies include: stable fluctuation frequency, periodic fluctuation frequency and accidental fluctuation frequency; the multiple load fluctuation frequency characteristic components include: stable fluctuation frequency characteristic component, periodic fluctuation frequency characteristic component and accidental fluctuation frequency characteristic component; The discrete wavelet transform uses Haar wavelet as the wavelet basis function.

3. The load estimation method based on user profile according to claim 1, characterized in that: The cluster analysis is performed on the multiple load fluctuation frequency characteristic components to obtain multiple cluster center curves, including: Cluster analysis is performed on various load fluctuation frequency characteristic components using a fast density peak clustering algorithm based on improved KNN to obtain multiple cluster center curves. The cluster center curve is divided into a stable frequency component cluster curve, a periodic frequency component cluster curve and an accidental frequency component cluster curve according to the load fluctuation frequency characteristic component.

4. A method for load estimation based on user profile as claimed in claim 3, characterized in that: The improved fast density peak clustering algorithm based on KNN includes: Data selection steps: Selecting a target component as a sample for cluster analysis, wherein the target component is any one of a stable fluctuation frequency characteristic component, a periodic fluctuation frequency characteristic component, and an accidental fluctuation frequency characteristic component; Cluster analysis preparation steps: Calculate any sample x i The Euclidean distance d(x i ,x j ); Arrange the Euclidean distance d(x) in ascending order i ,x j ), then the kth sample of the Euclidean distance is NN k (x i ); Cluster analysis calculation steps: Calculate x i The k nearest neighbors of are expressed as: KNN(x i )={j∈X|d(x i ,x j )≤d(x i ,NN k (x i ))} Using KNN(x i ) Calculate x i The local density The expression is: In the formula, N is the number of samples, p is the percentage of the number of samples N, K = p × N; it can be seen that K is determined by the parameter p, The larger the value, the greater the i The greater the local density; According to the local density Calculating KNN distance The expression is: In the formula, KNN distance is the NN of this sample and its kth sample k (x i )’s distance; The load fluctuation frequency characteristic components simultaneously exceed the local density Threshold and KNN distance The data of the threshold is determined as the cluster center; wherein the decision variable of the cluster center The expression is: In the formula, It follows a long-tail distribution; Cluster analysis results steps: According to the data of the cluster center, the cluster curve corresponding to the target component is obtained, which is recorded as TLP A or TLP Di .

5. The method for load estimation based on user profile according to claim 1, characterized in that: The daily load characteristic curve is obtained based on the plurality of cluster center curves, including: pass A plurality of cluster center curves are reconstructed to obtain a daily load characteristic curve.

6. A method for load estimation based on user profile as claimed in claim 1, characterized in that: The method of calculating the daily loads at the multiple moments by Monte Carlo to obtain the estimated daily loads at the multiple moments includes: Steps to build a random probability model: Obtaining the distribution parameters of the daily loads at the multiple moments as random variables, and establishing a Monte Carlo model; Steps to determine risk variables and probability distribution: In fuzzy multi-attribute decision making, I i (X) is a risk variable, which is a discrete random variable sample value determined by the membership function. In the Monte Carlo simulation, there are n risk variables. For a single daily load at multiple moments, U is a discontinuous value ranging from u1, u2, ..., u n , and u1 <u2<…<u n , I i The expressions of the probability density function (p) and distribution function (F) of (X) are as follows: p(μ i )=p{U=μ i } Steps to get an estimate: According to I i The probability distribution of (X) generates random numbers and derives the distribution of the target variable. For any discrete time variable, the expression of the sampling method of discrete distribution is as follows: Where U F is the corresponding transformation probability of the random number, ξ is an interval random number, through random sampling, according to U F Get the corresponding I i (X) By performing N random samplings, the estimated daily load at multiple moments is obtained.

7. A load estimation device based on user portrait, characterized in that: include: An acquisition module is used to obtain the annual load curve and load estimate of the target user; A curve decomposition module, used for decomposing the annual load curve according to multiple load fluctuation frequencies to obtain multiple load fluctuation frequency characteristic components; A cluster analysis module, used for performing cluster analysis on the multiple load fluctuation frequency characteristic components to obtain multiple cluster center curves; A combination module, used for obtaining a daily load characteristic curve based on a plurality of cluster center curves; An estimation module, used to obtain the daily load at multiple times according to the daily load characteristic curve and the load estimation value, and to estimate the daily load at multiple times by Monte Carlo calculation of the daily load at the multiple times; Wherein, the estimation module is used for: Determine the daily loads at the multiple moments according to the product of the load ratios at the multiple moments in the daily load characteristic curve and the load estimate; The load estimation value is determined based on the population or land area of ​​the target users and the load index value, and the load estimation value includes the power load estimation value and the cooling and heating load estimation value; The power load estimate is determined by the load density method, and the expression is: In the formula, To estimate the annual or monthly electricity consumption of target users, is the estimated target user population or land area, is the electricity density, which is the average electricity consumption per person or per land area; The estimated cold and hot loads include: estimated building demand load, estimated domestic hot water load and estimated industrial heat load; The building demand load estimate is the building air conditioning load, expressed as: Where W q is the cooling load of air conditioning, E q is the air conditioning cooling index, W a is the air conditioning heat load, E a is the air conditioning thermal index, G k The floor area of ​​the building being air-conditioned; The estimated value of the domestic hot water load is the bathing water load, and the expression is: In the formula, Q max is the maximum load of domestic hot water, Q a is the average heat load of domestic hot water, D h is the hourly variation coefficient; q w is the domestic hot water index, A is the total building area; The industrial heat load estimate is the steam load, expressed as: L=dcR In the formula, L is the amount of steam required by the industry; d is the steam consumption index of the industrial building; c is the floor area of ​​the industrial building, and R is the volume ratio of the industrial building.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images