A system and method for elastic aggregation of distributed electric heating load characteristics

Abstract

This invention discloses a system and method for elastically aggregating distributed electric heating load characteristics in the field of power system analysis. The system comprises the following steps: receiving electric heating load data from distributed electric heating users; preprocessing the electric heating load data; clustering distributed electric heating users using the FCM clustering algorithm, using seven load characteristic indicators as clustering indicators based on the preprocessed electric heating load data; and evaluating clustering quality and determining the optimal number of clusters by establishing three clustering effectiveness indicators. This invention solves the problem of identifying and aggregating the characteristics of distributed electric heating users, thereby facilitating the management and regulation of electric heating load groups and enhancing the controllability of electric heating load groups.

Description

Technical Field

[0001] The present invention relates to a system and method for elastically aggregating distributed electric heating load characteristics, and belongs to the technical field of power system analysis. Background Art

[0002] Against the backdrop of prominent global energy security issues and severe environmental pollution, vigorously developing new energy sources such as wind and solar power generation and achieving a transition to renewable energy in energy production is a critical requirement for sustainable energy and economic development in China and globally. Jilin's winter heating period is long and demand for heat is high. Clean heating, represented by thermal storage electric heating, has gradually gained scale and holds enormous potential. As flexible and adjustable loads with time-shifting capabilities, electric-thermal load groups have significant potential for increasing the absorption of new energy and fulfilling their absorption weight responsibilities. It is necessary to fully tap the backup, peak-shaving, and frequency-regulating potential of electric-thermal loads involved in new energy absorption, and to coordinate the absorption of new energy on a larger energy allocation scale.

[0003] So far, the elastic aggregation method of distributed electric heating loads has been greatly limited in engineering application due to its large number, wide range, and complex electricity consumption behavior. In addition, there is little historical data on the electric-heat loads of existing distributed electric heating users, and the collected data has large areas of missing and abnormal situations, which increases the complexity of the distributed electric-heat load group aggregation. Summary of the Invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a system and method for elastic aggregation of distributed electric heating load characteristics, so as to solve the problem of feature identification and aggregation of distributed electric heating users, thereby facilitating the management and regulation of electric-heating load groups and improving the controllable potential of electric-heating load groups.

[0005] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0006] In a first aspect, the present invention provides a method for elastically aggregating distributed electric heating load characteristics, comprising:

[0007] Receive electric heating load data from decentralized electric heating users;

[0008] Preprocess the electric heating load data of decentralized electric heating users;

[0009] According to the pre-processed electric heating load data of decentralized electric heating users, seven types of load characteristic indicators are used as clustering indicators of decentralized electric heating users, and the FCM clustering algorithm is used to cluster decentralized electric heating users.

[0010] Three clustering effectiveness indices are established to evaluate clustering quality and determine the optimal number of clusters.

[0011] Furthermore, data preprocessing includes:

[0012] Identify whether the collected raw data set contains outliers or missing values;

[0013] In response to abnormal or missing electric heating load data at certain times of the day, the adjacent value interpolation method is used to fill it;

[0014] In response to the missing electric heating load data of a day, the load value at the corresponding time of the previous day is used instead.

[0015] Furthermore, the seven types of load characteristic indicators include peak power consumption rate, normal power consumption rate, valley power consumption rate, load rate, peak-valley difference, peak-valley difference rate and heating season imbalance coefficient:

[0016] The peak power consumption rate is expressed as:

[0017]

[0018] Where R P represents the peak power consumption rate; t peak represents the starting time of the peak period; t PEAK represents the end time of the peak period; t and P represent the time and electric heating load power respectively; P t represents the electric heating load power at time t;

[0019] The average power consumption rate is expressed as:

[0020]

[0021] Where R F represents the average power consumption rate; t flat represents the starting time of the normal period; t FLAT Represents the end time of the normal period;

[0022] The off-peak power consumption rate is expressed as:

[0023]

[0024] Where R V represents the valley power consumption rate; t valley represents the starting time of the valley period; t VALLEY Represents the end time of the valley period;

[0025] The load factor is expressed as:

[0026] R L =aveP t / max P t

[0027] Where RL Represents load rate; ave represents the average value; max represents the maximum value;

[0028] The peak-to-valley difference is expressed as:

[0029] D PV =max P t -min P t

[0030] Where D PV represents the peak-to-valley difference; min represents the minimum value;

[0031] The peak-to-valley difference rate is expressed as:

[0032] R PVD =(max P t -min P t ) / max P t

[0033] Where R PVD represents the peak-to-valley ratio;

[0034] The heating season imbalance coefficient is expressed as:

[0035]

[0036] Where R U represents the heating season imbalance coefficient; m represents the number of months; P m Represents the electric heating load power in month m.

[0037] Furthermore, the objective function of the FCM clustering algorithm is expressed as:

[0038]

[0039] In the formula, N represents the number of samples; K represents the number of clusters; u ij represents the membership of sample i to class j; m represents the weighted index; x i represents the i-th sample; c j represents the cluster center of the jth cluster;

[0040] The degree of membership is expressed as:

[0041]

[0042] Where c k Represents the cluster center of the kth cluster;

[0043] The cluster center of the jth cluster is expressed as:

[0044]

[0045] Furthermore, the three clustering effectiveness indices include the XB index, the CHI index, and the DBI index, where:

[0046] The XB indicator is expressed as:

[0047]

[0048] Where x j represents the jth sample; c i represents the cluster center of cluster i;

[0049] The CHI indicator is expressed as:

[0050]

[0051] Where, represents the average distance between all samples; represents the average distance of samples in the kth cluster; n k represents the number of samples in the k-th cluster, represents the average distance of samples in cluster i, n i represents the number of samples in cluster i;

[0052] The DBI indicator is expressed as:

[0053]

[0054] Where, σ i represents the average distance from all points in cluster i to the cluster center, σ j represents the average distance from all points in cluster j to the cluster center; d(c i ,c j ) represents the distance between the centers of two clusters.

[0055] In a second aspect, the present invention provides a system for elastically aggregating distributed electric heating load characteristics, comprising:

[0056] Data receiving module: used to receive electric heating load data of decentralized electric heating users;

[0057] Preprocessing module: used to preprocess the electric heating load data of decentralized electric heating users;

[0058] Clustering module: It is used to cluster distributed electric heating users based on the pre-processed electric heating load data, using seven types of load characteristic indicators as clustering indicators for distributed electric heating users, and using the FCM clustering algorithm to cluster distributed electric heating users;

[0059] Evaluation module: used to evaluate clustering quality and determine the optimal number of clusters by establishing three clustering effectiveness indicators.

[0060] In a third aspect, the present invention provides a device for elastically aggregating load characteristics of distributed electric heating, comprising a processor and a storage medium;

[0061] The storage medium is used to store instructions;

[0062] The processor is configured to operate according to the instructions to execute the steps of any of the above methods.

[0063] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] This paper validates an elastic aggregation method that incorporates characteristic indicators of electric heating loads by selecting electric and thermal load data from distributed electric heating users. The method demonstrates that this method can effectively and accurately aggregate distributed electric heating loads. This method accurately identifies and aggregates the characteristics of distributed electric heating users, facilitating the management and regulation of electric and thermal load groups, increasing their controllability, and providing a basis for power grid regulation of electric heating users. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a flow chart of a method for elastically aggregating distributed electric heating load characteristics provided in the first embodiment of the present invention;

[0067] Figure 2 This is a flow chart of the FCM clustering algorithm provided in Example 1 of the present invention;

[0068] Figure 3 is a graph of the FCM clustering objective function provided in the first embodiment of the present invention;

[0069] Figure 4 This is a numerical distribution curve diagram of three types of effectiveness indicators provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0070] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention.

[0071] Example 1:

[0072] This embodiment provides a method for elastically aggregating distributed electric heating load characteristics. To better understand the purpose, structure, and function of the present invention, the following is a detailed description of the method for elastically aggregating distributed electric heating load characteristics in conjunction with the accompanying drawings.

[0073] Step 1: preprocess the collected electric heating load data of decentralized electric heating users, that is, identify whether the collected original data set contains abnormal values ​​or missing values;

[0074] Step 2: Based on the result obtained in step 1, determine whether the load data of decentralized electric heating users contains abnormal values ​​or missing values. If there are abnormal or missing electric heating load data at certain times of the day, fill them in using the adjacent value interpolation method. If the electric heating load data of a day is missing, use the load value of the corresponding time of the previous day instead.

[0075] Step 3. Based on the pre-processed electric heating load data of decentralized electric heating users in the province, seven types of load characteristic indicators with clear physical meanings are used as clustering indicators for decentralized electric heating users. The seven types of load characteristic indicators include peak power consumption rate, normal power consumption rate, valley power consumption rate, load rate, peak-valley difference, peak-valley difference rate and heating season imbalance coefficient.

[0076] The peak power consumption rate is expressed as:

[0077]

[0078] In formula (1), R P represents the peak power consumption rate; t peak represents the starting time of the peak period; t PEAK represents the end time of the peak period; t and P represent the time and electric heating load power respectively; P t represents the electric heating load power at time t;

[0079] The average power consumption rate is expressed as:

[0080]

[0081] In formula (2), R F represents the average power consumption rate; t flat represents the starting time of the normal period; t FLAT Represents the end time of the normal period;

[0082] The off-peak power consumption rate is expressed as:

[0083]

[0084] In formula (3), R V represents the valley power consumption rate; t valley represents the starting time of the valley period; t VALLEY Represents the end time of the valley period;

[0085] The load factor is expressed as:

[0086] RL =aveP t / max P t (4)

[0087] In formula (4), R L Represents load rate; ave represents the average value; max represents the maximum value;

[0088] The peak-to-valley difference is expressed as:

[0089] D PV =max P t -min P t (5)

[0090] In formula (5), D PV represents the peak-to-valley difference; min represents the minimum value;

[0091] The peak-to-valley difference rate is expressed as:

[0092] R PVD =(max P t -min P t ) / max P t (6)

[0093] In formula (6), R PVD represents the peak-to-valley ratio;

[0094] The heating season imbalance coefficient is expressed as:

[0095]

[0096] In formula (7), R U represents the heating season imbalance coefficient; m represents the number of months; P m Represents the electric heating load power in month m.

[0097] Step 4: Use the FCM clustering algorithm to cluster decentralized electric heating users to achieve accurate aggregation of decentralized electric heating users.

[0098] First, since different types of load characteristic indicators vary greatly, it is not convenient to compare data. Therefore, the clustering indicator data needs to be normalized before cluster analysis. Here, extreme value sequence normalization is used. After normalization, all values ​​are between 0 and 1. The original data samples are normalized according to formula (8).

[0099]

[0100] In the formula, max[x i1 ,x i2 ,···,x i96] is the maximum value in the characteristic index data of the i-th type electric heating load.

[0101] Secondly, the FCM clustering algorithm is based on the fuzzy c partitioning of the objective function, and obtains K uniform fuzzy sets by optimizing the objective function. Its steps are as follows:

[0102] 1) Given the number of clusters K, the fuzzy degree m, the maximum number of iterations and the iteration termination condition;

[0103] 2) Initialize the cluster prototype and update the fuzzy membership matrix u according to formula (9) ij ;

[0104]

[0105] Where u ij Represents the membership of sample i to class j, and must satisfy 0≤u ij ≤1 and The constraints, represents the sum of the membership of each sample to each cluster is 1; K represents the number of clusters; m represents the weighted index, which is generally 2; x i represents the i-th sample; c j represents the cluster center of the jth cluster; c k Represents the cluster center of the kth cluster.

[0106] 3) Calculate the cluster center c according to formula (10) j ;

[0107]

[0108] Where N represents the number of samples;

[0109] 4) Calculate the objective function according to formula (11). If the objective function difference is less than the threshold or the number of iterations is greater than the set maximum number of iterations, the algorithm stops, otherwise go to step 2).

[0110]

[0111] Step 5: Evaluate the clustering quality and determine the optimal number of clusters by establishing three clustering effectiveness indices. The three clustering effectiveness indices include XB index, CHI index and DBI index.

[0112] The XB indicator is expressed as:

[0113]

[0114] Where x j represents the jth sample, c irepresents the cluster center of cluster i; the other characters have the same meaning as formula (9). The numerator reflects the compactness within the cluster; the smaller the value, the more compact it is; the denominator reflects the separation between clusters; the larger the value, the better the separation. Therefore, the smaller the value of indicator XB, the better the clustering effect.

[0115] The CHI indicator is expressed as:

[0116]

[0117] Where, represents the average distance between all samples; represents the average distance of samples in the kth cluster; n k represents the number of samples in the k-th cluster, represents the average distance of samples in cluster i, n i Represents the number of samples in cluster i. The larger the CHI index value, the smaller the intra-class distance and the larger the inter-class distance of the clustering result, and the better the clustering effect.

[0118] The DBI indicator is expressed as:

[0119]

[0120] Where σ i represents the average distance from all points in cluster i to the cluster center, σ j represents the average distance from all points in cluster j to the cluster center, σ i +σ j represents the sum of the average distances of all points in the cluster to the cluster center point; d(c i ,c j ) represents the distance between the centers of two clusters. The smaller the DBI index value, the closer the clusters are within the same cluster and the farther apart the different clusters are. In other words, the smaller the intra-cluster distance and the larger the inter-cluster distance, the better the clustering effect.

[0121] Example 2:

[0122] A system for elastically aggregating distributed electric heating load characteristics, which can implement the method for elastically aggregating distributed electric heating load characteristics described in Example 1, includes:

[0123] Data receiving module: used to receive electric heating load data of decentralized electric heating users;

[0124] Preprocessing module: used to preprocess the electric heating load data of decentralized electric heating users;

[0125] Clustering module: It is used to cluster distributed electric heating users based on the pre-processed electric heating load data, using seven types of load characteristic indicators as clustering indicators for distributed electric heating users, and using the FCM clustering algorithm to cluster distributed electric heating users;

[0126] Evaluation module: used to evaluate clustering quality and determine the optimal number of clusters by establishing three clustering effectiveness indicators.

[0127] Example 3:

[0128] The embodiment of the present invention further provides a device for elastically aggregating distributed electric heating load characteristics, which can implement the elastic aggregation method for distributed electric heating load characteristics described in the first embodiment, including a processor and a storage medium;

[0129] The storage medium is used to store instructions;

[0130] The processor is configured to operate according to the instructions to execute the steps of the following method:

[0131] Receive electric heating load data from decentralized electric heating users;

[0132] Preprocess the electric heating load data of decentralized electric heating users;

[0133] According to the pre-processed electric heating load data of decentralized electric heating users, seven types of load characteristic indicators are used as clustering indicators of decentralized electric heating users, and the FCM clustering algorithm is used to cluster decentralized electric heating users.

[0134] Three clustering effectiveness indices are established to evaluate clustering quality and determine the optimal number of clusters.

[0135] Example 4:

[0136] An embodiment of the present invention further provides a computer-readable storage medium that can implement the method for elastically aggregating distributed electric heating load characteristics described in Example 1. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the following method steps:

[0137] Receive electric heating load data from decentralized electric heating users;

[0138] Preprocess the electric heating load data of decentralized electric heating users;

[0139] According to the pre-processed electric heating load data of decentralized electric heating users, seven types of load characteristic indicators are used as clustering indicators of decentralized electric heating users, and the FCM clustering algorithm is used to cluster decentralized electric heating users.

[0140] Three clustering effectiveness indices are established to evaluate clustering quality and determine the optimal number of clusters.

[0141] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0142] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 steps in the process. 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.

[0143] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 1 The function specified in one or more boxes.

[0144] 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 the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0145] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for elastic aggregation of distributed electric heating load characteristics, characterized in that: include: Receive electric heating load data from decentralized electric heating users; Preprocess the electric heating load data of decentralized electric heating users; According to the pre-processed electric heating load data of decentralized electric heating users, seven types of load characteristic indicators are used as clustering indicators of decentralized electric heating users, and the FCM clustering algorithm is used to cluster decentralized electric heating users. The clustering quality is evaluated and the optimal number of clusters is determined by establishing three clustering effectiveness indices. Among them, the seven types of load characteristic indicators include peak power consumption rate, normal power consumption rate, valley power consumption rate, load rate, peak-valley difference, peak-valley difference rate and heating season imbalance coefficient: The peak power consumption rate is expressed as: Where R P represents the peak power consumption rate; t peak represents the starting time of the peak period; t PEAK represents the end time of the peak period; t and P represent the time and electric heating load power respectively; P t represents the electric heating load power at time t; The average power consumption rate is expressed as: Where R F represents the average power consumption rate; t flat represents the starting time of the normal period; t FLAT Represents the end time of the normal period; The off-peak power consumption rate is expressed as: Where R V represents the valley power consumption rate; t valley represents the starting time of the valley period; t VALLEY Represents the end time of the valley period; The load factor is expressed as: R L =aveP t / maxP t Where R L Represents load rate; ave represents the average value; max represents the maximum value; The peak-to-valley difference is expressed as: D PV =maxP t -minP t Where D PV represents the peak-to-valley difference; min represents the minimum value; The peak-to-valley difference rate is expressed as: R PVD =(maxP t -minP t ) / maxP t Where R PVD represents the peak-to-valley ratio; The heating season imbalance coefficient is expressed as: Where R U represents the heating season imbalance coefficient; ms represents the number of months; P ms represents the electric heating load power in ms month; The three clustering effectiveness indicators include XB index, CHI index and DBI index, among which: The XB indicator is expressed as: Where x j represents the jth sample; c i represents the cluster center of cluster i; N represents the number of samples; K represents the number of clusters; u ij represents the membership of sample i to class j; m represents the weighted index; c j represents the cluster center of the jth cluster; The CHI indicator is expressed as: Where, represents the average distance between all samples; represents the average distance of samples in the kth cluster; n k represents the number of samples in the k-th cluster, represents the average distance of samples in cluster i, n i represents the number of samples in cluster i; The DBI indicator is expressed as: Where, σ i represents the average distance from all points in cluster i to the cluster center, σ j represents the average distance from all points in cluster j to the cluster center; d(c i ,c j ) represents the distance between the centers of two clusters.

2. The elastic aggregation method of distributed electric heating load characteristics according to claim 1 is characterized in that: Data preprocessing includes: Identify whether the collected raw data set contains outliers or missing values; In response to abnormal or missing electric heating load data at certain times of the day, the adjacent value interpolation method is used to fill it; In response to the missing electric heating load data of a day, the load value at the corresponding time of the previous day is used instead.

3. The elastic aggregation method of distributed electric heating load characteristics according to claim 1 is characterized in that: The objective function of the FCM clustering algorithm is expressed as: Where x i represents the i-th sample; The degree of membership is expressed as: Where c k Represents the cluster center of the kth cluster; The cluster center of the jth cluster is expressed as:

4. A system for elastically aggregating distributed electric heating load characteristics based on the method for elastically aggregating distributed electric heating load characteristics according to any one of claims 1 to 3, characterized in that: include: Data receiving module: used to receive electric heating load data of decentralized electric heating users; Preprocessing module: used to preprocess the electric heating load data of decentralized electric heating users; Clustering module: It is used to cluster distributed electric heating users based on the pre-processed electric heating load data, using seven types of load characteristic indicators as clustering indicators for distributed electric heating users, and using the FCM clustering algorithm to cluster distributed electric heating users; Evaluation module: used to evaluate clustering quality and determine the optimal number of clusters by establishing three clustering effectiveness indicators.

5. An elastic aggregation device with distributed electric heating load characteristics, characterized in that: including processor and storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images