Residential district design stage total load analysis method and device adopting interval prediction and application of residential district design stage total load analysis method and device

Abstract

The invention discloses a residential district design stage total load analysis method and device adopting interval prediction and application. The method comprises the following steps: acquiring historical data of a plurality of residential districts in a set range near a new residential district, and taking the historical data as calculation data and input training sample data; obtaining time sequence load external characteristic power data according to the calculation data; determining maximum load data and time sequence equivalent load data through the time sequence load external characteristic power data, and taking the maximum load data and the time sequence equivalent load data as output training sample data; respectively constructing a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model; training the prediction model by inputting and outputting training samples; inputting design data into the trained prediction model to obtain maximum load interval data and time sequence equivalent load interval data; and comparing the upper limit values of the two pieces of data, and taking the large value as the total load of the new residential district. Reasonable calculation load is obtained by using historical data, and the problem that an empirical method is too conservative is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of load calculation for building design, and in particular to a total load analysis method, device and application in the design phase of a residential area based on interval prediction. Background Art

[0002] In order to save energy and reduce carbon emissions, the penetration rate of distributed energy on the user side of the power grid continues to increase, and new loads such as electric vehicles are gradually increasing. However, in the design plans of existing residential communities, the reported capacity of residential communities is based on empirical values, which are often larger than actual demand and fail to take into account the impact of emerging factors such as building photovoltaics and electric vehicles.

[0003] At present, the existing load calculation methods generally use empirical methods such as unit index method, demand coefficient method and utilization coefficient method. The unit index method relies on data induction and is simple in calculation, so the accuracy is low and it is only suitable for estimation; the demand coefficient method and utilization coefficient method mainly rely on empirical coefficients to calculate, and all equipment power needs to be known, but the equipment in the design stage and the actual use stage are not completely consistent, and the error is large in some scenarios.

[0004] The prediction method provides a solution to the above problems. The prediction method is a method that uses statistics, machine learning, data mining and other technologies to model historical data to predict the future trend of an event. Point prediction methods include regression prediction, classification prediction and time series prediction, while interval prediction is based on point prediction and obtains a prediction interval at a certain confidence level based on probability theory. In order to ensure a certain capacity of spare equipment, it is effective to use the upper limit of the interval prediction as a conservative total load calculation value. Therefore, how to design a new total load calculation method for residential communities to provide a reference for community equipment configuration has become an urgent problem to be solved. Summary of the invention

[0005] To this end, the present invention provides a total load analysis method, device and application in the design stage of a residential area using interval prediction. The method uses historical data based on an interval prediction method to obtain a reasonable calculated load, thereby solving the problem that the empirical method is too conservative.

[0006] In order to achieve the above-mentioned object, the present invention provides the following technical solution: S1, obtaining historical data of several residential communities within a set range near a new residential community according to a set data source; using the obtained historical data as calculation data and input training sample data;

[0007] S2. Obtain the time-series load external characteristic power data of several nearby residential quarters through calculation according to the calculated data; determine the maximum load data and time-series equivalent load data of several nearby residential quarters through the time-series load external characteristic power data; and use the maximum load data and the time-series equivalent load data as output training sample data;

[0008] S3, respectively constructing a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model; training the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model through the input training sample data and the output training sample data;

[0009] S4, inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, and obtaining the maximum load interval data and the time series equivalent load interval data of the new residential quarter;

[0010] S5. Compare the upper limit value of the maximum load interval data of the new residential quarter with the upper limit value of the time series equivalent load interval data, and take the larger value of the two as the total load of the new residential quarter.

[0011] As a preferred solution of the total load analysis method in the design phase of a residential area based on interval prediction, in the process of using the acquired historical data as the calculation data and the input training sample data, the calculation data includes: time series power data of several nearby residential areas, building photovoltaic time series power data and electric vehicle charging and discharging time series power data;

[0012] The input training sample data includes: household data, building area data, building roof area data and the number of charging piles of several nearby residential communities.

[0013] As a preferred scheme for the total load analysis method in the residential area design stage based on interval prediction, in the process of respectively constructing the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model, the multi-input single-output interval prediction model is constructed using the maximum load data of several nearby residential areas as output sample data; and the multi-input multi-output interval prediction model is constructed using the time series equivalent load interval data of several nearby residential areas as output sample data.

[0014] As a preferred scheme of the total load analysis method in the design stage of residential communities based on interval prediction, in the process of inputting the design data of the new residential community into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the design data of the new residential community includes: the number of households in the new residential community, the building area data, the building roof area data and the number of charging piles.

[0015] As a preferred solution of the total load analysis method in the residential quarter design phase based on interval prediction, in the process of inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the confidence level is set to 95%.

[0016] The present invention also provides a total load analysis device for a residential area design phase based on interval prediction, based on the above total load analysis method for a residential area design phase based on interval prediction, comprising:

[0017] A calculation data and input training sample data acquisition module is used to acquire historical data of several residential communities within a set range near the new residential community according to a set data source; and use the acquired historical data as calculation data and input training sample data;

[0018] An output training sample data acquisition module is used to obtain the time-series load external characteristic power data of several nearby residential communities through calculation according to the calculation data; determine the maximum load data and time-series equivalent load data of several nearby residential communities through the time-series load external characteristic power data; and use the maximum load data and the time-series equivalent load data as output training sample data;

[0019] A prediction model construction module, used to respectively construct a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model; train the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model through the input training sample data and the output training sample data;

[0020] A prediction interval data acquisition module, used for inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, and obtaining the maximum load interval data and time series equivalent load interval data of the new residential quarter;

[0021] The total load acquisition module is used to compare the upper limit value of the maximum load interval data of the new residential area with the upper limit value of the time series equivalent load interval data, and take the larger value of the two as the total load of the new residential area.

[0022] As a preferred solution of the total load analysis device in the design stage of a residential area based on interval prediction, in the calculation data and input training sample data acquisition module, in the process of using the acquired historical data as the calculation data and the input training sample data, the calculation data includes: time series power data of several nearby residential areas, building photovoltaic time series power data and electric vehicle charging and discharging time series power data;

[0023] The input training sample data includes: household data, building area data, building roof area data and the number of charging piles of several nearby residential communities.

[0024] As a preferred solution of the total load analysis device in the residential area design stage based on interval prediction, in the prediction model construction module, in the process of respectively constructing the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model, the multi-input single-output interval prediction model is constructed using the maximum load data of several nearby residential areas as output sample data; and the multi-input multi-output interval prediction model is constructed using the time series equivalent load interval data of several nearby residential areas as output sample data.

[0025] As a preferred solution of the total load analysis device in the design stage of a residential area based on interval prediction, in the prediction interval data acquisition module, in the process of inputting the design data of the new residential area into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the design data of the new residential area includes: the number of households in the new residential area, the building area data, the building roof area data and the number of charging piles.

[0026] As a preferred solution of the total load analysis device in the residential quarter design stage based on interval prediction, in the prediction interval data acquisition module, when inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the confidence level is set to 95%.

[0027] A computer-readable storage medium includes instructions, which, when executed on a computer, enable the computer to execute the total load analysis method at the design stage of a residential quarter using interval prediction.

[0028] The present invention has the following advantages: historical data of several residential communities within a set range near a new residential community are obtained according to a set data source; the obtained historical data are used as calculation data and input training sample data; according to the calculation data, the time-series load external characteristic power data of several nearby residential communities are obtained by calculation; the maximum load data and the time-series equivalent load data of several nearby residential communities are determined by the time-series load external characteristic power data; the maximum load data and the time-series equivalent load data are used as output training sample data; a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model are respectively constructed; the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model are trained by the input training sample data and the output training sample data; the design data of the new residential community is input into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, and the maximum load interval data and the time-series equivalent load interval data of the new residential community are obtained; the upper limit value of the maximum load interval data of the new residential community is compared with the upper limit value of the time-series equivalent load interval data, and the larger value of the two is taken as the total load of the new residential community. The total load calculation method for the residential area design stage of the present invention, after obtaining the historical data of other communities within the set range near the new residential area, after data processing, constructs and trains the interval prediction models of multiple inputs and single outputs and multiple inputs and multiple outputs, and then predicts two types of interval data based on the design data of the new residential area, and finally compares and takes the upper limit maximum value as the total load. Considering that the original total load calculation methods in the design stage are all empirical methods such as data induction and empirical coefficients, their accuracy is low, the error is large in some scenarios, and the results are too conservative, causing unnecessary waste. Therefore, the present invention can solve the above problems based on the interval prediction method, model other residential historical data, and construct two interval prediction models with maximum load and time series equivalent load as output, obtain two sets of more conservative interval data through prediction, and in order to ensure a certain spare capacity, the maximum value of the upper limits of the two is used as the final calculation result, which not only ensures accuracy but also ensures redundancy in actual production, and at the same time does not require cumbersome manual calculations and experience-based calculation coefficient selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic flow chart of a total load analysis method for a residential quarter design phase using interval prediction provided in Embodiment 1 of the present invention;

[0030] Figure 2 A schematic flow chart of specific steps of the total load analysis method for the residential quarter design phase using interval prediction provided in Embodiment 1 of the present invention;

[0031] Figure 3A schematic diagram of interval prediction results and actual cell demand in a possible embodiment provided in Embodiment 1 of the present invention;

[0032] Figure 4 This is a schematic diagram of the architecture of the total load analysis device in the residential quarter design phase based on interval prediction provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0033] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Example 1

[0035] See also Figure 1 and Figure 2 Embodiment 1 of the present invention provides a total load analysis method for a residential quarter design phase based on interval prediction, comprising the following steps:

[0036] S1. Obtain historical data of several residential communities within a set range near the new residential community according to a set data source; use the acquired historical data as calculation data and input training sample data;

[0037] S2. Obtain the time-series load external characteristic power data of several nearby residential quarters through calculation according to the calculated data; determine the maximum load data and time-series equivalent load data of several nearby residential quarters through the time-series load external characteristic power data; and use the maximum load data and the time-series equivalent load data as output training sample data;

[0038] S3, respectively constructing a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model; training the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model through the input training sample data and the output training sample data;

[0039] S4, inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, and obtaining the maximum load interval data and the time series equivalent load interval data of the new residential quarter;

[0040] S5. Compare the upper limit value of the maximum load interval data of the new residential quarter with the upper limit value of the time series equivalent load interval data, and take the larger value of the two as the total load of the new residential quarter.

[0041] In this embodiment, in step S1, in the process of using the acquired historical data as the calculation data and the input training sample data, the calculation data includes: time series power data of several nearby residential areas, building photovoltaic time series power data and electric vehicle charging and discharging time series power data;

[0042] The input training sample data includes: household data, building area data, building roof area data and the number of charging piles of several nearby residential communities.

[0043] Specifically, according to the set data source, historical data of multiple residential communities near the newly built community are obtained, including the number of households data n house , building area data S building , building roof area data S roof 、Number of charging piles n charge , Residential time series power data P building (t), building photovoltaic time series power data P PV (t) and the electric vehicle charging and discharging time series power data P EV (t).

[0044] Set the input training sample to the number of households in other residential areas n house , building area data S building , building roof area data S roof and the number of charging piles n charge ,The above data are relatively easy to obtain in the design phase, so these data are used as input training samples;

[0045] Set the calculation data to the time series power data P of residents in other residential areas building (t), building photovoltaic time series power data P PV (t) and the electric vehicle charging and discharging time series power data P EV (t), the above data are strongly correlated with the cell load size in actual scenarios, so these data are used as calculation data.

[0046] In this embodiment, in step S2, according to the calculation data, the time-series load external characteristic power data P of several nearby residential areas are obtained by calculation. LC (t);

[0047] Specifically, based on the calculation data of other residential areas P building (t), P PV (t) and P EV (t), the time series load external characteristic power data P is calculated by the following formula LC (t):

[0048] P LC(t) = P building (t)-P PV (t)+P EV (t)

[0049] Time series load external characteristic power data P LC The meaning of (t) is the characteristic load size outside the cell in actual scenarios.

[0050] Determine the maximum load data and time-series equivalent load data of several nearby residential quarters through the time-series load external characteristic power data;

[0051] Specifically, based on P LC (t) Further screening to determine the time series equivalent load data P of other residential areas LE (t), for P building (t) Screen and determine the maximum load data P of other residential areas L,max , P L,max is single point data, and P LE (t) is the time series data. Considering both of them simultaneously can fully cover various characteristics of prediction; the maximum load data P L,max The calculation formula is:

[0052] P L,max =max(P building (t))

[0053] The two are used as output training samples of the two prediction models, respectively, containing both single-point and time series features.

[0054] In this embodiment, in step S3, in the process of respectively constructing the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model, the multi-input single-output interval prediction model is constructed using the maximum load data of several nearby residential communities as output sample data; and the multi-input multi-output interval prediction model is constructed using the time series equivalent load interval data of several nearby residential communities as output sample data.

[0055] Specifically, construct a P L,max It is a multi-input single-output interval prediction model for output samples to reflect single-point features; construct a P LE (t) is a multi-input and multi-output interval prediction model for output samples to reflect the time series characteristics;

[0056] The multi-input single-output interval prediction model and the multi-input multi-output interval prediction model are trained using the input training sample data and the output training sample data.

[0057] In this embodiment, in step S4, the design data of the new residential quarter is input into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, so as to obtain the maximum load interval data and the time series equivalent load interval data of the new residential quarter;

[0058] Specifically, obtain the design data of the new residential area, including the number of households in the new residential area n house,new , building area data S building,new , building roof area data S roof,new and the number of charging piles n charge,new ;

[0059] The design data of the new residential area is input into two prediction models to perform multiple-input single-output and multiple-input multiple-output interval predictions;

[0060] In order to ensure a certain reserve capacity and at the same time the result is not too conservative, a 95% confidence level is used to perform interval prediction, and two prediction results are obtained: the predicted maximum load interval data R = (P L,max,lower ,P L,max,upper ) and the forecasted time series equivalent load interval data S = (P LE,lower (t),P LE,upper (t)).

[0061] In this embodiment, in step S5, the upper limit value of the maximum load interval data of the new residential quarter is compared with the upper limit value of the time series equivalent load interval data, and the larger value of the two is taken as the total load of the new residential quarter.

[0062] Specifically, in order to ensure a certain spare capacity, the maximum value P of the upper limit of the data interval of the timing equivalent load is screened. LE,upper (t) max As a choice of prediction results; select the upper limit value P of the maximum load data interval L,max,upper As another option for predicting the results; LE,upper (t) max and P L,max,upper Compare the two values ​​and take the maximum value as the total load P Load .

[0063] The interval prediction method selected by the present invention is the least squares support vector machine (LS-SVM) method, which is a variant of the support vector machine (SVM) and has been used to solve various problems such as load prediction and fault classification. Therefore, the present invention selects this method for explanation, but various other interval prediction methods are applicable to the present invention, and no specific limitation is made thereto.

[0064] In a possible embodiment, an actual calculation example based on a newly built cell and its neighboring cells is provided as follows:

[0065] After obtaining the historical data of multiple communities within a set range near the new residential community, they are divided into calculation data and input training samples. The calculation data are processed to obtain the time-series load external characteristic power of multiple nearby communities, and the maximum load data and time-series equivalent load data are determined as output training samples. According to the LSSVM interval prediction method and the obtained input and output training samples, two prediction models are constructed and trained respectively. Then the data of the new community design stage is obtained and substituted into the trained model for multi-input single-output and multi-input multi-output predictions. The two prediction interval data of the predicted maximum load interval data and the predicted time-series equivalent load interval data of the new community are obtained with a 95% confidence level. The maximum value of the upper limit value of the data interval of the time-series equivalent load is compared with the upper limit value of the maximum load data interval, and the maximum value is taken as the total load.

[0066] like Figure 3 As shown in the interval prediction results and the actual demand of the cell, the upper limit of the maximum load interval is 4466.819kW, the maximum value of the data interval upper limit value of the timing equivalent load is 5023.500kW, and 5023.500kW is selected as the total load. Compared with the actual demand of 4224.533kW, it can be seen that the total load calculated by the present invention is close to the actual power demand on the basis of ensuring a certain spare capacity, thus avoiding a large amount of redundancy in the actual reported capacity.

[0067] In summary, the present invention obtains historical data of several residential communities within a set range near a new residential community according to a set data source; uses the obtained historical data as calculation data and input training sample data; obtains time-series load external characteristic power data of several nearby residential communities through calculation according to the calculation data; determines the maximum load data and time-series equivalent load data of several nearby residential communities through the time-series load external characteristic power data; uses the maximum load data and the time-series equivalent load data as output training sample data; constructs a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model respectively; trains the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model through the input training sample data and the output training sample data; inputs the design data of the new residential community into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, and obtains the maximum load interval data and time-series equivalent load interval data of the new residential community; compares the upper limit value of the maximum load interval data of the new residential community with the upper limit value of the time-series equivalent load interval data, and takes the larger value of the two as the total load of the new residential community. The total load calculation method for the residential area design stage of the present invention, after obtaining the historical data of other communities within the set range near the new residential area, after data processing, constructs and trains the interval prediction models of multiple inputs and single outputs and multiple inputs and multiple outputs, and then predicts two types of interval data based on the design data of the new residential area, and finally compares and takes the upper limit maximum value as the total load. Considering that the original total load calculation methods in the design stage are all empirical methods such as data induction and empirical coefficients, their accuracy is low, the error is large in some scenarios, and the results are too conservative, causing unnecessary waste. Therefore, the present invention can solve the above problems based on the interval prediction method, model other residential historical data, and construct two interval prediction models with maximum load and time series equivalent load as output, obtain two sets of more conservative interval data through prediction, and in order to ensure a certain spare capacity, the maximum value of the upper limits of the two is used as the final calculation result, which not only ensures accuracy but also ensures redundancy in actual production, and at the same time does not require cumbersome manual calculations and experience-based calculation coefficient selection.

[0068] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0069] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] Example 2

[0071] See also Figure 4 Embodiment 2 of the present invention also provides a total load analysis device for a residential quarter design phase based on interval prediction, comprising:

[0072] The calculation data and input training sample data acquisition module 001 is used to acquire historical data of several residential communities within a set range near the new residential community according to a set data source; and use the acquired historical data as calculation data and input training sample data;

[0073] Output training sample data acquisition module 002, used to obtain time-series load external characteristic power data of several nearby residential communities through calculation according to the calculated data; determine maximum load data and time-series equivalent load data of several nearby residential communities through the time-series load external characteristic power data; and use the maximum load data and the time-series equivalent load data as output training sample data;

[0074] The prediction model construction module 003 is used to respectively construct a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model; train the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model through the input training sample data and the output training sample data;

[0075] Prediction interval data acquisition module 004, used for inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, and obtaining the maximum load interval data and time series equivalent load interval data of the new residential quarter;

[0076] The total load acquisition module 005 is used to compare the upper limit value of the maximum load interval data of the new residential quarter with the upper limit value of the time series equivalent load interval data, and take the larger value of the two as the total load of the new residential quarter.

[0077] In this embodiment, in the calculation data and input training sample data acquisition module 001, in the process of using the acquired historical data as the calculation data and the input training sample data, the calculation data includes: time series power data of several nearby residential areas, building photovoltaic time series power data and electric vehicle charging and discharging time series power data;

[0078] The input training sample data includes: household data, building area data, building roof area data and the number of charging piles of several nearby residential communities.

[0079] In this embodiment, in the prediction model construction module 003, in the process of respectively constructing the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model, the multi-input single-output interval prediction model is constructed using the maximum load data of several nearby residential communities as output sample data; and the multi-input multi-output interval prediction model is constructed using the time series equivalent load interval data of several nearby residential communities as output sample data.

[0080] In this embodiment, in the prediction interval data acquisition module 004, in the process of inputting the design data of the new residential area into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the design data of the new residential area includes: the number of households in the new residential area, the building area data, the building roof area data and the number of charging piles.

[0081] At the same time, the confidence level is set to 95%.

[0082] It should be noted that the information interaction, execution process and other contents between the modules of the above-mentioned system are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown above in the present application, and will not be repeated here.

[0083] Example 3

[0084] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code for a method for analyzing the total load in the design stage of a residential community based on interval prediction is stored. The program code includes instructions for executing the method for analyzing the total load in the design stage of a residential community based on interval prediction of embodiment 1 or any possible implementation thereof.

[0085] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0086] Example 4

[0087] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0088] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the total load analysis method for the residential quarter design stage based on interval prediction of Example 1 or any possible implementation thereof.

[0089] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0090] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0091] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0092] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A total load analysis method for residential quarters design phase using interval prediction, characterized in that: The following steps are involved: S1. Obtain historical data of several residential communities within a set range near the new residential community according to a set data source; use the acquired historical data as calculation data and input training sample data; S2. Obtain the time-series load external characteristic power data of several nearby residential quarters through calculation according to the calculated data; determine the maximum load data and time-series equivalent load data of several nearby residential quarters through the time-series load external characteristic power data; and use the maximum load data and the time-series equivalent load data as output training sample data; S3, respectively constructing a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model; training the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model through the input training sample data and the output training sample data; S4, inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, and obtaining the maximum load interval data and the time series equivalent load interval data of the new residential quarter; S5. Compare the upper limit value of the maximum load interval data of the new residential quarter with the upper limit value of the time series equivalent load interval data, and take the larger value of the two as the total load of the new residential quarter.

2. The total load analysis method for residential quarter design phase using interval prediction according to claim 1 is characterized in that: In S1, the calculation data includes the time-series power data of several nearby residential communities, the building photovoltaic time-series power data and the electric vehicle charging and discharging time-series power data; the input training sample data includes the number of households data, building area data, building roof area data and the number of charging piles of several nearby residential communities.

3. The total load analysis method for residential quarter design phase using interval prediction according to claim 1 is characterized in that: In S3, in the process of respectively constructing the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model, the multi-input single-output interval prediction model is constructed using the maximum load data of several nearby residential communities as output sample data; and the multi-input multi-output interval prediction model is constructed using the time series equivalent load interval data of several nearby residential communities as output sample data.

4. The total load analysis method for residential quarter design phase using interval prediction according to claim 1 is characterized in that: In S4, in the process of inputting the design data of the new residential area into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the design data of the new residential area includes the number of households, building area data, building roof area data and the number of charging piles in the new residential area.

5. The total load analysis method for residential quarter design phase using interval prediction according to claim 1 is characterized in that: In S4, in the process of inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the confidence level is set to 95%.

6. A total load analysis device for a residential area design phase using interval prediction, using the total load analysis method for a residential area design phase using interval prediction as claimed in any one of claims 1 to 5, characterized in that: include: A calculation data and input training sample data acquisition module is used to acquire historical data of several residential communities within a set range near the new residential community according to a set data source; Using the acquired historical data as calculation data and input training sample data; An output training sample data acquisition module is used to obtain the time-series load external characteristic power data of several nearby residential communities through calculation according to the calculation data; determine the maximum load data and time-series equivalent load data of several nearby residential communities through the time-series load external characteristic power data; and use the maximum load data and the time-series equivalent load data as output training sample data; A prediction model construction module, used to respectively construct a multi-input single-output interval prediction model and a multi-input multi-output interval prediction model; train the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model through the input training sample data and the output training sample data; A prediction interval data acquisition module, used for inputting the design data of the new residential quarter into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, and obtaining the maximum load interval data and time series equivalent load interval data of the new residential quarter; The total load acquisition module is used to compare the upper limit value of the maximum load interval data of the new residential area with the upper limit value of the time series equivalent load interval data, and take the larger value of the two as the total load of the new residential area.

7. The total load analysis device for residential quarter design phase based on interval prediction according to claim 6 is characterized in that: In the calculation data and input training sample data acquisition module, in the process of using the acquired historical data as the calculation data and the input training sample data, the calculation data includes: time-series power data of several nearby residential communities, building photovoltaic time-series power data and electric vehicle charging and discharging time-series power data; the input training sample data includes household number data, building area data, building roof area data and the number of charging piles of several nearby residential communities.

8. The total load analysis device for residential quarter design phase based on interval prediction according to claim 6 is characterized in that: In the prediction model construction module, in the process of respectively constructing the multi-input single-output interval prediction model and the multi-input multi-output interval prediction model, the multi-input single-output interval prediction model is constructed using the maximum load data of several nearby residential communities as output sample data; the multi-input multi-output interval prediction model is constructed using the time series equivalent load interval data of several nearby residential communities as output sample data; in the prediction interval data acquisition module, in the process of inputting the design data of the new residential community into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the design data of the new residential community includes: the number of households in the new residential community, the building area data, the building roof area data and the number of charging piles; in the prediction interval data acquisition module, in the process of inputting the design data of the new residential community into the trained multi-input single-output interval prediction model and the multi-input multi-output interval prediction model for prediction, the confidence level is set to 95%.

9. An information data processing terminal for implementing the total load analysis method for the residential quarter design phase using interval prediction as described in any one of claims 1 to 5.

10. A computer-readable storage medium comprising instructions, which, when executed on a computer, enables the computer to execute the method for analyzing total load in the design phase of a residential area using interval prediction as claimed in any one of claims 1 to 5.

Images