Meteorological data fused distribution transformer reverse transmission and heavy overload risk early warning method and system

Abstract

The invention discloses a distribution transformer reverse transmission and heavy overload risk early warning method and system fused with meteorological data. The method comprises the following steps: acquiring meteorological data, equipment related data and power utilization related data; an analysis model is constructed, wherein the analysis model comprises a distribution transformer and meteorological data through fusion model, a distribution transformer equipment load calculation model, an ARIMA prediction model and a weather comprehensive index calculation model; establishing a photovoltaic reverse transmission risk early warning model and a heavy overload comprehensive risk early warning model, and solving the photovoltaic reverse transmission risk early warning model and the heavy overload comprehensive risk early warning model in combination with parameters obtained by the analysis model; and carrying out reverse transmission risk early warning or heavy overload risk early warning on the basis of the distribution transformer reverse transmission risk value and the distribution transformer heavy overload risk value calculated by the comprehensive risk early warning model. According to the invention, corresponding early warning is provided for equipment reverse transmission and heavy overload conditions possibly caused under extreme weather conditions in combination with meteorological data and equipment power utilization data, so that comprehensive and accurate early warning protection of the distribution transformer system is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of risk warning for distribution transformers, and more specifically, to a distribution transformer reverse transmission and heavy overload risk warning method and system integrating meteorological data. Background Art

[0002] With the development of economy and society, the demand for electricity is increasing, the scale of distribution network is becoming larger and larger, and the stability and reliability of its operation are crucial to the continuous supply of electricity. Therefore, many related technical solutions are used to warn and predict the stability and reliability of equipment operation and lines, such as a distribution network risk assessment method containing distributed photovoltaic power sources, a power meteorological data fusion method based on multi-source meteorological forecast, system and storage medium and process, a distribution transformer overload prediction method based on big data analysis, device and medium, etc., providing a method for business personnel and operators to quickly predict and evaluate the power supply risks that may exist in equipment and lines.

[0003] Existing patent document 1 (CN109165846A) proposes a risk assessment method for a distribution network containing distributed photovoltaic power sources, which is a fast and accurate risk assessment of the distribution network for distributed photovoltaic power generation and the randomness of loads, while existing technical document 2 (CN1 15964675A) proposes a power meteorological data fusion method, system, storage medium and process based on multi-source meteorological forecasts, which is for refined power meteorological forecasts. The existing technical solutions have the problem of insufficient fusion of meteorological forecast data or are not applied to the distribution transformer network equipment for photovoltaic reverse transmission and heavy overload risk warning, resulting in inaccurate and incomplete warning results. Summary of the invention

[0004] In order to solve the deficiencies in the prior art, the present invention provides a distribution transformer reverse transmission and heavy overload risk warning method and system integrating meteorological data, which can realize accurate warning of distribution transformer photovoltaic reverse transmission and heavy overload risks.

[0005] The present invention adopts the following technical solution.

[0006] A distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data comprises the following steps:

[0007] Step 1, collecting meteorological data, equipment-related data and electricity-related data;

[0008] Step 2: construct an analysis model, including a distribution transformer and meteorological data integration model, a distribution transformer equipment load calculation model, an ARIMA prediction model, and a weather comprehensive index calculation model;

[0009] Step 3: Establish a photovoltaic reverse transmission risk warning model and a heavy overload comprehensive risk warning model, and solve the photovoltaic reverse transmission risk warning model and the heavy overload comprehensive risk warning model by combining the parameters obtained by the analysis model;

[0010] Step 4: Based on the distribution transformer reverse transmission risk value and the distribution transformer heavy overload risk value calculated by the comprehensive risk warning model, a reverse transmission risk warning or a heavy overload risk warning is performed.

[0011] Preferably, in step 1, the meteorological data includes: daily temperature data, temperature forecast data, weather conditions, and daily sunshine duration;

[0012] Equipment-related data include: distribution transformer archive data, distribution transformer ledger data, pole-mounted transformer ledger data, distribution station data, distribution transformer 96-point load data, power curve data, and voltage regulation equipment data;

[0013] Electricity consumption related data include: electricity user data, metering data, and distribution power data.

[0014] Preferably, the distribution transformer and meteorological data integration model specifically includes:

[0015] According to the 96-point load data of the distribution transformer and the daily temperature data, the 96-point load data of the daily distribution transformer and the daily temperature data are matched at similar time points: based on the time point corresponding to the 96-point load data of the distribution transformer, the temperature data of the nearest time point calculated forward from the current time point is taken to obtain the associated combination of load-temperature data.

[0016] Preferably, the distribution transformer equipment load calculation model specifically includes: correlating the distribution transformer archive data and daily monitoring load data through the distribution transformer 96-point load data, recording the heavy overload time of the equipment, and forming the heavy overload period data.

[0017] Preferably, the weather comprehensive index calculation model specifically includes:

[0018] Using the temperature forecast data, calculate the comprehensive weather index Wt:

[0019]

[0020] Where β is the photovoltaic output irradiance coefficient, G1 is the irradiance measured by the reference device, G2 is the target irradiance of the DUT, T2 is the target temperature of the DUT, and T1 is the measured temperature of the DUT.

[0021] Preferably, the construction of the ARIMA forecasting model specifically includes:

[0022] By analyzing the autocorrelation function ACF and partial autocorrelation function PACF of the unsteady and first-order difference of the time series data, the influence coefficient φ of the past value on the current value and the influence coefficient θ of the error term are obtained. According to the AIC and BIC criteria and the analysis of the residual sequence, the appropriate ARIMA model order value is selected;

[0023] Obtain the reverse load forecast value FT of the distribution transformer for the next n days based on the ARIMA model:

[0024] F T =φ1x t-1 +.....+φ p x t-p +θ1∈ t-1 +.....+θ q ∈ t-q +∈ t

[0025] Among them, x t is the 96-point data observation value of the distribution transformer load at time point t, φ1~φ p represents the 1st to pth influence coefficients, θ1~θ q represents the influence coefficient of the 1st to qth error terms, ∈ t represents the error term at time point t.

[0026] Preferably, a photovoltaic reverse transmission risk warning model is constructed, and the distribution transformer reverse transmission risk value Gt is calculated using the weighted average method as follows:

[0027] G t =(W t )*F T *T r *SOC

[0028] Among them, F T is the predicted value of the reverse load of the distribution transformer, Wt is the comprehensive weather index Wt, Tr is the sunshine time parameter, and SOC is the state of charge, which ranges from 0 to 1.

[0029] Preferably, the sunshine time parameter Tr is calculated as follows:

[0030] T r =(sunshine duration / 24)*η

[0031] Where η is the transmittance coefficient of the cloud layer in the sky, which is divided into [0, 1] according to the transmittance of the cloud layer in different weather types. On a sunny day, η is 1, and on a rainy day, η is 0. On a cloudy day, it is a decimal between 0 and 1 according to the transmittance of the cloud layer in the sky.

[0032] Preferably, a comprehensive early warning model for heavy overload risk is constructed, and the calculation formula for the heavy overload risk value Gt of the distribution transformer is as follows:

[0033] G t =(W t )*FT*C h *SOC

[0034] Where Wt is the comprehensive weather index, FT is the predicted value of the reverse load of the distribution transformer, and C h is the load reference parameter of the distribution transformer equipment, C h The calculation method is the ratio of the monthly average load of the distribution transformer to the contract capacity. SOC is the state of charge and takes a value between 0 and 1.

[0035] The present invention also proposes a distribution transformer reverse transmission and heavy overload risk warning system integrating meteorological data, which is used to implement the distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data, including: a data acquisition module, an analysis model construction module, an early warning model construction module, a solution module, and an early warning module;

[0036] The data acquisition module is used to collect meteorological data, equipment-related data, and electricity-related data;

[0037] The analysis model building module is used to build analysis models, including the distribution transformer and meteorological data integration model, distribution transformer equipment load calculation model, ARIMA prediction model, and weather comprehensive index calculation model;

[0038] The early warning model building module is used to establish a photovoltaic reverse transmission risk early warning model and a heavy overload comprehensive risk early warning model;

[0039] The solution module solves the photovoltaic reverse transmission risk warning model and the heavy overload comprehensive risk warning model constructed by the warning model construction module in combination with the parameters obtained by the analysis model, and obtains the distribution transformer reverse transmission risk value and the distribution transformer heavy overload risk value;

[0040] The early warning module issues a backflow risk warning or a heavy overload risk warning based on the backflow risk value and the heavy overload risk value of the distribution transformer obtained by the solution module.

[0041] The present invention also provides a terminal, comprising a processor and a storage medium;

[0042] The storage medium is used to store instructions;

[0043] The processor is used to operate according to the instructions to execute the steps of the distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data.

[0044] The present invention also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data are implemented.

[0045] The beneficial effect of the present invention lies in that, compared with the prior art, the present invention constructs a distribution transformer photovoltaic reverse transmission risk warning model and a distribution transformer heavy overload risk warning model. The distribution transformer photovoltaic reverse transmission risk warning model relies on the historical and current measurement data of the reverse power of 96 distribution transformers in the procurement system and the distribution transformer archive data, and combines the improved exponential smoothing method to calculate the predicted reverse load data for a single day in the next 7 days. During the prevention of photovoltaic reverse transmission, combined with the meteorological forecast data, corresponding equipment and other warnings are provided for possible reverse transmission of the distribution transformer; the distribution transformer heavy overload risk warning model uses the historical and current measurement data of the forward power of 96 distribution transformers in the procurement system and the distribution transformer archive data to calculate the distribution transformer heavy overload risk level, and provides corresponding warnings for possible equipment heavy overload situations under extreme weather conditions, such as high temperature or extreme cold, thereby realizing comprehensive and accurate early warning protection for the distribution transformer system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of the distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data in the present invention;

[0047] Figure 2 It is a structural diagram of the distribution transformer reverse transmission and heavy overload risk warning system integrating meteorological data in the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0049] like Figure 1 As shown, the present invention proposes a distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data, which specifically includes the following steps:

[0050] Step 1, collecting meteorological data of the area where the distribution transformer equipment is located, equipment-related data of the distribution transformer equipment, and electricity-related data;

[0051] In the present invention, relevant data can be obtained through the meteorological platform, PMS system (equipment asset management system), D5000 system (dispatching automation system), marketing business system and electricity consumption collection system;

[0052] Specifically, the data to be collected include:

[0053] 1. Meteorological data include: daily temperature data, temperature forecast data, weather conditions, and daily sunshine duration;

[0054] 2. Equipment-related data include: distribution transformer archive data, distribution transformer ledger data, pole-mounted transformer ledger data, distribution station data, distribution transformer 96-point load data, power curve data, and voltage regulation equipment data;

[0055] 3. Electricity consumption related data include: electricity user data, metering data, and distribution power data.

[0056] The equipment in the present invention refers to the distribution transformer equipment, and the meteorological information refers to the meteorological information of the area where the distribution transformer equipment is located;

[0057] Specifically, meteorological data is obtained through the meteorological platform;

[0058] The D5000 system is used to obtain 96-point load data, power curve data, and voltage regulation equipment data of distribution transformers.

[0059] Obtain distribution transformer archive data, distribution transformer ledger data, pole-mounted transformer ledger data and distribution station data through the PMS system;

[0060] Obtain electricity user data and metering data through the marketing business system;

[0061] The power distribution data, power user data and metering data are obtained through the power consumption collection system.

[0062] Further preferably, data integration is performed on the collected data: data from multiple systems are aggregated to form multiple source business data tables in a unified data format.

[0063] Further preferably, the integrated data is preprocessed: based on multiple source business data tables, a multi-dimensional intermediate table is formed through methods such as ETL tools, scripting, data consistency verification, statistical analysis, etc., to ensure the quality and accuracy of the data, unify the data format, and provide reliable data support for subsequent risk prediction.

[0064] Step 2: construct an analysis model, including a distribution transformer and meteorological data integration model, a distribution transformer equipment load calculation model, an ARIMA prediction model, a weather comprehensive index calculation model, and a distribution transformer risk calculation model;

[0065] Among them, the fusion model of distribution transformer and meteorological data: use the 96-point load data of distribution transformer, associate the temperature data in meteorological data, and compare the daily load and temperature data to achieve the fusion of distribution transformer and meteorological data. Specifically, find similar time points for matching the daily distribution transformer load 96-point data and daily temperature data. Based on the time point corresponding to the 96-point data of distribution transformer load, taking into account the lag of load and temperature, take the temperature data of the nearest time point calculated forward from the current time point to obtain the associated combination of load-temperature data.

[0066] Distribution transformer equipment load calculation model: through the 96-point load data of the distribution transformer, the distribution transformer archive data is associated, the load data is monitored daily, the heavy overload time is recorded, and the heavy overload period data is formed.

[0067] Weather comprehensive index calculation model: Based on the temperature data every 15 minutes every day, the temperature benchmark values ​​and sunshine in different seasons are established to calculate the daily weather comprehensive index. The weather comprehensive index is used to correct the forecast value to obtain the corrected forecast value.

[0068] Using the temperature forecast data, calculate the comprehensive weather index Wt:

[0069]

[0070] Where β is the photovoltaic output irradiance coefficient, G1 is the irradiance measured by the reference device, G2 is the target irradiance of the DUT (device under test), T2 is the target temperature of the DUT, and T1 is the measured temperature of the DUT.

[0071] Furthermore, Wt is a key indicator for risk warning. Given α as the initial parameter, its value starts from 0.8 and changes with the monthly average value of the distribution transformer reverse power data. β is the photovoltaic output irradiance coefficient, G1 is the irradiance measured by the reference device, G2 is the target irradiance of the DUT, T2 is the target temperature of the DUT, and T1 is the measured temperature of the DUT.

[0072] ARIMA forecasting model: The required forecast data is obtained through the ARIMA model and the data sorted out by the above model. The ACF and PACF of the autocorrelation function after the unsteady and first-order difference of the time series data are analyzed. According to the AIC and BIC criteria and the analysis of the residual sequence, the appropriate ARIMA model order is selected, including the values ​​of p, q, and d in ARIMA (p, d, q), as follows:

[0073] The time series analysis and prediction is performed based on the collected 96 points of historical daily distribution transformer load data to determine whether the 96 points of distribution transformer load data are stable time series data. The determination method is as follows:

[0074] By calculating the mean, variance and covariance of the data, if the three indicators do not change significantly over time, it means that the time series data is stable, otherwise it means that the time series data is unstable;

[0075] Furthermore, if the 96-point data of the distribution transformer load is unstable, differential calculation is performed on it. The P-order differential calculation formula is as follows:

[0076]

[0077] In the formula, Indicates the difference between the current value at the current P level and the value at the previous moment;

[0078] represents the value at the current moment at the P-1th order;

[0079] represents the value of the previous moment at the P-1th order;

[0080] The calculation of P is a recursive step until the 96-point data of the distribution transformer load are obtained to be stable, at which point the order of P is used as the value of parameter d in the ARIMA model.

[0081] If the 96-point data of the distribution transformer load is stable, the parameter d value is 0.

[0082] The ACF formula used is as follows:

[0083]

[0084] In the formula, ACF(k) indicates that the time series is lagged;

[0085] k represents the lag period, that is, the time interval between the current time point and the comparison time point;

[0086] n represents the lag period, that is, the time interval between the current time point and the comparison time point;

[0087] t represents a specific time point in the time series;

[0088] Z t , Z t-k They represent the observed value of the time series at time point t and the observed value of the time series at time point tk respectively;

[0089] represents the sample mean of the time series Z.

[0090] The q value was obtained by the maximum lag point of the autocorrelation coefficient (ACF) plot.

[0091] AIC formula:

[0092] AIC=-21n(L)+2K

[0093] Among them, AIC represents Akaike's information criterion, which is used to measure the trade-off between the goodness of fit and complexity of the model, L represents the maximum likelihood estimate of the ARIMA model, that is, how well the model fits the data, and K represents the number of ARIMA model parameters.

[0094] Similarly, the BIC formula is as follows:

[0095] BIC=-21n(L)+Kln(n)

[0096] Where BIC represents the Bayesian information criterion, which is also used for model selection.

[0097] By comparing the values ​​of AIC and BIC of different difference orders, the p and q values ​​corresponding to the minimum AIC and BIC are taken as the p and q values ​​of the ARIMA model.

[0098] After determining the p, d, and q values ​​in the ARIMA model, obtain the distribution transformer reverse load forecast value FT for the next n days based on the ARIMA model. Specifically:

[0099] F T =φ1x t-1 +.....+φ p x t-p +θ1∈ t-1 +.....+θ q ∈ t-q +∈ t

[0100] Among them, x t is the 96-point data observation value of the distribution transformer load at time point t, φ is the influence coefficient of the past value on the current value, and θ represents the influence coefficient of q error terms. These coefficients are derived from ACF and PACF, ∈ t It represents the error term at time point t, with a mean of 0 and a variance of σ 2 Independently distributed random variables.

[0101] Step 3: Establish a photovoltaic reverse transmission risk warning model and a heavy overload comprehensive risk warning model, and solve the photovoltaic reverse transmission risk warning model and the heavy overload comprehensive risk warning model in combination with the parameters obtained by the analysis model to obtain the distribution transformer reverse transmission risk value and the distribution transformer heavy overload risk value;

[0102] A photovoltaic reverse transmission risk warning model is constructed, and the distribution transformer reverse transmission risk value Gt is calculated using the weighted average method as follows:

[0103] G t =(W t )*FT*Tr*SOC

[0104] Among them, the load forecast value FT within n days and the weather comprehensive index Wt of the temperature forecast are used to calculate the distribution transformer reverse transmission risk level Gt. The sunshine time parameter Tr plays the role of correcting the weather comprehensive index and forming the risk warning details. SOC is the state of charge, and the value is 0 to 1.

[0105] The calculation of sunshine time parameter Tr is as follows:

[0106] Calculate Tr based on the weather conditions and daily sunshine duration in the collected meteorological data

[0107] T r =(sunshine duration / 24)*η

[0108] Wherein, η is the transmittance coefficient of the cloud layer in the sky, which is divided into [0, 1] according to the transmittance of the cloud layer in different weather types. On a sunny day, η is 1, and on a rainy day, η is 0. On a cloudy day, η is taken as an appropriate decimal between 0 and 1 according to the transmittance of the cloud layer in the sky, for example, it is taken as 0.2 when it is cloudy, and 0.8 when it is partly cloudy.

[0109] The comprehensive early warning model for heavy overload risk has the following specific calculation process:

[0110] Calculate F using the ARIMA model T Secondly, using the weather comprehensive index Wt, combined with the distribution transformer load benchmark parameter C h , and the distribution transformer heavy overload risk value Gt is obtained. The specific formula is:

[0111] G t =(W t )*F T *C h *SOC

[0112] In the formula, C h is the load reference parameter of the distribution transformer equipment, C h The calculation method is the ratio of the monthly average load of the distribution transformer to the contract capacity.

[0113] Step 4: Based on the distribution transformer reverse transmission risk value and distribution transformer heavy overload risk value calculated by the two comprehensive risk warning models, combined with the preset distribution transformer reverse transmission warning value and distribution transformer heavy overload warning value, determine whether a reverse transmission risk warning or a heavy overload risk warning is needed.

[0114] Further preferably, the prediction result details are collected to form a heavy overload warning result table and a photovoltaic reverse transmission warning result table;

[0115] The early warning result table includes the predicted number of distribution transformers that may be at risk in the next week, and presents them one by one by date. It also lists the number of equipment at risk, the jurisdiction unit, etc., and gives a forecast list for distribution lines, distribution transformers and other equipment, identifies the equipment at risk and implements corresponding early warning measures.

[0116] like Figure 2 As shown, the present invention also proposes a distribution transformer reverse transmission and heavy overload risk warning system integrating meteorological data, which is used to implement the distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data, and the system includes: a data acquisition module, an analysis model construction module, an early warning model construction module, a solution module, and an early warning module;

[0117] The data acquisition module is used to collect meteorological data, equipment-related data, and electricity-related data;

[0118] The analysis model building module is used to build analysis models, including the distribution transformer and meteorological data integration model, distribution transformer equipment load calculation model, ARIMA prediction model, and weather comprehensive index calculation model;

[0119] The early warning model building module is used to establish a photovoltaic reverse transmission risk early warning model and a heavy overload comprehensive risk early warning model;

[0120] The solution module solves the photovoltaic reverse transmission risk warning model and the heavy overload comprehensive risk warning model constructed by the warning model construction module in combination with the parameters obtained by the analysis model, and obtains the distribution transformer reverse transmission risk value and the distribution transformer heavy overload risk value;

[0121] The early warning module issues a backflow risk warning or a heavy overload risk warning based on the backflow risk value and the heavy overload risk value of the distribution transformer obtained by the solution module.

[0122] The beneficial effect of the present invention is that, compared with the prior art, it combines meteorological data and equipment power consumption data to provide corresponding early warnings for equipment reverse transmission and heavy overload situations that may occur under extreme weather conditions, and by building a reasonable risk early warning model, it can achieve comprehensive and accurate early warning protection for the distribution transformer system.

[0123] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0124] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0125] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0126] The computer program instructions for performing the disclosed operation may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the disclosed invention.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data, characterized in that: The steps include: Step 1, collecting meteorological data, equipment-related data and electricity-related data; Step 2: construct an analysis model, including a distribution transformer and meteorological data integration model, a distribution transformer equipment load calculation model, an ARIMA prediction model, and a weather comprehensive index calculation model; Step 3: Establish a photovoltaic reverse transmission risk warning model and a heavy overload comprehensive risk warning model, and solve the photovoltaic reverse transmission risk warning model and the heavy overload comprehensive risk warning model by combining the parameters obtained by the analysis model; Step 4: Based on the distribution transformer reverse transmission risk value and the distribution transformer heavy overload risk value calculated by the comprehensive risk warning model, a reverse transmission risk warning or a heavy overload risk warning is performed.

2. The distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data according to claim 1 is characterized in that: In step 1, the meteorological data includes: daily temperature data, temperature forecast data, weather conditions, and daily sunshine duration; Equipment-related data include: distribution transformer archive data, distribution transformer ledger data, pole-mounted transformer ledger data, distribution station data, distribution transformer 96-point load data, power curve data, and voltage regulation equipment data; Electricity consumption related data include: electricity user data, metering data, and distribution power data.

3. The distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data according to claim 2 is characterized in that: The distribution transformer and meteorological data integration model specifically includes: According to the 96-point load data of the distribution transformer and the daily temperature data, the 96-point load data of the daily distribution transformer and the daily temperature data are matched at similar time points: based on the time point corresponding to the 96-point load data of the distribution transformer, the temperature data of the nearest time point calculated forward from the current time point is taken to obtain the associated combination of load-temperature data.

4. The distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data according to claim 2 is characterized in that: The distribution transformer equipment load calculation model specifically includes: through the distribution transformer 96-point load data, associating the distribution transformer archive data and daily monitoring load data, recording the heavy overload time of the equipment, and forming the heavy overload period data.

5. The distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data according to claim 2 is characterized in that: The weather comprehensive index calculation model specifically includes: Using the temperature forecast data, calculate the comprehensive weather index Wt: Where β is the photovoltaic output irradiance coefficient, G1 is the irradiance measured by the reference device, G2 is the target irradiance of the DUT, T2 is the target temperature of the DUT, and T1 is the measured temperature of the DUT.

6. The distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data according to claim 2 is characterized in that: The construction of the ARIMA forecasting model specifically includes: By analyzing the autocorrelation function ACF and partial autocorrelation function PACF of the unsteady and first-order difference of the time series data, the influence coefficient φ of the past value on the current value and the influence coefficient θ of the error term are obtained. According to the AIC and BIC criteria and the analysis of the residual sequence, the appropriate ARIMA model order value is selected; Obtain the reverse load forecast value FT of the distribution transformer for the next n days based on the ARIMA model: F T =φ1x t-1 +.....+φ p x t-p +θ1∈ t-1 +.....+θ q ∈ t-q +∈ t Among them, x t is the 96-point data observation value of the distribution transformer load at time point t, φ1~φ p represents the 1st to pth influence coefficients, θ1~θ q represents the influence coefficient of the 1st to qth error terms, ∈ t represents the error term at time point t.

7. The distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data according to claim 1 is characterized in that: A photovoltaic reverse transmission risk warning model is constructed, and the distribution transformer reverse transmission risk value Gt is calculated using the weighted average method as follows: G t =(W t )*FT*Tr*SOC Among them, FT is the predicted value of the reverse load of the distribution transformer, Wt is the comprehensive weather index Wt, Tr is the sunshine time parameter, and SOC is the state of charge, which ranges from 0 to 1.

8. The distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data according to claim 7 is characterized in that: The calculation of sunshine time parameter Tr is as follows: T r =(sunshine duration / 24)*η Where η is the transmittance coefficient of the cloud layer in the sky, which is divided into [0, 1] according to the transmittance of the cloud layer in different weather types. On a sunny day, η is 1, and on a rainy day, η is 0. On a cloudy day, it is a decimal between 0 and 1 according to the transmittance of the cloud layer in the sky.

9. The distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data according to claim 1 is characterized in that: A comprehensive early warning model for heavy overload risk is constructed, and the calculation formula for the heavy overload risk value Gt of the distribution transformer is as follows: G t =(W t )*F T *C h *SOC Where Wt is the comprehensive weather index, F T is the predicted value of the reverse load of the distribution transformer, C h is the load reference parameter of the distribution transformer equipment, C h The calculation method is the ratio of the monthly average load of the distribution transformer to the contract capacity. SOC is the state of charge and takes a value between 0 and 1.

10. A distribution transformer reverse transmission and heavy overload risk warning system integrating meteorological data, used to implement the distribution transformer reverse transmission and heavy overload risk warning method integrating meteorological data as claimed in any one of claims 1 to 9, characterized in that: include: Data collection module, analysis model building module, early warning model building module, solution module, early warning module; The data acquisition module is used to collect meteorological data, equipment-related data, and electricity-related data; The analysis model building module is used to build analysis models, including the distribution transformer and meteorological data integration model, distribution transformer equipment load calculation model, ARIMA prediction model, and weather comprehensive index calculation model; The early warning model building module is used to establish a photovoltaic reverse transmission risk early warning model and a heavy overload comprehensive risk early warning model; The solution module solves the photovoltaic reverse transmission risk warning model and the heavy overload comprehensive risk warning model constructed by the warning model construction module in combination with the parameters obtained by the analysis model, and obtains the distribution transformer reverse transmission risk value and the distribution transformer heavy overload risk value; The early warning module issues a backflow risk warning or a heavy overload risk warning based on the backflow risk value and the heavy overload risk value of the distribution transformer obtained by the solution module.

11. A terminal comprising a processor and a storage medium; characterized in that: 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 1-9.

12. 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 9 are implemented.

Images