A regional energy consumption monitoring management and early warning system based on power grid platform

Abstract

The present invention discloses a regional energy consumption monitoring management and early warning system based on a power grid platform, which relates to the technical field of power grid energy consumption monitoring. A regional planning data collection module is set to pre-collect regional planning data of each power consumption area, a regional historical energy consumption data collection module is set to pre-collect historical energy consumption data in each power consumption area, a regional energy consumption prediction model training module trains a regional energy consumption prediction model, a regional energy consumption real-time collection module collects in real time the actual cycle energy consumption and the predicted energy consumption time series of each energy consumption collection cycle in each power consumption area, a power grid energy consumption monitoring module generates an early warning result, and a regional energy consumption early warning module warns of the energy consumption of the power consumption area based on the early warning result and the regional planning data, thereby improving the accuracy of the early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid energy consumption monitoring, and in particular to a regional energy consumption monitoring management and early warning system based on a power grid platform. Background Art

[0002] The grid platform faces diverse demands and challenges in supplying power to different areas of the city. Modern cities usually include multiple types of areas, each with its own specific energy needs and characteristics.

[0003] For example, commercial areas in cities are usually busy and crowded places that require a continuous and stable power supply to support various commercial activities, such as office buildings, shopping malls, and restaurants. The power demand in commercial areas often has diurnal fluctuations because the power consumption varies greatly during the day and night.

[0004] Secondly, the residential areas of the city need to provide electricity to thousands of households. The electricity demand in these areas is usually dominated by household electricity;

[0005] In addition, cities may also include industrial areas, which often require large amounts of electricity to support production and manufacturing processes. The power requirements of industrial areas may vary with production cycles and demand fluctuations;

[0006] Early warning of energy consumption in different electricity consumption areas is an important task, which involves key aspects of energy management and sustainable development;

[0007] At present, the method of early warning of energy consumption generally adopts the threshold method, that is, when the energy consumption of a certain area exceeds a certain threshold, an early warning is issued; however, this method is difficult to cope with normal electricity demand under special conditions, such as abnormal energy consumption caused by peak electricity consumption during hot weather;

[0008] To this end, the present invention proposes a regional energy consumption monitoring management and early warning system based on a power grid platform. Summary of the invention

[0009] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a regional energy consumption monitoring management and early warning system based on a power grid platform, which improves the accuracy of early warning.

[0010] To achieve the above-mentioned purpose, according to Embodiment 1 of the present invention, a regional energy consumption monitoring management and early warning system based on a power grid platform is proposed, comprising a regional planning data collection module, a regional historical energy consumption data collection module, a regional energy consumption prediction model training module, a regional energy consumption real-time collection module, a power grid energy consumption monitoring module and a regional energy consumption early warning module; wherein each module is electrically connected;

[0011] The regional planning data collection module is used to collect the regional planning data of each power consumption area in the power grid platform in advance;

[0012] The method of pre-collecting the regional planning data of each power consumption area in the power grid platform is:

[0013] According to the urban regional planning scheme, the city is divided into several different types of electricity consumption areas;

[0014] Collect the location and area range of each power consumption area;

[0015] The types, locations and area ranges of all power consumption areas are combined into regional planning data;

[0016] The regional planning data collection module sends the regional planning data to the regional energy consumption early warning module;

[0017] The regional historical energy consumption data collection module is used to collect the historical energy consumption data of each power consumption area in advance;

[0018] The method of pre-collecting the historical energy consumption data in each power consumption area is as follows:

[0019] Preset the prediction time window length and energy consumption collection cycle length;

[0020] For each power consumption area, the power consumed by the power consumption area in the energy consumption collection period is collected once every energy consumption collection period, and the consumed power collected each time is marked as periodic energy consumption;

[0021] For each electricity consumption area, the energy consumption of each prediction time window length period is organized into a set of energy consumption time series in chronological order;

[0022] For each energy consumption time series, collect the periodic energy consumption of the next energy consumption collection period after the end time of the energy consumption time series as the regional energy consumption label;

[0023] All energy consumption time series and the regional energy consumption labels corresponding to the energy consumption time series constitute the historical energy consumption data;

[0024] The regional historical energy consumption data collection module sends the historical energy consumption data of all power consumption areas to the regional energy consumption prediction model training module;

[0025] The regional energy consumption prediction model training module is used to train a regional energy consumption prediction model to predict the energy consumption of the next energy consumption collection cycle in each power consumption area based on historical energy consumption data;

[0026] The method of training a regional energy consumption prediction model for predicting the energy consumption of the next energy consumption collection cycle in each power consumption area is:

[0027] For each electricity consumption area:

[0028] Each group of energy consumption time series in the historical energy consumption data is used as the input of the regional energy consumption prediction model. The regional energy consumption prediction model uses the predicted value of the regional energy consumption label corresponding to each group of energy consumption time series as the output, and uses the regional energy consumption label of the next energy consumption collection cycle of each group of energy consumption time series in the historical energy consumption data as the prediction target, and takes minimizing the sum of prediction errors of the regional energy consumption label as the training target; the regional energy consumption prediction model is trained until the sum of prediction errors reaches convergence and the training is stopped;

[0029] The regional historical energy consumption data collection module sends all regional energy consumption prediction models to the power grid energy consumption monitoring module;

[0030] The regional energy consumption real-time collection module is used to collect the actual cycle energy consumption and predicted energy consumption time series of each energy consumption collection cycle in each power consumption area in real time;

[0031] The method of real-time collection of actual cycle energy consumption in each energy consumption collection cycle in each power consumption area and prediction of energy consumption time series is as follows:

[0032] For each electricity consumption area, every other energy consumption collection cycle, the periodic energy consumption of the electricity consumption area is collected through the electric energy meter as the actual periodic energy consumption, and the energy consumption time series composed of the periodic energy consumption of the predicted time window length before the energy consumption collection cycle is used as the predicted energy consumption time series;

[0033] The regional energy consumption real-time collection module sends the collected actual periodic energy consumption and predicted energy consumption time series of each power consumption area to the power grid energy consumption monitoring module;

[0034] The power grid energy consumption monitoring module is used to obtain the predicted period energy consumption based on the predicted energy consumption time series and the regional energy consumption prediction model, and generate early warning results based on the predicted period energy consumption and the actual period energy consumption;

[0035] The method of obtaining the predicted periodic energy consumption based on the predicted energy consumption time series and the regional energy consumption prediction model is:

[0036] For each power consumption area, before each energy consumption collection cycle arrives, the predicted energy consumption time series corresponding to the energy consumption collection cycle is input into the regional energy consumption prediction model corresponding to the power consumption area, and the predicted value of the regional energy consumption label of the power consumption area in the energy consumption collection cycle is obtained, and the predicted value of the regional energy consumption label is used as the predicted period energy consumption;

[0037] The method of generating the warning result based on the predicted periodic energy consumption and the actual periodic energy consumption is as follows:

[0038] The number of the power consumption area is marked as i, and the number of the energy consumption collection period is marked as j;

[0039] The actual cycle energy consumption of the jth energy consumption collection cycle in the i-th power consumption area is marked as Ri j;

[0040] The predicted period energy consumption of the jth energy consumption collection period in the i-th power consumption area is marked as Pi j;

[0041] Calculate the energy consumption deviation Cij1 of the j1th energy consumption collection cycle of the i-th power consumption area from the 1st to the j-1th energy consumption collection cycle; wherein j1=1, 2, 3...j-1;

[0042] The calculation formula of the energy consumption deviation Cij is:

[0043] Calculate the average value Ai of the energy consumption deviation from the 1st to the j-1th energy consumption collection cycle;

[0044] Calculate the energy consumption deviation Cij of the jth energy consumption collection cycle;

[0045] Calculate the energy consumption mean deviation Hij of the jth energy consumption collection cycle, where the calculation formula of the energy consumption mean deviation Hij is:

[0046] For the i-th power consumption area, if Hij is greater than the preset first warning threshold, the warning result is set to pending warning; if Hij is less than or equal to the preset first warning threshold, the warning result is set to no warning required;

[0047] The power grid energy consumption monitoring module sends the early warning results of each power consumption area to the regional energy consumption early warning module;

[0048] The regional energy consumption early warning module is used to warn the energy consumption of the power consumption area based on the early warning results and regional planning data;

[0049] The method of early warning the energy consumption of the power consumption area based on the early warning results and regional planning data is:

[0050] If the warning results of all power consumption areas are no need for warning, no warning will be issued;

[0051] If the warning result of any power consumption area is pending warning, perform the following steps:

[0052] Step 11: Mark the power consumption area with the warning result as to be warned as i1;

[0053] A threshold value Y of the number of surrounding areas is preset, and the average value of the energy consumption deviation of the Y power consumption areas closest to the center of the i1th power consumption area is counted as the average value of the surrounding deviation Zj;

[0054] The average value of the energy consumption deviation of all power consumption areas of the same type as the i1th power consumption area is calculated as the average value of the same type deviation Lj;

[0055] Step 12: Calculate the comprehensive deviation Ki1j of the i1th power consumption area, where the calculation formula of the comprehensive deviation Ki1j is: Ki1j=b1×|Ci1j-Zj|+b2×|Ci1j-Lj|;

[0056] If the comprehensive deviation Ki1j is greater than the preset second warning threshold, an early warning for the i1th power consumption area is issued to the power grid supervisor; otherwise, no early warning is issued.

[0057] According to Embodiment 2 of the present invention, a regional energy consumption monitoring management and early warning method based on a power grid platform is proposed, comprising the following steps:

[0058] Collect regional planning data of each power consumption area in the power grid platform in advance;

[0059] Collect historical energy consumption data in each electricity consumption area in advance;

[0060] Based on historical energy consumption data, a regional energy consumption prediction model is trained to predict the energy consumption of the next energy consumption collection cycle in each power consumption area;

[0061] Real-time collection of actual cycle energy consumption and predicted energy consumption time series in each energy consumption collection cycle in each power consumption area;

[0062] Obtain predicted periodic energy consumption based on predicted energy consumption time series and regional energy consumption prediction model, and generate early warning results based on predicted periodic energy consumption and actual periodic energy consumption;

[0063] Based on the early warning results and regional planning data, early warning is issued for energy consumption in power consumption areas.

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

[0065] Collect regional planning data of each power consumption area in the power grid platform in advance;

[0066] Collect historical energy consumption data of each power consumption area in advance, and train a regional energy consumption prediction model to predict the energy consumption of the next energy consumption collection cycle in each power consumption area based on the historical energy consumption data. Collect the actual cycle energy consumption and the predicted energy consumption time series of each energy consumption collection cycle in each power consumption area in real time, obtain the predicted cycle energy consumption based on the predicted energy consumption time series and the regional energy consumption prediction model, generate early warning results based on the predicted cycle energy consumption and the actual cycle energy consumption, and issue early warnings on the energy consumption of the power consumption area based on the early warning results and regional planning data; analyze whether early warnings are needed by comparing the predicted and actual values ​​of energy consumption of different types of power consumption areas, and then comparing the relationship with the historical prediction deviation of the power consumption area, the prediction deviation of surrounding power consumption areas, and the prediction deviation of the same type of power consumption areas, thereby improving the accuracy of early warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a module connection relationship diagram of the regional energy consumption monitoring management and early warning system based on the power grid platform in Example 1 of the present invention;

[0068] Figure 2 It is a flow chart of a method for monitoring, managing and warning regional energy consumption based on a power grid platform in Embodiment 2 of the present invention;

[0069] Figure 3 This is a schematic diagram of the structure of an electronic device in Embodiment 3 of the present invention;

[0070] Figure 4 This is a schematic diagram of the computer-readable storage medium structure in Example 4 of the present invention. DETAILED DESCRIPTION

[0071] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0072] Example 1

[0073] like Figure 1 As shown, a regional energy consumption monitoring management and early warning system based on a power grid platform includes a regional planning data collection module, a regional historical energy consumption data collection module, a regional energy consumption prediction model training module, a regional energy consumption real-time collection module, a power grid energy consumption monitoring module and a regional energy consumption early warning module; wherein each module is electrically connected;

[0074] The regional planning data collection module is mainly used to collect regional planning data of each power consumption area in the power grid platform in advance;

[0075] In a preferred embodiment, the method of pre-collecting the regional planning data of each power consumption area in the power grid platform is:

[0076] According to the urban regional planning scheme, the city is divided into several different types of power consumption areas; it can be understood that the power consumption areas can be divided into office areas, living areas, light industrial areas, heavy industrial areas and other types, and the functions of each power consumption area can also be further divided. For example, the light industrial area can be further divided into food industrial areas, textile industrial areas, etc.; the specific division method is determined according to the actual monitoring needs;

[0077] Collect the location and area range of each power consumption area;

[0078] The types, locations and area ranges of all power consumption areas are combined into regional planning data;

[0079] The regional planning data collection module sends the regional planning data to the regional energy consumption early warning module;

[0080] The regional historical energy consumption data collection module is mainly used to collect historical energy consumption data in each power consumption area in advance;

[0081] In a preferred embodiment, the method of pre-collecting the historical energy consumption data in each power consumption area is:

[0082] Preset the prediction time window length and energy consumption collection cycle length;

[0083] For each power consumption area, the power consumed by the power consumption area in the energy consumption collection period is collected once every energy consumption collection period, and the consumed power collected each time is marked as periodic energy consumption; it can be understood that the consumed power can be collected in real time by using energy consumption monitoring equipment such as power meters;

[0084] For each electricity consumption area, the energy consumption of each prediction time window length period is organized into a set of energy consumption time series in chronological order; it should be noted that the energy consumption time series is collected in a sliding window manner;

[0085] Specifically, an example of the energy consumption time series and the sliding window method may be [100, 110, 120]. In this example, the energy consumption collected in the first energy consumption collection cycle is 100kw, the energy consumption collected in the second energy consumption collection cycle is 110kw, and the energy consumption collected in the third energy consumption collection cycle is 120kw; and the sliding window method means that the second energy consumption time series collected may be [110, 120, 130], that is, it slides an energy consumption collection cycle based on the first energy consumption time series;

[0086] For each energy consumption time series, collect the periodic energy consumption of the next energy consumption collection period after the end time of the energy consumption time series as the regional energy consumption label;

[0087] All energy consumption time series and the regional energy consumption labels corresponding to the energy consumption time series constitute the historical energy consumption data;

[0088] The regional historical energy consumption data collection module sends the historical energy consumption data of all power consumption areas to the regional energy consumption prediction model training module;

[0089] The regional energy consumption prediction model training module is mainly used to train a regional energy consumption prediction model to predict the energy consumption of the next energy consumption collection cycle in each power consumption area based on historical energy consumption data;

[0090] In a preferred embodiment, the method of training a regional energy consumption prediction model for predicting the energy consumption of the next energy consumption collection cycle in each power consumption area is:

[0091] For each electricity consumption area:

[0092] Each group of energy consumption time series in the historical energy consumption data is used as the input of the regional energy consumption prediction model. The regional energy consumption prediction model uses the predicted value of the regional energy consumption label corresponding to each group of energy consumption time series as the output, and uses the regional energy consumption label of the next energy consumption collection period of each group of energy consumption time series in the historical energy consumption data as the prediction target, and takes minimizing the sum of prediction errors of the regional energy consumption label as the training target; the regional energy consumption prediction model is trained until the sum of the prediction errors reaches convergence, and the training is stopped, and a regional energy consumption prediction model is trained to output the regional energy consumption label of the next energy consumption collection period predicted according to the energy consumption time series; preferably, the sum of the prediction errors can be the mean square error; as an example of the regional energy consumption prediction model, for the example of the energy consumption time series [100, 110, 120], the prediction target of the model is to predict the regional energy consumption label of the next energy consumption collection period as 130 as much as possible based on the energy consumption time series;

[0093] The regional historical energy consumption data collection module sends all regional energy consumption prediction models to the power grid energy consumption monitoring module;

[0094] The regional energy consumption real-time collection module is mainly used to collect the actual cycle energy consumption and the predicted energy consumption time series of each energy consumption collection cycle in each power consumption area in real time;

[0095] In a preferred embodiment, the method of real-time collection of actual periodic energy consumption in each energy consumption collection period in each power consumption area and prediction of energy consumption time series is as follows:

[0096] For each electricity consumption area, every other energy consumption collection cycle, the periodic energy consumption of the electricity consumption area is collected through the electric energy meter as the actual periodic energy consumption, and the energy consumption time series composed of the periodic energy consumption of the predicted time window length before the energy consumption collection cycle is used as the predicted energy consumption time series;

[0097] The regional energy consumption real-time collection module sends the collected actual periodic energy consumption and predicted energy consumption time series of each power consumption area to the power grid energy consumption monitoring module;

[0098] The power grid energy consumption monitoring module is mainly used to obtain the predicted period energy consumption based on the predicted energy consumption time series and the regional energy consumption prediction model, and generate early warning results based on the predicted period energy consumption and the actual period energy consumption;

[0099] In a preferred embodiment, the method of obtaining the predicted periodic energy consumption based on the predicted energy consumption time series and the regional energy consumption prediction model is:

[0100] For each power consumption area, before each energy consumption collection cycle arrives, the predicted energy consumption time series corresponding to the energy consumption collection cycle is input into the regional energy consumption prediction model corresponding to the power consumption area, and the predicted value of the regional energy consumption label of the power consumption area in the energy consumption collection cycle is obtained, and the predicted value of the regional energy consumption label is used as the predicted period energy consumption;

[0101] Furthermore, the method of generating the warning result based on the predicted periodic energy consumption and the actual periodic energy consumption is:

[0102] The number of the power consumption area is marked as i, and the number of the energy consumption collection period is marked as j;

[0103] The actual cycle energy consumption of the jth energy consumption collection cycle in the i-th power consumption area is marked as Rij;

[0104] The predicted period energy consumption of the jth energy consumption collection period in the i-th power consumption area is marked as Pij;

[0105] Calculate the energy consumption deviation Cij1 of the j1th energy consumption collection cycle of the i-th power consumption area from the 1st to the j-1th energy consumption collection cycle; wherein j1=1, 2, 3...j-1;

[0106] The calculation formula of the energy consumption deviation Cij is:

[0107] Calculate the average value Ai of the energy consumption deviation from the 1st to the j-1th energy consumption collection cycle;

[0108] Calculate the energy consumption deviation Cij of the jth energy consumption collection cycle;

[0109] Calculate the energy consumption mean deviation Hij of the jth energy consumption collection cycle, where the calculation formula of the energy consumption mean deviation Hij is:

[0110] For the i-th power consumption area, if Hij is greater than the preset first warning threshold, the warning result is set to pending warning; if Hij is less than or equal to the preset first warning threshold, the warning result is set to no warning required;

[0111] The power grid energy consumption monitoring module sends the early warning results of each power consumption area to the regional energy consumption early warning module;

[0112] The regional energy consumption warning module is mainly used to warn the energy consumption of the power consumption area based on the warning results and regional planning data;

[0113] In a preferred embodiment, the method of early warning the energy consumption of the power consumption area based on the early warning result and the regional planning data is:

[0114] If the warning results of all power consumption areas are no need for warning, no warning will be issued;

[0115] If the warning result of any power consumption area is pending warning, perform the following steps:

[0116] Step 11: Mark the power consumption area with the warning result as to be warned as i1;

[0117] A threshold value Y of the number of surrounding areas is preset, and the average value of the energy consumption deviation of the Y power consumption areas closest to the center of the i1th power consumption area is counted as the surrounding deviation average value Zj; the center distance may be the distance between the center positions of each power consumption area; it can be understood that the surrounding deviation average value expresses the energy consumption deviation of the power consumption areas adjacent to the i1th power consumption area. When the energy consumption deviation of the i1th power consumption area is similar to that of the adjacent power consumption area, there is a possibility that the area has a special situation and requires a large amount of electric energy;

[0118] The average value of the energy consumption deviation of all power consumption areas of the same type as the i1th power consumption area is calculated as the same type deviation average value Lj; it can be understood that the same type deviation average value expresses the energy consumption deviation of the same type of power consumption areas in the entire urban area. Under certain conditions, a certain type of power consumption area requires more electricity. For example, when the weather is hot, the office area or living area requires more electricity to support the use of air conditioning equipment;

[0119] Step 12: Calculate the comprehensive deviation Ki1j of the i1th power consumption area, where the calculation formula of the comprehensive deviation Ki1j is: Ki1j=b1×|Ci1j-Zj|+b2×|Ci1j-Lj|;

[0120] If the comprehensive deviation Ki1j is greater than the preset second warning threshold, an early warning for the i1th power consumption area is issued to the power grid supervisor; otherwise, no early warning is issued.

[0121] Example 2

[0122] like Figure 2 As shown, a regional energy consumption monitoring management and early warning method based on a power grid platform includes the following steps:

[0123] Collect regional planning data of each power consumption area in the power grid platform in advance;

[0124] Collect historical energy consumption data in each electricity consumption area in advance;

[0125] Based on historical energy consumption data, a regional energy consumption prediction model is trained to predict the energy consumption of the next energy consumption collection cycle in each power consumption area;

[0126] Real-time collection of actual cycle energy consumption and predicted energy consumption time series in each energy consumption collection cycle in each power consumption area;

[0127] Obtain predicted periodic energy consumption based on predicted energy consumption time series and regional energy consumption prediction model, and generate early warning results based on predicted periodic energy consumption and actual periodic energy consumption;

[0128] Based on the early warning results and regional planning data, early warning is issued for energy consumption in power consumption areas.

[0129] Example 3

[0130] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, according to another aspect of the present application, an electronic device 100 is also provided. The electronic device 100 may include one or more processors and one or more memories. The memory stores a computer readable code, and when the computer readable code is executed by one or more processors, the regional energy consumption monitoring management and early warning method based on the power grid platform as described above can be executed.

[0131] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3As shown, the electronic device 100 may include a bus 101, one or more CPUs 102, a read-only memory (ROM) 103, a random access memory (RAM) 104, a communication port 105 connected to a network, an input / output component 106, a hard disk 107, etc. The storage device in the electronic device 100, such as ROM 103 or hard disk 107, may store the regional performance consumption monitoring management and early warning method based on the power grid platform provided in this application. The regional performance consumption monitoring management and early warning method based on the power grid platform may, for example, include the following steps: pre-collecting the regional planning data of each power consumption area in the power grid platform; pre-collecting the historical energy consumption data of each power consumption area; based on the historical energy consumption data, training a regional energy consumption prediction model that predicts the energy consumption of the next energy consumption collection cycle in each power consumption area; real-time collection of the actual cycle energy consumption and the predicted energy consumption time series in each power consumption area for each energy consumption collection cycle; obtaining the predicted cycle energy consumption based on the predicted energy consumption time series and the regional energy consumption prediction model, and generating an early warning result based on the predicted cycle energy consumption and the actual cycle energy consumption; based on the early warning result and the regional planning data, early warning of the energy consumption of the power consumption area.

[0132] Furthermore, the electronic device 100 may further include a user interface 108. Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0133] Example 4

[0134] Figure 4 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 4 As shown, a computer-readable storage medium 200 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 200. When the computer-readable instructions are executed by the processor, the regional energy consumption monitoring management and early warning method based on the power grid platform according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium 200 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0135] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, and when the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0136] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0137] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0138] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0139] The above preset parameters or preset thresholds are all set by technicians in this field according to actual conditions or obtained by simulating a large amount of data.

[0140] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A regional energy consumption monitoring management and early warning system based on a power grid platform, characterized in that: It includes a regional planning data collection module, a regional historical energy consumption data collection module, a regional energy consumption prediction model training module, a regional energy consumption real-time collection module, a power grid energy consumption monitoring module and a regional energy consumption early warning module; wherein each module is electrically connected; The regional planning data collection module is used to collect the regional planning data of each power consumption area in the power grid platform in advance, and send the regional planning data to the regional energy consumption early warning module; The regional historical energy consumption data collection module is used to collect the historical energy consumption data of each power consumption area in advance, and send the historical energy consumption data of all power consumption areas to the regional energy consumption prediction model training module; The regional energy consumption prediction model training module is used to train a regional energy consumption prediction model to predict the energy consumption of the next energy consumption collection cycle in each power consumption area based on historical energy consumption data, and send all regional energy consumption prediction models to the power grid energy consumption monitoring module; The regional energy consumption real-time collection module is used to collect the actual cycle energy consumption and predicted energy consumption time series of each energy consumption collection cycle in each power consumption area in real time, and send the collected actual cycle energy consumption and predicted energy consumption time series of each power consumption area to the power grid energy consumption monitoring module; The power grid energy consumption monitoring module is used to obtain the predicted period energy consumption based on the predicted energy consumption time series and the regional energy consumption prediction model, generate early warning results based on the predicted period energy consumption and the actual period energy consumption, and send the early warning results of each power consumption area to the regional energy consumption early warning module; The regional energy consumption early warning module is used to warn the energy consumption of the power consumption area based on the early warning results and regional planning data; The method of generating the warning result based on the predicted periodic energy consumption and the actual periodic energy consumption is as follows: The number of the power consumption area is marked as i, and the number of the energy consumption collection period is marked as j; The actual cycle energy consumption of the jth energy consumption collection cycle in the i-th power consumption area is marked as Rij; The predicted period energy consumption of the jth energy consumption collection period in the i-th power consumption area is marked as Pij; Calculate the energy consumption deviation Cij1 of the j1th energy consumption collection cycle of the i-th power consumption area from the 1st to the j-1th energy consumption collection cycle; where j1=1, 2, 3...j-1; The calculation formula of the energy consumption deviation Cij is: ; Calculate the average value Ai of the energy consumption deviation from the 1st to the j-1th energy consumption collection cycle; Calculate the energy consumption deviation Cij of the jth energy consumption collection cycle; Calculate the energy consumption mean deviation Hij of the jth energy consumption collection cycle, where the calculation formula of the energy consumption mean deviation Hij is: ; For the i-th power consumption area, if Hij is greater than the preset first warning threshold, the warning result is set to pending warning; if Hij is less than or equal to the preset first warning threshold, the warning result is set to no warning required.

2. According to claim 1, a regional energy consumption monitoring management and early warning system based on a power grid platform is characterized in that: The method of pre-collecting the regional planning data of each power consumption area in the power grid platform is: According to the urban regional planning scheme, the city is divided into several different types of electricity consumption areas; Collect the location and area range of each power consumption area; The types, locations and area ranges of all power consumption areas form regional planning data.

3. According to claim 2, a regional energy consumption monitoring management and early warning system based on a power grid platform is characterized in that: The method of pre-collecting the historical energy consumption data in each power consumption area is as follows: Preset the prediction time window length and energy consumption collection cycle length; For each power consumption area, the power consumed by the power consumption area in the energy consumption collection period is collected once every energy consumption collection period, and the consumed power collected each time is marked as periodic energy consumption; For each electricity consumption area, the energy consumption of each prediction time window length period is organized into a set of energy consumption time series in chronological order; For each energy consumption time series, collect the periodic energy consumption of the next energy consumption collection period after the end time of the energy consumption time series as the regional energy consumption label; All energy consumption time series and the regional energy consumption labels corresponding to the energy consumption time series constitute the historical energy consumption data.

4. A regional energy consumption monitoring management and early warning system based on a power grid platform according to claim 3, characterized in that: The method of training a regional energy consumption prediction model for predicting the energy consumption of the next energy consumption collection cycle in each power consumption area is: For each electricity consumption area: Each group of energy consumption time series in the historical energy consumption data is used as the input of the regional energy consumption prediction model. The regional energy consumption prediction model uses the predicted value of the regional energy consumption label corresponding to each group of energy consumption time series as the output, and uses the regional energy consumption label of the next energy consumption collection cycle of each group of energy consumption time series in the historical energy consumption data as the prediction target, and minimizes the sum of the prediction errors of the regional energy consumption labels as the training target; The regional energy consumption prediction model is trained until the sum of the prediction errors reaches convergence and then the training is stopped.

5. According to claim 1, a regional energy consumption monitoring management and early warning system based on a power grid platform is characterized in that: The method of obtaining the predicted periodic energy consumption based on the predicted energy consumption time series and the regional energy consumption prediction model is: For each electricity consumption area, before each energy consumption collection cycle arrives, the predicted energy consumption time series corresponding to the energy consumption collection cycle is input into the regional energy consumption prediction model corresponding to the electricity consumption area, and the predicted value of the regional energy consumption label of the electricity consumption area in the energy consumption collection cycle is obtained, and the predicted value of the regional energy consumption label is used as the predicted period energy consumption.

6. A regional energy consumption monitoring management and early warning system based on a power grid platform according to claim 1, characterized in that: The method of early warning the energy consumption of the power consumption area based on the early warning results and regional planning data is: If the warning results of all power consumption areas are no need for warning, no warning will be issued; If the warning result of any power consumption area is pending warning, perform the following steps: Step 11: Mark the power consumption area with the warning result as to be warned as i1; A threshold value Y of the number of surrounding areas is preset, and the average value of the energy consumption deviation of the Y power consumption areas closest to the center of the i1th power consumption area is counted as the average value of the surrounding deviation Zj; The average value of the energy consumption deviation of all power consumption areas of the same type as the i1th power consumption area is calculated as the average value of the same type deviation Lj; Step 12: Calculate the comprehensive deviation Ki1j of the i1th power consumption area, where the calculation formula of the comprehensive deviation Ki1j is: ; If the comprehensive deviation Ki1j is greater than the preset second warning threshold, an early warning for the i1th power consumption area is issued to the power grid supervisor; Otherwise, no warning is issued.

7. A regional energy consumption monitoring management and early warning method based on a power grid platform, which is implemented based on the system according to any one of claims 1 to 6, characterized in that: The following steps are involved: Collect regional planning data of each power consumption area in the power grid platform in advance; Collect historical energy consumption data in each electricity consumption area in advance; Based on historical energy consumption data, a regional energy consumption prediction model is trained to predict the energy consumption of the next energy consumption collection cycle in each power consumption area; Real-time collection of actual cycle energy consumption and predicted energy consumption time series in each energy consumption collection cycle in each power consumption area; Obtain predicted periodic energy consumption based on predicted energy consumption time series and regional energy consumption prediction model, and generate early warning results based on predicted periodic energy consumption and actual periodic energy consumption; Based on the early warning results and regional planning data, early warning is issued for energy consumption in power consumption areas.

8. An electronic device, characterized in that: include: processor and memory, wherein The memory stores a computer program that can be called by the processor; The processor executes the regional performance consumption monitoring, management and early warning method based on the power grid platform as described in claim 7 in the background by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: A rewritable computer program is stored thereon; When the computer program runs on a computer device, the computer device executes the regional energy consumption monitoring management and early warning method based on the power grid platform as claimed in claim 7 in the background.

Images