Intelligent power distribution energy-saving power supply system and method

Abstract

The invention discloses an intelligent power distribution energy-saving power supply system and method, relates to the technical field of power systems, and solves the technical problems that the user experience is poor due to the lack of consideration of the user participation degree in the prior art, and the efficiency of intelligent power distribution energy-saving power supply is low due to the fact that the electric quantity generated by renewable energy cannot meet the user demand. Obtaining predicted electricity consumption of the plurality of areas through an electric power prediction model; calculating a regional power utilization priority coefficient according to the regional data; the power station state is adjusted according to the predicted electricity consumption and the regional electricity consumption priority coefficient, the user participation degree is considered, whether the generating capacity meets the electricity consumption requirement or not is predicted, regulation and control are conducted in advance, the situation of insufficient power supply is reduced, and the user experience and the power supply efficiency are improved.

Description

Technical Field

[0001] The present application belongs to the technical field of power systems, and specifically relates to an intelligent power distribution and energy-saving power supply system and method. Background Art

[0002] The power supply system refers to the entire system that transmits electric energy from the power source to the user end and meets the user's electricity demand. According to the different characteristics of the power supply system, it can be divided into many types, such as TN system, IT system, TT system, etc. The power supply system is one of the indispensable infrastructures in modern society. It provides people with a stable and reliable power supply and guarantees people's production and living needs. With the development of science and technology and the progress of society, the power supply system will continue to develop and improve, providing people with better quality, more efficient and intelligent power services.

[0003] The prior art (invention patent application with publication number CN108390408A) discloses an intelligent power distribution and energy-saving power supply system, including solar panels, solar controllers, wind power generators, wind power controllers, grid rectifiers, battery packs, inverters and intelligent power distribution systems; the input is from the main grid and output to the DC bus through the grid rectifier; the solar panels and wind power generators are output to the DC bus through the solar controller and the wind power controller respectively; the battery pack is connected to the DC bus; the inverter is connected to the DC bus and the intelligent power distribution system; the intelligent power distribution system includes a monitoring unit and a plurality of output power distribution control circuits; the monitoring unit is connected to the solar controller, the wind power controller, the inverter and the grid rectifier through an internal communication bus.

[0004] The above case achieved the purpose of intelligent energy saving through different compensation methods of the main power grid and battery packs, but failed to consider the impact of user participation on intelligent distribution and energy-saving power supply, resulting in poor user experience; at the same time, it only considered renewable energy for power supply for user use, without considering that the amount of electricity generated by renewable energy could not meet user needs, which may lead to the problem of low efficiency of intelligent distribution and energy-saving power supply; therefore, the intelligent distribution and energy-saving power supply system still needs further improvement. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes an intelligent power distribution and energy-saving power supply system and method, which are used to solve the technical problems that the prior art lacks consideration of user participation, resulting in a poor user experience, and the amount of electricity generated by renewable energy cannot meet user needs, resulting in low efficiency of intelligent power distribution and energy-saving power supply.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides an intelligent power distribution and energy-saving power supply system, including: a data acquisition module, a data analysis module, an early warning module and a database;

[0007] The data acquisition module is used to acquire power station data and regional data through data acquisition equipment;

[0008] The data analysis module: obtains the predicted power consumption of several regions through a power prediction model, wherein the power prediction model is constructed through an artificial intelligence model; calculates the regional power priority coefficient according to the regional data; and adjusts the power station status according to the predicted power consumption and the regional power priority coefficient;

[0009] The early warning module: makes prompts according to the alarm signal and contacts the management personnel.

[0010] The present application obtains the predicted electricity consumption of several regions through an electricity prediction model; calculates the regional electricity priority coefficient based on the regional data; adjusts the power station status according to the predicted electricity consumption and the regional electricity priority coefficient, takes user participation into consideration, predicts whether the power generation can meet the electricity demand and adjusts it in advance, reduces the occurrence of power shortages, and improves the user experience and power supply efficiency.

[0011] Furthermore, the power prediction model is constructed by an artificial intelligence model, including:

[0012] Obtaining certain historical regional environmental data, historical electricity consumption, time characteristics and recording time within the regional data;

[0013] Integrate historical regional environmental data, historical electricity consumption, and time characteristics with the same recording time into a time vector;

[0014] Integrate each time vector into several prediction sequences according to the order of recording time;

[0015] Divide several prediction sequences into training set, test set and validation set in chronological order;

[0016] Select an AI model as the base model;

[0017] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0018] By verifying the pre-trained model on the test set, we finally obtain an electricity prediction model whose input is several prediction sequences and output is the predicted electricity consumption.

[0019] Furthermore, the calculation of the regional electricity priority coefficient according to the regional data includes:

[0020] Get user level YJ in regional data i And its corresponding quantity YS i ;

[0021] Determine user level YJ i Does YJ exist in i Greater than the level threshold;

[0022] Yes, set the regional electricity priority coefficient to the maximum value in the coefficient range;

[0023] No, by the formula QYYX = g × tan -1 (Σ i α i ×YJ i ×YS i / DS) calculates the regional electricity priority coefficient QYYX; where α i is the weight coefficient, α i Adaptively generated from regional data; g is the proportional coefficient, g∈(0,π / 2); DS is the number of people per unit.

[0024] Furthermore, the user level is calculated by using the user feature level and the user behavior level, including:

[0025] Obtain user feature level YTJ and user behavior level YXJ;

[0026] By the formula YJ = β 1 ×YTJ+β 2 ×YXJ calculates user level YJ;

[0027] Among them, β 1 and β 2 is the weight coefficient, β 1 and β 2 ∈(0,1).

[0028] Furthermore, the user behavior level is calculated based on the user's historical electricity consumption, including:

[0029] Obtain the user's historical electricity consumption and its corresponding recording time, as well as energy-saving electricity consumption JD;

[0030] Extract several non-energy-saving days FJT greater than JD in the historical electricity consumption and energy-saving days JT less than or equal to JD in the historical electricity consumption;

[0031] When FJT is greater than or equal to JT, let the user behavior level YXJ = 0;

[0032] Otherwise, by formula Calculate the user behavior level YXJ; where β 3 and β 4 is the weight coefficient, β 3 and β 4 ∈(0, 1); DJ is the unit level, DT is the unit day.

[0033] Furthermore, the α i Adaptively generated from regional data, including:

[0034] Get user level YJ in regional data i ;

[0035] Through the formula α i =YJ i / Σ i YJ i Calculate the weight coefficient α corresponding to the user level i .

[0036] Furthermore, the adjusting the power station state according to the predicted power consumption and the regional power consumption priority coefficient includes:

[0037] Obtaining predicted power consumption YYDj, regional power consumption priority coefficients QYYXj and power station data for several regions; the power station data includes renewable power energy KZN, energy storage power energy CN, other power energy QN and environmental data;

[0038] Predicting the predicted power generation YD of renewable electric energy according to a power generation prediction model; the power generation prediction model is constructed by an artificial intelligence model;

[0039] Determine whether CN+YD is greater than ∑(YYDj); wherein j represents the number of the region, j=1, 2, ..., N; N is the total number of regions;

[0040] Yes, suspend the use of other power sources;

[0041] No, determine whether CN+YD+QN is greater than ∑(YYDj); if yes, resume using other electric energy sources for power supply, and the power supply of other electric energy sources is |∑(YYDj)-(CN+YD)|;

[0042] No, the power station status is regulated based on the regional power priority coefficient and power station data.

[0043] This application calculates the regional electricity priority coefficient based on regional data. When the power generation cannot meet the electricity demand, the power station status is dynamically adjusted according to the regional electricity priority coefficient. At the same time, the user's electricity consumption behavior is taken into account in the calculation of the regional electricity priority coefficient, thereby enhancing the user's experience of intelligent power distribution and energy-saving power supply.

[0044] Furthermore, the power generation prediction model is constructed by an artificial intelligence model, including:

[0045] Obtain historical environmental data, historical equipment data, historical power generation and recording time of renewable electric energy;

[0046] Integrate historical environmental data, historical equipment data, and historical power generation with the same recording time into a time vector;

[0047] Integrate each time vector into several prediction sequences according to the order of recording time;

[0048] Divide several prediction sequences into training set, test set and validation set in chronological order;

[0049] Select an AI model as the base model;

[0050] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0051] By verifying the pre-trained model on the test set, we finally get a power generation prediction model whose input is several prediction sequences and output is the predicted power generation.

[0052] Furthermore, the power station status is regulated according to the regional power priority coefficient and the power station data, including:

[0053] Obtain regional predicted electricity consumption and its corresponding regional electricity priority coefficient, energy storage power energy in power station data, predicted power generation and other power energy;

[0054] Sort the regional power consumption priority coefficients from large to small; when there is a maximum value in the coefficient range among several regional power consumption priority coefficients; extract several predicted power consumptions corresponding to the maximum value, and sum up the several predicted power consumptions to obtain the predicted total power consumption;

[0055] Determine whether the predicted total power consumption is greater than CN+YD+QN; if so, generate an emergency power alarm signal and contact the management personnel to increase the transmission of other power energy sources;

[0056] No, electricity will be transmitted according to the regional electricity priority coefficient from large to small.

[0057] Another aspect of the present invention provides an intelligent power distribution energy-saving power supply method, comprising:

[0058] S0: Obtain power station data and regional data;

[0059] S1: Obtaining predicted power consumption of several regions through a power prediction model, wherein the power prediction model is constructed through an artificial intelligence model; calculating a regional power consumption priority coefficient based on regional data;

[0060] S2: Calculate the regional power consumption priority coefficient based on regional data; adjust the power station status based on the predicted power consumption and the regional power consumption priority coefficient;

[0061] S3: Prompt according to the alarm signal and contact the management.

[0062] Compared with the prior art, the beneficial effects of this application are:

[0063] 1. This application obtains the predicted electricity consumption of several regions through the power forecasting model; calculates the regional electricity priority coefficient based on the regional data; adjusts the power station status according to the predicted electricity consumption and the regional electricity priority coefficient, takes user participation into consideration, predicts whether the power generation can meet the electricity demand and adjusts it in advance, reduces the occurrence of power shortage, and improves the user experience and power supply efficiency.

[0064] 2. This application calculates the regional electricity priority coefficient based on regional data. When the power generation cannot meet the electricity demand, the power station status is dynamically adjusted according to the regional electricity priority coefficient. At the same time, the user's electricity consumption behavior is taken into account in the calculation of the regional electricity priority coefficient, which increases the user's experience of intelligent power distribution and energy-saving power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1 A schematic diagram of the principle of an intelligent power distribution and energy-saving power supply system of the present application;

[0067] Figure 2 This is a flow chart of an intelligent power distribution and energy-saving power supply method of the present application. DETAILED DESCRIPTION

[0068] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0069] See also Figure 1 , the first aspect of the present application provides an intelligent power distribution energy-saving power supply system, including: a data acquisition module, a data analysis module, an early warning module and a database;

[0070] Data acquisition module: obtain power station data and regional data through data acquisition equipment; data acquisition equipment includes various sensors, etc. Power station data includes renewable power energy, energy storage power energy, other power energy and environmental data, etc.; regional data includes regional number and regional environmental data, user level and quantity, etc.;

[0071] Data analysis module: obtain the predicted power consumption of several regions through the power prediction model, which is constructed through the artificial intelligence model; calculate the regional power priority coefficient based on regional data, which refers to the coefficient of regional priority power supply; adjust the power station status according to the predicted power consumption and the regional power priority coefficient;

[0072] Early warning module: Prompts are given based on alarm signals and management personnel are contacted; alarm signals include power emergency alarm signals, etc.

[0073] This embodiment obtains the predicted electricity consumption of several regions through the electricity prediction model; calculates the regional electricity priority coefficient according to the regional data; adjusts the power station status according to the predicted electricity consumption and the regional electricity priority coefficient. The calculation of the regional electricity priority coefficient takes user participation into consideration, which greatly improves the user experience. At the same time, it considers in advance whether the predicted power generation can meet the electricity demand, and dynamically adjusts the power station status accordingly, thereby reducing the occurrence of power shortage and improving power supply efficiency.

[0074] The power prediction model in this embodiment is constructed by an artificial intelligence model, including:

[0075] Obtaining certain historical regional environmental data, historical electricity consumption, time characteristics and recording time within the regional data;

[0076] Integrate historical regional environmental data, historical electricity consumption, and time characteristics with the same recording time into a time vector;

[0077] Integrate each time vector into several prediction sequences according to the order of recording time;

[0078] Divide several prediction sequences into training set, test set and validation set in chronological order; the ratio between training set, test set and validation set is 7:2:1;

[0079] Select an artificial intelligence model as the basic model; artificial intelligence models include LSTM models, etc.;

[0080] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0081] By verifying the pre-trained model on the test set, we finally obtain an electricity prediction model whose input is several prediction sequences and output is the predicted electricity consumption.

[0082] In this embodiment, the calculation of the regional electricity priority coefficient according to the regional data includes:

[0083] Get user level YJ in regional data i And its corresponding quantity YS i ;

[0084] Determine user level YJ i Does YJ exist in i Greater than the level threshold; the level threshold is set based on experience;

[0085] Yes, the regional priority power consumption coefficient is set to the maximum value in the coefficient range; the range of the regional priority power consumption coefficient in this embodiment is between 0 and 1, so the regional priority power consumption coefficient is set to the maximum value in the coefficient range as 1;

[0086] No, by the formula QYYX = g × tan -1 (Σ i α i ×YJ i ×YS i / DS) calculates the regional electricity priority coefficient QYYX; where α i is the weight coefficient, α i It is adaptively generated by regional data; g is a proportional coefficient, g∈(0,π / 2), and the setting of g is to make the regional electricity priority coefficient range from 0 to 1; DS is the number of people per unit, and the specific value is set according to experience. In this embodiment, DS is set to 1 person; the weight coefficient within a region is determined. When the weight coefficient is determined, the higher the user level and the more people it corresponds to, the higher the priority power supply to the region, and thus the regional electricity priority coefficient increases accordingly.

[0087] The user level in this embodiment is calculated by the user feature level and the user behavior level, including:

[0088] Obtain the user characteristic level YTJ and the user behavior level YXJ; the user characteristic level is obtained by experts based on the user's family member identity and family member physical condition;

[0089] By the formula YJ = β 1 ×YTJ+β 2 ×YXJ calculates user level YJ;

[0090] Among them, β 1 and β 2 is the weight coefficient, β 1 and β 2∈(0, 1), the specific value is set according to experience; once the user characteristic level is determined, it will not be changed unless special circumstances occur, so the user level increases with the increase of the user behavior level; in this embodiment, for example, the user characteristic level of a major disease is set higher, and once a power outage occurs, the consequences for such users are extremely serious.

[0091] In this embodiment, the user behavior level is calculated based on the user's historical power consumption, including:

[0092] Obtain the user's historical electricity consumption and its corresponding recording time, as well as energy-saving electricity consumption JD;

[0093] Extract several non-energy-saving days FJT greater than JD in the historical electricity consumption and energy-saving days JT less than or equal to JD in the historical electricity consumption;

[0094] When FJT is greater than or equal to JT, let the user behavior level YXJ = 0;

[0095] Otherwise, by formula Calculate the user behavior level YXJ; where β 3 and β 4 is the weight coefficient, β 3 and β 4 ∈(0, 1), the specific value is set according to experience; DJ is the unit level, DT is the unit day, and the specific value is set according to experience; the more energy-saving days a user has, the better the user's energy-saving behavior is, so the user's behavior level should be higher; therefore, the user's behavior level increases accordingly.

[0096] In this embodiment, α i Adaptively generated from regional data, including:

[0097] Get user level YJ in regional data i ;

[0098] Through the formula α i =YJ i / Σ i YJ i Calculate the weight coefficient α corresponding to the user level i ; The weight coefficient corresponding to the user level is related to the number of user levels in the area; the higher the user level, the higher the corresponding weight coefficient.

[0099] In this embodiment, adjusting the power station state according to the predicted power consumption and the regional power consumption priority coefficient includes:

[0100] Obtain the predicted electricity consumption YYDj, regional electricity priority coefficient QYYXj and power station data for several regions; the power station data includes renewable electric energy KZN, energy storage electric energy CN, other electric energy QN and environmental data;

[0101] Predict the predicted power generation YD of renewable electric energy according to the power generation prediction model; the power generation prediction model is constructed through an artificial intelligence model;

[0102] Determine whether CN+YD is greater than ∑(YYDj); wherein j represents the number of the region, j=1, 2, ..., N; N is the total number of regions;

[0103] Yes, suspend the use of other power sources;

[0104] No, determine whether CN+YD+QN is greater than ∑(YYDj); if yes, resume using other electric energy sources for power supply, the power supply of other electric energy sources is |∑(YYDj)-(CN+YD)|; in this embodiment, other electric energy sources for power supply are other electric energy sources other than renewable electric energy and energy storage electric energy, and renewable electric energy is used preferentially to improve energy saving efficiency;

[0105] No, the power station status is regulated based on the regional power priority coefficient and power station data.

[0106] This embodiment calculates the regional electricity priority coefficient based on regional data. When the power generation cannot meet the electricity demand, the power station status is dynamically adjusted according to the regional electricity priority coefficient. At the same time, the user's electricity consumption behavior is taken into account in the calculation of the regional electricity priority coefficient, thereby enhancing the user's experience of intelligent power distribution and energy-saving power supply.

[0107] The power generation prediction model in this embodiment is constructed by an artificial intelligence model, including:

[0108] Obtain historical environmental data, historical equipment data, historical power generation and recording time of renewable electric energy;

[0109] Integrate historical environmental data, historical equipment data, and historical power generation with the same recording time into a time vector;

[0110] Integrate each time vector into several prediction sequences according to the order of recording time;

[0111] Divide several prediction sequences into training set, test set and validation set in chronological order; the ratio between training set, test set and validation set is 7:2:1;

[0112] Select an artificial intelligence model as the basic model; artificial intelligence models include LSTM models, etc.;

[0113] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0114] By verifying the pre-trained model on the test set, we finally get a power generation prediction model whose input is several prediction sequences and output is the predicted power generation.

[0115] In this embodiment, the power station status is regulated according to the regional power priority coefficient and the power station data, including:

[0116] Obtain regional predicted electricity consumption and its corresponding regional electricity priority coefficient, energy storage power energy in power station data, predicted power generation and other power energy;

[0117] Sort the regional power priority coefficients from large to small; when there is a maximum value in the coefficient range among several regional power priority coefficients; extract several predicted power consumptions corresponding to the maximum value, and sum up the several predicted power consumptions to obtain the predicted total power consumption; first determine whether there are special users in several regions, and as long as there are special users in the region, the power supply to the region will be given priority; if there is a special user in the region where the power consumption is greater than the power generation, an alarm signal needs to be issued for emergency power supply to ensure the living needs of special users, thereby improving the user experience;

[0118] Determine whether the predicted total power consumption is greater than CN+YD+QN; if so, generate an emergency power alarm signal and contact the management personnel to increase the transmission of other power energy sources;

[0119] No, electricity is transmitted according to the regional electricity priority coefficient from large to small; priority is given to ensuring electricity supply to areas with the largest regional electricity priority coefficient, realizing intelligent power distribution and improving user experience.

[0120] See also Figure 2 Another aspect of the present application provides an intelligent power distribution and energy-saving power supply method, including:

[0121] S0: Obtain power station data and regional data;

[0122] S1: The predicted power consumption of several regions is obtained through the power prediction model, which is constructed through the artificial intelligence model; the regional power consumption priority coefficient is calculated based on the regional data;

[0123] S2: Calculate the regional power consumption priority coefficient based on regional data; adjust the power station status based on the predicted power consumption and the regional power consumption priority coefficient;

[0124] S3: Prompt according to the alarm signal and contact the management.

[0125] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0126] The working principle of this application is as follows: by acquiring power station data and regional data; obtaining the predicted power consumption of several regions according to the power forecast model and calculating the regional power consumption priority coefficient according to the regional data; adjusting the power station status according to the predicted power consumption and the regional power consumption priority coefficient; making prompts according to the alarm signal and contacting the management personnel, taking user participation into consideration, predicting whether the power generation can meet the power consumption demand and making adjustments in advance, reducing the occurrence of power shortages, improving the user experience and power supply efficiency, and avoiding the problem that the existing technology lacks consideration of user participation, resulting in poor user experience, and the power generated by renewable energy cannot meet user needs, resulting in low efficiency of smart power distribution and energy-saving power supply.

[0127] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. An intelligent power distribution and energy-saving power supply system, characterized in that: include: Data collection module, data analysis module, early warning module and database; The data acquisition module is used to acquire power station data and regional data through data acquisition equipment; The data analysis module: obtains the predicted power consumption of several regions through a power prediction model, wherein the power prediction model is constructed through an artificial intelligence model; calculates the regional power priority coefficient according to the regional data; and adjusts the power station status according to the predicted power consumption and the regional power priority coefficient; The early warning module: makes prompts according to the alarm signal and contacts the management personnel.

2. The intelligent power distribution and energy-saving power supply system according to claim 1, characterized in that: The power prediction model is constructed by an artificial intelligence model, including: Obtaining certain historical regional environmental data, historical electricity consumption, time characteristics and recording time within the regional data; Integrate historical regional environmental data, historical electricity consumption, and time characteristics with the same recording time into a time vector; Integrate each time vector into several prediction sequences according to the order of recording time; Divide several prediction sequences into training sets, test sets and validation sets in chronological order; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtain an electricity prediction model whose input is several prediction sequences and output is the predicted electricity consumption.

3. The intelligent power distribution and energy-saving power supply system according to claim 1, characterized in that: The calculating of the regional electricity priority coefficient according to the regional data includes: Get user level YJ in regional data i And its corresponding quantity YS i ; Determine user level YJ i Does YJ exist in i Greater than the level threshold; Yes, set the regional electricity priority coefficient to the maximum value in the coefficient range; No, by the formula QYYX = g × tan -1 (∑ i α i ×YJ i ×YS i / DS) calculates the regional electricity priority coefficient QYYX; where α i is the weight coefficient, α i Adaptively generated from regional data; g is the proportional coefficient, g∈(0,π / 2); DS is the number of people per unit.

4. The intelligent power distribution and energy-saving power supply system according to claim 3, characterized in that: The user level is calculated through the user feature level and the user behavior level, including: Obtain user feature level YTJ and user behavior level YXJ; The user level YJ is calculated by the formula YJ = β1 × YTJ + β2 × YXJ; Among them, β1 and β2 are weight coefficients, β1 and β2∈(0,1).

5. The intelligent power distribution and energy-saving power supply system according to claim 4, characterized in that: The user behavior level is calculated based on the user's historical electricity consumption, including: Obtain the user's historical electricity consumption and its corresponding recording time, as well as energy-saving electricity consumption JD; Extract several non-energy-saving days FJT greater than JD in the historical electricity consumption and energy-saving days JT less than or equal to JD in the historical electricity consumption; When FJT is greater than or equal to JT, let the user behavior level YXJ = 0; Otherwise, by formula Calculate the user behavior level YXJ; where β3 and β4 are weight coefficients, β3 and β4∈(0,1); DJ is the unit level, and DT is the unit day.

6. The intelligent power distribution and energy-saving power supply system according to claim 3, characterized in that: The α i Adaptively generated from regional data, including: Get user level YJ in regional data i ; Through the formula α i =YJ i / ∑ i YJ i Calculate the weight coefficient α corresponding to the user level i .

7. The intelligent power distribution and energy-saving power supply system according to claim 1, characterized in that: The generating of the power station adjustment state according to the predicted power consumption and the regional power consumption priority coefficient includes: Obtaining predicted power consumption YYDj, regional power consumption priority coefficients QYYXj and power station data for several regions; the power station data includes renewable electric energy, energy storage electric energy, other electric energy and environmental data; Predicting the predicted power generation YD of renewable electric energy according to a power generation prediction model; the power generation prediction model is constructed by an artificial intelligence model; Determine whether the sum of the energy storage power and the predicted power generation is greater than the sum of the predicted power consumption; Yes, suspend the use of other power sources; If no, determine whether the sum of the energy storage power, the predicted power generation and other power sources is greater than the predicted power consumption; if yes, resume using other power sources, and the power supply of other power sources is the absolute value of the difference between the sum of the predicted power consumption and the sum of the energy storage power and the predicted power generation; No, the power station status is regulated based on the regional power priority coefficient and power station data.

8. The intelligent power distribution and energy-saving power supply system according to claim 7, characterized in that: The power generation prediction model is constructed by an artificial intelligence model, including: Obtain historical environmental data, historical equipment data, historical power generation and recording time of renewable electric energy; Integrate historical environmental data, historical equipment data, and historical power generation with the same recording time into a time vector; Integrate each time vector into several prediction sequences according to the order of recording time; Divide several prediction sequences into training sets, test sets and validation sets in chronological order; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally get a power generation prediction model whose input is several prediction sequences and output is the predicted power generation.

9. The intelligent power distribution and energy-saving power supply system according to claim 7, characterized in that: The control of the power station status according to the regional power priority coefficient and the power station data includes: Obtain regional predicted electricity consumption and its corresponding regional electricity priority coefficient, energy storage power energy in power station data, predicted power generation and other power energy; Sort the regional power consumption priority coefficients from large to small; when there is a maximum value in the coefficient range among several regional power consumption priority coefficients; extract several predicted power consumptions corresponding to the maximum value, and sum up the several predicted power consumptions to obtain the predicted total power consumption; Determine whether the total predicted electricity consumption is greater than the sum of the energy storage power, predicted power generation and other power sources; if so, generate an emergency power alarm signal and contact the management personnel to increase the transmission of other power sources; No, electricity will be transmitted according to the regional electricity priority coefficient from large to small.

10. An intelligent power distribution and energy-saving power supply method, applied to an intelligent power distribution and energy-saving power supply system according to any one of claims 1 to 9, characterized in that: include: S0: Obtain power station data and regional data; S1: Obtaining predicted power consumption of several regions through a power prediction model, wherein the power prediction model is constructed through an artificial intelligence model; calculating a regional power consumption priority coefficient based on regional data; S2: Calculate the regional power consumption priority coefficient based on regional data; adjust the power station status based on the predicted power consumption and the regional power consumption priority coefficient; S3: Prompt according to the alarm signal and contact the management.

Images