A multi-source data interactive management system and method based on big data

Abstract

The present invention discloses a multi-source data interaction management system and method based on big data, belonging to the field of computer technology. The system includes a demand side, a supply side, a database and an interaction management module; the demand side is used to record the user's energy demand data information, and the recorded information data is sorted and sent to the interaction management module; the supply side is used to supply the demand side, record the energy supply data information, and send the data to the interaction management module after sorting; the database is used to store and manage historical information data; the interaction management module is used to analyze and process the current energy information data, and control the supply of the supply side according to the current energy information data and the historical big data in the database; in the present invention, the abnormal data is cleaned before the data analysis, and the reliability of the prediction is enhanced; the big data from different sources is analyzed to improve the learning ability and decision-making ability of the system.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a multi-source data interaction management system and method based on big data. Background Art

[0002] Big data refers to a large and diverse collection of data that often comes from different sources and contains a variety of information. It collects data from different levels and provides a more comprehensive perspective and insight. Big data contains rich information. By analyzing and mining the data, hidden trends and correlations can be discovered, providing support for decision-making and problem solving. At present, processing and analyzing big data faces challenges in data acquisition, data transmission, processing and analysis.

[0003] Multi-source data refers to data from different sources and channels, with different characteristics and attributes. In life, some power systems use multiple modules to supply power. However, it is difficult to uniformly regulate these modules during the power supply process. There is also a risk of transmission errors in the data transmission process, which may lead to incorrect judgments during the data analysis process, thus affecting the stability of the power system. Summary of the invention

[0004] The purpose of the present invention is to provide a multi-source data interaction management system and method based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-source data interaction management system based on big data, the system includes a demand side, a supply side, a database and an interaction management module;

[0006] The demand side is used to record the user's energy demand data information, and send the recorded information data to the interactive management module after sorting; the supply side is used to supply the demand side, record the energy supply data information, and send the data to the interactive management module after sorting; the database is used to store and manage historical information data; the interactive management module is used to analyze and process the current energy information data, and control the supply of the supply side according to the current energy information data and the historical big data in the database;

[0007] Among them, the current energy information data includes the energy demand information data sent by the current demand side and the energy supply information data sent by the current supply side; the historical big data includes the historical energy demand information big data from the demand side and the historical energy supply information big data from the supply side; the energy data information is various electricity usage information.

[0008] According to the above technical solution, the supply end includes n levels of supply units; each level of supply unit includes an energy supply system;

[0009] Where n represents the number of supply units in the supply end, n≥2;

[0010] The energy supply system on the demand side is various power supply systems.

[0011] According to the above technical solution, the interaction management module includes a data processing unit, a data analysis unit and a control unit;

[0012] The data processing unit is used to receive and process current energy information data, correct erroneous data, and ensure data accuracy;

[0013] The data analysis unit is used to analyze the current energy information data according to the historical big data in the database, and store the analyzed current energy information data in the database;

[0014] The control unit is used to control the supply end to supply the demand end according to the analysis data.

[0015] A multi-source data interaction management method based on big data, the method comprising the following steps:

[0016] S10, the demand side generates energy demand, and the supply side supplies the demand side;

[0017] S20, collecting real-time energy demand data of users on the demand side, and cleaning and processing the energy demand data;

[0018] S30, collecting real-time energy information data supplied by the supply side;

[0019] S40, analyzing the data collected in step S20 and the historical big data in the database to predict the total energy demand at the demand side at the next moment;

[0020] S50, analyzing the real-time energy supply information data collected in step S30, the energy demand forecast data in step S40 and the historical big data in the database, and intelligently coordinating the energy supply on the supply side;

[0021] S60, sending the analyzed data to a database for storage;

[0022] Among them, the current energy information data includes the energy demand information data sent by the current demand side and the energy supply information data sent by the current supply side; the historical big data includes the historical energy demand information big data from the demand side and the historical energy supply information big data from the supply side.

[0023] In step S20, when the demand side is connected to multiple energy demand devices, there will be a lot of collected data in the demand side. Therefore, there is often a risk of transmission error in the transmission of the collected data. In order to eliminate abnormal values ​​in the collected data and protect the integrity of the data, the energy demand data needs to be cleaned and processed. The method steps are as follows:

[0024] S101, analyzing energy demand data to obtain a real-time energy demand set A(t) at the demand side; wherein A(t) = {a1(t), a2(t), a3(t), ..., a n (t)}; a1(t), a2(t), a3(t),..., a n (t) represents the energy demand of each data point on the demand side at time t;

[0025] S102, using the isolation forest algorithm, using the demand-side real-time energy demand set A(t) to train the isolation forest model, and calculating the abnormal score of each data point in the energy demand data set, recorded as set B(t); where B(t) = {b1(t), b2(t), b3(t), ..., b n (t)}; b1(t), b2(t), b3(t),..., b n (t) represents the abnormal score of each data point in the energy demand data at time t;

[0026] The isolation forest algorithm can accurately find outliers in energy collection data without being affected by imbalanced data distribution;

[0027] S103, set a threshold K, compare the abnormal score of each data point in the collection B(t) with K, and determine whether each data point in A(t) is abnormal; when b i (t)≥K, then it corresponds to b i The energy demand data point in (t) is abnormal; when b i When (t)<K, it corresponds to b i The energy demand data point in (t) is normal;

[0028] S104, correcting abnormal data in A(t);

[0029] Among them, K represents the threshold when the energy demand data is abnormal, which is obtained by the anomaly score of the known abnormal data in the database; n represents the number of data points on the demand side.

[0030] When the data points in A(t) are abnormal, the steps for correcting the abnormal data points are as follows:

[0031] S201, determine the abnormal data point a in A(t) i (t);

[0032] S202, according to a in the database i (t) historical big data information, taking a i (t) The first m items of data a i (t-1), a i (t-2), a i (t-3), ..., a i (tm), establish the independent variable as t and the dependent variable as a i The univariate multiple linear regression model is expressed as:

[0033] a i =β0+β1t+β2t 2 +...+β m t m +ε;

[0034] Among them, β0, β1, β2,..., β m is the regression coefficient; ε is the error term;

[0035] S203, substituting the time t corresponding to the abnormal data point into the regression model of step S202, and the obtained value is the corrected abnormal data;

[0036] Among them, m represents the corresponding a taken from the database i (t) The number of historical big data;

[0037] In order to correct the abnormal data in time and not affect the energy supply efficiency of the supply side to the demand side, only the historical data before the abnormal data is used as the basis for correction. The abnormal data is corrected by establishing a univariate multiple linear regression model.

[0038] In step S40, the total energy demand X is obtained through the real-time energy demand data of the user at the demand end. t ; Based on the historical demand-side energy demand data and the current demand-side energy demand data in the database, the LSTM algorithm is used to predict the demand-side energy demand Y at the next moment t ;

[0039] The LSTM algorithm is used to predict the total energy demand at the next moment based on the change cycle of the total energy demand on the demand side in historical data, so that the management system that has long relied on big data has a learning mechanism and improves the reliability of the prediction.

[0040] The supply end includes n levels of supply units; when the current supply unit cannot meet the energy demand of the demand end, the next level of supply unit is controlled to join the demand end supply;

[0041] Wherein, n represents the number of supply unit levels in the supply end, n≥2.

[0042] In the process of energy supply of some systems, multiple supply systems are often used, and the maximum energy supply per unit time of each supply system is limited. When the demand side is at its peak, the lack of coordination between different supply units may lead to unstable supply. Therefore, the supply units are adjusted in advance by means of advance prediction. The method steps for intelligent coordination of energy supply on the supply side are as follows:

[0043] S301, analyzing the historical big data in the database to obtain the maximum supply per unit time of the energy supply system corresponding to each level of supply unit k1, k2, ..., k n ; Set the supply interval of each level supply unit to be

[0044] Among them, k i represents the maximum supply per unit time of the energy supply system corresponding to the i-th supply unit;

[0045] S302: Based on the predicted total energy demand Y at the next moment t Determine the number of supply units at the supply end at the next moment, w, when Y t When the interval threshold is reached, the next level supply unit is started in advance;

[0046] S303, analyzing the real-time energy supply information data of the supply side to obtain the energy supply amount z1(t), z2(t), ..., z1(t) of the energy supply system in each level of supply unit at the current moment. n (t);

[0047] Among them, z i (t) represents the energy supply amount of the energy supply system corresponding to the i-th supply unit at the current moment;

[0048] S304, z i (t) and k i For comparison; when z i (t)<k i When k is controlled, the energy supply of the i+1th level supply unit is i -z i (t) The supply is handed over to the i-th level supply unit; in order to prevent inaccurate prediction data and improve system stability, the supply unit is closed only when the i+1-th level supply unit has no supply task;

[0049] Because z i (t)≥k i The situation has been predicted in advance by step S302, so only z needs to be considered i (t)<k i situation.

[0050] Since the maximum energy supply per unit time of the energy supply system will be affected by factors such as system equipment aging and system autonomous update, it is necessary to i Continuously update to ensure the accuracy of intelligent regulation of the energy system, so the maximum energy supply per unit time of the energy supply system corresponding to each level of supply unit is k i It will change with the maximum energy supply per unit time data during the period when the supply system is at its maximum working efficiency; among them, the calculated k i The method steps are:

[0051] S401, setting the time period when the energy supply system in each level of supply unit is at maximum working efficiency as a cycle;

[0052] S402, when the number of supply units at the supply end is w≥2, record the maximum energy supply data per unit time of each energy supply system corresponding to the supply unit in the w-1-level supply unit within the cycle;

[0053] S403. When the cycle ends, the sliding average method is used to process the cycle data, and then the average value method is used to calculate the maximum energy supply data per unit time in the cycle after processing. The average value obtained is the k after the change. i ;

[0054] Since the number of supply units on the supply side w≥2, the corresponding energy supply systems in the w-1 level supply units are at maximum working efficiency. By using the sliding average method and the average method, the system threshold k is effectively predicted. i The changes improve the stability of the system.

[0055] Compared with the prior art, the beneficial effects achieved by the present invention are: providing a multi-source data interaction management system and method based on big data, collecting and cleaning the electricity consumption data of demand-side users, eliminating abnormal values, and enhancing the accuracy of data analysis and prediction and the stability of system power supply; integrating big data from different sources in the power system, analyzing the data information hidden in the big data, improving the learning ability of the power system, and optimizing the real-time control of electricity by the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0057] Figure 1 It is a structural schematic diagram of a multi-source data interactive management system based on big data of the present invention;

[0058] Figure 2It is a schematic diagram of the steps of a multi-source data interaction management method based on big data of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] See also Figure 1 to Figure 2 ,The present invention provides a technical solution: a multi-source data interaction management system based on big data, the system includes a demand side, a supply side, a database and an interaction management module;

[0061] The demand side is used to record the user's energy demand data information, and send the recorded information data to the interactive management module after sorting; the supply side is used to supply the demand side, record the energy supply data information, and send the data to the interactive management module after sorting; the database is used to store and manage historical information data; the interactive management module is used to analyze and process the current energy information data, and control the supply of the supply side according to the current energy information data and the historical big data in the database;

[0062] Among them, the current energy information data includes the energy demand information data sent by the current demand side and the energy supply information data sent by the current supply side; the historical big data includes the historical energy demand information big data from the demand side and the historical energy supply information big data from the supply side.

[0063] The supply end includes n levels of supply units; each level of supply unit includes an energy supply system;

[0064] Wherein, n represents the number of supply units in the supply end, n≥2.

[0065] The interaction management module includes a data processing unit, a data analysis unit and a control unit;

[0066] The data processing unit is used to receive and process current energy information data, correct erroneous data, and ensure data accuracy;

[0067] The data analysis unit is used to analyze the current energy information data according to the historical big data in the database, and store the analyzed current energy information data in the database;

[0068] The control unit is used to control the supply end to supply the demand end according to the analysis data.

[0069] A multi-source data interaction management method based on big data, the method comprising the following steps:

[0070] S10, the demand side generates energy demand, and the supply side supplies the demand side;

[0071] S20, collecting real-time energy demand data of users on the demand side, and cleaning and processing the energy demand data;

[0072] S30, collecting real-time energy information data supplied by the supply side;

[0073] S40, analyzing the data collected in step S20 and the historical big data in the database to predict the total energy demand at the demand side at the next moment;

[0074] S50, analyzing the real-time energy supply information data collected in step S30, the energy demand forecast data in step S40 and the historical big data in the database, and intelligently coordinating the energy supply on the supply side;

[0075] S60, sending the analyzed data to a database for storage;

[0076] Among them, the current energy information data includes the energy demand information data sent by the current demand side and the energy supply information data sent by the current supply side; the historical big data includes the historical energy demand information big data from the demand side and the historical energy supply information big data from the supply side.

[0077] In step S20, the method steps for cleaning and processing the energy demand data are as follows:

[0078] S101, analyzing energy demand data to obtain a real-time energy demand set A(t) at the demand side; wherein A(t) = {a1(t), a2(t), a3(t), ..., a n (t)}; a1(t), a2(t), a3(t),..., a n (t) represents the energy demand of each data point on the demand side at time t;

[0079] S102, using the isolation forest algorithm, using the demand-side real-time energy demand set A(t) to train the isolation forest model, and calculating the abnormal score of each data point in the energy demand data set, recorded as set B(t); where B(t) = {b1(t), b2(t), b3(t), ..., b n (t)}; b1(t), b2(t), b3(t),..., b n (t) represents the abnormal score of each data point in the energy demand data at time t;

[0080] S103, set a threshold K, compare the abnormal score of each data point in the collection B(t) with K, and determine whether each data point in A(t) is abnormal; when b i (t)≥K, then it corresponds to b i The energy demand data point in (t) is abnormal; when b i When (t)<K, it corresponds to b i The energy demand data point in (t) is normal;

[0081] S104, correcting abnormal data in A(t);

[0082] Among them, K represents the threshold when the energy demand data is abnormal, which is obtained by the anomaly score of the known abnormal data in the database; n represents the number of data points on the demand side.

[0083] When the data points in A(t) are abnormal, the steps for correcting the abnormal data points are as follows:

[0084] S201, determine the abnormal data point a in A(t) i (t);

[0085] S202, according to a in the database i (t) historical big data information, taking a i (t) The first m items of data a i (t-1), a i (t-2), a i (t-3), ..., a i (tm), establish the independent variable as t and the dependent variable as a i The univariate multiple linear regression model is expressed as:

[0086] a i =β0+β1t+β2t 2 +...+β m t m +ε;

[0087] Among them, β0, β1, β2,..., β m is the regression coefficient; ε is the error term;

[0088] S203, substituting the time t corresponding to the abnormal data point into the regression model of step S202, and the obtained value is the corrected abnormal data;

[0089] Among them, m represents the corresponding a taken from the database i (t) The number of historical big data.

[0090] In step S40, the total energy demand X is obtained through the real-time energy demand data of the user at the demand end.t ; Based on the historical demand-side energy demand data and the current demand-side energy demand data in the database, the LSTM algorithm is used to predict the demand-side energy demand Y at the next moment t .

[0091] The supply end includes n levels of supply units; when the current supply unit cannot meet the energy demand of the demand end, the next level of supply unit is controlled to join the demand end supply;

[0092] Wherein, n represents the number of supply unit levels in the supply end, n≥2.

[0093] The method steps for intelligently coordinating energy supply on the supply side are:

[0094] S301, analyzing the historical big data in the database to obtain the maximum supply per unit time of the energy supply system corresponding to each level of supply unit k1, k2, ..., k n ; Set the supply interval of each level supply unit to be

[0095] Among them, k i represents the maximum supply per unit time of the energy supply system corresponding to the i-th supply unit;

[0096] S302: Based on the predicted total energy demand Y at the next moment t Determine the number of supply units at the supply end at the next moment, w, when Y t When the interval threshold is reached, the next level supply unit is started in advance;

[0097] S303, analyzing the real-time energy supply information data of the supply side to obtain the energy supply amount z1(t), z2(t), ..., z1(t) of the energy supply system in each level of supply unit at the current moment. n (t);

[0098] Among them, z i (t) represents the energy supply amount of the energy supply system corresponding to the i-th supply unit at the current moment;

[0099] S304, z i (t) and k i For comparison; when z i (t)<k i When k is controlled, the energy supply of the i+1th level supply unit is i -z i (t) The supply is handed over to the i-th level supply unit; when the i+1-th level supply unit has no supply task, the supply unit is turned off.

[0100] The maximum energy supply per unit time of the energy supply system corresponding to each level of supply unit k i It will change with the maximum energy supply per unit time data during the period when the supply system is at its maximum working efficiency; among them, the calculated k i The method steps are:

[0101] S401, setting the time period when the energy supply system in each level of supply unit is at maximum working efficiency as a cycle;

[0102] S402, when the number of supply units at the supply end is w≥2, record the maximum energy supply data per unit time of each energy supply system corresponding to the supply unit in the w-1-level supply unit within the cycle;

[0103] S403. When the cycle ends, the sliding average method is used to process the cycle data, and then the average value method is used to calculate the maximum energy supply data per unit time in the cycle after processing. The average value obtained is the k after the change. i .

[0104] In this embodiment:

[0105] The system is a small power supply system, specifically a household clean energy power supply system, in which the demand side is the user's electrical equipment, the supply side is the solar power generation system, the wind power generation system and the power grid, and the interactive management module is an intelligent power control processor, and both the demand side and the supply side in the system are connected to the processor;

[0106] Among them, the solar power generation system is the power supply system corresponding to the first supply unit, the wind power generation system is the power supply system corresponding to the second supply unit; the power grid is the power supply system corresponding to the third supply unit;

[0107] When the user has a demand for electricity, the processor controls the solar power generation system to supply power to the electrical equipment first;

[0108] Collect the real-time electricity demand data of users in the system to obtain the set A of electricity demand of each user at time t; collect the isolation forest algorithm to find the abnormal data in the set A(t), and according to the historical big data information recorded in the database in the processor, take the first 20 items of abnormal data at the current time t to establish a univariate multiple linear regression model, substitute the time t into the model, and the value obtained is the corrected abnormal data;

[0109] The electric energy intelligent control processor analyzes the cleaned data to obtain the total power consumption X of the demand side at the moment t, and uses the LSTM algorithm to predict the total power consumption Y of the demand side at the next moment. t ;

[0110] The electric energy intelligent control processor analyzes the historical big data in the database and obtains that the maximum supply threshold of the solar power generation system is k1, and the maximum supply threshold of the wind power generation system is k2; at this time, the supply interval of the solar power generation system is [0, k1), and the supply interval of the wind power generation system is [k1, k1+k2);

[0111] At a certain moment t1:

[0112] At this time, the supply unit level at the supply end is the first level;

[0113] According to Y t It is predicted that the supply unit level of the supply end at the next moment will be the second level;

[0114] The electric energy intelligent control processor controls the wind power generation system in advance to supply power for the next moment;

[0115] At another time t2:

[0116] At this time, the supply unit level at the supply end is the second level;

[0117] According to Y t It is predicted that the supply unit level of the supply side at the next moment will be the first level;

[0118] At this time, the solar power generation system supplies z1 per unit time; z1(t2)<k1; the electric energy intelligent control processor controls the wind power generation system to supply the power k1-z1(t2) to the solar power generation system; when the solar power generation system has no supply task, the electric energy intelligent control processor controls the wind power generation system to shut down;

[0119] When the power supply is finished, the analyzed data will be sent to the database for storage;

[0120] During the power supply process, the solar power generation system reaches its maximum power supply per unit time at [t3, t4]. By analyzing the maximum power supply per unit time data within this cycle, the sliding average method is used to process the cycle data, and then the average value method is used to obtain a new k1.

[0121] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0122] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. 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.

Claims

1. A multi-source data interaction management method based on big data, characterized by: The method comprises the following steps: S10, the demand side generates energy demand, and the supply side supplies the demand side; S20, collecting real-time energy demand data of users on the demand side, and cleaning and processing the energy demand data; S30, collecting real-time energy information data supplied by the supply side; S40, analyzing the data collected in step S20 and the historical big data in the database to predict the total energy demand at the demand side at the next moment; S50, analyzing the real-time energy supply information data collected in step S30, the energy demand forecast data in step S40 and the historical big data in the database, and intelligently coordinating the energy supply on the supply side; S60, sending the analyzed data to a database for storage; Among them, the current energy information data includes the energy demand information data sent by the current demand side and the energy supply information data sent by the current supply side; the historical big data includes the historical energy demand information big data of the demand side and the historical energy supply information big data of the supply side; In step S20, the method steps for cleaning and processing the energy demand data are as follows: S101, analyzing energy demand data to obtain a real-time energy demand set A(t) at the demand side; wherein A(t) = {a1(t), a2(t), a3(t), ..., a n (t)}; a1(t), a2(t), a3(t),..., a n (t) represents the energy demand of each data point on the demand side at time t; S102, using the isolation forest algorithm, using the demand-side real-time energy demand set A(t) to train the isolation forest model, and calculating the abnormal score of each data point in the energy demand data set, recorded as set B(t); where B(t) = {b1(t), b2(t), b3(t), ..., b n (t)}; b1(t), b2(t), b3(t),..., b n (t) represents the abnormal score of each data point in the energy demand data at time t; S103, set a threshold K, compare the abnormal score of each data point in the collection B(t) with K, and determine whether each data point in A(t) is abnormal; when b i (t)≥K, then it corresponds to b i The energy demand data point in (t) is abnormal; when b i (t)<K, then it corresponds to b i The energy demand data point in (t) is normal; S104, correcting abnormal data in A(t); Among them, K represents the threshold when the energy demand data is abnormal, which is obtained by the abnormal score of the known abnormal data in the database; n represents the number of data points in the demand side; When the data points in A(t) are abnormal, the steps for correcting the abnormal data points are as follows: S201, determine the abnormal data point a in A(t) i (t); S202, according to a in the database i (t) historical big data information, taking a i (t) The first m items of data a i (t-1), a i (t-2), a i (t-3), ..., a i (tm), establish the independent variable as t and the dependent variable as a i The univariate multiple linear regression model is expressed as: a i =β0+β1t+β2t 2 +...+b m t m +e; Among them, β0, β1, β2,..., β m is the regression coefficient; ε is the error term; S203, substituting the time t corresponding to the abnormal data point into the regression model of step S202, and the obtained value is the corrected abnormal data; Among them, m represents the corresponding a taken from the database i (t) The number of historical big data; In step S40, the total energy demand X is obtained through the real-time energy demand data of the user at the demand end. t ; Based on the historical demand-side energy demand data and the current demand-side energy demand data in the database, the LSTM algorithm is used to predict the demand-side energy demand Y at the next moment t ; The supply end includes n levels of supply units; when the current supply unit cannot meet the energy demand of the demand end, the next level of supply unit is controlled to join the demand end supply; Wherein, n represents the number of supply unit levels in the supply end, n≥2; The method steps for intelligently coordinating energy supply on the supply side are: S301, analyzing the historical big data in the database to obtain the maximum supply per unit time of the energy supply system corresponding to each level of supply unit k1, k2, ..., k n ; Set the supply intervals of each level supply unit to [0, k1), [k1, k1+k2), ..., Among them, k i represents the maximum supply per unit time of the energy supply system corresponding to the i-th supply unit; S302: Based on the predicted total energy demand Y at the next moment t Determine the number of supply units at the supply end at the next moment, w, when Y t When the interval threshold is reached, the next level supply unit is started in advance; S303, analyzing the real-time energy supply information data of the supply side to obtain the energy supply amount z1(t), z2(t), ..., z1(t) of the energy supply system in each level of supply unit at the current moment. n (t); Among them, z i (t) represents the energy supply amount of the energy supply system corresponding to the i-th supply unit at the current moment; S304, z i (t) and k i For comparison; when z i (t)<k i When the energy supply of the i+1th level supply unit is controlled, i -z i (t) The supply is handed over to the i-th level supply unit; when the i+1-th level supply unit has no supply task, the supply unit is turned off; The maximum energy supply per unit time of the energy supply system corresponding to each level of supply unit k i It will change with the maximum energy supply per unit time data during the period when the supply system is at its maximum working efficiency; among them, the calculated k i The method steps are: S401, setting the time period when the energy supply system in each level of supply unit is at maximum working efficiency as a cycle; S402, when the number of supply units at the supply end is w≥2, record the maximum energy supply data per unit time of each energy supply system corresponding to the supply unit in the w-1-level supply unit within the cycle; S403. When the cycle ends, the sliding average method is used to process the cycle data, and then the average value method is used to calculate the maximum energy supply data per unit time in the cycle after processing. The average value obtained is the k after the change. i .

2. A multi-source data interaction management system based on big data, applied to a multi-source data interaction management method based on big data as claimed in claim 1, characterized in that: The system includes demand side, supply side, database and interaction management module; The demand side is used to record the user's energy demand data information, and send the recorded information data to the interactive management module after sorting; the supply side is used to supply the demand side, record the energy supply data information, and send the data to the interactive management module after sorting; the database is used to store and manage historical information data; the interactive management module is used to analyze and process the current energy information data, and control the supply of the supply side according to the current energy information data and the historical big data in the database; Among them, the current energy information data includes the energy demand information data sent by the current demand side and the energy supply information data sent by the current supply side; the historical big data includes the historical energy demand information big data of the demand side and the historical energy supply information big data of the supply side; The supply end includes n levels of supply units; each level of supply unit includes an energy supply system; Where n represents the number of supply units in the supply end, n≥2; The interaction management module includes a data processing unit, a data analysis unit and a control unit; The data processing unit is used to receive and process current energy information data, correct erroneous data, and ensure data accuracy; The data analysis unit is used to analyze the current energy information data according to the historical big data in the database, and store the analyzed current energy information data in the database; The control unit is used to control the supply end to supply the demand end according to the analysis data.

Images