Multi-energy cooperative energy-saving control system and method based on Internet of Things

Abstract

The invention discloses a multi-energy collaborative energy-saving control system and method based on the Internet of Things, and relates to the technical field of energy-saving control, and the control method comprises the following steps: collecting the energy consumption data change condition in each collaborative process, and generating a corresponding collaborative record; analyzing the actual energy-saving condition and carrying out abnormity identification; any type of energy is selected, the expected allowable deviation of the selected type of energy is analyzed, and the collaborative association condition between the selected energy and other types of energy is obtained; identifying abnormal association conditions among different types of energy to obtain an expected energy-saving rate of any type; when cooperative control is carried out every time, real-time change conditions of energy consumption data of various energy sources are analyzed, and real-time energy-saving conditions of various energy sources are obtained; based on the expected allowable deviation and the expected energy-saving rate range of the various energy sources, performing abnormity judgment on the cooperative control conditions of the various energy sources; and misjudgment caused by the fact that a traditional model cannot recognize abnormal association can be avoided.

Description

Technical Field

[0001] This invention relates to the field of energy-saving control technology, specifically to a multi-energy collaborative energy-saving control system and method based on the Internet of Things. Background Technology

[0002] With the rapid development of IoT technology, coordinated control and management of multiple energy sources has become an important way to achieve efficient energy utilization in buildings, parks and even cities. Through the widespread deployment of sensor networks, real-time data on the production, transmission, consumption and environment of multiple energy sources are collected, and future state prediction and optimized scheduling are carried out based on the established coordinated energy-saving management model in order to achieve the optimal overall energy efficiency of the system.

[0003] However, in actual operation, due to factors such as equipment performance degradation, changes in environmental factors, and difficulty in accurate modeling, deviations between the actual operating state and the model's predictions are inevitable. Existing collaborative energy-saving management models generally lack the ability to analyze prediction deviations in detail and fail to effectively distinguish between "reasonable deviations" and "abnormal deviations," which seriously restricts the improvement of collaborative energy-saving effects and the reliability of system operation. Summary of the Invention

[0004] The purpose of this invention is to provide a multi-energy collaborative energy-saving control system and method based on the Internet of Things to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a multi-energy collaborative energy-saving control method based on the Internet of Things, the control method comprising the following steps:

[0006] Step S100: Monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, and generate corresponding collaborative records; analyze the actual energy saving situation after any collaborative record is completed, and identify anomalies in the collaborative records.

[0007] Step S200: Select any type of energy, analyze the differences between each normal collaborative record, and obtain the expected allowable deviation of the selected type of energy; based on the differences in energy saving between different collaborative records, obtain the collaborative correlation between the selected energy and other types of energy.

[0008] Step S300: Analyze the collaborative relationships between different types of energy in any abnormal collaborative record, identify the abnormal relationships between different types of energy; analyze the energy saving of any different types of energy in each collaborative record, and obtain the expected energy saving rate of any type.

[0009] Step S400: Whenever coordinated control is performed, the real-time changes in energy consumption data of various energy sources are analyzed to obtain the real-time energy saving status of various energy sources; based on the expected allowable deviation and expected energy saving rate range of various energy sources, anomaly judgment is made on the coordinated control status of various energy sources.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S101: Obtain the collaboration cycle of any complete collaboration process, and divide the collaboration cycle into several unit time points. Use monitoring equipment to collect the energy consumption values ​​of various energy sources at each unit time point; arbitrarily select one energy source, construct a two-dimensional Cartesian coordinate system with the unit time point as the horizontal axis and the energy consumption value as the vertical axis, and present the changes in the energy consumption value of the selected energy source; obtain the changes in the energy consumption value of various energy sources in the collaboration process, and match the energy consumption values ​​of various energy sources according to the collection time points to generate a collaboration record;

[0012] Step S102: Randomly select a collaborative record, and randomly select an energy source from the selected collaborative records. Set the energy consumption value of the selected energy source at the initial time point to H. start At the same time, the energy consumption value H of the selected energy source after the collaborative process is obtained. end The energy saving rate ε = (H) in the selected collaborative record was calculated. start -H end ) / H start ;

[0013] Step S103: Preset a desired energy saving rate ε for the selected energy source. ex If ε < ε ex If an anomaly is detected, the selected energy sources are marked as anomalies; the number of energy types with anomaly marks in the selected collaborative records is counted as n, and the total number of energy types is set to n. total The proportion of anomalous energy in the selected collaborative records is δ = n / n total Preset an abnormality percentage threshold δ th If δ≥δ th If δ < δ, then the selected collaborative record will be set as an abnormal collaborative record. th If it is, it is set as a normal collaborative record; in the process of collaborative control of various energy sources, the coordination between various energy sources needs to be considered. Therefore, the preset expected energy saving rate does not represent the actual energy saving situation. Therefore, it is necessary to judge whether there is an anomaly by the number of anomaly types.

[0014] Furthermore, step S200 includes the following steps:

[0015] Step S201: Randomly select an energy source and arbitrarily select a normal collaborative record. Obtain the energy saving rate ε of the selected energy source in the selected abnormal collaborative record. If the selected energy source has an abnormal marker in the selected abnormal collaborative record, obtain the expected energy saving rate ε of the selected energy source. ex The deviation amplitude of the selected energy source in the selected abnormal collaborative record was calculated to be f = (ε ex -ε) / ε ex And set it as the characteristic deviation amplitude; obtain the characteristic deviation amplitude of the selected energy source in all normal collaborative records, and select the characteristic deviation amplitude with the largest value as the expected allowable deviation of the selected energy source;

[0016] Step S202: In addition to the selected energy source, arbitrarily select another energy source and set it as the comparison energy source. Arbitrarily select a collaborative record. If, in the selected collaborative record, there is exactly one energy source with an abnormal marker between the selected energy source and the comparison energy source, then set the selected energy source and the comparison energy source as an associated energy group, thus obtaining several associated energy groups for the selected collaborative record. In the process of multiple energy collaboration, when saving energy for certain types of energy sources, it is also necessary to improve the use of other energy sources. Therefore, the two will be associated.

[0017] Step S203: Obtain the associated energy groups for each collaborative record. If several associated energy groups are identical, classify the identical associated energy groups into the same type of energy group; count the number of energy groups contained in each type of energy group, and set the number of energy groups in the a-th type of energy group as m. a The total number of collaborative records obtained is m total The proportion β of energy group a was calculated. a =m a / m total and the proportion of quantity β a Set as the synergistic correlation value for energy group a; the synergistic correlation value reflects the correlation between energy-saving energy and deviation energy, that is, the probability that when the energy consumption value of one energy decreases, the energy consumption value of the other energy increases.

[0018] Furthermore, step S300 includes the following steps:

[0019] Step S301: Arbitrarily obtain the synergistic correlation value β of the energy group of type a. a A preset association threshold β th If β a ≥β th If so, the energy group of type a is set as the target energy group; arbitrarily select a target energy group, and set the energy in the selected target energy group that has a deviation amplitude as the deviation energy; arbitrarily extract a collaborative record containing the selected target energy group, and if the extracted collaborative record is an abnormal collaborative record, then obtain the deviation amplitude f of the deviation energy;

[0020] Step S302: Set the expected allowable deviation of the deviation energy as f. max If f≤f max Then, the extracted collaborative record is set as a feature collaborative record; another energy source in the selected target energy group is set as an energy-saving energy source, and the energy-saving rate of the energy-saving energy source in the extracted collaborative record is obtained as ε; the energy-saving rate of the energy-saving energy source in any collaborative record is obtained, and the energy-saving rate of the energy-saving energy source is divided into two data sets according to whether the collaborative record is an abnormal collaborative record, and the numerical range of the two data sets is obtained respectively. The numerical range of the data set corresponding to the normal collaborative record is set as (ε1) min ,ε1 max If the numerical ranges of two data sets overlap and ε > ε1 max If the energy-saving energy is set as an abnormal energy-saving energy, the selected target energy group in the extracted collaborative record will be set as an abnormal energy group. For overlapping ranges, for example, if the value range of the normal collaborative record is (20%, 40%), and the value range of the abnormal collaborative record is (10%, 30%), then the overlapping range between the two is (30%, 40%). In addition, the energy saving rate of various energy sources is not necessarily better the higher it is. Because if the energy saving rate of one energy source is too high under comprehensive collaborative control, the energy consumption value of other energy sources needs to be increased to make up for it. In the comprehensive collaboration, this will affect the progress of collaborative energy saving. Therefore, it is necessary to analyze the maximum energy saving rate in order to obtain a more accurate and reasonable energy saving range.

[0021] Step S303: Randomly select an abnormal energy group, extract the abnormal energy saving energy in the selected abnormal energy group, obtain the energy saving rate of the abnormal energy saving energy in each collaborative record, obtain the numerical range of the abnormal energy saving energy in the normal collaborative record, select the energy saving rate with the largest value in the numerical range and set it as the maximum expected energy saving rate of the abnormal energy saving energy, set the expected energy saving rate as the minimum expected energy saving rate, and obtain the expected energy saving rate range of the abnormal energy saving energy.

[0022] Furthermore, step S400 includes the following steps:

[0023] Step S401: Real-time acquisition of energy consumption values ​​for various energy sources; extraction of initial energy consumption values ​​at the start of coordinated control; extraction of actual energy consumption values ​​for various energy sources during coordinated control; arbitrary selection of one type of energy source; if the actual energy consumption value of the selected energy source exceeds the initial energy consumption value, the actual deviation amplitude f of the selected energy source is obtained. now If the actual energy consumption of the selected energy source is lower than the initial energy consumption, then the actual energy saving rate ε of the selected energy source is obtained. now ;

[0024] Step S402: Set the expected allowable deviation for energy selection as f ex And the expected energy saving rate range is [ε1 ’ ex ,ε2 ’ ex If the actual energy saving rate ε is selected... now Satisfying ε now <ε1 ’ ex or ε now >ε2 ’ ex Alternatively, select the actual deviation range f of the energy. now Satisfy f now >f ex If an anomaly is detected, the energy source will be selected and marked as abnormal, and an anomaly alert will be sent to the current collaborative control process.

[0025] To better implement the above methods, a multi-energy collaborative energy-saving control system is also proposed. The control system includes a collaborative recording and analysis module, an expected deviation analysis module, an abnormal energy-saving analysis module, and a real-time predictive analysis module.

[0026] The collaborative record analysis module is used to monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, generate corresponding collaborative records, analyze the actual energy saving after any collaborative record is completed, and identify anomalies in the collaborative records.

[0027] The expected deviation analysis module is used to select any type of energy, analyze the differences between each normal collaborative record, and obtain the expected allowable deviation of the selected energy type; based on the differences in energy saving between different collaborative records, the collaborative correlation between the selected energy and other types of energy is obtained.

[0028] The abnormal energy saving analysis module is used to analyze the collaborative relationship between different types of energy in any abnormal collaborative record, identify the abnormal relationship between different types of energy, analyze the energy saving of any different types of energy in each collaborative record, and obtain the expected energy saving rate of any type.

[0029] The real-time predictive analysis module is used to analyze the real-time changes in energy consumption data of various energy sources whenever coordinated control is performed, and to obtain the real-time energy saving status of various energy sources; based on the expected allowable deviation and expected energy saving rate range of various energy sources, it makes anomaly judgments on the coordinated control status of various energy sources.

[0030] Furthermore, the collaborative record analysis module includes a collaborative data acquisition unit and a collaborative anomaly identification unit;

[0031] The collaborative data acquisition unit is used to monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, and generate corresponding collaborative records; the collaborative anomaly identification unit is used to analyze the actual energy saving situation after any collaborative record is completed, and to identify anomalies in the collaborative record.

[0032] Furthermore, the expectation deviation analysis module includes an expectation deviation setting unit and a collaborative association identification unit;

[0033] The expected deviation setting unit is used to select any type of energy and analyze the differences between each normal collaborative record to obtain the expected allowable deviation of the selected type of energy; the collaborative association identification unit is used to obtain the collaborative association between the selected energy and other types of energy based on the differences in energy saving between different collaborative records.

[0034] Furthermore, the abnormal energy-saving analysis module includes an abnormal correlation identification unit and an energy-saving magnitude analysis unit;

[0035] The abnormal correlation identification unit is used to analyze the collaborative correlation between different types of energy in any abnormal collaborative record and to identify the abnormal correlation between different types of energy; the energy saving amplitude analysis unit is used to analyze the energy saving of any different types of energy in each collaborative record and to obtain the expected energy saving rate of any type.

[0036] Furthermore, the real-time collaborative analysis module includes a real-time energy-saving analysis unit and a real-time anomaly identification unit;

[0037] The real-time energy-saving analysis unit is used to analyze the real-time changes in energy consumption data of various energy sources whenever coordinated control is performed, and to obtain the real-time energy-saving status of various energy sources; the real-time anomaly identification unit is used to judge the anomalies in the coordinated control of various energy sources based on the expected allowable deviation and expected energy-saving rate range of various energy sources.

[0038] Compared with the prior art, the beneficial effects of the present invention are:

[0039] 1. By establishing a collaborative record analysis mechanism and identifying abnormal correlations, this invention can accurately distinguish between reasonable deviations and abnormal deviations in the energy collaboration process. By using the abnormal proportion threshold and collaborative correlation value, it can avoid misjudgments caused by the inability of traditional models to identify abnormal correlations, thus significantly improving the stability of system operation and the controllability of energy-saving effects.

[0040] 2. This invention constructs the expected allowable deviation and expected energy saving rate range through historical data, and combines it with real-time energy consumption analysis to dynamically adjust the synergistic strategy of different energy sources; by identifying the synergistic mode of related energy groups, it effectively achieves the optimal selection of overall energy efficiency;

[0041] 3. By analyzing and detecting energy consumption deviations in the collaborative control process and triggering abnormal alerts, this invention can help maintenance personnel quickly locate problematic energy sources, prevent local anomalies from spreading to the entire system, reduce energy waste and equipment wear, and significantly reduce the cost of manual inspection and troubleshooting. Attached Figure Description

[0042] Figure 1 This is a schematic diagram illustrating the steps of a multi-energy collaborative energy-saving control method based on the Internet of Things.

[0043] Figure 2 This is a schematic diagram of a multi-energy collaborative energy-saving control system based on the Internet of Things. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Example: Figures 1 to 2 As shown, this invention provides a multi-energy collaborative energy-saving control method based on the Internet of Things. The control method includes the following steps:

[0046] Step S100: Monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, and generate corresponding collaborative records; analyze the actual energy saving situation after any collaborative record is completed, and identify anomalies in the collaborative records.

[0047] Step S100 includes the following steps:

[0048] Step S101: Obtain the collaboration cycle of any complete collaboration process, and divide the collaboration cycle into several unit time points. Use monitoring equipment to collect the energy consumption values ​​of various energy sources at each unit time point; arbitrarily select one energy source, construct a two-dimensional Cartesian coordinate system with the unit time point as the horizontal axis and the energy consumption value as the vertical axis, and present the changes in the energy consumption value of the selected energy source; obtain the changes in the energy consumption value of various energy sources in the collaboration process, and match the energy consumption values ​​of various energy sources according to the collection time points to generate a collaboration record;

[0049] Step S102: Randomly select a collaborative record, and randomly select an energy source from the selected collaborative records. Set the energy consumption value of the selected energy source at the initial time point to H. start At the same time, the energy consumption value H of the selected energy source after the collaborative process is obtained.end The energy saving rate ε = (H) in the selected collaborative record was calculated. start -H end ) / H start ;

[0050] Step S103: Preset a desired energy saving rate ε for the selected energy source. ex If ε < ε ex If an anomaly is detected, the selected energy source is marked; the number of energy types with anomaly marks in the selected collaborative records is counted as n, and the total number of energy types is set to n. total The proportion of anomalous energy in the selected collaborative records is δ = n / n total Preset an abnormality percentage threshold δ th If δ≥δ th If δ < δ, then the selected collaborative record will be set as an abnormal collaborative record. th If so, it is set as a normal collaborative record;

[0051] Example 1: Three energy sources are selected: electricity, natural gas, and solar energy. A collaborative record is randomly selected, and the initial energy consumption value of electricity is 1000, and the final energy consumption value is 800; the initial energy consumption value of natural gas is 500, and the final energy consumption value is 450; the initial energy consumption value of electricity is 300, and the final energy consumption value is 330. The calculated energy saving rate is 0.2 for electricity, 0.1 for natural gas, and -0.1 for solar energy. The preset expected energy saving rate for the three energy sources is 0.15, so natural gas and solar energy are marked as abnormal.

[0052] Step S200: Select any type of energy, analyze the differences between each normal collaborative record, and obtain the expected allowable deviation of the selected type of energy; based on the differences in energy saving between different collaborative records, obtain the collaborative correlation between the selected energy and other types of energy.

[0053] Step S200 includes the following steps:

[0054] Step S201: Randomly select an energy source and arbitrarily select a normal collaborative record. Obtain the energy saving rate ε of the selected energy source in the selected abnormal collaborative record. If the selected energy source has an abnormal marker in the selected abnormal collaborative record, obtain the expected energy saving rate ε of the selected energy source. ex The deviation amplitude of the selected energy source in the selected abnormal collaborative record was calculated to be f = (ε ex -ε) / ε ex And set it as the characteristic deviation amplitude; obtain the characteristic deviation amplitude of the selected energy source in all normal collaborative records, and select the characteristic deviation amplitude with the largest value as the expected allowable deviation of the selected energy source;

[0055] Example 2: Three normal collaborative records are selected respectively. The deviation amplitude of record 1 is f1 = (0.15-0.14) / 0.15 = 0.067, the deviation amplitude of record 2 is f2 = (0.15-0.13) / 0.15 = 0.133, and the deviation amplitude of record 3 is f3 = (0.15-0.12) / 0.15 = 0.2. The expected allowable deviation is 0.2.

[0056] Step S202: In addition to the selected energy, arbitrarily select another energy and set it as the comparison energy. Arbitrarily select a collaborative record. If, in the selected collaborative record, there is only one energy with an abnormal marker between the selected energy and the comparison energy, then set the selected energy and the comparison energy as an associated energy group to obtain several associated energy groups of the selected collaborative record.

[0057] Step S203: Obtain the associated energy groups for each collaborative record. If several associated energy groups are identical, classify the identical associated energy groups into the same type of energy group; count the number of energy groups contained in each type of energy group, and set the number of energy groups in the a-th type of energy group as m. a The total number of collaborative records obtained is m total The proportion β of energy group a was calculated. a =m a / m total and the proportion of quantity β a Set as the synergistic correlation value for energy group a.

[0058] Step S300: Analyze the collaborative relationships between different types of energy in any abnormal collaborative record, identify the abnormal relationships between different types of energy; analyze the energy saving of any different types of energy in each collaborative record, and obtain the expected energy saving rate of any type.

[0059] Step S300 includes the following steps:

[0060] Step S301: Arbitrarily obtain the synergistic correlation value β of the energy group of type a. a A preset association threshold β th If β a ≥β th If so, the energy group of type a is set as the target energy group; arbitrarily select a target energy group, and set the energy in the selected target energy group that has a deviation amplitude as the deviation energy; arbitrarily extract a collaborative record containing the selected target energy group, and if the extracted collaborative record is an abnormal collaborative record, then obtain the deviation amplitude f of the deviation energy;

[0061] Step S302: Set the expected allowable deviation of the deviation energy as f. max If f≤f maxThen, the extracted collaborative record is set as a feature collaborative record; another energy source in the selected target energy group is set as an energy-saving energy source, and the energy-saving rate of the energy-saving energy source in the extracted collaborative record is obtained as ε; the energy-saving rate of the energy-saving energy source in any collaborative record is obtained, and the energy-saving rate of the energy-saving energy source is divided into two data sets according to whether the collaborative record is an abnormal collaborative record, and the numerical range of the two data sets is obtained respectively. The numerical range of the data set corresponding to the normal collaborative record is set as (ε1) min ,ε1 max If the numerical ranges of two data sets overlap and ε > ε1 max Then the energy-saving energy will be set as an abnormal energy-saving energy, and the selected target energy group in the extracted collaborative record will be set as an abnormal energy group;

[0062] Step S303: Randomly select an abnormal energy group, extract the abnormal energy saving energy in the selected abnormal energy group, obtain the energy saving rate of the abnormal energy saving energy in each collaborative record, obtain the numerical range of the abnormal energy saving energy in the normal collaborative record, select the energy saving rate with the largest value in the numerical range and set it as the maximum expected energy saving rate of the abnormal energy saving energy, set the expected energy saving rate as the minimum expected energy saving rate, and obtain the expected energy saving rate range of the abnormal energy saving energy.

[0063] Step S400: Whenever coordinated control is performed, analyze the real-time changes in energy consumption data of various energy sources to obtain the real-time energy saving status of various energy sources; based on the expected allowable deviation and expected energy saving rate range of various energy sources, make anomaly judgments on the coordinated control status of various energy sources.

[0064] Step S400 includes the following steps:

[0065] Step S401: Real-time acquisition of energy consumption values ​​for various energy sources; extraction of initial energy consumption values ​​at the start of coordinated control; extraction of actual energy consumption values ​​for various energy sources during coordinated control; arbitrary selection of one type of energy source; if the actual energy consumption value of the selected energy source exceeds the initial energy consumption value, the actual deviation amplitude f of the selected energy source is obtained. now If the actual energy consumption of the selected energy source is lower than the initial energy consumption, then the actual energy saving rate ε of the selected energy source is obtained. now ;

[0066] Step S402: Set the expected allowable deviation for energy selection as f ex And the expected energy saving rate range is [ε1 ’ ex ,ε2 ’ ex If the actual energy saving rate ε is selected... now Satisfying ε now <ε1 ’ex or ε now >ε2 ’ ex Alternatively, select the actual deviation range f of the energy. now Satisfy f now >f ex If an anomaly is detected, the energy source will be selected and marked as abnormal, and an anomaly alert will be sent to the current collaborative control process.

[0067] A multi-energy collaborative energy-saving control system, comprising a collaborative recording and analysis module, an expected deviation analysis module, an abnormal energy-saving analysis module, and a real-time predictive analysis module;

[0068] The collaborative record analysis module is used to monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, generate corresponding collaborative records, analyze the actual energy saving after any collaborative record is completed, and identify anomalies in the collaborative records.

[0069] The expected deviation analysis module is used to select any type of energy, analyze the differences between each normal collaborative record, and obtain the expected allowable deviation of the selected energy type; based on the differences in energy saving between different collaborative records, the collaborative correlation between the selected energy and other types of energy is obtained.

[0070] The abnormal energy saving analysis module is used to analyze the collaborative relationship between different types of energy in any abnormal collaborative record, identify the abnormal relationship between different types of energy, analyze the energy saving of any different types of energy in each collaborative record, and obtain the expected energy saving rate of any type.

[0071] The real-time predictive analysis module is used to analyze the real-time changes in energy consumption data of various energy sources whenever coordinated control is performed, and to obtain the real-time energy saving status of various energy sources; based on the expected allowable deviation and expected energy saving rate range of various energy sources, it makes anomaly judgments on the coordinated control status of various energy sources.

[0072] The collaborative record analysis module includes a collaborative data acquisition unit and a collaborative anomaly identification unit.

[0073] The collaborative data acquisition unit is used to monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, and generate corresponding collaborative records; the collaborative anomaly identification unit is used to analyze the actual energy saving situation after any collaborative record is completed, and to identify anomalies in the collaborative record.

[0074] The expected deviation analysis module includes an expected deviation setting unit and a collaborative association identification unit.

[0075] The expected deviation setting unit is used to select any type of energy and analyze the differences between each normal collaborative record to obtain the expected allowable deviation of the selected type of energy; the collaborative association identification unit is used to obtain the collaborative association between the selected energy and other types of energy based on the differences in energy saving between different collaborative records.

[0076] The abnormal energy-saving analysis module includes an abnormal correlation identification unit and an energy-saving magnitude analysis unit.

[0077] The abnormal correlation identification unit is used to analyze the collaborative correlation between different types of energy in any abnormal collaborative record and to identify the abnormal correlation between different types of energy; the energy saving amplitude analysis unit is used to analyze the energy saving of any different types of energy in each collaborative record and to obtain the expected energy saving rate of any type.

[0078] The real-time collaborative analysis module includes a real-time energy-saving analysis unit and a real-time anomaly identification unit.

[0079] The real-time energy-saving analysis unit is used to analyze the real-time changes in energy consumption data of various energy sources whenever coordinated control is performed, and to obtain the real-time energy-saving status of various energy sources; the real-time anomaly identification unit is used to judge the anomalies in the coordinated control of various energy sources based on the expected allowable deviation and expected energy-saving rate range of various energy sources.

[0080] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A multi-energy collaborative energy-saving control method based on the Internet of Things, characterized in that: The control method includes the following steps: Step S100: Monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, and generate corresponding collaborative records; analyze the actual energy saving situation after any collaborative record is completed, and identify anomalies in the collaborative records. Step S200: Select any type of energy, analyze the differences between each normal collaborative record, and obtain the expected allowable deviation of the selected type of energy; based on the differences in energy saving between different collaborative records, obtain the collaborative correlation between the selected energy and other types of energy. Step S300: Analyze the collaborative relationships between different types of energy in any abnormal collaborative record, identify the abnormal relationships between different types of energy; analyze the energy saving of any different types of energy in each collaborative record, and obtain the expected energy saving rate of any type. Step S400: Whenever coordinated control is performed, the real-time changes in energy consumption data of various energy sources are analyzed to obtain the real-time energy saving status of various energy sources; based on the expected allowable deviation and expected energy saving rate range of various energy sources, anomaly judgment is made on the coordinated control status of various energy sources.

2. The multi-energy collaborative energy-saving control method based on the Internet of Things according to claim 1, characterized in that: Step S100 includes the following steps: Step S101: Obtain the collaboration cycle of any complete collaboration process, and divide the collaboration cycle into several unit time points. Use monitoring equipment to collect the energy consumption values ​​of various energy sources at each unit time point; arbitrarily select one energy source, construct a two-dimensional Cartesian coordinate system with the unit time point as the horizontal axis and the energy consumption value as the vertical axis, and present the changes in the energy consumption value of the selected energy source; obtain the changes in the energy consumption value of various energy sources in the collaboration process, and match the energy consumption values ​​of various energy sources according to the collection time points to generate a collaboration record; Step S102: Randomly select a collaborative record, and randomly select an energy source from the selected collaborative records. Set the energy consumption value of the selected energy source at the initial time point to H. start At the same time, the energy consumption value H of the selected energy source after the collaborative process is obtained. end The energy saving rate ε = (H) in the selected collaborative record was calculated. start -H end ) / H start ; Step S103: Preset a desired energy saving rate ε for the selected energy source. ex If ε < ε ex If an anomaly is detected, the selected energy sources are marked as anomalies; the number of energy types with anomaly marks in the selected collaborative records is counted as n, and the total number of energy types is set to n. total The proportion of anomalous energy in the selected collaborative records is δ = n / n total Preset an abnormality percentage threshold δ th If δ≥δ th If δ < δ, then the selected collaborative record will be set as an abnormal collaborative record. th If so, it is set as a normal collaborative record.

3. The multi-energy collaborative energy-saving control method based on the Internet of Things according to claim 2, characterized in that: Step S200 includes the following steps: Step S201: Randomly select an energy source and arbitrarily select a normal collaborative record. Obtain the energy saving rate ε of the selected energy source in the selected abnormal collaborative record. If the selected energy source has an abnormal marker in the selected abnormal collaborative record, obtain the expected energy saving rate ε of the selected energy source. ex The deviation amplitude of energy selection in the selection of abnormal collaborative records was calculated to be f = (ε ex -ε) / ε ex And set it as the characteristic deviation amplitude; obtain the characteristic deviation amplitude of the selected energy source in all normal collaborative records, and select the characteristic deviation amplitude with the largest value as the expected allowable deviation of the selected energy source; Step S202: In addition to the selected energy, arbitrarily select another energy and set it as the comparison energy. Arbitrarily select a collaborative record. If, in the selected collaborative record, there is only one energy with an abnormal marker between the selected energy and the comparison energy, then set the selected energy and the comparison energy as an associated energy group to obtain several associated energy groups of the selected collaborative record. Step S203: Obtain the associated energy groups for each collaborative record. If several associated energy groups are identical, classify the identical associated energy groups into the same type of energy group; count the number of energy groups contained in each type of energy group, and set the number of energy groups in the a-th type of energy group as m. a The total number of collaborative records obtained is m total The proportion β of energy group a was calculated. a =m a / m total and the proportion of quantity β a Set as the synergistic correlation value for energy group a.

4. The multi-energy collaborative energy-saving control method based on the Internet of Things according to claim 3, characterized in that: Step S300 includes the following steps: Step S301: Arbitrarily obtain the synergistic correlation value β of the energy group of type a. a A preset association threshold β th If β a ≥β th If so, the energy group of type a is set as the target energy group; arbitrarily select a target energy group, and set the energy in the selected target energy group that has a deviation amplitude as the deviation energy; arbitrarily extract a collaborative record containing the selected target energy group, and if the extracted collaborative record is an abnormal collaborative record, then obtain the deviation amplitude f of the deviation energy; Step S302: Set the expected allowable deviation of the deviation energy as f. max If f≤f max Then, the extracted collaborative record is set as a feature collaborative record; another energy source in the selected target energy group is set as an energy-saving energy source, and the energy-saving rate of the energy-saving energy source in the extracted collaborative record is obtained as ε; the energy-saving rate of the energy-saving energy source in any collaborative record is obtained, and the energy-saving rate of the energy-saving energy source is divided into two data sets according to whether the collaborative record is an abnormal collaborative record, and the numerical range of the two data sets is obtained respectively. The numerical range of the data set corresponding to the normal collaborative record is set as (ε1) min ,ε1 max If the numerical ranges of two data sets overlap and ε > ε1 max Then the energy-saving energy will be set as an abnormal energy-saving energy, and the selected target energy group in the extracted collaborative record will be set as an abnormal energy group; Step S303: Randomly select an abnormal energy group, extract the abnormal energy saving energy in the selected abnormal energy group, obtain the energy saving rate of the abnormal energy saving energy in each collaborative record, obtain the numerical range of the abnormal energy saving energy in the normal collaborative record, select the energy saving rate with the largest value in the numerical range and set it as the maximum expected energy saving rate of the abnormal energy saving energy, set the expected energy saving rate as the minimum expected energy saving rate, and obtain the expected energy saving rate range of the abnormal energy saving energy.

5. The multi-energy collaborative energy-saving control method based on the Internet of Things according to claim 4, characterized in that: Step S400 includes the following steps: Step S401: Real-time acquisition of energy consumption values ​​for various energy sources; extraction of initial energy consumption values ​​at the start of coordinated control; extraction of actual energy consumption values ​​for various energy sources during coordinated control; arbitrary selection of one type of energy source; if the actual energy consumption value of the selected energy source exceeds the initial energy consumption value, the actual deviation amplitude f of the selected energy source is obtained. now If the actual energy consumption of the selected energy source is lower than the initial energy consumption, then the actual energy saving rate ε of the selected energy source is obtained. now ; Step S402: Set the expected allowable deviation for energy selection as f ex And the expected energy saving rate range is [ε1 ’ ex ,ε2 ’ ex If the actual energy saving rate ε is selected... now Satisfying ε now <ε1 ’ ex or ε now >ε2 ’ ex Alternatively, select the actual deviation range f of the energy. now Satisfy f now >f ex If an anomaly is detected, the energy source will be selected and marked as abnormal, and an anomaly alert will be sent to the current collaborative control process.

6. A multi-energy collaborative energy-saving control system, used to execute the Internet of Things-based multi-energy collaborative energy-saving control method according to any one of claims 1-5, characterized in that: The control system includes a collaborative recording and analysis module, an expected deviation analysis module, an abnormal energy-saving analysis module, and a real-time predictive analysis module; The collaborative record analysis module is used to monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, generate corresponding collaborative records, analyze the actual energy saving situation after any collaborative record is completed, and identify anomalies in the collaborative records. The expected deviation analysis module is used to select any type of energy, analyze the differences between each normal collaborative record, and obtain the expected allowable deviation of the selected type of energy; based on the differences in energy saving between different collaborative records, the collaborative correlation between the selected energy and other types of energy is obtained. The abnormal energy saving analysis module is used to analyze the collaborative relationship between different types of energy in any abnormal collaborative record, identify the abnormal relationship between different types of energy, analyze the energy saving of any different types of energy in each collaborative record, and obtain the expected energy saving rate of any type. The real-time predictive analysis module is used to analyze the real-time changes in energy consumption data of various energy sources whenever coordinated control is performed, and to obtain the real-time energy saving status of various energy sources; based on the expected allowable deviation and expected energy saving rate range of various energy sources, it makes anomaly judgments on the coordinated control status of various energy sources.

7. A multi-energy collaborative energy-saving control system according to claim 6, characterized in that: The collaborative recording and analysis module includes a collaborative data acquisition unit and a collaborative anomaly identification unit; The collaborative data acquisition unit is used to monitor the energy consumption data of several energy sources through pre-deployed monitoring equipment, collect the changes in energy consumption data during each collaborative process, and generate corresponding collaborative records; the collaborative anomaly identification unit is used to analyze the actual energy saving situation after any collaborative record is completed, and to identify anomalies in the collaborative record.

8. A multi-energy collaborative energy-saving control system according to claim 6, characterized in that: The expected deviation analysis module includes an expected deviation setting unit and a collaborative correlation identification unit; The expected deviation setting unit is used to select any type of energy, analyze the differences between each normal collaborative record, and obtain the expected allowable deviation of the selected type of energy. The collaborative association identification unit is used to obtain the collaborative association between the selected energy source and other types of energy sources based on the differences in energy saving between different collaborative records.

9. A multi-energy collaborative energy-saving control system according to claim 6, characterized in that: The abnormal energy-saving analysis module includes an abnormal correlation identification unit and an energy-saving magnitude analysis unit; The abnormal correlation identification unit is used to analyze the collaborative correlation between different types of energy in any abnormal collaborative record and to identify the abnormal correlation between different types of energy; the energy saving amplitude analysis unit is used to analyze the energy saving of any different types of energy in each collaborative record and to obtain the expected energy saving rate of any type.

10. A multi-energy collaborative energy-saving control system according to claim 6, characterized in that: The real-time collaborative analysis module includes a real-time energy-saving analysis unit and a real-time anomaly identification unit; The real-time energy-saving analysis unit is used to analyze the real-time changes in energy consumption data of various energy sources whenever coordinated control is performed, and to obtain the real-time energy-saving status of various energy sources; the real-time anomaly identification unit is used to make anomaly judgments on the coordinated control status of various energy sources based on the expected allowable deviation and expected energy-saving rate range of various energy sources.

Images