A control method for ultra-low load operation of a distributed combined unit

Abstract

The present invention provides a method for controlling the ultra-low load operation of a distributed combined unit, belonging to the field of operation control, including: obtaining the historical operation information and regional emission standard information of the distributed combined unit within a specified operation cycle, and determining a first standard and first information; extracting features from the first information according to the first standard to determine first features, and constructing an operation control model; obtaining the real-time operation state information and real-time emission information of the distributed combined unit; analyzing the real-time operation state information and real-time emission information based on the operation control model to generate a control signal, so as to realize the ultra-low load operation control. It can realize the real-time control adjustment and refined control of the distributed combined unit on the premise of protecting the environment and equipment safety, enhance the flexibility and response speed of the unit operation, improve the operation efficiency, operation stability and reliability, improve the energy utilization rate, and improve the thermoelectric co-generation economy of the whole plant.

Description

Technical Field

[0001] The present invention relates to the technical field of operation control, and particularly to a method for controlling the ultra-low load operation of a distributed combined unit. Background Art

[0002] The control of ultra-low load operation of a distributed combined unit can be applied to multiple technical fields, such as power system dispatching and operation management, industrial production process control, building energy management, and smart grid and microgrid. In the current operation control technology, there are deficiencies in data integration and analysis, which cannot achieve refined control of the system, timely communication and coordinated management cannot be achieved between distributed units, and the system stability and reliability are poor.

[0003] Therefore, the present invention provides a method for controlling the ultra-low load operation of a distributed combined unit. Summary of the Invention

[0004] The present invention provides a method for controlling the ultra-low load operation of a distributed combined unit to solve the defects in operation control in the prior art.

[0005] On the one hand, the present invention provides a method for controlling the ultra-low load operation of a distributed combined unit, including:

[0006] S101: Obtain the historical operation information and regional emission standard information of the distributed combined unit within a specified operation cycle, wherein a first standard is determined based on the regional emission standard information and a first piece of information is determined based on the historical operation information;

[0007] S102: Extract features from the first piece of information according to the first standard to determine a first feature, and construct an operation control model based on the first piece of information and the first feature;

[0008] S103: Obtain the real-time operation status information and real-time emission information of the distributed combined unit;

[0009] S104: Analyze the real-time operation status information and real-time emission information based on the operation control model to generate a control signal, and the distributed combined unit realizes ultra-low load operation control based on the control signal.

[0010] According to the method for controlling the ultra-low load operation of a distributed combined unit provided by the present invention, determining the first standard based on the regional emission standard information includes:

[0011] Determine the emission limit value of each sub-emission based on the regional emission standard information;

[0012] Take a% of the value lower than the corresponding emission limit value of each sub-emission as the first limit value;

[0013] Determine the first standard based on the first limit values corresponding to all sub-emission substances.

[0014] According to a distributed combined unit ultra-low load operation control method provided by the present invention, determining first information based on historical operation information includes:

[0015] Divide the historical operation information into a training set and a test set, extract the training set that meets the first standard, and determine the first information of the training set, where the first information includes load information, power information, voltage information, and frequency information of the distributed combined unit that meets the first standard within a specified operation cycle.

[0016] According to a distributed combined unit ultra-low load operation control method provided by the present invention, performing feature extraction on the first information to determine first features includes:

[0017] Extract the load values of the distributed combined unit at each hour of operation time within a specified operation cycle from the first information;

[0018] Draw a load curve based on the load values at each hour of operation time within the same specified operation cycle, and determine the fitting value corresponding to the load curve;

[0019] Based on the load curve and fitting value of each specified operation cycle, determine the corresponding load characteristic value;

[0020]

[0021]

[0022]

[0023] Wherein, N2 represents the number of hours within a specified operation cycle, CL i1 represents the load characteristic value within the specified operation cycle i1, F1 i1 represents the fitting value within the specified operation cycle i1, L j1 represents the load value at the j1-th hour within the specified operation cycle i1, represents the load average value of the specified operation cycle i1, σL j1 represents the standard deviation of the load value of the specified operation cycle i1, represents the load fluctuation value of the specified operation cycle i1, α1 i1 represents the load fluctuation coefficient of the specified operation cycle i1, ε represents the kurtosis adjustment value, represents the load stability value of the specified operation cycle i1, α2 i1 represents the load stability coefficient of the specified operation cycle i1;

[0024] Determine the load characteristic set based on the load characteristic values corresponding to all specified operating cycles.

[0025] According to a distributed combined unit ultra-low load operation control method provided by the present invention, feature extraction is performed on the first information to determine the first feature, and it further includes:

[0026] Extract the power value, voltage value, and frequency value corresponding to each sub-unit in the distributed combined unit in the specified operating cycle from the first information;

[0027] Based on the power value, voltage value, and frequency value at each hour of operation time within all specified operating cycles, draw a power curve, a voltage curve, and a frequency curve, where each curve contains N1 specified operating cycles;

[0028] Perform interval division on the values of each curve, and respectively extract the first power value, the first voltage value, and the first frequency value at the hour of operation time corresponding to the divided interval from the power curve, the voltage curve, and the frequency curve, and then determine the power conditional entropy, the voltage conditional entropy, and the frequency conditional entropy under the corresponding value divided interval;

[0029]

[0030]

[0031]

[0032]

[0033] Among them, H(Po|V,F) L1 represents the conditional entropy of the variable power Po determined under the conditions of the variable voltage V and the variable frequency F in the corresponding value divided interval L1, H(V|Po,F) L1 represents the conditional entropy of the variable voltage V determined under the conditions of the variable power Po and the variable frequency F in the corresponding value interval L1, H(F|V,Po) L1 represents the conditional entropy of the variable frequency F determined under the conditions of the variable voltage V and the variable power Po in the corresponding value interval L1, H(Po,V,F) L1 represents the joint entropy of the variable power Po, the variable voltage V, and the variable frequency F in the corresponding value interval L1, Nu Po 、Nu V 、Nu F respectively represent the occurrence numbers of the power value, the voltage value, and the frequency value within all specified operating cycles, and Nu Po =Nu V =Nu F , respectively represent the value coverage interval numbers of the first power value, the first voltage value, and the first frequency value under the corresponding value interval L1, respectively represent the influence coefficients of the first power value, the first voltage value, and the first frequency value within the corresponding value interval L1, and N1 represents the number of hours of operation involved in the corresponding value division interval L1; P(Po1 k1 ,V1 k1 ,F1 k1 ) represents the joint probability based on the power Po1, voltage V1, and frequency F1 at the k1-th hour of operation time in the corresponding value division interval L1 k1 , voltage V1 k1 , and frequency F1 k1 ; P(V1 k1 ,F1 k1 ) represents the joint probability based on the voltage V1 and frequency F1 at the k1-th hour of operation time in the corresponding value division interval L1 k1 , and frequency F1 k1 ; P(Po1 k1 ,F1 k1 ) represents the joint probability based on the power Po1 and frequency F1 at the k1-th hour of operation time in the corresponding value division interval L1 k1 , and frequency F1 k1 ; P(V1 k1 ,Po1 k1 ) represents the joint probability based on the power Po1 and voltage V1 at the k1-th hour of operation time in the corresponding value division interval L1 k1 , voltage V1 k1 ;

[0034] Determine the power feature set, voltage feature set, and frequency feature set based on the corresponding power conditional entropy, voltage conditional entropy, and frequency conditional entropy within each value interval;

[0035] Among them, the first features include: load feature set, power feature set, voltage feature set, and frequency feature set.

[0036] According to a distributed combined unit ultra-low load operation control method provided by the present invention, an operation control model is constructed based on the first information and the first features, including:

[0037] Taking the training set information as the input and the control information corresponding to the training set as the output, and constructing an operation control model in combination with the first features;

[0038] Inputting the test set information into the operation control model to generate corresponding control signals, comparing the control information and control signals of the test set, evaluating the operation control model according to the comparison results, and debugging and optimizing the operation control model.

[0039] A method for controlling the ultra-low load operation of a distributed combined unit provided by the present invention, wherein the real-time operation status information includes the load information of the distributed combined unit, the power information of each sub-unit, the voltage information, and the frequency information;

[0040] The real-time emission information includes the emission values of each sub-emission substance.

[0041] A method for controlling the ultra-low load operation of a distributed combined unit provided by the present invention, wherein the control signal includes a dynamic adjustment instruction for each sub-unit.

[0042] Compared with the prior art, the beneficial effects of the present application are as follows:

[0043] Determine the first information and the first standard through the historical operation information of the distributed combined unit and the regional emission standard information, extract the first features of the first information and construct an operation control model, analyze the obtained real-time operation status information and real-time emission information based on the operation control model, and generate a control signal to realize the ultra-low load operation control, which can realize the real-time control adjustment and refined control of the distributed combined unit on the premise of protecting the environment and equipment safety, enhance the flexibility and response speed of the unit operation, improve the operation efficiency, operation stability and reliability, improve the energy utilization rate, and improve the thermoelectric co-generation economy of the whole plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 It is a schematic flowchart of a method for controlling the ultra-low load operation of a distributed combined unit provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0047] Embodiment 1:

[0048] An embodiment of the present invention provides a method for controlling the ultra-low load operation of a distributed combined unit, asFigure 1 As shown, it includes:

[0049] S101: Obtain the historical operation information and regional emission standard information of the distributed combined unit within a specified operation period. Among them, determine the first standard based on the regional emission standard information and determine the first information based on the historical operation information;

[0050] S102: Extract features from the first information according to the first standard to determine the first feature, and construct an operation control model based on the first information and the first feature;

[0051] S103: Obtain the real-time operation status information and real-time emission information of the distributed combined unit;

[0052] S104: Analyze the real-time operation status information and real-time emission information based on the operation control model to generate a control signal, and the distributed combined unit realizes ultra-low load operation control based on the control signal.

[0053] In this embodiment, the historical operation information includes the load information of the distributed combined unit within the specified operation period, the power information corresponding to each sub-unit, voltage information, and frequency information.

[0054] In this embodiment, the first information represents the training set information that meets the first standard.

[0055] In this embodiment, the first feature includes a load feature set, a power feature set, a voltage feature set, and a frequency feature set.

[0056] In this embodiment, the real-time operation status information includes the load information of the distributed combined unit, the power information of each sub-unit, voltage information, and frequency information.

[0057] In this embodiment, the real-time emission information includes the emission values of each sub-emission substance.

[0058] In this embodiment, the control signal includes dynamic adjustment instructions for each sub-unit. For example, the distributed combined unit includes 3 sub-units, namely sub-unit 1, sub-unit 2, and sub-unit 3. The control signal has 3 dynamic adjustment instructions for sub-unit 1, 1 dynamic adjustment instruction for sub-unit 2, and 4 dynamic adjustment instructions for sub-unit 3. Then the control signal includes 8 dynamic adjustment instructions, and the 1 control adjustment instruction for sub-unit 2 can be empty.

[0059] Beneficial effects of the above technical solution: Determine the first information and the first standard based on the historical operation information of the distributed combined unit and the regional emission standard information, extract the first features of the first information and construct an operation control model, analyze the obtained real-time operation status information and real-time emission information based on the operation control model, and generate a control signal to achieve ultra-low load operation control. It can realize real-time control adjustment and refined control of the distributed combined unit on the premise of protecting the environment and equipment safety, enhance the flexibility and response speed of the unit operation, improve the operation efficiency, operation stability and reliability, improve the energy utilization rate, and improve the thermoelectric co-generation economy of the whole plant.

[0060] Embodiment 2:

[0061] The embodiment of the present invention provides a method for controlling ultra-low load operation of a distributed combined unit, which determines the first standard based on the regional emission standard information, including:

[0062] Determine the emission limit value of each sub-emission based on the regional emission standard information;

[0063] Take a% of the value lower than the corresponding emission limit value of each sub-emission substance as the first limit value;

[0064] Determine the first standard based on the first limit values corresponding to all sub-emission substances.

[0065] In this embodiment, the sub-emission substance may be NO x , volatile organic compounds, particulate matter, and SO x etc.

[0066] In this embodiment, the first limit value of the same sub-emission substance is higher than the emission limit value. For example, if the emission limit value of a certain sub-emission substance is y, the first limit value is y×a%.

[0067] In this embodiment, the first standard includes all sub-emission substances and the first limit value corresponding to each sub-emission substance.

[0068] Beneficial effects of the above technical solution: Determine the first limit value of each sub-emission based on the regional emission standard information, and determine the first standard according to the first limit values of all sub-emissions, which can effectively control and reduce the emission level of the distributed combined unit, reduce the emission of air pollutants, protect the environment and improve air quality.

[0069] Embodiment 3:

[0070] The embodiment of the present invention provides a method for controlling ultra-low load operation of a distributed combined unit, which determines the first information based on the historical operation information, including:

[0071] Divide the historical operation information into a training set and a test set, extract the training set that meets the first criterion, and determine the first information of the training set, where the first information includes the load information, the power information corresponding to each sub-unit, the voltage information, and the frequency information of the distributed combined unit that meets the first criterion within the specified operation period.

[0072] In this embodiment, the training set is used to construct an operation control model, and the test set is used to evaluate, debug, and optimize the operation control model.

[0073] In this embodiment, the first information represents the historical operation information that meets the first criterion in the training set.

[0074] The beneficial effects of the above technical solution: Dividing the historical operation information into a training set and a test set, and determining the first information of the training set can screen the historical operation information, provide a data basis for extracting the first feature, improve the accuracy and generalization of the operation control model, enhance the flexibility of the unit operation, and reduce the unit's air exhaust or frequent start-stop frequency.

[0075] Embodiment 4:

[0076] The embodiment of the present invention provides a method for controlling the ultra-low load operation of a distributed combined unit, which extracts the first feature from the first information, including:

[0077] Extract the load value of the distributed combined unit in the first information at each hour of operation within the specified operation period;

[0078] Based on the load values at each hour of operation within the same specified operation period, draw a load curve and determine the fitting value corresponding to the load curve;

[0079] Based on the load curve and the fitting value of each specified operation period, determine the corresponding load characteristic value;

[0080]

[0081]

[0082]

[0083] Among them, N2 represents the number of hours within the specified operation period, CL i1 represents the load characteristic value within the specified operation period i1, F1 i1 represents the fitting value within the specified operation period i1, L j1 represents the load value at the j1th hour within the specified operation period i1, represents the average load of the specified operation period i1, σL j1 represents the standard deviation of the load value of the specified operation period i1, It represents the load fluctuation value of the specified operation cycle i1, α1 i1 It represents the load fluctuation coefficient of the specified operation cycle i1, ε represents the kurtosis adjustment value, It represents the load stability value of the specified operation cycle i1, α2 i1 It represents the load stability coefficient of the specified operation cycle i1;

[0084] Determine the load characteristic set based on the load characteristic values corresponding to all specified operation cycles.

[0085] In this embodiment, the horizontal axis of the load curve is the operation time, and the vertical axis is the load value.

[0086] In this embodiment, the fitted value represents the value obtained after fitting the curve plotted by the load values at all operation times within the specified operation cycle, that is, this fitted value can represent the curve.

[0087] In this embodiment, the kurtosis adjustment value compares the load stability value with the normal distribution. If the load stability value is greater than the kurtosis adjustment value, it means that the distribution of all load values within the specified operation cycle is steeper than the normal distribution. If the load stability value is less than the kurtosis adjustment value, it means that the distribution of all load values within the specified operation cycle is flatter than the normal distribution.

[0088] In this embodiment, the closer the load stability value is to 0, the more stable the load data is. The greater the load stability value is than 0, the more unstable the load data is.

[0089] In this embodiment, each specified operation cycle corresponds to a load characteristic value. The number of load characteristic values included in the load characteristic set is N1. For example, the first information includes the load values of the distributed combined unit at each hour of operation time within N1 specified operation cycles. Each specified operation cycle corresponds to a load curve, and each load curve corresponds to a fitted value. According to the load curve and the fitted value of each specified operation cycle, the corresponding load characteristic value is determined. The load characteristic set is composed of the compliance characteristic values respectively corresponding to N1 specified cycles.

[0090] The beneficial effects of the above technical solution: By determining the load characteristic values of each specified operation cycle through the first information and determining the load characteristic set based on the load characteristic values corresponding to all specified operation cycles, it is possible to comprehensively analyze and grasp the load conditions of the distributed combined unit under all specified operation cycles, provide a characteristic basis for constructing an operation control model to achieve ultra-low load operation control, so as to improve energy utilization efficiency and the thermoelectricity co-generation economy of the whole plant.

[0091] Embodiment 5:

[0092] The embodiment of the present invention provides a method for ultra-low load operation control of a distributed combined unit, which extracts features from the first information to determine the first feature, and further includes:

[0093] Extract the corresponding power values, voltage values, and frequency values of each sub-unit in the distributed combined unit in the first information during the specified operating cycle;

[0094] Based on the power values, voltage values, and frequency values at each hourly operating time during all specified operating cycles, draw a power curve, a voltage curve, and a frequency curve, where each curve contains N1 specified operating cycles;

[0095] Perform interval partitioning on the values of each curve, and respectively extract the first power value, the first voltage value, and the first frequency value at the hourly operating time corresponding to the divided intervals from the power curve, the voltage curve, and the frequency curve, and then determine the power conditional entropy, the voltage conditional entropy, and the frequency conditional entropy under the corresponding value divided intervals;

[0096]

[0097]

[0098]

[0099]

[0100] Among them, H(Po|V,F) L1 represents the conditional entropy of the variable power Po determined under the conditions of the variable voltage V and the variable frequency F in the corresponding value divided interval L1, H(V|Po,F) L1 represents the conditional entropy of the variable voltage V determined under the conditions of the variable power Po and the variable frequency F in the corresponding value interval L1, H(F|V,Po) L1 represents the conditional entropy of the variable frequency F determined under the conditions of the variable voltage V and the variable power Po in the corresponding value interval L1, H(Po,V,F) L1 represents the joint entropy of the variable power Po, the variable voltage V, and the variable frequency F in the corresponding value interval L1, Nu Po 、Nu V 、Nu F respectively represent the occurrence numbers of the power values, the voltage values, and the frequency values during all specified operating cycles, and Nu Po =Nu V =Nu F , respectively represent the value coverage interval numbers of the first power value, the first voltage value, and the first frequency value under the corresponding value interval L1, respectively represent the influence coefficients of the first power value, the first voltage value, and the first frequency value within the corresponding value interval L1, N1 represents the number of hourly operating times involved in the corresponding value divided interval L1; P(Po1 k1 ,V1k1 , F1 k1 ) represents the joint probability based on power Po1 at the k1-th hour of operation time in the corresponding value division interval L1 k1 , voltage V1 k1 , frequency F1 k1 , and P(V1 k1 , F1 k1 ) represents the joint probability based on voltage V1 at the k1-th hour of operation time in the corresponding value division interval L1 k1 , frequency F1 k1 , and P(Po1 k1 , F1 k1 ) represents the joint probability based on power Po1 at the k1-th hour of operation time in the corresponding value division interval L1 k1 , frequency F1 k1 , and P(V1 k1 , Po1 k1 ) represents the joint probability based on power Po1 at the k1-th hour of operation time in the corresponding value division interval L1 k1 , voltage V1 k1 ;

[0101] Determine the power feature set, voltage feature set, and frequency feature set based on the corresponding power conditional entropy, voltage conditional entropy, and frequency conditional entropy within each value interval;

[0102] Among them, the first feature includes: load feature set, power feature set, voltage feature set, and frequency feature set.

[0103] In this embodiment, the horizontal axis of the power curve is the operation time, and the vertical axis is the power value; the horizontal axis of the voltage curve is the operation time, and the vertical axis is the voltage value; the horizontal axis of the frequency curve is the operation time, and the vertical axis is the frequency value.

[0104] In this embodiment, each specified operation cycle corresponds to a sub-power curve, a sub-voltage curve, and a sub-frequency curve.

[0105] In this embodiment, the power curve includes the sub-power curves corresponding to all operation cycles. For example, the first information includes the power values at each hour of operation time of the distributed combined unit within N1 specified operation cycles. Each specified operation cycle corresponds to a sub-power curve, and the power curve includes N1 sub-power curves. The principles of the voltage curve and the frequency curve are similar and will not be elaborated here.

[0106] In this embodiment, the power values are divided into M corresponding value intervals based on the power curve. For example, the interval of the power values corresponding to the power curve on the vertical axis is [a, b], and the interval [a, b] is divided into [a, b1), [b1, b2), …, [b M-2 , b M-1), [b M-1 , b], where [a, b1) represents the value range L1, including the power value a and excluding the power value b1, and so on. [b M-1 , b] represents the value range LM, including both the power value b M-1 and the power value b. The principle of dividing the voltage value and frequency value into M corresponding value ranges based on the voltage curve and frequency curve is similar and will not be elaborated here.

[0107] In this embodiment, the power conditional entropy represents the power instability of the distributed combined unit under the conditions of all variables voltage and frequency in the corresponding value range; the voltage conditional entropy represents the voltage instability of the distributed combined unit under the conditions of all variables power and frequency in the corresponding value range; the frequency conditional entropy represents the frequency instability of the distributed combined unit under the conditions of all variables voltage and power in the corresponding value range.

[0108] In this embodiment, the greater the power conditional entropy, voltage conditional entropy, and frequency conditional entropy, the more unstable the power change, voltage change, and frequency change of the distributed combined unit; the smaller the power conditional entropy, voltage conditional entropy, and frequency conditional entropy, the more stable the power change, voltage change, and frequency change of the distributed combined unit.

[0109] In this embodiment, the number of power conditional entropies included in the power feature set is the same as the number of value ranges divided by all power values. For example, all power values of the distributed combined unit in all specified operating cycles included in the first information are divided into M value ranges, and each value range corresponds to a conditional power entropy. Then the power feature set contains M power conditional entropies, and the principles of the voltage feature set and frequency feature set are similar and will not be elaborated here.

[0110] Beneficial effects of the above technical solution: By determining the power conditional entropy, voltage conditional entropy, and frequency conditional entropy of each value range through the first information, and determining the power feature set, voltage feature set, and frequency feature set, it is possible to comprehensively analyze and grasp the power conditions, voltage conditions, and frequency conditions of the distributed combined unit under all specified operating cycles, providing a characteristic basis for constructing an operation control model to achieve ultra-low load operation control, so as to improve energy utilization efficiency and the thermoelectric co-generation economy of the whole plant.

[0111] Embodiment 6:

[0112] The embodiment of the present invention provides a method for ultra-low load operation control of a distributed combined unit, which constructs an operation control model based on the first information and the first feature, including:

[0113] Taking the training set information as the input and the control information corresponding to the training set as the output, and constructing an operation control model in combination with the first feature;

[0114] Input the test set information into the operation control model to generate corresponding control signals, compare the control information of the test set with the control signals, evaluate the operation control model according to the comparison results, and debug and optimize the operation control model.

[0115] In this embodiment, the control information of the test set is compared with the control signals. The control information includes sub-control information corresponding to each sub-unit, and the control signals include dynamic adjustment instructions corresponding to each sub-unit. The sub-control information and the dynamic adjustment instructions of the same sub-unit are compared, and the comparison results of all sub-units are evaluated.

[0116] In this embodiment, if the control signals generated by the model are consistent with the control information in the test set or have a very high accuracy, it indicates that the operation control model has good prediction ability and adaptability.

[0117] Advantages of the above technical solution: By constructing an operation control model through training set information and the first feature, and performing model evaluation and debugging optimization, real-time control adjustment and refined control of the distributed combined units can be achieved on the premise of protecting the environment and equipment safety.

[0118] Embodiment 7:

[0119] An embodiment of the present invention provides a method for controlling the ultra-low load operation of a distributed combined unit. The real-time operation state information includes the load information of the distributed combined unit, the power information of each sub-unit, voltage information, and frequency information;

[0120] The real-time emission information includes the emission values of each sub-emission substance.

[0121] In this embodiment, each sub-emission substance included in the first standard corresponds to an emission value.

[0122] Advantages of the above technical solution: By determining the real-time operation state information and the real-time emission information, data basis can be provided for generating control signals, and the ultra-low load operation control of the distributed combined unit can be realized.

[0123] Embodiment 8:

[0124] An embodiment of the present invention provides a method for controlling the ultra-low load operation of a distributed combined unit. The control signals include dynamic adjustment instructions for each sub-unit.

[0125] In this embodiment, the dynamic adjustment instructions can be transmitted to the corresponding sub-units through a distributed communication network, and the sub-units make quick responses and adjustments according to the corresponding dynamic adjustment instructions.

[0126] In this embodiment, through the real-time operation state information and the real-time emission information, refined control of the distributed combined unit is achieved according to the control signals.

[0127] In this embodiment, the number of dynamic adjustment instructions included in the control signal may be greater than the number of sub-units. There may be multiple dynamic adjustment instructions for the same sub-unit. If a certain sub-unit does not require dynamic adjustment, the corresponding dynamic adjustment instruction for this sub-unit is empty.

[0128] Advantages of the above technical solution: Determining the dynamic adjustment instructions for each sub-unit according to the control signal can enable each sub-unit to quickly respond to load changes, make adjustments in a timely manner, and improve operation efficiency, operation stability, and reliability.

[0129] The method embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

[0130] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for ultra-low load operation of a distributed combined unit, characterized in that, Including: S101: Obtain the historical operation information and regional emission standard information of the distributed combined unit during a specified operation period. Among them, determine the first standard based on the regional emission standard information and determine the first information based on the historical operation information; S102: Extract features from the first information according to the first standard to determine the first feature, and construct an operation control model based on the first information and the first feature; S103: Obtain the real-time operation status information and real-time emission information of the distributed combined unit; S104: Analyze the real-time operation status information and real-time emission information based on the operation control model to generate a control signal, and the distributed combined unit realizes ultra-low load operation control based on the control signal; Among them, determining the first information based on the historical operation information includes: Divide the historical operation information into a training set and a test set, extract the training set that meets the first standard, and determine the first information of the training set. Among them, the first information includes the load information, the power information, the voltage information, and the frequency information of the distributed combined unit that meet the first standard during the specified operation period; Among them, extracting features from the first information to determine the first feature includes: Extract the load value of the distributed combined unit in the first information at each hour of operation time during the specified operation period; Draw a load curve based on the load values at each hour of operation time within the same specified operation period, and determine the fitting value corresponding to the load curve; Determine the corresponding load characteristic value based on the load curve and the fitting value of each specified operation period; Among them, N2 represents the number of hours in a specified operating cycle, represents the load characteristic value in the specified operating cycle i1, represents the fitted value in the specified operating cycle i1, represents the load value at the j1-th hour in the specified operating cycle i1, represents the average load of the specified operating cycle i1, represents the standard deviation of the load value of the specified operating cycle i1, represents the load fluctuation value of the specified operating cycle i1, represents the load fluctuation coefficient of the specified operating cycle i1, represents the kurtosis adjustment value, represents the load stability value of the specified operating cycle i1, represents the load stability coefficient of the specified operating cycle i1; Determine the load characteristic set based on the load characteristic values corresponding to all specified operation periods.

2. The ultra-low load operation control method of a distributed combined unit according to claim 1, characterized in that, Determining the first standard based on the regional emission standard information includes: Determine the emission limit value of each sub-emission based on the regional emission standard information; Take the value lower than the emission limit value corresponding to each sub-emission substance as the first limit value; Determine the first standard based on the first limit values corresponding to all sub-emission substances.

3. The ultra-low load operation control method of a distributed combined unit according to claim 1, characterized in that, Extracting features from the first information to determine the first feature also includes: Extract the power value, voltage value, and frequency value corresponding to each sub-unit in the distributed combined unit during the specified operation period from the first information; Draw a power curve, a voltage curve, and a frequency curve based on the power values, voltage values, and frequency values at each hour of operation time within all specified operation periods. Among them, each curve contains N1 specified operation periods; Divide the value range of each curve, and extract the first power value, the first voltage value, and the first frequency value at the hour of operation time corresponding to the divided value range from the power curve, the voltage curve, and the frequency curve respectively, and then determine the power conditional entropy, the voltage conditional entropy, and the frequency conditional entropy corresponding to the divided value range; Among them, represents the conditional entropy of the variable voltage corresponding to the variable voltage in the value division interval L1 , variable frequency under the condition of the determined variable power , represents the conditional entropy of the variable power corresponding to the variable power in the value interval L1 , variable frequency under the condition of the determined variable voltage , represents the conditional entropy of the variable frequency corresponding to the variable voltage in the value interval L1 , variable power under the condition of the determined variable frequency , represents the joint entropy of the variable power , variable voltage V, and variable frequency F in the value interval L1 , respectively represent the occurrence numbers of the power value, voltage value, and frequency value in all specified operating cycles, and , , , respectively represent the value coverage interval numbers of the first power value, first voltage value, and first frequency value under the corresponding value interval L1 , , respectively represent the influence coefficients of the first power value, first voltage value, and first frequency value in the corresponding value interval L1. N1 represents the number of hours of operation time involved in the corresponding value division interval L1; represents the joint probability based on power , voltage , frequency at the k1-th hour of operation time in the corresponding value division interval L1 represents the joint probability based on voltage , frequency at the k1-th hour of operation time in the corresponding value division interval L1 represents the joint probability based on power , frequency at the k1-th hour of operation time in the corresponding value division interval L1 represents the joint probability based on power , voltage at the k1-th hour of operation time in the corresponding value division interval L1; Determine the power feature set, the voltage feature set, and the frequency feature set based on the power conditional entropy, the voltage conditional entropy, and the frequency conditional entropy corresponding to each value range; Among them, the first feature includes: the load feature set, the power feature set, the voltage feature set, and the frequency feature set.

4. A method for controlling the ultra-low load operation of a distributed combined unit according to claim 1, characterized in that Constructing an operation control model based on the first information and the first feature includes: Take the training set information as the input and the control information corresponding to the training set as the output, and construct an operation control model in combination with the first feature; Input the test set information into the operation control model to generate corresponding control signals, compare the control information of the test set with the control signals, evaluate the operation control model according to the comparison results, and debug and optimize the operation control model.

5. A distributed combined unit ultra-low load operation control method according to claim 1, characterized in that, The real-time operation state information includes the load information of the distributed combined units, the power information of each sub-unit, the voltage information, and the frequency information; The real-time emission information includes the emission values of each sub-emission substance.

6. A method for controlling the ultra-low load operation of a distributed combined unit according to claim 1, characterized in that, The control signals include dynamic adjustment instructions for each sub-unit.

Images