A data-driven thermal power unit regulation capability evaluation method and system

Abstract

The present invention discloses a method and system for evaluating the regulating capability of thermal power units based on data drive. The method of the present invention includes determining data of five evaluation indicators, namely, output regulation range R, AGC mode operation interval S, regulation rate V, regulation accuracy E, and response time T of multiple thermal power units; quantifying the data of each evaluation indicator respectively; determining the weight of each evaluation indicator respectively; and summing the quantified results of each evaluation indicator based on the determined weights to obtain the evaluation result of the regulating capability of any thermal power unit. The present invention utilizes the operating data of multiple thermal power units, does not need to conduct unit flexibility evaluation tests, and greatly reduces the workload of conducting thermal power unit flexibility evaluation; can realize dynamic evaluation of the flexibility of thermal power units, avoids the drawbacks of existing evaluation methods, and can provide a reference for flexible optimization and scheduling of power systems.

Description

Technical Field

[0001] The invention relates to a method for evaluating the performance of a thermal power unit, and in particular to a method and system for evaluating the regulating capability of a thermal power unit based on data drive. Background Art

[0002] In recent years, the proportion of power generation from new energy sources such as wind power and photovoltaics has increased rapidly. However, due to their intermittent and uncertain characteristics, they have also brought great challenges to the safety and stability of the power system. At present, most wind power, photovoltaic and other new energy sites still do not have the ability to adjust their output, and the hydropower regulation margin is insufficient, making thermal power the main supporting power source to ensure the safety and stability of the power system. Its flexible supply capacity has become an important basis for judging the flexibility of the power system and its ability to absorb new energy.

[0003] The regulation capacity of thermal power units is a comprehensive representation of the output strain performance and automation level of thermal power units. At present, there is no unified evaluation standard for the regulation capacity of thermal power units. Some regions evaluate based on the maximum regulation range of the units reported by thermal power companies, and some regions evaluate the flexibility of thermal power units by conducting peak regulation capacity tests. However, in practice, due to the adjustment of the operation mode of thermal power units or changes in equipment conditions, their flexible supply capacity will also change accordingly, but the above two methods cannot achieve dynamic perception of the flexibility of thermal power units. The support capacity of the power grid side for thermal power units is actually in an "offline" and "passive" acceptance state. Accurately and actively evaluating the regulation capacity of thermal power units and preferentially dispatching thermal power units with better flexibility will help the safe and stable operation of the power grid. Summary of the invention

[0004] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a data-driven method and system for evaluating the regulation capability of thermal power units is provided. The present invention utilizes the operating data of multiple thermal power units and does not require unit flexibility evaluation tests, thereby greatly reducing the workload of conducting flexibility evaluation of thermal power units. It can realize dynamic evaluation of the flexibility of thermal power units, avoid the drawbacks of existing evaluation methods, and provide a reference for flexible optimization and scheduling of power systems.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A data-driven thermal power unit regulation capability evaluation method includes:

[0007] S1, determine the data of five evaluation indicators including output adjustment range R, AGC mode operation range S, adjustment rate V, adjustment accuracy E, and response time T of multiple thermal power units;

[0008] S2, quantify the data of each evaluation index respectively;

[0009] S3, determine the weight of each evaluation index respectively;

[0010] S4, performing weighted summation of the quantified results of various evaluation indicators based on the determined weights to obtain an evaluation result of the regulation capability of any thermal power unit.

[0011] Optionally, the calculation function expression of the output adjustment range R in step S1 is:

[0012] R=P max -P min ,

[0013] In the above formula, P max is the maximum output of the thermal power unit during the evaluation period, P min is the minimum output of the thermal power unit in the evaluation period; the calculation function expression of the AGC operation interval S in step S1 is:

[0014]

[0015] In the above formula, is the maximum output of the thermal power unit in AGC mode during the evaluation period, is the minimum output of the thermal power unit in the AGC mode during the evaluation period; the calculation function expression of the response time T in step S1 is:

[0016] T = t1-t0,

[0017] In the above formula, t0 is the moment when the unit load command begins to change, and t1 is the moment when the unit actual load begins to change, and the change amplitude exceeds the regulation dead zone range and no longer reverses in trend.

[0018] Optionally, the calculation function expression of the adjustment rate V in step S1 is:

[0019] V=ΔP / Δt=(P up -P down ) / (t up -t down ),

[0020] Among them, V is the regulation rate, ΔP is the actual load change of the unit, Δt is the time change, and ΔP satisfies ΔP ≥ 10% P e , P e is the rated load of the unit; P up and P down are the loads when the actual load reaches the target load command change range of the specified upper limit ratio and the specified lower limit ratio when the unit changes load, respectively, 10 ,t 90They are respectively the moments when the actual load reaches the target load command with a change range of the specified upper limit ratio and the specified lower limit ratio when the unit changes load.

[0021] Optionally, the calculation function expression of the adjustment accuracy E in step S1 is:

[0022]

[0023] In the above formula, P z is the target load instruction, P i is the output point of the ith unit after the actual load of the unit enters the regulation dead zone for the first time, P e is the rated load of the unit, and N is the number of unit output points after the actual load of the unit enters the regulation dead zone for the first time.

[0024] Optionally, when the data of each evaluation index is quantified in S2, the function expression for quantifying the output adjustment range R is:

[0025] IN R =R / P e ×100%,

[0026] In the above formula, IN R is the quantitative result of the output adjustment range R, P e is the rated load of the unit; the quantified function expression for the AGC mode operation interval S is:

[0027] IN S =S / P e ×100%,

[0028] In the above formula, IN R The quantification result of the AGC mode operation interval S is as follows; the steps of quantifying the data of any one of the three evaluation indicators of the adjustment rate V, the adjustment accuracy E, and the response time T include:

[0029] S2.1, for the data of the current evaluation index, the fuzzy clustering algorithm is used to perform cluster analysis on the data of the current evaluation index obtained within the evaluation period to obtain the cluster center Wherein, subscript i=1,2,…,c, c is the number of categories of fuzzy clustering, and c≥2;

[0030] S2.2, based on the obtained cluster center, the curve expression of the current evaluation index is obtained by polynomial fitting: Where y represents the output value of the polynomial fitting function, f represents the fitting function, Represents the cluster center vector, and the value interval of the current evaluation index is obtained from the data sample [N in ,N en ], the value interval [Nin ,N en ] is divided into multiple sub-intervals, and the current evaluation index is quantified according to the following formula:

[0031]

[0032] In the above formula, IN represents the quantitative value of the current evaluation index; B = [b1, b2, ..., b l ], is a set of weighted coefficients of each sub-interval, b i is the weight coefficient of each sub-interval, i = 1, ..., l, l represents the number of sub-intervals, [N in ,N en ] is the value range of the current evaluation index, N1~N l Respectively represent the boundary values ​​of the evaluation indicators of each divided sub-interval;

[0033] S2.3, determine the value bias type of the current evaluation index. If the larger the value of the current evaluation index is, the better the regulation ability of the thermal power unit is, then the quantitative value IN of the current evaluation index is normalized according to the following formula:

[0034] r ji =[x ji -min j (x ji )] / [max j (x ji )-min j (x ji )],

[0035] Otherwise, the quantitative value IN of the current evaluation index is normalized according to the following formula:

[0036] r ji =[max j (x ji )-x ji ] / [max j (x ji )-min j (x ji )],

[0037] Among them, r ji is the quantitative result of the jth evaluation index of the i-th thermal power unit, x ji is the jth evaluation index of the i-th thermal power unit after the evaluation index is quantified, i=1,2,…,m, j=1,2,…5, m is the number of thermal power units, max j (x ji ), min j (x ji) are the maximum and minimum values ​​of the jth evaluation index in all thermal power units respectively; the quantification of the current evaluation index is completed.

[0038] Optionally, determining the weight of each evaluation index in step S3 includes:

[0039] S3.1, for any j-th evaluation index, calculate its entropy value e according to the following formula j :

[0040]

[0041] In the above formula, the variable k satisfies k = 1 / ln(m), ln is the natural logarithm, m is the number of thermal power units, h ij The function expression is:

[0042]

[0043] In the above formula, r ij It represents the quantitative result of the jth evaluation index of the i-th thermal power unit;

[0044] S3.2, according to the entropy value e of any j-th evaluation index j Calculate the corresponding coefficient of variation β j , and its calculation function expression is:

[0045] β j =1-e j ,

[0046] S3.3, according to the difference coefficient β of any j-th evaluation index j Calculate the entropy weight coefficient p of the jth evaluation index j , and its calculation function expression is:

[0047]

[0048] In the above formula, n is the total number of evaluation indicators;

[0049] S3.4, according to the entropy weight coefficient p of any j-th evaluation index j Calculate the comprehensive weight ω of the jth evaluation index j , and its calculation function expression is:

[0050] ω j =λ j ·p j +(1-λ j )·q j ,

[0051] In the above formula, λ j is the subjective and objective compromise coefficient of the jth evaluation index, and satisfies 0≤λj ≤1;q j is the importance of the jth evaluation indicator determined subjectively by experts and satisfies 0≤q j ≤1.

[0052] Optionally, in step S4, the calculation function expression for weighted summation of the quantified results of each evaluation index based on the determined weights is:

[0053]

[0054] In the above formula, F i represents the evaluation result of the regulation capability of the i-th thermal power unit, r ij represents the quantitative result of the jth evaluation index of the i-th thermal power unit, ω j Represents the comprehensive weight of the j-th evaluation index.

[0055] Optionally, after step S4, the method further includes sorting the evaluation results of the regulation capabilities of the multiple thermal power units when scheduling the multiple thermal power units, and selecting the thermal power units with the higher ranking of the regulation capability evaluation results for priority scheduling.

[0056] In addition, the present invention also provides a data-driven thermal power unit regulation capability evaluation system, comprising a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the steps of the data-driven thermal power unit regulation capability evaluation method.

[0057] In addition, the present invention also provides a computer-readable storage medium, in which a computer program is stored, and the computer program is used to be programmed or configured by a microprocessor to execute the steps of the data-driven thermal power unit regulation capability evaluation method.

[0058] Compared with the prior art, the present invention mainly has the following advantages:

[0059] 1. The present invention can realize dynamic evaluation of the flexibility of thermal power units, avoid the drawbacks of existing evaluation methods, and provide a reference for flexible optimization and scheduling of power systems.

[0060] 2. The present invention utilizes the operating data of the unit and does not require the unit flexibility evaluation test, which greatly reduces the workload of conducting the flexibility evaluation of the thermal power unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0062] Figure 2 This is the adjustment range data analysis of unit A during the evaluation period in the embodiment of the present invention.

[0063] Figure 3 This is the regulation rate data analysis of unit A during the evaluation period in the embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following will take 5 600MW supercritical wet-cooled thermal power units in a certain place as evaluation objects and an evaluation period of 15 days as an example to further explain in detail the data-driven thermal power unit regulation capacity evaluation method and system of the present invention.

[0065] like Figure 1 As shown, the data-driven thermal power unit regulation capability evaluation method of this embodiment includes:

[0066] S1, determine the data of five evaluation indicators including output adjustment range R, AGC mode operation range S, adjustment rate V, adjustment accuracy E, and response time T of multiple thermal power units;

[0067] S2, quantify the data of each evaluation index respectively;

[0068] S3, determine the weight of each evaluation index respectively;

[0069] S4, performing weighted summation of the quantified results of various evaluation indicators based on the determined weights to obtain an evaluation result of the regulation capability of any thermal power unit.

[0070] The calculation function expression of the output adjustment range R in step S1 is:

[0071] R=P max -P min ,

[0072] In the above formula, P max is the maximum output of the thermal power unit during the evaluation period, P min is the minimum output of the thermal power unit in the evaluation period; the calculation function expression of the AGC operation interval S in step S1 is:

[0073]

[0074] In the above formula, is the maximum output of the thermal power unit in AGC mode during the evaluation period, is the minimum output of the thermal power unit in the AGC mode during the evaluation period; the calculation function expression of the response time T in step S1 is:

[0075] T = t1-t0,

[0076] In the above formula, t0 is the moment when the unit load command begins to change, and t1 is the moment when the unit actual load begins to change, and the change amplitude exceeds the regulation dead zone range and no longer reverses in trend.

[0077] The calculation function expression of the adjustment rate V in step S1 is:

[0078] V=ΔP / Δt=(P up -P down ) / (t up -t down ),

[0079] Among them, V is the regulation rate, ΔP is the actual load change of the unit, Δt is the time change, and ΔP satisfies ΔP ≥ 10% P e , P e is the rated load of the unit; P up and P down are the loads when the actual load reaches the target load command change range of the specified upper limit ratio and the specified lower limit ratio when the unit changes load, respectively, 10 ,t 90 They are respectively the moments when the actual load reaches the target load command with a change range of the specified upper limit ratio and the specified lower limit ratio when the unit changes load.

[0080] The calculation function expression of the adjustment accuracy E in step S1 is:

[0081]

[0082] In the above formula, P z is the target load instruction, P i is the output point of the ith unit after the actual load of the unit enters the regulation dead zone for the first time, P e is the rated load of the unit, and N is the number of unit output points after the actual load of the unit enters the regulation dead zone for the first time.

[0083] Among them, when the data of each evaluation index are quantified in S2, the function expression for quantifying the output adjustment range R is:

[0084] IN R =R / P e ×100%,

[0085] In the above formula, IN R is the quantitative result of the output adjustment range R, P e is the rated load of the unit; the quantified function expression for the AGC mode operation interval S is:

[0086] IN S =S / P e ×100%,

[0087] In the above formula, IN R is the quantitative result of the AGC mode operation interval S; in this embodiment, during the evaluation period, the adjustment range R data obtained according to the operation data of unit A is analyzed as follows Figure 2 shown.

[0088] The steps of quantifying the data of any one of the three evaluation indicators of the adjustment rate V, the adjustment accuracy E, and the response time T include:

[0089] S2.1, for the data of the current evaluation index, the fuzzy clustering algorithm is used to perform cluster analysis on the data of the current evaluation index obtained within the evaluation period to obtain the cluster center Wherein, subscript i=1,2,…,c, c is the number of categories of fuzzy clustering, and c≥2;

[0090] S2.2, based on the obtained cluster center, the curve expression of the current evaluation index is obtained by polynomial fitting: Where y represents the output value of the polynomial fitting function, f represents the fitting function, Represents the cluster center vector, and the value interval of the current evaluation index is obtained from the data sample [N in ,N en ], the value interval [N in ,N en ] is divided into multiple sub-intervals, and the current evaluation index is quantified according to the following formula:

[0091]

[0092] In the above formula, IN represents the quantitative value of the current evaluation index; B = [b1, b2, ..., b l ], is a set of weighted coefficients of each sub-interval, b i is the weight coefficient of each sub-interval, i = 1, ..., l, l represents the number of sub-intervals, [N in ,N en ] is the value range of the current evaluation index, N1~N l Respectively represent the boundary values ​​of the evaluation indicators of each sub-interval; Based on the above formula, it can be seen that the value interval [N in ,N en ] is divided into multiple sub-intervals, that is, the value interval [N in ,N en ] is divided into l sub-intervals. After obtaining l sub-intervals, the weighted coefficients b of different sub-intervals can be divided according to the importance of each sub-interval. i ;

[0093] S2.3, determine the value bias type of the current evaluation index. If the larger the value of the current evaluation index is, the better the regulation ability of the thermal power unit is, then the quantitative value IN of the current evaluation index is normalized according to the following formula:

[0094] r ji =[x ji -min j (x ji )] / [max j (x ji )-min j (x ji )],

[0095] Otherwise, the quantitative value IN of the current evaluation index is normalized according to the following formula:

[0096] r ji =[max j (x ji )-x ji ] / [max j (x ji )-min j (x ji )],

[0097] Among them, r ji is the quantitative result of the jth evaluation index of the i-th thermal power unit, x ji is the jth evaluation index of the i-th thermal power unit after the evaluation index is quantified, i=1,2,…,m, j=1,2,…5, m is the number of thermal power units, max j (x ji ), min j (x ji ) are the maximum and minimum values ​​of the jth evaluation index of all thermal power units respectively; the current evaluation index is quantified. For example, in this embodiment, during the evaluation period, the adjustment rate V data obtained according to the operation data of unit A is analyzed as follows: Figure 3 As shown, the functional expression of the fitting function is as follows Figure 3 Shown in the lower middle.

[0098] In this embodiment, the weights of various evaluation indicators are determined in step S3, including:

[0099] S3.1, for any j-th evaluation index, calculate its entropy value e according to the following formula j :

[0100]

[0101] In the above formula, the variable k satisfies k = 1 / ln(m), ln is the natural logarithm, m is the number of thermal power units, h ijThe function expression is:

[0102]

[0103] In the above formula, r ij It represents the quantitative result of the jth evaluation index of the i-th thermal power unit;

[0104] S3.2, according to the entropy value e of any j-th evaluation index j Calculate the corresponding coefficient of variation β j , and its calculation function expression is:

[0105] β j =1-e j ,

[0106] S3.3, according to the difference coefficient β of any j-th evaluation index j Calculate the entropy weight coefficient p of the jth evaluation index j , and its calculation function expression is:

[0107]

[0108] In the above formula, n is the total number of evaluation indicators;

[0109] S3.4, according to the entropy weight coefficient p of any j-th evaluation index j Calculate the comprehensive weight ω of the jth evaluation index j , and its calculation function expression is:

[0110] ω j =λ j ·p j +(1-λ j )·q j ,

[0111] In the above formula, λ j is the subjective and objective compromise coefficient of the jth evaluation index, and satisfies 0≤λ j ≤1;q j is the importance of the jth evaluation indicator determined subjectively by experts and satisfies 0≤q j ≤1. In this embodiment, take λ j =0.5(j=1,2,…5);q j (j=1,2,…5) are 0.20, 0.33, 0.27, 0.13, and 0.07 respectively.

[0112] In this embodiment, the calculation function expression of weighted summation of the quantified results of each evaluation index based on the determined weights in step S4 is:

[0113]

[0114] In the above formula, F i represents the evaluation result of the regulation capability of the i-th thermal power unit, r ij represents the quantitative result of the jth evaluation index of the i-th thermal power unit, ω j In this embodiment, the evaluation results obtained for 5 thermal power units (A to E) are shown in Table 1.

[0115] Table 1: Evaluation results of each unit.

[0116]

[0117]

[0118] In this embodiment, after step S4, the process also includes sorting the evaluation results of the regulation capabilities of the multiple thermal power units when scheduling the multiple thermal power units, and selecting the thermal power units with the higher ranking of the regulation capability evaluation results for priority scheduling.

[0119] In summary, the data-driven thermal power unit regulation capability evaluation method of this embodiment utilizes the operating data of multiple thermal power units and does not require unit flexibility evaluation tests, which greatly reduces the workload of conducting thermal power unit flexibility evaluation; it can realize dynamic evaluation of thermal power unit flexibility, avoids the drawbacks of existing evaluation methods, and can provide a reference for flexible optimization and scheduling of power systems.

[0120] In addition, this embodiment also provides a data-driven thermal power unit regulation capability evaluation system, including an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the steps of the aforementioned data-driven thermal power unit regulation capability evaluation method.

[0121] In addition, this embodiment also provides a computer-readable storage medium, in which a computer program is stored. The computer program is used to be programmed or configured by a microprocessor to execute the steps of the aforementioned data-driven thermal power unit regulation capability evaluation method.

[0122] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A data-driven method for evaluating the regulation capability of thermal power units, characterized in that: include: S1, determine the output adjustment range of multiple thermal power units R , AGC mode operation range S , adjust the rate V , Adjustment accuracy E , Response time T There are five evaluation indicators in total; S2, quantify the data of each evaluation index respectively; S3, determine the weight of each evaluation index respectively; S4, performing weighted summation of the quantified results of various evaluation indicators based on the determined weights to obtain an evaluation result of the regulation capability of any thermal power unit; When the data of each evaluation index is quantified in step S2, the output adjustment range is R The function expression for quantization is: IN R = R / P e ×100% ， In the above formula, IN R Output adjustment range R The quantitative results of P e is the rated load of the unit; For AGC mode operation range S The function expression for quantization is: IN S = S / P e ×100% ， In the above formula, IN S AGC mode operation range S The quantitative results of the adjustment rate V , Adjustment accuracy E , Response time T The steps to quantify the data of any of the three evaluation indicators include: S2.1, for the data of the current evaluation index, the fuzzy clustering algorithm is used to perform cluster analysis on the data of the current evaluation index obtained within the evaluation period to obtain the cluster center , where the subscript i =1,2,…, c , c is the number of categories of fuzzy clustering and satisfies c ≥2; S2.2, based on the obtained cluster center, the curve expression of the current evaluation index is obtained by polynomial fitting: , where y represents the output value of the polynomial fitting function, f represents the fitting function, , represents the cluster center vector, and the value interval of the current evaluation index is obtained from the data sample [ N in , N en ], the value interval [ N in , N en ] is divided into multiple sub-intervals, and the current evaluation index is quantified according to the following formula: In the above formula, IN Indicates the quantitative value of the current evaluation index; B =[ b 1, b 2, …, b l ], is a set of weighted coefficients of each sub-interval, b i is the weight coefficient of each sub-interval, i =1,…, l , l represents the number of subintervals, [ N in , N en ] is the value range of the current evaluation index, N 1 ～N l Respectively represent the boundary values ​​of the evaluation indicators of each divided sub-interval; S2.3, determine the value bias type of the current evaluation index. If the current evaluation index value is larger, it means the thermal power unit has better regulation ability. Then the quantitative value of the current evaluation index is IN The normalization is performed according to the following formula: ， Otherwise, the quantitative value of the current evaluation index IN The normalization is performed according to the following formula: ， in, r ji For the i The first thermal power unit j The quantitative results of the evaluation indicators are x ji After the evaluation index is quantified i The first thermal power unit j evaluation indicators, i =1,2,…, m , j =1,2,…5, m is the number of thermal power units, max j ( x ji ), min j ( x ji ) are respectively the first j The maximum and minimum values ​​of the evaluation indicators; the quantification of the current evaluation indicators is completed.

2. The data-driven thermal power unit regulation capability evaluation method according to claim 1 is characterized in that: Output adjustment range in step S1 R The calculation function expression is: R = P max - P min ， In the above formula, P max is the maximum output of the thermal power unit during the evaluation period, P min is the minimum output of the thermal power unit during the evaluation period; the AGC mode operation interval in step S1 S The calculation function expression is: ， In the above formula, is the maximum output of the thermal power unit in AGC mode during the evaluation period, is the minimum output of the thermal power unit in AGC mode during the evaluation period; the response time in step S1 T The calculation function expression is: T=t 1 -t 0， In the above formula, t 0 is the moment when the unit load command starts to change, t 1 is the moment when the actual load of the unit begins to change, and the change amplitude exceeds the regulation dead zone range and no longer reverses in trend.

3. The data-driven thermal power unit regulation capability evaluation method according to claim 1 is characterized in that: In step S1, the rate is adjusted V The calculation function expression is: V =D P / D t =( P up - P down ) / ( t up -t down ), in, V is the adjustment rate, Δ P is the actual load change of the unit, Δ t is the time variation, Δ P Satisfy Δ P ≥10 % P e , P e is the rated load of the unit; P up and P down They are the loads when the actual load reaches the target load command change range of the specified upper limit ratio and the specified lower limit ratio when the unit changes load. t 10 , t 90 They are respectively the moments when the actual load reaches the target load command with a change range of the specified upper limit ratio and the specified lower limit ratio when the unit changes load.

4. The data-driven thermal power unit regulation capability evaluation method according to claim 1 is characterized in that: Adjustment accuracy in step S1 E The calculation function expression is: ， In the above formula, P z is the target load instruction, P i The actual load of the unit enters the regulation dead zone for the first time. i Each unit output point, P e is the rated load of the unit, and N is the number of unit output points after the actual load of the unit enters the regulation dead zone for the first time.

5. The data-driven thermal power unit regulation capability evaluation method according to claim 1 is characterized in that: The weights of various evaluation indicators are determined in step S3, including: S3.1, for any j The entropy value of each evaluation index is calculated according to the following formula e j : ， In the above formula, the variable k satisfy k =1 / ln( m ), ln is the natural logarithm, m is the number of thermal power units, h ij The function expression is: ， In the above formula, r ij Indicates i The first thermal power unit j Quantitative results of the evaluation indicators; S3.2, according to any j Entropy value of evaluation index e j Calculate the corresponding coefficient of variation β j , and its calculation function expression is: β j =1- e j ， S3.3, according to any j The coefficient of difference of the evaluation indicators β j Calculate the j Entropy weight coefficient of evaluation index p j , and its calculation function expression is: In the above formula, n is the total number of evaluation indicators; S3.4, according to any j Entropy weight coefficient of evaluation index p j Calculate the j The comprehensive weight of the evaluation indicators ω j , and its calculation function expression is: ω j = λ j · p j +(1- λ j )· q j ， In the above formula, λ j For the j The subjective and objective compromise coefficient of the evaluation index, and it satisfies 0≤ λ j ≤1; q j For the j The importance of the evaluation indicators is determined by experts and meets the requirement of 0≤ q j ≤1.

6. The data-driven thermal power unit regulation capability evaluation method according to claim 1 is characterized in that: In step S4, the calculation function expression of weighted summation of the quantified results of each evaluation index based on the determined weights is: ， In the above formula, F i Indicates i The evaluation results of the regulation capability of each thermal power unit are r ij Indicates i The first thermal power unit j The quantitative results of the evaluation indicators are ω j Indicates j The comprehensive weight of the evaluation indicators.

7. The data-driven thermal power unit regulation capability evaluation method according to claim 1 is characterized in that: After step S4, the method further includes sorting the evaluation results of the regulation capabilities of the multiple thermal power units when scheduling the multiple thermal power units, and selecting the thermal power units with higher rankings of the regulation capability evaluation results for priority scheduling.

8. A data-driven thermal power unit regulation capability evaluation system, comprising a microprocessor and a memory connected to each other, characterized in that: The microprocessor is programmed or configured to execute the steps of the data-driven thermal power unit regulation capability evaluation method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored therein, characterized in that: The computer program is used to be programmed or configured by a microprocessor to execute the steps of the data-driven thermal power unit regulation capability evaluation method as described in any one of claims 1 to 7.

Images