A power plant wide load intelligent dispatching management method and system

Abstract

The present application relates to the technical field of power load scheduling, in particular to a power plant wide load intelligent scheduling management method and system, comprising: integrating voltage signals and operating parameters of each coal-fired unit to form an input data set; using a time delay model to analyze each coal-fired unit in the input data set, recording the time delay time of each coal-fired unit, and obtaining the time delay mapping relationship derived by the model at any time; using the time delay mapping relationship, combining the adjustment stability under different load intervals, and determining the effective scheduling sub-interval in different load intervals; drawing a multi-time delay change curve with the time stamp corresponding to the effective scheduling sub-interval as the horizontal axis and the load value and the time delay time as the vertical axis, and determining the preparation delay time of each effective scheduling sub-interval; taking the data corresponding to the effective scheduling sub-interval and the preparation delay time as input, and solving the optimal operating parameters at each time. The efficiency and accuracy of power scheduling are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power load scheduling, in particular to a power plant wide load intelligent scheduling management method and system. BACKGROUND

[0002] Currently, the coal-fired unit coordinated control system mainly adopts the traditional load feedforward + PID control strategy. However, under the background of new power system construction, the coal-fired unit generally has problems such as unstable combustion due to variable coal quality, large fluctuation of main parameters in complex working conditions, safe operation of heating surface, and poor grid performance under wide load. The existing control technology has deficiencies in precise modeling, working condition adaptation, overall coordination ability, etc., and it is difficult to realize the comprehensive improvement of the coordinated control ability of the unit under complex working conditions. At the same time, due to the large inertia and nonlinear dynamic characteristics of the coal-fired unit itself, as well as the performance limitations of the conventional PID plus feedforward control strategy algorithm in traditional DCS control, the parameter operation stability and rapidity are not high.

[0003] For example, Chinese patent publication CN119994923A discloses a resource scheduling method and device, electronic equipment and storage medium, the method comprising: obtaining adjustable load resource data of a power system within a preset time period, inputting the adjustable load resource data into a preset generation side low-carbon scheduling model to obtain n groups of resource scheduling modes, determining n groups of generation feature indexes corresponding to the n groups of resource scheduling modes, inputting the n groups of resource scheduling modes into a preset load side low-carbon scheduling model to obtain n groups of load side power consumption data, determining n groups of load side power consumption feature indexes corresponding to the n groups of load side power consumption data, determining n coordination degree values based on the n groups of generation feature indexes and the n groups of load side power consumption feature indexes, determining the maximum coordination degree value in the n coordination degree values, determining the resource scheduling mode corresponding to the maximum coordination degree value, and obtaining the target resource scheduling mode.

[0004] For example, Chinese patent publication CN119742795A discloses a power equipment load scheduling method and system based on big data analysis; a multi-feature time series machine learning model is used to predict the future power load in the selected scheduling area, to determine whether to generate a power load supply shortage prompt, in the case of power load supply shortage, to determine whether there is available standby power source in combination with the power supply parameters of the standby power source, and to perform power load scheduling on the power of the standby power source according to the scheduling duration.

[0005] The prior art quantifies the resource scheduling mode by power supply cost and the device power supply preparation time during power supply scheduling to complete the distribution processing of power scheduling; these processing modes are biased towards the power cost of device scheduling and the time cost of starting device scheduling, but ignore the time delay level and influence of power equipment, which makes it difficult to identify the response lag phenomenon of the power scheduling process, and makes the adjustment prone to instability and rigidity, resulting in redundancy and time waste of power scheduling. SUMMARY

[0006] In order to solve the above technical problems, the technical scheme adopted by the present application is: a power plant wide load intelligent scheduling management method, comprising: S1, when the scheduling instruction is executed, continuously collecting the voltage signal of the high-voltage side, integrating the voltage signal with the operating parameters of each coal-fired unit to form an input data set.

[0007] S2, using a time delay model to analyze each coal-fired unit in the input data set, recording the time delay time of each coal-fired unit, and obtaining the time delay mapping relationship derived by the model at any time.

[0008] S3, using the time delay mapping relationship, combining the adjustment stability under different load intervals, and determining the effective scheduling sub-interval in different load intervals.

[0009] S4, taking the time stamp corresponding to the effective scheduling sub-interval as the horizontal axis, and taking the load value and the time delay time as the vertical axis to draw a multi-time delay change curve, and determining the preparation delay time of each effective scheduling sub-interval.

[0010] S5, taking the data corresponding to the effective scheduling sub-interval and the preparation delay time as input to solve the optimal operating parameters at each time.

[0011] A power plant wide load intelligent scheduling management system, comprising: a data acquisition module for continuously collecting the voltage signal of the high-voltage side when the scheduling instruction is executed, integrating the voltage signal with the operating parameters of each coal-fired unit to form an input data set.

[0012] A time delay analysis module for using a time delay model to analyze each coal-fired unit in the input data set, recording the time delay time of each coal-fired unit, and obtaining the time delay mapping relationship derived by the model at any time.

[0013] An interval judgment module for using the time delay mapping relationship, combining the adjustment stability under different load intervals, and determining the effective scheduling sub-interval in different load intervals.

[0014] A delay identification module for taking the time stamp corresponding to the effective scheduling sub-interval as the horizontal axis, and taking the load value and the time delay time as the vertical axis to draw a multi-time delay change curve, and determining the preparation delay time of each effective scheduling sub-interval.

[0015] A parameter output module is configured to take data corresponding to the effective scheduling sub-interval and the preparation delay time as input, and solve the optimal operation parameter at each time.

[0016] The present application has the following advantages: 1. The present application continuously collects high-voltage signals, integrates various coal-fired unit operation parameters, adopts a load interval method, records time lag time according to load intervals, generates a multi-dimensional state vector and fits a time lag mapping relationship, avoids the problem of time lag mapping distortion caused by parameter confusion, sets quantitative data for the current coal-fired unit response to the scheduling instruction, and facilitates subsequent analysis of parameter analysis under the influence of multiple time lags.

[0017] 2. The present application splits the load interval into fine-grained load points, determines data that meet normal parameter constraint conditions in the current load interval in the form of parameter constraints and load fluctuations, avoids the influence of invalid load points on the scheduling process, ensures that equipment under different load intervals can determine their load change conditions, and ensures safe and stable operation of the unit in a wide load interval.

[0018] 3. The present application calculates the preparation delay time of the scheduling instruction, determines the key nodes of the instruction issuing point, the output reaching point, and the time lag average value when each scheduling instruction meets the standard, judges whether the instruction window meets the merging condition, realizes the association and merging of multiple instructions, and makes the instruction association and interval time lag able to be processed cooperatively; finally, the multi-objective optimal operation parameter is solved, so that the effective scheduling sub-interval under the time lag analysis can be matched with the corresponding parameter, and the efficiency and accuracy of power scheduling are improved. BRIEF DESCRIPTION OF DRAWINGS

[0019] The present application will be further described below in combination with the drawings and examples.

[0020] Figure 1 It is a flowchart of a power plant wide load intelligent scheduling management method.

[0021] Figure 2 It is a flowchart of step S2 of a power plant wide load intelligent scheduling management method.

[0022] Figure 3 It is a flowchart of step S3 of a power plant wide load intelligent scheduling management method.

[0023] Figure 4 It is a flowchart of step S4 of a power plant wide load intelligent scheduling management method.

[0024] Figure 5 It is a system framework diagram of a power plant wide load intelligent scheduling management system. DETAILED DESCRIPTION

[0025] Embodiments of the present application are described in detail below. The embodiments described below are exemplary only, and are not to be construed as limiting the present application. Where specific technical or conditions are not described in the embodiments, the techniques or conditions described in the literature in the art or according to the product specifications are used.

[0026] Referring to Figure 1 A power plant wide load intelligent scheduling management method, comprising: S1, continuously collecting the voltage signal of the high-voltage side when the scheduling instruction is executed, integrating the voltage signal with the operating parameters of each coal-fired unit to form an input data set.

[0027] S2, using a time delay model to analyze each coal-fired unit in the input data set, recording the time delay time of each coal-fired unit, and obtaining the time delay mapping relationship derived by the model at any time.

[0028] S3, using the time delay mapping relationship, combining the regulation stability in different load intervals, and determining the effective scheduling sub-interval in different load intervals.

[0029] S4, drawing a multi-time delay change curve with the time stamp corresponding to the effective scheduling sub-interval as the horizontal axis and the load value and the time delay time as the vertical axis, and determining the preparation delay time of each effective scheduling sub-interval.

[0030] S5, taking the data corresponding to the effective scheduling sub-interval and the preparation delay time as input, and solving the optimal operating parameters at each time.

[0031] In step S1, the voltage signal of the high-voltage side is continuously collected, and the voltage signal is bound with the operating parameters of each coal-fired unit. The operating parameters can include boiler temperature, pressure, flow, coal input, air-coal ratio, and induced draft fan speed, etc. representing the operating data of the coal-fired unit, as well as the scheduling instruction and load data set by the current power grid under scheduling, so as to monitor the working condition of each coal-fired unit under power grid scheduling.

[0032] When the voltage signal of the high-voltage side is known, the line voltage effective value of the high-voltage side, the line current effective value of the high-voltage side can be measured through the voltage signal, and then the active power, the reactive power, and the ratio of the active power to the rated active power (percentage load) can be directly obtained, so that the actual load of the coal-fired unit under the power grid scheduling can be known, and the binding condition of these load values and the operating parameters of each coal-fired unit can be calculated.

[0033] The implementation of step S1 includes: when any scheduling instruction is obtained, determining the scheduling instruction when each coal-fired unit is running based on the operating parameters of each coal-fired unit; determining the active power under the current work with the voltage signal under the execution of the scheduling instruction, and recording the load interval of each coal-fired unit with the active power, and synchronizing the value range of the load interval to the input data set.

[0034] In the execution of the wide load scheduling process, the load interval at which each scheduling instruction is issued is recorded in real time to determine the working condition of each coal-fired unit, and the load interval represents the value range of the percentage load under the corresponding instruction, which explains the size of the active power output by the current coal-fired unit.

[0035] The output data will be divided according to the value range of the load interval to form multiple input data sets, such as the priority scheduling load interval with a load percentage of 35% or less, the conventional load interval with a load percentage of 45%-100%, and the transition load interval with a load percentage of about 40%±5%. The value form of each load interval quantifies the processing method under different load interval scheduling, and further determines the time required for each scheduling instruction and the processing efficiency.

[0036] In an embodiment of the present application, as shown in Figure 2 The implementation of step S2 includes: S21, recording the time lag time of each coal-fired unit after the execution of the scheduling instruction according to the load interval corresponding to the input data set.

[0037] The currently recorded time lag time is the time difference between the time when the input parameter starts to change after the execution of the scheduling instruction and the time when the actual output starts to change significantly. This time difference is used to represent the time lag characteristics corresponding to the current input parameter. The set time lag model is used to analyze the gain under the execution of the current scheduling instruction, thereby distinguishing the time lag mapping relationship under different load intervals.

[0038] When the time lag model is cited, the MPC control algorithm is generally used, and its model ; wherein, represents the output value of the MPC control algorithm, representing the gain of the i-th load interval after the execution of the current scheduling instruction; i represents the index of different load intervals, such as i=1, 2, 3 corresponding to the priority scheduling load interval, the conventional load interval and the transition load interval respectively; represents the gain coefficient of the i-th load interval, which indicates the proportion of steady-state output change caused by input change; represents the time lag time of the i-th load interval. When recording the time lag time, the input parameter changes at least by 2%, and the actual output changes at least by 5%, thereby determining the working condition of each coal-fired unit under the current scheduling instruction. represents the inertia time constant of the i-th load interval, reflecting the speed of system response; represents the Laplace operator. According to the description of the time lag model, the time lag time and the relative parameters under the execution of each scheduling instruction are recorded, thereby quantifying the control situation of each scheduling instruction on the coal-fired unit.

[0039] S22, when the data in the input data set changes, generate a multi-dimensional state vector with each changed input data as a variable.

[0040] When generating the multi-dimensional state vector, it is necessary to determine the parameters in the input data set that mainly affect the execution effect of the scheduling instruction, combine these parameters into a multi-dimensional state vector, and calculate the mapping relationship under different load intervals.

[0041] The implementation of step S22 includes: setting based on the initial state of the input data set, and constructing an initial state vector.

[0042] For each initial state vector, determine the parameter category corresponding to the initial state vector; and combine the parameters under each parameter category as a group of reference state vectors.

[0043] The dimension and arrangement order corresponding to each reference state vector are obtained to obtain the output multi-dimensional state vector.

[0044] When constructing the multi-dimensional state vector, it is necessary to determine its parameter category first, so as to screen the parameters that respond to the scheduling instruction, such as the parameter category which will be set based on the category of the current scheduling instruction, such as grid side instruction, unit side fuel instruction and unit side steam instruction; each instruction corresponds to multiple parameters, such as electrical parameters corresponding to grid side instruction, combustion parameters corresponding to unit side fuel instruction, and equipment parameters corresponding to unit side steam instruction, etc.

[0045] At this time, the grid side instruction can correspond to the high voltage side line voltage effective value, the high voltage side line current effective value, the target load and the grid frequency deviation, which will directly respond to the load tracking accuracy and the frequency response effect during scheduling.

[0046] The unit side fuel instruction can correspond to the coal input quantity, the same layer coal powder concentration deviation, the same layer coal powder flow rate deviation and the actual air-coal ratio, which can cause output deviation and thus affect the load accuracy of the overall output. After the relevant time lag in combustion, it can affect the execution of power scheduling.

[0047] The unit side steam instruction can correspond to the main steam pressure, the main steam temperature, the turbine governing valve opening degree and the metal pipe wall temperature, which represent the actual operation of the coal-fired unit and can indirectly affect the actual output under power scheduling. It is the theme of monitoring the normal operation of each device. At this time, the time lag time is introduced to determine the scheduling situation under the normal operation of each coal-fired unit, and then calculate the influence of the time lag time on each instruction.

[0048] When setting the reference state vector, the implementation further includes: taking the real-time operation parameters of the coal-fired unit as the operation state component.

[0049] The operation parameters controlled by the scheduling instruction are taken as the instruction scheduling component.

[0050] The running state component and the instruction scheduling component are spliced to obtain a reference state vector as an output.

[0051] The real-time state and the target state are distinguished at this time. For example, the parameters of the running state component can include actual coal input, actual air-coal ratio, actual main steam pressure, actual valve opening degree, and the like. The instruction scheduling component is a target value under the running state component, which illustrates the value relationship between the target value and the real-time value of the current multi-dimensional state vector in different load intervals.

[0052] As for the dimension and arrangement order corresponding to each reference state vector, the dimension represents the parameter category, which is sorted according to the order of electricity→fuel→equipment to explain the sequential process under the change of different parameters.

[0053] It should be noted that when the multi-dimensional state vector is set, the gain of the multi-dimensional state vector is calculated only when any parameter in the multi-dimensional state vector changes by more than 2% and the actual output changes by at least 5%, otherwise only the fitting coefficient corresponding to the parameter is used to complete the time lag mapping relationship between the input data set and the load interval.

[0054] S23, fitting the time lag time and the load interval at any time using the multi-dimensional state vector to determine the time lag mapping relationship between the input data set and the load interval in each load interval.

[0055] During fitting, the parameters corresponding to the multi-dimensional state vector are generated, and the multi-dimensional state vector and the load interval are used as inputs to complete the processing of the data in each load interval in the form of a quadratic polynomial fitting.

[0056] For example, the fitting form is as follows: ; wherein, represents the time lag time under the condition of the real-time load percentage and the change of any parameter in the multi-dimensional state vector; represents the real-time load percentage, the value of which corresponds to the range of each load interval; represents the parameters of the multi-dimensional state vector, such as coal content, valve opening degree, and the like, which represent the parameters that can be adjusted and affect the operation of the coal-fired unit after the scheduling instruction is issued; 、 、 and represents the fitting coefficient of the i-th load interval, which is solved by the least square method to illustrate the change in each load interval when the input data set changes.

[0057] The finally output time lag mapping relationship records the gain value, fitting coefficient, load interval, and the like to explain the relative gain under the execution of each instruction.

[0058] In one embodiment of the present invention, in step S3, the load points under different load ranges are determined by using the time delay mapping relationship, and each data point is judged to determine whether it conforms to the description of stable regulation, so as to prevent the coal-fired unit operating parameters from changing too much when the dispatching command is executed, resulting in unstable overall output and reduced dispatching efficiency.

[0059] like Figure 3 As shown, the implementation of step S3 includes: S31, dividing the load interval into multiple load points according to the actual load percentage value within the load interval; each divided load point represents a certain sampling time, such as the value of a set of input datasets within the load interval at a sampling interval of 1s. At this time, based on the load value of each coal-fired unit at each scheduling, the values ​​of multiple load points within the current load interval will be determined. When all constraints or indicators are satisfied, the load point is marked as valid, thereby distinguishing the sub-intervals of each load interval that can effectively respond to the instructions under different scheduling instructions, thus describing the load scheduling situation under multiple scenarios.

[0060] S32 retrieves the range and fluctuation amplitude of the time delay corresponding to the load point, and determines the controllability of the time delay corresponding to each load point.

[0061] The core of time delay controllability is that the time delay time is within a reasonable range and the fluctuation amplitude is small. Its controllability can be determined by extracting the grid's mandatory requirements on the unit's response speed and converting them into the upper limit of the time delay. Then, by combining the physical characteristics of multiple devices (the time delay time required in the process of combustion → steam → output), the lower limit of the time delay can be determined. Finally, by combining its historical operating parameters, the fluctuation of the upper and lower limits of the time delay can be determined, thereby determining the time delay controllability of each load point.

[0062] Therefore, the range of time delay values ​​will be derived from the time delay mapping relationship, and the fluctuation amplitude of the time delay will be quantified according to the standard deviation of the same load point in 10 consecutive calculations. For example, the time delay value range in the priority scheduling load interval is [25s, 45s], with a fluctuation amplitude ≤ 5s; the time delay value range in the normal load interval is [15s, 30s], with a fluctuation amplitude ≤ 2s. The normal section has stable operating conditions, and its time delay fluctuation needs to be even smaller; the value in the transition load interval is between the priority scheduling and normal conditions, with a time delay value range of [20s, 35s] and a fluctuation amplitude ≤ 3s. This is used to judge the time delay controllability of the load point under multiple load intervals.

[0063] The above numerical values are only for illustrative purposes. If the dispatching operation data is used as the setting subject, the upper and lower limits of the time lag can be set in the form of average value ± 2 times standard deviation according to the confidence interval of the time lag time, and the fluctuation amplitude can be quantified by calculating the standard deviation according to the historical data of the same load point, and then the response to the dispatching instruction under the current situation is illustrated.

[0064] S33, after the time lag controllability determination is completed, the constraint condition corresponding to the load point is queried, and the adjustment stability under the execution of the dispatching instruction is judged according to the data value of each load point at the corresponding time point.

[0065] In verifying the adjustment stability, the constraint condition is mostly the constraint of the stability of the voltage signal, to prevent large voltage fluctuation and cause the problem of power quality decline. For example, first determine the operating parameters of the coal-fired unit, such as the parameters of main steam pressure and coal powder concentration, which belong to the confidence interval under normal operation, then check the load deviation and voltage fluctuation corresponding to the actual output, and take the two as the main constraint conditions. After the load deviation and voltage fluctuation belong to the normal value of the corresponding load interval, it can be judged that the voltage fluctuation is small under the execution of the dispatching instruction, and finally the load points meeting the constraint conditions are output.

[0066] The current load point represents the minimum dispatching unit load value split from the original load interval according to the working condition sensitivity. For example, taking 0.5% as a step, every 0.5% is a load point, then the absolute deviation of the actual processing and the target load of the dispatching instruction at the same time and the same unit is checked to define the load deviation, and the voltage fluctuation at the corresponding time is simultaneously called to determine the adjustment stability of the execution of the dispatching instruction.

[0067] At this time, each load point will call data from a multi-dimensional state vector at the same time stamp, one is the actual output under the motion state component, and the other is the target load under the instruction dispatching component, so as to obtain the absolute deviation of the actual output and the target load. This deviation represents the relative deviation of the corresponding data of a certain minimum dispatching unit load value.

[0068] It should be noted that each load point represents the load value counted at the corresponding time, and each load point directly corresponds to the specific data at a time. As for the deviation corresponding to the load point, the deviation is to illustrate the difference between the target load and the actual load of the dispatching instruction at the corresponding time, which is the main content of the current verification of the load point stability.

[0069] For the load deviation of the load point, different judgment thresholds are set based on different load intervals, and the current load deviation is required to be less than the judgment threshold. For example, the priority dispatching / normal / transition load interval will be set to 3%, 2% and 2.5% in turn, and the load deviation at the corresponding time point is required to be as small as possible.

[0070] At the same time, the voltage fluctuation at the corresponding moment will be determined according to the voltage fluctuation in the grid regulation document, and the voltage fluctuation amplitude cannot exceed ±2% of the rated voltage regardless of the load interval; then, in the order of priority scheduling / conventional / transition load interval, ±1.8%, ±1.5% and ±1.6% of the rated voltage are set in turn; in addition to these values, the voltage fluctuation can also be set by the confidence interval of the historical data, so as to check the specific situation of the load point at the corresponding moment.

[0071] In S34, the load point whose time delay controllability and regulation stability are both judged to pass is regarded as an effective load point, and the continuous effective load points are merged to form an output effective scheduling sub-interval.

[0072] Only the load point whose regulation stability and time delay controllability are both judged to pass is regarded as an effective load point to explain the execution effectiveness of the scheduling instruction at the corresponding time, and the corresponding load points are combined into a sub-interval; the sub-interval is essentially a set of load points selected from the original load interval, which are time delay controllable, regulation stable and constraint compliant, to ensure that the scheduling instruction can be accurately executed, and the corresponding data can be regarded as a reliable peak regulation and frequency modulation data pool, which is convenient for subsequent optimization control of scheduling instruction execution.

[0073] In an embodiment of the present application, the step is implemented by analyzing the multi-time delay change curve to identify the load mutation points before and after scheduling, to predict the time delay superposition risk, and to determine the preparation delay time under the corresponding scheduling instruction issuance, so as to determine the response of each unit under time delay reaction.

[0074] The multi-time delay change curve formed has a time stamp representing the horizontal axis, a load value representing the left vertical axis, which can be represented by actual output or load percentage; and a time delay time representing the right vertical axis, which represents the time delay range of the sub-interval.

[0075] As shown in FIG. 4, the implementation of step S4 includes the following steps: Figure 4 S41, according to the multi-time delay change curve, the instruction issuance point, the output compliance point and the time delay average of the effective scheduling sub-interval are obtained respectively as the key node list of the multi-time delay change curve; the instruction issuance point represents the time point of the scheduling instruction issuance, if there are multiple continuous instructions in the same effective scheduling sub-interval, the time point of each scheduling instruction needs to be recorded; the output compliance point needs to determine the time when the actual load coincides with the target load or enters ±1%, to determine the time when the actual output reaches the target load.

[0076] The time delay average represents the average value under a single scheduling instruction execution, if there are multiple scheduling instructions in the same effective scheduling sub-interval, the average value of these instructions needs to be taken.

[0077] S42, based on the input key node list, determine the instruction window of each dispatch instruction when issued, and determine whether the scheduling instructions before the current instruction window meet the merging condition according to the sending situation of each instruction window.

[0078] After obtaining the key node list, the time window of each scheduling instruction is divided from the time period of the current effective scheduling sub-interval, and it is judged whether the multi-instruction window can be merged to avoid repeated calculation of the preparation delay time.

[0079] The dimensions of the merging condition will be based on the mean deviation of the time lag (calculated by the coefficient of variation of the time lag time, and the deviation is quantified by the ratio of the standard deviation to the mean), the instruction window timing (indicating the time interval between two instruction windows), and the load change rate, so as to determine the merging situation under the execution of multiple scheduling instructions.

[0080] Therefore, the implementation mode of step S42 includes: for any instruction window, determining the merging condition of the current instruction window; the dimensions of the merging condition will be based on the mean deviation of the time lag, the instruction window timing and the load change rate.

[0081] When all the merging conditions are met, it is considered that the scheduling instructions before the current instruction window meet the merging condition.

[0082] For the merging condition of the mean deviation of the time lag, when the coefficient of variation between the continuous instruction windows is ≤5%, it is considered that the mean deviation of the time lag meets the merging condition.

[0083] For the instruction window timing, the time interval between the instruction window of the last scheduling instruction and the current instruction window is required to be less than the preset time interval, that is, it is determined that the instruction window corresponding to the last scheduling instruction and the current instruction window are continuous or overlapping; the preset time interval can be set based on the average value of the time interval between the continuous instruction windows, or a confidence interval with a confidence level of 95% is selected, which is set in the form of average value ± 1.96 standard deviation, and the upper limit value of the confidence interval is set as the preset time interval, so as to cover the response requirements of more than 95% of the units, and thus explain the continuous situation between the instruction windows.

[0084] As for the merging condition of the load change rate, the load target change rate of the combined load values of the two instruction windows is required to be less than 2%, that is, the actual scheduling targets of multiple scheduling instructions are close, so as to merge the data under the same description.

[0085] S43, if the merging condition is met, the preparation delay time of the corresponding effective scheduling sub-interval is set based on the merged instruction issuing point and the output standard point.

[0086] After meeting the merging condition, the time point of merging multiple scheduling instructions, reacquire the earliest instruction issuing point and the latest output standard point, the difference between the two time points, the actual scheduling completion preparation delay time after the current scheduling instruction is issued, this time will be bound to the corresponding load interval, to determine the required time length of the corresponding load interval under the scheduling adjustment.

[0087] S44, if the merging condition is not met, determine whether each scheduling instruction has been completed, and extract the instruction window length corresponding to the current scheduling instruction to output the preparation delay time.

[0088] When the merging condition is not met, it means that the interval between each scheduling instruction is long, and it is necessary to determine whether each scheduling instruction has been completed. At this time, the load value can be used to determine whether the load value and the target load are within 1% of the continuous time point. If the values at the continuous time points meet the condition, it means that the scheduling instruction has been completed. At this time, the preparation delay time of the output can be obtained by subtracting the instruction issuing point from the output standard point.

[0089] If the load value is always close to the target load, it means that the current instruction has not been executed, or the current scheduling instruction has not been executed to the standard, and the corresponding data needs to be marked and the load value is continuously obtained to obtain the time point of the completion of the scheduling instruction.

[0090] In an embodiment of the present application, in step S5, in addition to the parameters representing the interval and time properties, the two parameters essentially correspond to a parameter set under certain constraints. For example, the effective scheduling sub-interval in step S3 limits the constraints of multiple data groups, output deviation, etc. The preparation delay time represents the time constraints when the scheduling instruction is started and when it is completed. Under the parameter set constrained by these two parameters, the optimal operating parameters at the corresponding time are solved, and the output data combination is obtained.

[0091] Therefore, the implementation of step S5 includes: S51, setting a target function for each effective scheduling sub-interval according to the goals of minimizing coal consumption, minimizing output deviation, and minimizing parameter fluctuation.

[0092] When setting the target function, the goals of minimizing coal consumption, minimizing output deviation, and minimizing parameter fluctuation are prioritized. Minimizing coal consumption means that the ratio of the coal consumption rate to the maximum allowed coal consumption rate in each effective scheduling sub-interval. Similarly, minimizing output deviation means that the ratio of the output deviation to the maximum allowed output deviation can be used to ensure the response to the scheduling instruction. Minimizing parameter fluctuation means that the ratio of the main steam pressure fluctuation, CO concentration fluctuation, and voltage fluctuation to the maximum allowed fluctuation. The average of the ratios of the three fluctuations is calculated to indicate the parameter fluctuation, avoiding equipment fatigue under power scheduling.

[0093] The target function is set to minimize the coal consumption, minimize the output deviation and minimize the parameter fluctuation value, and the weights can be set to 0.4, 0.3 and 0.3 in turn; the coal consumption of the coal-fired unit is preferentially ensured, and the response and fluctuation thereof are checked simultaneously; the weights can also be quantified by the proportion of the characteristic value in the total characteristic value in the form of eigenvalue decomposition, to quantify the priority of each parameter under power dispatching.

[0094] S52, particle swarm solving is performed according to the target function, and the optimal operation parameter corresponding to the effective scheduling sub-interval is determined.

[0095] When the particle swarm is solved, the following steps can be used: 1. 100 parameter particles are initialized, each parameter particle corresponds to a group of data, and it is assumed that the wind-coal ratio and the coal are used as the example values, the wind-coal ratio is 1.4-1.5, and the coal is 80-90t / h.

[0096] 2. The target function value of each particle is calculated; 3. Iteration is performed for 50 times, and the particle moves to the minimum value of the target function; 4. The particle corresponding to the minimum F is the final output parameter, and the optimal operation parameter is obtained.

[0097] When the effective scheduling sub-interval belongs to different load intervals, the calculation method will be adjusted, for example, in the priority scheduling load interval, the above calculation process will be followed to obtain the optimal operation parameter under rapid scheduling.

[0098] If in the normal load interval, the target function of the calculation will be solved after the out-of-range solution, and a plurality of iterations are additionally obtained, and the operation parameters that minimize the coal consumption are selected from the solving values of the parameters about the minimum coal consumption, to obtain the optimal operation parameter in the normal mode.

[0099] If in the transition load interval, the target function of the calculation will additionally select the load change rate when the particle swarm is initialized, and select the particle in the transition condition, for example, the particle with a load change rate ≤5% / min, and finally iterate the optimal operation parameter in the transition load interval.

[0100] As shown in Figure 5 The present application also provides a power plant wide load intelligent scheduling management system, which comprises a data acquisition module, a time delay analysis module, an interval judgment module, a delay identification module and a parameter output module; wherein the output end of the data acquisition module is connected with the time delay analysis module, the output end of the time delay analysis module is connected with the interval judgment module, the output end of the interval judgment module is connected with the delay identification module, and the output end of the delay identification module is connected with the parameter output module.

[0101] The data acquisition module is configured to continuously acquire the voltage signal of the high-voltage side when the dispatching instruction is executed, integrate the voltage signal with the operation parameters of each coal-fired unit, and form an input data set.

[0102] The time delay analysis module is configured to analyze each coal-fired unit in the input data set by using a time delay model, record the time delay time of each coal-fired unit, and obtain a time delay mapping relationship derived by the model at any time.

[0103] The interval judgment module is configured to determine effective dispatching subintervals in different load intervals by using the time delay mapping relationship and combining the regulation stability in different load intervals.

[0104] The delay identification module is configured to draw a multi-time delay change curve with the time stamp corresponding to the effective dispatching subinterval as the horizontal axis and the load value and the time delay time as the vertical axis, and determine the preparation delay time of each effective dispatching subinterval.

[0105] The parameter output module is configured to take the data corresponding to the effective dispatching subinterval and the preparation delay time as input, and solve the optimal operation parameters at each time.

[0106] Although the embodiments of the present application have been shown and described above, it should be understood that the above-described embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application, which are still covered by the protection scope of the present application.

Claims

1. A power plant wide load intelligent dispatching management method, characterized in that, Comprise: S1, when the scheduling instruction is executed, continuously collect the voltage signal of the high-voltage side, integrate the voltage signal with the operation parameters of each coal-fired unit to form an input data set; S2, analyze each coal-fired unit in the input data set using a time delay model, record the time delay time of each coal-fired unit, and obtain the time delay mapping relationship derived by the model at any time; The implementation mode of step S2 comprises: S21, according to the load interval corresponding to the input data set, record the time delay time of each coal-fired unit after the execution of the scheduling instruction; S22, when the data in the input data set changes, generate a multi-dimensional state vector with each changed input data as a variable; S23, use the multi-dimensional state vector to fit the time delay time and the load interval at any time, and determine the time delay mapping relationship between the input data set and the load interval according to the fitting mode of each load interval; According to the parameters corresponding to the multi-dimensional state vector, the multi-dimensional state vector and the load interval are used as inputs, and the time delay time is determined in the form of quadratic polynomial fitting; the fitting coefficients, time delay time, load interval and multi-dimensional state vector after fitting are regarded as the output time delay mapping relationship; S3, use the time delay mapping relationship to determine the effective scheduling sub-interval in different load intervals combined with the regulation stability under different load intervals; The implementation mode of step S3 comprises: S31, according to the actual load percentage value in the load interval, the load interval is divided into multiple load points; S32, call the value range and fluctuation amplitude of the time delay time corresponding to the load point, and judge the time delay controllability corresponding to each load point; S33, after the time delay controllability determination is completed, the constraint conditions corresponding to the load point are queried, and the regulation stability under the execution of the scheduling instruction is judged according to the data value of each load point at the corresponding time point; S34, the load point which passes the time delay controllability and regulation stability is regarded as an effective load point, and the continuous effective load points are combined to form the output effective scheduling sub-interval; S4, draw a multi-time delay change curve with the time stamp corresponding to the effective scheduling sub-interval as the horizontal axis and the load value and time delay time as the vertical axis, and determine the preparation delay time of each effective scheduling sub-interval; The implementation mode of step S4 comprises: S41, according to the multi-time delay change curve, the instruction issuing point, the output standard point and the time delay average of the effective scheduling sub-interval are obtained respectively as the key node list of the multi-time delay change curve; S42, based on the input key node list, determine the instruction window of each scheduling instruction issuing time, and determine whether the scheduling instruction before the current instruction window satisfies the merging condition according to the sending situation of each instruction window; S43, if the merging condition is satisfied, set the preparation delay time of the corresponding effective scheduling sub-interval with the merged instruction issuing point and output standard point; S44, if the merging condition is not satisfied, judge whether each scheduling instruction has been executed, and extract the instruction window length corresponding to the current scheduling instruction to output the preparation delay time; S5, take the data corresponding to the effective scheduling sub-interval and the preparation delay time as input, and solve the optimal operation parameters at each time.

2. The power plant wide load intelligent dispatching management method according to claim 1, characterized in that, The implementation mode of step S1 comprises: When the dispatching instruction is obtained, the dispatching instruction of each coal-fired unit is determined based on the operating parameters of each coal-fired unit; the active power under the current work is determined based on the voltage signal under the execution of the dispatching instruction, and the load interval of each coal-fired unit is recorded by the active power, and the value range of the load interval is synchronized to the input data set.

3. The power plant wide load intelligent dispatching management method according to claim 1, characterized in that, The implementation of step S22 includes: Based on the initial state of the input data set, an initial state vector is constructed; For each initial state vector, the parameter category corresponding to the initial state vector is determined; and the parameter combination under each parameter category is taken as a group of reference state vectors; The dimension and arrangement order corresponding to each reference state vector are obtained to obtain the output multi-dimensional state vector.

4. The power plant wide load intelligent dispatching management method according to claim 3, characterized in that, When the reference state vector is set, the implementation further includes: The real-time operating parameters of the coal-fired unit are taken as the operating state component; The operating parameters controlled by the dispatching instruction are taken as the instruction dispatching component; After the operating state component and the instruction dispatching component are spliced, the reference state vector is taken as the output.

5. The power plant wide load intelligent dispatching management method according to claim 4, characterized in that, The implementation of step S42 includes: For any instruction window, the merging condition of the current instruction window is determined; the dimension of the merging condition is based on the time lag mean deviation, the instruction window time sequence and the load change rate; When all the merging conditions are met, it is considered that the dispatching instruction before the current instruction window meets the merging condition.

6. The power plant wide load intelligent dispatching management method according to claim 1, characterized in that, The implementation of step S5 includes: S51, setting a target function for each effective dispatching sub-interval according to the objectives of minimizing coal consumption, minimizing output deviation and minimizing parameter fluctuation; S52, performing particle swarm solving according to the target function to determine the optimal operating parameters corresponding to the effective dispatching sub-interval.

7. A power plant wide load intelligent dispatching management system for performing the steps of a power plant wide load intelligent dispatching management method according to any one of claims 1-6, characterized in that, It includes: The data acquisition module is used to continuously acquire the voltage signal of the high-voltage side when the dispatching instruction is executed, integrate the voltage signal with the operating parameters of each coal-fired unit, and form an input data set; The time lag analysis module is used to analyze each coal-fired unit in the input data set by using the time lag model, record the time lag time of each coal-fired unit, and obtain the time lag mapping relationship derived by the model at any time; The interval judgment module is used to determine the effective dispatching sub-interval in different load intervals by using the time lag mapping relationship and combining the adjustment stability under different load intervals; The delay identification module is used to draw a multi-time lag change curve with the time stamp corresponding to the effective dispatching sub-interval as the horizontal axis and the load value and the time lag time as the vertical axis to determine the preparation delay time of each effective dispatching sub-interval; The parameter output module is used to take the data corresponding to the effective dispatching sub-interval and the preparation delay time as input to solve the optimal operating parameters at each time.

Images