Power dispatching method

Abstract

The invention relates to power dispatching, in particular to a power dispatching method, which comprises the following steps of: constructing a power system historical dispatching knowledge graph containing historical dispatching data and historical dispatching knowledge data; matching the scheduling data of the scheduling day with historical scheduling data to obtain a first similarity data set of the scheduling data; matching the scheduling text data of the scheduling day with historical scheduling knowledge data to obtain a second similarity data set of the scheduling text data; fusing the first similarity data set and the second similarity data set by taking a preset time length as a unit to obtain a fused similarity data set; matching data in the fusion similarity data set with historical scheduling knowledge data, fitting to obtain a power generation curve of a scheduling day, and regulating and controlling the power system according to the power generation curve; acquiring a voltage signal and a current signal of the transformer substation in real time, and calculating to obtain a power factor; according to the technical scheme provided by the invention, the defect that the power system is difficult to accurately and timely dispatch can be effectively overcome.

Description

Technical Field

[0001] The invention relates to electric power dispatching, and in particular to an electric power dispatching method. Background Art

[0002] Automated power dispatch refers to the use of automation technology and intelligent algorithms to realize the dispatch process of the power system, which involves real-time monitoring of the power system, data analysis and decision-making to achieve control and optimization of various parts of the power system.

[0003] In traditional power dispatching, manual monitoring, planning and control of the operation of various power equipment are required. This method has certain limitations, such as complex operation, slow response speed, and susceptibility to subjective factors. At the same time, traditional power dispatching methods rely more on the experience of dispatchers for dispatching, and may not be able to perform accurate dispatching when electricity demand changes. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides a power dispatching method, which can effectively overcome the defect of the prior art that it is difficult to accurately and timely dispatch the power system.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] A power dispatching method comprises the following steps:

[0009] S1. Construct a knowledge graph of historical dispatching of power system containing historical dispatching data and historical dispatching knowledge data;

[0010] S2. Match the dispatch data of the dispatch day with the historical dispatch data to obtain a first similarity data set of the dispatch data;

[0011] S3, matching the dispatch text data of the dispatch day with the historical dispatch knowledge data to obtain a second similarity data set of the dispatch text data;

[0012] S4, fusing the first similarity data set and the second similarity data set in units of a preset time length to obtain a fused similarity data set;

[0013] S5. Match the data in the fusion similarity data set with the historical dispatch knowledge data, and fit the power generation curve of the dispatch day, and regulate the power system according to the power generation curve;

[0014] S6. Collect the voltage signal and current signal of the substation in real time, calculate the power factor, and draw a power factor change curve;

[0015] S7. When the power factor changes in a downward trend, calculate the power factor change rate of the current period;

[0016] S8. When the power factor change rate is greater than a preset threshold, determine the three-phase reactive power difference value after a preset interval period;

[0017] S9. Control the reactive power compensation device to perform compensation operation according to the three-phase reactive power difference value.

[0018] Preferably, the power system historical dispatch knowledge graph containing historical dispatch data and historical dispatch knowledge data is constructed in S1, including:

[0019] S11, collecting historical dispatching data and historical dispatching knowledge data;

[0020] S12. Create entity nodes and attribute data of entity nodes using historical dispatch data and historical dispatch knowledge data, construct edge data according to the relationship of attribute data of entity nodes, and complete the construction of historical dispatch knowledge graph of power system;

[0021] S13. Use the graph database platform to store the power system historical dispatch knowledge graph in a graph structure.

[0022] Preferably, in S2, the scheduling data of the scheduling day is matched with the historical scheduling data to obtain a first similarity data set of scheduling data, including:

[0023] The dispatch data of the dispatch day is matched with the historical dispatch data by using cosine similarity to obtain a first similarity data set of the dispatch data;

[0024] Among them, historical dispatch data includes voltage, line power, load and generator output.

[0025] Preferably, in S3, the scheduling text data of the scheduling day is matched with the historical scheduling knowledge data to obtain a second similarity data set of the scheduling text data, including:

[0026] The language model-based retrieval method LMIR is used to match the scheduling text data of the scheduling day with the historical scheduling knowledge data to obtain a second similarity data set of the scheduling text data;

[0027] Among them, the historical dispatching knowledge data includes historical dispatching text data and power generation curves, and the historical dispatching text data includes power generation guidance policies, maintenance plans, dispatching logs and dispatching personnel operation methods.

[0028] Preferably, in S5, the data in the fused similarity data set is matched with the historical dispatch knowledge data, and the power generation curve of the dispatch day is fitted, and the power system is regulated according to the power generation curve, including:

[0029] S51, sorting the data in the fusion similarity data set from large to small according to the fusion similarity values, and selecting the fusion similarity values ​​of a preset number of days;

[0030] S52, selecting historical dispatching knowledge data of corresponding days from the historical dispatching knowledge data of the power system historical dispatching knowledge graph, and obtaining corresponding power generation curves one by one to obtain a power generation curve data set;

[0031] S53. Fit the power generation curve data set to obtain the power generation curve of the dispatching day, and regulate the power system according to the power generation curve.

[0032] Preferably, when the power factor change rate is greater than a preset threshold value in S8, determining the three-phase reactive power difference value after a preset interval period includes:

[0033] S81, constructing a three-dimensional correlation diagram according to the historical load types, historical load changes, and historical three-phase reactive power changes of the users under the substation;

[0034] S82, obtaining the load type, load change and three-phase reactive power value of the users under the substation in the current period, extracting the three-phase reactive power value after the preset interval period according to the three-dimensional association diagram, and calculating the initial value of the three-phase reactive power difference after the preset interval period;

[0035] S83. Determine a three-phase reactive power difference value after a preset interval period according to the initial value of the three-phase reactive power difference.

[0036] Preferably, determining the three-phase reactive power difference value after a preset interval period according to the three-phase reactive power difference initial value in S83 includes:

[0037] The product of the initial value of the three-phase reactive power difference and the prediction coefficient is used as the three-phase reactive power difference value after the preset interval period;

[0038] Among them, the prediction coefficient includes a preset reference coefficient and an equipment failure rate coefficient.

[0039] Preferably, in S9, controlling the reactive power compensation device to perform compensation operation according to the three-phase reactive power difference value includes:

[0040] The preset interval period is divided into n time intervals, and the three-phase reactive power difference value is divided into n equal parts. Before each time interval, the contactor is controlled to close and the capacitor corresponding to the n equal parts of the three-phase reactive power difference value is put into operation.

[0041] Preferably, in S9, controlling the reactive power compensation device to perform compensation operation according to the three-phase reactive power difference value includes:

[0042] After each time interval, the three-phase reactive power difference value at that moment is calculated. If it is equal to the three-phase reactive power difference value not put into operation, the contactor is controlled to close before each time interval. Otherwise, the three-dimensional correlation diagram is corrected according to the calculation result and returns to S8.

[0043] (III) Beneficial effects

[0044] Compared with the prior art, the power dispatching method provided by the present invention has the following advantages:

[0045] Beneficial effects:

[0046] 1) Construct a knowledge graph of historical dispatching of the power system including historical dispatching data and historical dispatching knowledge data, match the dispatching data of the dispatching day with the historical dispatching data to obtain a first similarity data set of the dispatching data, match the dispatching text data of the dispatching day with the historical dispatching knowledge data to obtain a second similarity data set of the dispatching text data, fuse the first similarity data set and the second similarity data set in units of a preset time length to obtain a fused similarity data set, match the data in the fused similarity data set with the historical dispatching knowledge data, and fit the power generation curve of the dispatching day, and regulate the power system according to the power generation curve, match the dispatching data and dispatching text data of the dispatching day with the historical data, and obtain the power generation curve data set from the historical dispatching knowledge data according to the matching results, obtain the power generation curve of the dispatching day by fitting the power generation curve data set, and regulate the power system according to the power generation curve, so as to realize the rapid dispatch of the power system;

[0047] 2) Collect the voltage and current signals of the substation in real time, calculate the power factor, and draw the power factor change curve. When the power factor change shows a downward trend, calculate the power factor change rate of the current period. When the power factor change rate is greater than the preset threshold, determine the three-phase reactive power difference value after the preset interval period, and control the reactive compensation device to perform compensation operation according to the three-phase reactive power difference value, thereby effectively avoiding the problem of increased line loss and line instability caused by the increase of power equipment during power dispatching, which is conducive to accurate dispatching of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 It is a schematic diagram of the process of the present invention;

[0050] Figure 2 A schematic diagram of a process for fitting a power generation curve on a dispatching day and regulating a power system according to the power generation curve in the present invention;

[0051] Figure 3 It is a flow chart of controlling the reactive power compensation device to perform compensation operation according to the three-phase reactive power difference value in the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] A power dispatching method, such as Figure 1 and Figure 2 As shown, S1, constructing a power system historical dispatch knowledge graph containing historical dispatch data and historical dispatch knowledge data, specifically including:

[0054] S11, collecting historical dispatching data and historical dispatching knowledge data;

[0055] S12. Create entity nodes and attribute data of entity nodes using historical dispatch data and historical dispatch knowledge data, construct edge data according to the relationship of attribute data of entity nodes, and complete the construction of historical dispatch knowledge graph of power system;

[0056] S13. Use the graph database platform to store the power system historical dispatch knowledge graph in a graph structure.

[0057] S2. Match the dispatch data of the dispatch day with the historical dispatch data to obtain a first similarity data set of dispatch data, specifically including:

[0058] The dispatch data of the dispatch day is matched with the historical dispatch data by using cosine similarity to obtain a first similarity data set of the dispatch data;

[0059] Among them, historical dispatch data includes voltage, line power, load and generator output.

[0060] S3, matching the dispatch text data of the dispatch day with the historical dispatch knowledge data to obtain a second similarity data set of the dispatch text data, specifically including:

[0061] The language model-based retrieval method LMIR is used to match the scheduling text data of the scheduling day with the historical scheduling knowledge data to obtain a second similarity data set of the scheduling text data;

[0062] Among them, the historical dispatching knowledge data includes historical dispatching text data and power generation curves, and the historical dispatching text data includes power generation guidance policies, maintenance plans, dispatching logs and dispatching personnel operation methods.

[0063] S4. The first similarity dataset and the second similarity dataset are merged in units of a preset time length to obtain a merged similarity dataset.

[0064] S5. Match the data in the fusion similarity data set with the historical dispatch knowledge data, and fit the power generation curve of the dispatch day, and regulate the power system according to the power generation curve, including:

[0065] S51, sorting the data in the fusion similarity data set from large to small according to the fusion similarity values, and selecting the fusion similarity values ​​of a preset number of days;

[0066] S52, selecting historical dispatching knowledge data of corresponding days from the historical dispatching knowledge data of the power system historical dispatching knowledge graph, and obtaining corresponding power generation curves one by one to obtain a power generation curve data set;

[0067] S53. Fit the power generation curve data set to obtain the power generation curve of the dispatching day, and regulate the power system according to the power generation curve.

[0068] The above technical scheme constructs a power system historical dispatching knowledge graph including historical dispatching data and historical dispatching knowledge data, matches the dispatching data of the dispatching day with the historical dispatching data to obtain a first similarity data set of the dispatching data, matches the dispatching text data of the dispatching day with the historical dispatching knowledge data to obtain a second similarity data set of the dispatching text data, fuses the first similarity data set and the second similarity data set in units of a preset time length to obtain a fused similarity data set, matches the data in the fused similarity data set with the historical dispatching knowledge data, and fits the power generation curve of the dispatching day, regulates the power system according to the power generation curve, matches the dispatching data and the dispatching text data of the dispatching day with the historical data, and obtains the power generation curve data set from the historical dispatching knowledge data according to the matching results, obtains the power generation curve of the dispatching day by fitting the power generation curve data set, and regulates the power system according to the power generation curve, thereby enabling rapid dispatch of the power system.

[0069] like Figure 1 and Figure 3 As shown, S6, the voltage signal and current signal of the substation are collected in real time, the power factor is calculated, and a power factor change curve is drawn.

[0070] S7. When the power factor change shows a downward trend, calculate the power factor change rate of the current period.

[0071] S8. When the power factor change rate is greater than a preset threshold, determine the three-phase reactive power difference value after a preset interval period, specifically including:

[0072] S81, constructing a three-dimensional correlation diagram according to the historical load types, historical load changes, and historical three-phase reactive power changes of the users under the substation;

[0073] S82, obtaining the load type, load change and three-phase reactive power value of the users under the substation in the current period, extracting the three-phase reactive power value after the preset interval period according to the three-dimensional association diagram, and calculating the initial value of the three-phase reactive power difference after the preset interval period;

[0074] S83. Determine a three-phase reactive power difference value after a preset interval period according to the initial value of the three-phase reactive power difference.

[0075] Specifically, in S83, determining the three-phase reactive power difference value after a preset interval period according to the initial value of the three-phase reactive power difference includes:

[0076] The product of the initial value of the three-phase reactive power difference and the prediction coefficient is used as the three-phase reactive power difference value after the preset interval period;

[0077] Among them, the prediction coefficient includes a preset reference coefficient and an equipment failure rate coefficient.

[0078] S9, controlling the reactive power compensation device to perform compensation operation according to the three-phase reactive power difference value, specifically including:

[0079] Divide the preset interval into n time intervals, and divide the three-phase reactive power difference value into n equal parts, control the contactor to close before each time interval, and put into operation the capacitor corresponding to the n equal parts of the three-phase reactive power difference value;

[0080] After each time interval, the three-phase reactive power difference value at that moment is calculated. If it is equal to the three-phase reactive power difference value not put into operation, the contactor is controlled to close before each time interval. Otherwise, the three-dimensional correlation diagram is corrected according to the calculation result and returns to S8.

[0081] The above technical scheme collects the voltage signal and current signal of the substation in real time, calculates the power factor, and draws the power factor change curve. When the power factor change shows a downward trend, the power factor change rate of the current period is calculated. When the power factor change rate is greater than the preset threshold, the three-phase reactive power difference value after the preset interval period is determined, and the reactive compensation device is controlled to perform compensation operation according to the three-phase reactive power difference value, thereby effectively avoiding the problems of increased line loss and line instability caused by the increase of power equipment during the power dispatching process, which is helpful for accurate dispatching of the power system.

[0082] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will 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 power dispatching method, characterized in that: The following steps are involved: S1. Construct a knowledge graph of historical dispatching of power system containing historical dispatching data and historical dispatching knowledge data; S2. Match the dispatch data of the dispatch day with the historical dispatch data to obtain a first similarity data set of the dispatch data; S3, matching the dispatch text data of the dispatch day with the historical dispatch knowledge data to obtain a second similarity data set of the dispatch text data; S4, fusing the first similarity data set and the second similarity data set in units of a preset time length to obtain a fused similarity data set; S5. Match the data in the fusion similarity data set with the historical dispatch knowledge data, and fit the power generation curve of the dispatch day, and regulate the power system according to the power generation curve; S6. Collect the voltage signal and current signal of the substation in real time, calculate the power factor, and draw a power factor change curve; S7. When the power factor changes in a downward trend, calculate the power factor change rate of the current period; S8. When the power factor change rate is greater than a preset threshold, determine the three-phase reactive power difference value after a preset interval period; S9. Control the reactive power compensation device to perform compensation operation according to the three-phase reactive power difference value.

2. The power dispatching method according to claim 1, characterized in that: In S1, a knowledge graph of power system historical dispatching containing historical dispatching data and historical dispatching knowledge data is constructed, including: S11, collecting historical dispatching data and historical dispatching knowledge data; S12. Create entity nodes and attribute data of entity nodes using historical dispatch data and historical dispatch knowledge data, construct edge data according to the relationship of attribute data of entity nodes, and complete the construction of historical dispatch knowledge graph of power system; S13. Use the graph database platform to store the power system historical dispatch knowledge graph in a graph structure.

3. The power dispatching method according to claim 2, characterized in that: In S2, the dispatch data of the dispatch day is matched with the historical dispatch data to obtain a first similarity data set of dispatch data, including: The dispatch data of the dispatch day is matched with the historical dispatch data by using cosine similarity to obtain a first similarity data set of the dispatch data; Among them, historical dispatch data includes voltage, line power, load and generator output.

4. The power dispatching method according to claim 3, characterized in that: In S3, the dispatch text data of the dispatch day is matched with the historical dispatch knowledge data to obtain a second similarity data set of the dispatch text data, including: The language model-based retrieval method LMIR is used to match the scheduling text data of the scheduling day with the historical scheduling knowledge data to obtain a second similarity data set of the scheduling text data; Among them, the historical dispatching knowledge data includes historical dispatching text data and power generation curves, and the historical dispatching text data includes power generation guidance policies, maintenance plans, dispatching logs and dispatching personnel operation methods.

5. The power dispatching method according to claim 4, characterized in that: In S5, the data in the fusion similarity data set is matched with the historical dispatch knowledge data, and the power generation curve of the dispatch day is fitted, and the power system is regulated according to the power generation curve, including: S51, sorting the data in the fusion similarity data set from large to small according to the fusion similarity values, and selecting the fusion similarity values ​​of a preset number of days; S52, selecting historical dispatching knowledge data of corresponding days from the historical dispatching knowledge data of the power system historical dispatching knowledge graph, and obtaining corresponding power generation curves one by one to obtain a power generation curve data set; S53. Fit the power generation curve data set to obtain the power generation curve of the dispatching day, and regulate the power system according to the power generation curve.

6. The power dispatching method according to claim 1, characterized in that: In S8, when the power factor change rate is greater than a preset threshold, determining a three-phase reactive power difference value after a preset interval period includes: S81, constructing a three-dimensional correlation diagram according to the historical load types, historical load changes, and historical three-phase reactive power changes of the users under the substation; S82, obtaining the load type, load change and three-phase reactive power value of the users under the substation in the current period, extracting the three-phase reactive power value after the preset interval period according to the three-dimensional association diagram, and calculating the initial value of the three-phase reactive power difference after the preset interval period; S83. Determine a three-phase reactive power difference value after a preset interval period according to the initial value of the three-phase reactive power difference.

7. The power dispatching method according to claim 6, characterized in that: In S83, the three-phase reactive power difference value after the preset interval period is determined according to the initial value of the three-phase reactive power difference, including: The product of the initial value of the three-phase reactive power difference and the prediction coefficient is used as the three-phase reactive power difference value after the preset interval period; Among them, the prediction coefficient includes a preset reference coefficient and an equipment failure rate coefficient.

8. The power dispatching method according to claim 6, characterized in that: In S9, the reactive power compensation device is controlled to perform compensation operation according to the three-phase reactive power difference value, including: The preset interval period is divided into n time intervals, and the three-phase reactive power difference value is divided into n equal parts. Before each time interval, the contactor is controlled to close and the capacitor corresponding to the n equal parts of the three-phase reactive power difference value is put into operation.

9. The power dispatching method according to claim 8, characterized in that: In S9, the reactive power compensation device is controlled to perform compensation operation according to the three-phase reactive power difference value, including: After each time interval, the three-phase reactive power difference value at that moment is calculated. If it is equal to the three-phase reactive power difference value not put into operation, the contactor is controlled to close before each time interval. Otherwise, the three-dimensional correlation diagram is corrected according to the calculation result and returns to S8.

Images