Voltage control method based on tidal current bidirectional line voltage regulator and related device

Abstract

The invention relates to the technical field of data processing, and discloses a voltage control method based on a power flow bidirectional line voltage regulator and a related device, and the method comprises the steps: obtaining transformer area voltage historical data from a power distribution automation system; performing conversion processing on the transformer area voltage historical data to obtain a voltage time sequence; performing line voltage regulator day-ahead prediction on the voltage time sequence based on a long short-term memory neural network to obtain a transformer area voltage prediction value; performing phase difference calculation according to the transformer area voltage predicted value to obtain a target phase difference; judging a tidal current direction based on the target phase difference to obtain a target tidal current direction; and determining a line voltage regulator control strategy according to the target power flow direction and the power flow node voltage. By implementing the method provided by the invention, the accuracy of the line voltage regulator in the active power distribution application can be effectively improved, and the line voltage regulator can adapt to the flexible change of the tidal current direction while the operation reliability of the line voltage regulator is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a voltage control method based on a power flow bidirectional line voltage regulator and a related device. Background Art

[0002] Voltage compliance is one of the important levels for assessing the services of the power sector. The "voltage over-limit problem" of abnormal power supply voltage will reduce the efficiency of power supply and use equipment, endanger the safe and economic operation of the power grid, and cause some household appliances to be unable to be used normally, seriously affecting the production and life of residents. The feeder / line voltage regulator can change the voltage ratio without power outage, suppress the voltage fluctuation range, and ensure the continuity of power supply. In recent years, some technologies have introduced auxiliary coil design, power electronic switches and other technologies into on-load voltage regulation equipment, and also proposed to use hybrid solutions such as hybrid voltage regulation transformers and reactive power compensators to improve the voltage management effect. Despite this, the mainstream of voltage over-limit management in distribution networks is still on-load voltage regulation transformers based on mechanical switch switching, and the improvement of their performance still has important industrial value and wide application space. Therefore, how to improve the accuracy of line voltage regulators in active power distribution applications has become a problem that needs to be solved urgently. Summary of the invention

[0003] The present invention provides a voltage control method based on a power flow bidirectional line voltage regulator and a related device to solve the technical problem of how to improve the accuracy of the line voltage regulator in active power distribution applications.

[0004] In a first aspect, a voltage control method based on a power flow bidirectional line voltage regulator is provided, comprising:

[0005] Obtain historical data of substation voltage from the distribution automation system;

[0006] The historical data of the transformer area voltage is transformed and processed to obtain the voltage time series;

[0007] Based on the long short-term memory neural network, the line voltage regulator is predicted for the voltage time series to obtain the predicted value of the substation voltage.

[0008] According to the predicted value of the transformer area voltage, the phase difference is calculated to obtain the target phase difference;

[0009] Based on the target phase difference, the tidal current direction is determined to obtain the target tidal current direction;

[0010] The line voltage regulator control strategy is determined according to the target power flow direction and power flow node voltage.

[0011] In a second aspect, a voltage control device based on a power flow bidirectional line voltage regulator is provided, comprising:

[0012] An acquisition module is used to obtain historical data of the substation voltage from the distribution automation system;

[0013] The first processing module is used to convert the historical data of the transformer area voltage to obtain a voltage time series;

[0014] The second processing module is used to perform a day-ahead prediction of the line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a predicted value of the transformer area voltage;

[0015] The third processing module is used to calculate the phase difference according to the predicted value of the transformer area voltage to obtain the target phase difference;

[0016] A fourth processing module is used to determine the tidal current direction based on the target phase difference and obtain the target tidal current direction;

[0017] The determination module is used to determine the line voltage regulator control strategy according to the target power flow direction and the power flow node voltage.

[0018] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the voltage control method based on a power flow bidirectional line voltage regulator when executing the computer program.

[0019] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the voltage control method based on the power flow bidirectional line voltage regulator are implemented.

[0020] In the scheme implemented by the voltage control method and related devices based on the above-mentioned flow bidirectional line voltage regulator, the historical data of the substation voltage is obtained from the distribution automation system to further transform and process the historical data of the substation voltage to obtain a voltage time series, and the voltage time series is predicted by the line voltage regulator based on the long short-term memory neural network to obtain the substation voltage prediction value, and the phase difference is calculated based on the substation voltage prediction value to obtain the target phase difference, so that the flow direction can be judged based on the target phase difference to obtain the target flow direction, and then the line voltage regulator control strategy can be determined based on the target flow direction and the flow node voltage, which can improve the accuracy of the line voltage regulator in active distribution applications, and is conducive to improving the operating reliability of the line voltage regulator while enabling the line voltage regulator to adapt to flexible changes in the flow direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0022] Figure 1 1 is a schematic diagram of an application environment of a voltage control method based on a power flow bidirectional line voltage regulator in one embodiment of the present invention;

[0023] Figure 2 It is a flow chart of a voltage control method based on a power flow bidirectional line voltage regulator in one embodiment of the present invention;

[0024] Figure 3 is a single-line principle schematic diagram of an existing line voltage regulator in one embodiment of the present invention;

[0025] Figure 4 is a circuit diagram of a power flow bidirectional line voltage regulator according to an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of the voltage control effect based on the power flow bidirectional line voltage regulator in one embodiment of the present invention;

[0027] Figure 6 It is a structural schematic diagram of a voltage control device based on a power flow bidirectional line voltage regulator in one embodiment of the present invention;

[0028] Figure 7 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0029] Figure 8 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0031] With the access of a large number of distributed photovoltaic, electric vehicle charging piles, energy storage devices, etc. to the distribution network, the source-load interaction in the distribution network area is more frequent, and the network flow is more complex, resulting in more serious and frequent voltage limit problems at the distribution network nodes. When using the line voltage regulator based on the existing technology route, it is necessary to clarify the "power side" and "load side" and can only adapt to a single flow direction; in addition, for economic considerations, the existing technology generally uses on-load switches to achieve switching between operating gears. According to the discrete characteristics of its output voltage, the line voltage regulator often adopts a table-lookup control method, forming a regulation strategy such as the "Nine-square Diagram".

[0032] The control modes of line voltage regulators are divided into: a local control mode based on local voltage measurement information, which adopts the adjustment strategy described above, and a remote dispatch mode that relies on the distribution automation system. In the remote dispatch mode, the automation system calculates the dispatch instructions for the voltage regulation gear. This mode can identify changes in network topology, line length, etc., and has system optimization capabilities. However, with the development of the target substations, the time required for calculation and the risk of dimensional disasters continue to increase. The introduction of artificial intelligence algorithms is expected to solve this dilemma, but the existing algorithms focus on load forecasting and state prediction. It is still necessary to calculate the dispatch instructions for the voltage regulator gear through power flow calculation and optimization scheduling algorithms, and the calculation accuracy is seriously affected by the modeling level.

[0033] At the equipment level, the line voltage regulator can only adjust one gear at a time, and due to the life of its mechanical switch, it has a maximum daily adjustment limit (generally 6 to 10 times), so its voltage management response speed is often in the order of minutes or even hours. When the voltage in the active distribution network area fluctuates greatly, this feature can easily lead to failure of voltage regulation response or a reduction in the life of the voltage regulator switch under continuous operation.

[0034] In view of the above problems, the present invention proposes an improvement in the configuration method and control method of a line voltage regulator, which can adjust the layout of circuit breakers and voltage transformers, improve the operational reliability of the existing line voltage regulator, and enable the line voltage regulator to adapt to the flexible changes in the flow direction. At the same time, a data-driven voltage regulation prediction algorithm is proposed, which can comprehensively improve the control speed and accuracy of the line voltage regulator in active power distribution applications.

[0035] The voltage control method based on the power flow bidirectional line voltage regulator provided by the embodiment of the present invention can be applied in the following aspects: Figure 1In an application environment, the client communicates with the server through a network. Exemplarily, taking the medical and health scenario as an example, the target user (such as R&D personnel or management personnel) can upload the historical data of the substation voltage through the client. Accordingly, the server can obtain the historical data of the substation voltage through the client, so as to further transform and process the historical data of the substation voltage to obtain a voltage time series, and perform a day-ahead prediction of the line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a substation voltage prediction value, and perform a phase difference calculation based on the substation voltage prediction value to obtain a target phase difference, so that the flow direction can be judged based on the target phase difference, and the target flow direction can be obtained, and then the line voltage regulator control strategy can be determined based on the target flow direction and the flow node voltage, and the line voltage regulator control strategy can be fed back to the client. Accordingly, the client can receive the line voltage regulator control strategy from the server, and can display the line voltage regulator control strategy on the client for the target user to query or browse. By adopting the voltage control method based on the power flow bidirectional line voltage regulator provided in the present application, the accuracy of the line voltage regulator in active power distribution applications can be effectively improved, which is beneficial to improving the operating reliability of the line voltage regulator while enabling the line voltage regulator to adapt to flexible changes in power flow direction.

[0036] The client may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0037] See also Figure 2 As shown, Figure 2 A flow chart of a voltage control method based on a power flow bidirectional line voltage regulator provided in an embodiment of the present invention includes the following steps:

[0038] S10: Obtain historical data of the substation voltage from the distribution automation system.

[0039] The distribution automation system can provide rich operation data. The historical data of the substation voltage can be the data provided by the distribution automation system, which may include but is not limited to voltage data, such as phase voltage data, line voltage data and voltage fluctuation data; time data, such as timestamp and periodic data; operation-related data, such as load data, current data and power factor data; fault data, such as voltage over-limit data and power outage data, etc., which are not limited in this application.

[0040] It is understandable that the substation voltage history data may include the status of the substation voltage at different times in the past, providing material for subsequent analysis and prediction.

[0041] S20: converting the historical data of the substation voltage to obtain a voltage time series.

[0042] The server can obtain the historical data of the substation voltage from the distribution automation system, and further convert it into a voltage time series with a length of n. The specific representation can be as follows:

[0043] U=[u1,u2,...u t ,...u n ],

[0044] Among them, U is the voltage time series; u1 is the voltage value of the substation at time 1; u2 is the voltage value of the substation at time 2; u t is the voltage value of the substation at time t; u n is the voltage value of the substation at time n.

[0045] It is understandable that the voltage time series can better reflect the change pattern of voltage over time. By converting discrete historical data into a time series, it is convenient for subsequent mathematical modeling and analysis.

[0046] S30: Based on the long short-term memory neural network, the line voltage regulator is predicted for the voltage time series to obtain a predicted value of the substation voltage.

[0047] Among them, the Long Short-Term Memory (LSTM) neural network is suitable for processing time series data, especially when processing data with long-term dependencies. In the power system, the change of voltage may be affected by many factors and there is a certain time correlation. LSTM can effectively capture these characteristics, thereby making a more accurate prediction of the future substation voltage.

[0048] It should be understood that, based on the long short-term memory neural network, performing a day-ahead prediction of the line voltage regulator on the voltage time series to obtain a predicted value of the substation voltage refers to the process of performing a day-ahead prediction of the line voltage regulator. Among them, step S20, that is, based on the long short-term memory neural network, performing a day-ahead prediction of the line voltage regulator on the voltage time series to obtain a predicted value of the substation voltage, includes the following steps:

[0049] S21: Decomposing the voltage time series by using a time series algorithm to obtain a trend subsequence of voltage daily changes, a periodic subsequence of voltage regularity changes, and a residual subsequence of voltage mutations;

[0050] S22: Based on the long short-term memory neural network, a voltage prediction model for the substation area is constructed and obtained;

[0051] S23: using the substation voltage prediction model, and obtaining a trend prediction subsequence and a residual prediction subsequence according to the trend subsequence and the residual subsequence;

[0052] S24: Determine a predicted value of the substation voltage according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence.

[0053] The server can use a time series algorithm (or multiple time series algorithms) to decompose the voltage data into: a trend part U representing the daily change of voltage trend (t), which is the trend subsequence mentioned above; the periodic part U representing the regular change of voltage season (t), which is the above periodic subsequence; the residual part U representing the voltage mutation remainder (t), which is the above residual subsequence.

[0054] The server can be based on the trend subsequence U trend (t) and the residual subsequence U remainder (t), establish the area voltage prediction model. The specific formula can be as follows:

[0055] x trend =[time,U trend (t),U trend,max ,U trend,min ]

[0056] x remainder =[time,U remainder (t),U remainder,max ,U remainder,min ]

[0057] Among them, x trend is the trend prediction model; time is the time variable; U trend (t) is the trend subsequence; U trend,max is the maximum value of voltage in the trend subsequence; U trend,min is the minimum value of voltage in the trend subsequence; x remainder is the residual prediction model; U remainder (t) is the residual subsequence; U remainder,max is the maximum value of the voltage in the residual subsequence; U remainder,min is the minimum value of the voltage in the residual subsequence.

[0058] The server can further input them into the long short-term memory neural network to obtain the corresponding prediction quantity, that is, the trend prediction subsequence and the residual prediction subsequence

[0059] Optionally, the server can implement the step of determining the predicted value of the transformer area voltage according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence by the following formula. Exemplarily, at time t, the predicted value of the transformer area voltage is synthesized:

[0060]

[0061] Wherein, U(t) is the predicted value of the voltage in the substation area; U season (t) is the periodic subsequence; predicting a subsequence for said trend; is the residual prediction subsequence.

[0062] Furthermore, the server may output the predicted value to the line voltage regulator control strategy to obtain a corresponding gear position instruction.

[0063] The server can decompose the time series to obtain the trend part, the cycle part and the residual part, and then predict the trend part and the residual part based on LSTM, so as to further synthesize the predicted value of the substation voltage. The server can determine the voltage regulation strategy of the line voltage regulator and generate a day-ahead voltage regulation plan. Optionally, the server can make a cross-gear voltage regulation condition judgment to determine whether there is a cross-gear voltage regulation condition. If so (yes), the gear instruction is revised from the cross-gear voltage regulation moment forward; if not (no), the process ends directly.

[0064] Optionally, the present application proposes an improvement in the voltage regulator control strategy based on the voltage prediction: 1. Add time judgment. According to the time series, when it is predicted that the voltage crosses the threshold and lasts for a certain period of time, an action is executed, otherwise no action is executed; 2. According to the voltage regulator gear predicted by the day before, the time t when the adjacent gear adjustment needs to be crossed is determined. surge , according to the number of gears n that need to be crossed, from time t surge -n, correct the gear position command.

[0065] S40: Calculate the phase difference according to the predicted value of the substation voltage to obtain a target phase difference.

[0066] After obtaining the predicted voltage value of the substation, the relevant voltage reference phasor is selected and compared with the predicted voltage phasor of another phase or multiple phases. The phase difference between the two on the time axis is calculated through a specific mathematical algorithm. This is the target phase difference obtained. This phase difference can provide a key basis for subsequent analysis of the power system operation status such as determining the direction of the power flow.

[0067] It is understandable that phase difference is an important basis for determining the direction of power flow. By calculating the phase difference of voltage, we can further understand the power flow in the power system.

[0068] S50: Based on the target phase difference, determine the tidal current direction to obtain the target tidal current direction.

[0069] Based on the calculated target phase difference, when the phase difference presents a specific numerical characteristic, if the current phase leads the voltage phase, the flow direction is determined to be forward, that is, flowing from the power source to the load; if the current phase lags the voltage phase, the flow direction is determined to be reverse, that is, flowing from the load to the power source. In this way, the target flow direction is clarified, thereby providing key guiding information for the operation control and decision-making of the power system.

[0070] It is understandable that the flow direction is crucial to the control of the line voltage regulator; in a bidirectional flow scenario, accurate judgment of the flow direction can help the voltage regulator make correct regulation actions.

[0071] S60: Determine a line voltage regulator control strategy according to the target power flow direction and power flow node voltage.

[0072] By comprehensively considering the power flow direction and node voltage, a reasonable line voltage regulator control strategy can be formulated. For example, when the power flow direction is forward and the node voltage is too high, a voltage reduction strategy can be adopted; when the power flow direction is reverse and the node voltage is too low, a voltage increase strategy can be adopted.

[0073] It should be understood that determining the line voltage regulator control strategy according to the target power flow direction and the power flow node voltage refers to the process of how to determine the line voltage regulator control strategy. Among them, step S60, that is, determining the line voltage regulator control strategy according to the target power flow direction and the power flow node voltage, includes the following steps:

[0074] S61: Analyze the operation status of the power grid according to the target power flow direction and the power flow node voltage to obtain an operation status data set;

[0075] S62: Determine a line voltage regulator control strategy according to the operating status data set and the target power flow direction;

[0076] Among them, the step of determining the line voltage regulator control strategy according to the operating status data set and the target power flow direction is realized by a power flow bidirectional line voltage regulator circuit:

[0077] The power flow bidirectional line voltage regulator circuit comprises: a first isolating switch group, a second isolating switch group, a third isolating switch group, a first circuit breaker group, a second circuit breaker group, a third circuit breaker group, a first voltage transformer group, a second voltage transformer group, a first current transformer and a third current transformer, wherein:

[0078] On the grid side of the first isolating switch group, the first circuit breaker group is configured; on the grid side of the first circuit breaker group, the first voltage transformer group is added; on the grid side of the second isolating switch group, the second circuit breaker group is configured; on the grid side of the second circuit breaker group, the second voltage transformer group is added; the first current transformer is configured in the short-circuit switch group of the line voltage regulator (i.e., the first circuit breaker group + the first isolating switch group); and the third current transformer is configured in the bypass switch group of the line voltage regulator (i.e., the third circuit breaker group + the third isolating switch group).

[0079] For example, Figure 3 As shown, Figure 3 The single-line schematic diagram of the existing line voltage regulator is shown as an example. The existing line voltage regulator can carry out voltage management of the distribution network without affecting the main structure of the distribution system. Figure 3 As shown, TB is an autovoltage regulator, DL is a circuit breaker, G is an isolating switch, MOA is a lightning arrester, PT is a voltage transformer, and TA is a current transformer.

[0080] For example, Figure 4 As shown, Figure 4 The circuit schematic diagram of the power flow bidirectional line voltage regulator provided by the embodiment of the present solution is exemplarily shown, which can be used to adapt to the on-load voltage regulation in the bidirectional power flow scenario. Figure 4 As shown, the first circuit breaker group DL1 is configured on the grid side of the first isolating switch group G1; the first voltage transformer group PT1 is added on the grid side of the first circuit breaker group DL1 to measure the voltage of two phases in the three-phase electricity and supply power to the secondary system of the line voltage regulator; the second circuit breaker group DL2 is configured on the grid side of the second isolating switch group G2; the second voltage transformer group PT2 is added on the grid side of the second circuit breaker group DL2 to measure the voltage of two phases in the three-phase electricity and supply power to the secondary system of the line voltage regulator; the first current transformer TA1 is configured in the short-circuit switch group of the line voltage regulator (i.e., the first circuit breaker group DL1 + the first isolating switch group G1); the third current transformer TA3 is configured in the bypass switch group of the line voltage regulator (i.e., the third circuit breaker group DL3 + the third isolating switch group G3). The third current transformer is installed in a single-phase system without voltage transformers PT1 and PT2 to measure the current flowing through the phase.

[0081] It can be understood that the power flow bidirectional line voltage regulator circuit provided in the embodiment of the present solution can be used to realize the function of the line voltage regulator, and can perform voltage management of the distribution network without affecting the main structure of the distribution system.

[0082] It should be understood that determining the line voltage regulator control strategy based on the operating status data set and the target flow direction refers to the process of determining a specific line voltage regulator control strategy. Among them, step S62, that is, determining the line voltage regulator control strategy based on the operating status data set and the target flow direction, includes the following steps:

[0083] S621: If the operating status data set indicates that the voltage exceeds the limit, determine the target voltage exceeds the limit according to the upper limit range and the lower limit range;

[0084] S622: If the target voltage over-limit condition indicates that the voltage exceeds the lower limit, obtaining a target power flow direction;

[0085] S623: If the target flow direction indicates that the flow direction is forward, determining a gear adjustment parameter of the line voltage regulator;

[0086] S624: generating a gear adjustment instruction according to the gear adjustment parameter;

[0087] S625: Determine a line voltage regulator control strategy according to the gear adjustment instruction;

[0088] S626: If the target voltage over-limit condition indicates that the voltage exceeds the upper limit, and the power flow direction is positive, determining that the gear adjustment parameter is a downshift parameter;

[0089] S627: If the target voltage over-limit condition indicates that the voltage exceeds the upper limit, and the power flow direction is negative, then determining that the gear adjustment parameter is an up-shift parameter.

[0090] The server can determine the flow direction of the power flow by methods such as phase difference calculation, which can usually be divided into forward (flowing from the power supply side to the load side) and reverse (flowing from the load side to the power supply side). The server can further focus on the voltage value at the node, which can usually be the control node of the line voltage regulator. The server can judge the current operating status of the power grid based on the power flow direction and node voltage, such as whether there is a voltage over-limit (too high or too low), whether the power flow is within a reasonable range, etc.

[0091] Exemplarily, the server can read the current voltage and current data as the basis for subsequent calculations and judgments; calculate the phase difference based on the read voltage and current data to further determine the direction of the flow; after calculating the phase difference, the node voltage into which the flow flows can be selected as the control target to determine the voltage node that needs to be controlled.

[0092] Next, the server can determine whether the voltage of the control target exceeds the set upper and lower limits. At this time, there are two judgment branches: if the voltage exceeds the lower limit, further determine whether the flow direction is positive; if it is positive, perform an upshift operation, if it is reverse, perform a downshift operation; if the voltage exceeds the upper limit, further determine whether the flow direction is positive; if it is positive, perform a downshift operation, if it is reverse, perform an upshift operation. Optionally, if the voltage is within the normal range, no gear adjustment is performed.

[0093] Furthermore, the server may output a corresponding gear adjustment instruction according to the above judgment result.

[0094] It should be noted that when the voltage exceeds the lower limit, downshifting can reduce the output voltage of the voltage regulator to adapt to the lower voltage demand and avoid the impact of low voltage on user equipment. Upshifting can increase the output voltage of the voltage regulator to increase the low node voltage.

[0095] When the voltage exceeds the upper limit, the upshift can increase the output voltage of the voltage regulator, further reducing the voltage flowing to the load side to avoid excessive voltage. Downshift can reduce the output voltage of the voltage regulator to reduce the excessive node voltage. If the node voltage is within the normal range, regardless of the flow direction, the line voltage regulator keeps the current gear unchanged to maintain the current stable voltage output.

[0096] The corresponding line voltage regulator gear adjustment instructions may include instructions for upshifting, downshifting or keeping unchanged. The control instructions are sent to the control system of the line voltage regulator, and the line voltage regulator performs corresponding operations to adjust the voltage and ensure that the grid voltage is stable within a reasonable range.

[0097] For example, Figure 5 As shown, the solution proposed in this application can be used in the scenario of bidirectional change of power flow, and can reduce the amount of current sensors used. This application predicts the node voltage in the substation for the remote scheduling mode, and then directly generates scheduling instructions to improve the timeliness of the substation low voltage management instructions. Furthermore, in the input data processing link of the prediction algorithm, a time series algorithm is used to obtain multiple subsequences with more regularity, thereby improving the accuracy of the subsequent data prediction link.

[0098] The present application also proposes an improvement in the voltage regulation strategy. Based on the characteristic limitations of gear adjustment, the predicted gear command is corrected. Under conditions where gear adjustment needs to be skipped, action is taken in advance to increase the response speed, avoid missing the optimal voltage regulation time or erroneous operation, ensure the minimum switching action within the day, and achieve a balance between the life of the voltage regulator and the voltage regulation effect.

[0099] It can be seen that in the above scheme, the service end obtains the historical data of the substation voltage from the distribution automation system to further transform and process the historical data of the substation voltage to obtain a voltage time series, and based on the long short-term memory neural network, performs a day-ahead prediction of the line voltage regulator on the voltage time series to obtain a substation voltage prediction value, and performs a phase difference calculation based on the substation voltage prediction value to obtain a target phase difference, so that the flow direction can be judged based on the target phase difference to obtain the target flow direction, and then the line voltage regulator control strategy can be determined based on the target flow direction and the flow node voltage, which can improve the accuracy of the line voltage regulator in active distribution applications, and is beneficial to improving the operating reliability of the line voltage regulator while enabling the line voltage regulator to adapt to flexible changes in the flow direction.

[0100] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0101] In one embodiment, a voltage control device based on a power flow bidirectional line voltage regulator is provided, and the voltage control device based on a power flow bidirectional line voltage regulator corresponds one-to-one to the voltage control method based on a power flow bidirectional line voltage regulator in the above embodiment. Figure 6 As shown, the voltage control device based on the power flow bidirectional line voltage regulator includes an acquisition module 101, a determination module 102 and a processing module 103. The detailed description of each functional module is as follows:

[0102] The acquisition module 101 is used to acquire the historical data of the voltage in the substation from the distribution automation system;

[0103] The first processing module 102 is used to convert the historical data of the transformer area voltage to obtain a voltage time series;

[0104] The second processing module 103 is used to perform a day-ahead prediction of the line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a predicted value of the transformer area voltage;

[0105] The third processing module 104 is used to calculate the phase difference according to the predicted value of the transformer area voltage to obtain a target phase difference;

[0106] A fourth processing module 105 is used to determine the tidal current direction based on the target phase difference and obtain a target tidal current direction;

[0107] The determination module 106 is used to determine a line voltage regulator control strategy according to the target power flow direction and the power flow node voltage.

[0108] In one embodiment, the second processing module 103 is used to perform a day-ahead prediction of the line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a predicted value of the transformer area voltage, specifically for:

[0109] Decomposing the voltage time series by using a time series algorithm to obtain a trend subsequence of voltage daily changes, a periodic subsequence of voltage regularity changes, and a residual subsequence of voltage mutations;

[0110] Based on the long short-term memory neural network, the transformer area voltage prediction model is constructed and obtained;

[0111] Using the substation voltage prediction model, according to the trend subsequence and the residual subsequence, a trend prediction subsequence and a residual prediction subsequence are obtained;

[0112] The predicted value of the substation voltage is determined according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence.

[0113] In one embodiment, the second processing module 103 is used to determine the predicted value of the transformer area voltage according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence, specifically for:

[0114] The step of determining the predicted value of the transformer area voltage according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence is implemented by the following formula:

[0115]

[0116] Wherein, U(t) is the predicted value of the voltage in the substation area; U season (t) is the periodic subsequence; predicting a subsequence for said trend; is the residual prediction subsequence.

[0117] In one embodiment, the determination module 106 is used to determine the line voltage regulator control strategy according to the target power flow direction and the power flow node voltage, specifically for:

[0118] Analyze the operation status of the power grid according to the target power flow direction and the power flow node voltage to obtain an operation status data set;

[0119] Determining a line voltage regulator control strategy according to the operating status data set and the target power flow direction;

[0120] Among them, the step of determining the line voltage regulator control strategy according to the operating status data set and the target power flow direction is realized by a power flow bidirectional line voltage regulator circuit:

[0121] The power flow bidirectional line voltage regulator circuit comprises: a first isolating switch group, a second isolating switch group, a third isolating switch group, a first circuit breaker group, a second circuit breaker group, a third circuit breaker group, a first voltage transformer group, a second voltage transformer group, a first current transformer and a third current transformer, wherein:

[0122] On the grid side of the first isolating switch group, the first circuit breaker group is configured; on the grid side of the first circuit breaker group, the first voltage transformer group is added; on the grid side of the second isolating switch group, the second circuit breaker group is configured; on the grid side of the second circuit breaker group, the second voltage transformer group is added; the first current transformer is configured in the short-circuit switch group of the line voltage regulator (i.e., the first circuit breaker group + the first isolating switch group); and the third current transformer is configured in the bypass switch group of the line voltage regulator (i.e., the third circuit breaker group + the third isolating switch group).

[0123] In one embodiment, the determination module 106 is used to determine the line voltage regulator control strategy according to the operation status data set and the target power flow direction, specifically for:

[0124] If the operating status data set indicates that the voltage exceeds the limit, determining the target voltage exceeding the limit according to the upper limit range and the lower limit range;

[0125] If the target voltage over-limit condition indicates that the voltage exceeds the lower limit, obtaining the target power flow direction;

[0126] If the target flow direction indicates that the flow direction is positive, determining a gear adjustment parameter of the line voltage regulator;

[0127] generating a gear adjustment instruction according to the gear adjustment parameter;

[0128] A line voltage regulator control strategy is determined according to the gear adjustment instruction.

[0129] The present invention provides a voltage control device based on a power flow bidirectional line voltage regulator, which obtains historical data of the substation voltage from a distribution automation system, further transforms and processes the historical data of the substation voltage to obtain a voltage time series, and performs a day-ahead prediction of the line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a substation voltage prediction value, and performs a phase difference calculation based on the substation voltage prediction value to obtain a target phase difference, so that the power flow direction can be judged based on the target phase difference to obtain the target power flow direction, and then the line voltage regulator control strategy can be determined based on the target power flow direction and the power flow node voltage, which can improve the accuracy of the line voltage regulator in active power distribution applications, and is beneficial to improving the operating reliability of the line voltage regulator while enabling the line voltage regulator to adapt to flexible changes in the power flow direction.

[0130] The specific definition of the voltage control device based on the power flow bidirectional line voltage regulator can be found in the above definition of the voltage control method based on the power flow bidirectional line voltage regulator, which will not be repeated here. Each module in the above-mentioned voltage control device based on the power flow bidirectional line voltage regulator can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0131] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the functions or steps of the service end side of a voltage control method based on a flow bidirectional line voltage regulator are realized.

[0132] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, the functions or steps of the client side of a voltage control method based on a flow bidirectional line voltage regulator are realized.

[0133] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0134] Obtain historical data of substation voltage from the distribution automation system;

[0135] The historical data of the transformer area voltage is converted and processed to obtain a voltage time series;

[0136] Based on the long short-term memory neural network, the line voltage regulator is predicted for the voltage time series to obtain the predicted value of the transformer area voltage;

[0137] Calculating the phase difference according to the predicted value of the transformer area voltage to obtain a target phase difference;

[0138] Based on the target phase difference, determining the tidal current direction, and obtaining the target tidal current direction;

[0139] A line voltage regulator control strategy is determined according to the target power flow direction and power flow node voltage.

[0140] The present invention provides a computer device, which obtains historical data of substation voltage from a distribution automation system, further transforms and processes the historical data of substation voltage to obtain a voltage time series, and performs a day-ahead prediction of a line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a substation voltage prediction value, and performs a phase difference calculation based on the substation voltage prediction value to obtain a target phase difference, so that the power flow direction can be judged based on the target phase difference to obtain the target power flow direction, and then the line voltage regulator control strategy can be determined based on the target power flow direction and the power flow node voltage, so that the accuracy of the line voltage regulator in active power distribution applications can be improved, which is beneficial to improving the operating reliability of the line voltage regulator while enabling the line voltage regulator to adapt to flexible changes in the power flow direction.

[0141] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0142] Obtain historical data of substation voltage from the distribution automation system;

[0143] The historical data of the transformer area voltage is converted and processed to obtain a voltage time series;

[0144] Based on the long short-term memory neural network, the line voltage regulator is predicted for the voltage time series to obtain the predicted value of the transformer area voltage;

[0145] Calculating the phase difference according to the predicted value of the transformer area voltage to obtain a target phase difference;

[0146] Based on the target phase difference, determining the tidal current direction, and obtaining the target tidal current direction;

[0147] A line voltage regulator control strategy is determined according to the target power flow direction and power flow node voltage.

[0148] The present invention provides a computer-readable storage medium, which obtains historical data of substation voltage from a distribution automation system, further transforms and processes the historical data of substation voltage to obtain a voltage time series, and performs a day-ahead prediction of a line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a substation voltage prediction value, and performs a phase difference calculation based on the substation voltage prediction value to obtain a target phase difference, so that the power flow direction can be judged based on the target phase difference to obtain the target power flow direction, and then the line voltage regulator control strategy can be determined based on the target power flow direction and the power flow node voltage, which can improve the accuracy of the line voltage regulator in active power distribution applications, and is conducive to improving the operating reliability of the line voltage regulator while enabling the line voltage regulator to adapt to flexible changes in the power flow direction.

[0149] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0150] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0151] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0152] The embodiments described above 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 do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A voltage control method based on a power flow bidirectional line voltage regulator, characterized in that: The method comprises: Obtain historical data of substation voltage from the distribution automation system; The historical data of the transformer area voltage is converted and processed to obtain a voltage time series; Based on the long short-term memory neural network, the line voltage regulator is predicted for the voltage time series to obtain the predicted value of the transformer area voltage; Calculating the phase difference according to the predicted value of the transformer area voltage to obtain a target phase difference; Based on the target phase difference, determining the tidal current direction, and obtaining the target tidal current direction; A line voltage regulator control strategy is determined according to the target power flow direction and power flow node voltage.

2. The voltage control method based on the power flow bidirectional line voltage regulator according to claim 1, characterized in that: The method of performing a day-ahead prediction of the line voltage regulator on the voltage time series based on the long short-term memory neural network to obtain a predicted value of the transformer area voltage includes: Decomposing the voltage time series by using a time series algorithm to obtain a trend subsequence of voltage daily changes, a periodic subsequence of voltage regularity changes, and a residual subsequence of voltage mutations; Based on the long short-term memory neural network, the transformer area voltage prediction model is constructed and obtained; Using the substation voltage prediction model, according to the trend subsequence and the residual subsequence, a trend prediction subsequence and a residual prediction subsequence are obtained; The predicted value of the substation voltage is determined according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence.

3. The voltage control method based on the power flow bidirectional line voltage regulator according to claim 2, characterized in that: The step of determining the predicted value of the transformer area voltage according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence includes: The step of determining the predicted value of the transformer area voltage according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence is implemented by the following formula: Wherein, U(t) is the predicted value of the voltage in the substation area; U season (t) is the periodic subsequence; predicting a subsequence for said trend; is the residual prediction subsequence.

4. The voltage control method based on the power flow bidirectional line voltage regulator according to claim 3 is characterized in that: The determining of the line voltage regulator control strategy according to the target power flow direction and the power flow node voltage includes: Analyze the operation status of the power grid according to the target power flow direction and the power flow node voltage to obtain an operation status data set; Determining a line voltage regulator control strategy according to the operating status data set and the target power flow direction; Among them, the step of determining the line voltage regulator control strategy according to the operating status data set and the target power flow direction is realized by a power flow bidirectional line voltage regulator circuit: The power flow bidirectional line voltage regulator circuit comprises: a first isolating switch group, a second isolating switch group, a third isolating switch group, a first circuit breaker group, a second circuit breaker group, a third circuit breaker group, a first voltage transformer group, a second voltage transformer group, a first current transformer and a third current transformer, wherein: On the grid side of the first isolating switch group, the first circuit breaker group is configured; on the grid side of the first circuit breaker group, the first voltage transformer group is added; on the grid side of the second isolating switch group, the second circuit breaker group is configured; on the grid side of the second circuit breaker group, the second voltage transformer group is added; the first current transformer is configured in the short-circuit switch group of the line voltage regulator (i.e., the first circuit breaker group + the first isolating switch group); and the third current transformer is configured in the bypass switch group of the line voltage regulator (i.e., the third circuit breaker group + the third isolating switch group).

5. The voltage control method based on a power flow bidirectional line voltage regulator according to any one of claims 1 to 4, characterized in that: The determining of the line voltage regulator control strategy according to the operating status data set and the target power flow direction includes: If the operating status data set indicates that the voltage exceeds the limit, determining the target voltage exceeding the limit according to the upper limit range and the lower limit range; If the target voltage over-limit condition indicates that the voltage exceeds the lower limit, obtaining the target power flow direction; If the target flow direction indicates that the flow direction is forward, determining a gear adjustment parameter of the line voltage regulator; generating a gear adjustment instruction according to the gear adjustment parameter; determining a line voltage regulator control strategy according to the gear adjustment instruction; If the target voltage over-limit condition indicates that the voltage exceeds the upper limit, and the power flow direction is positive, then determining that the gear adjustment parameter is a downshift parameter; If the target voltage over-limit condition indicates that the voltage exceeds the upper limit, and the power flow direction is negative, then the gear adjustment parameter is determined to be an up-shift parameter.

6. A voltage control device based on a power flow bidirectional line voltage regulator, characterized in that: The voltage control device based on the power flow bidirectional line voltage regulator comprises: An acquisition module is used to obtain historical data of the substation voltage from the distribution automation system; The first processing module is used to convert the historical voltage data of the substation area to obtain a voltage time series; The second processing module is used to perform a day-ahead prediction of the line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a predicted value of the transformer area voltage; A third processing module is used to calculate the phase difference according to the predicted value of the transformer area voltage to obtain a target phase difference; A fourth processing module, configured to determine a tidal current direction based on the target phase difference, and obtain a target tidal current direction; The determination module is used to determine the line voltage regulator control strategy according to the target power flow direction and the power flow node voltage.

7. The voltage control device based on the power flow bidirectional line voltage regulator according to claim 6, characterized in that: The second processing module is used to perform a day-ahead prediction of the line voltage regulator on the voltage time series based on a long short-term memory neural network to obtain a predicted value of the transformer area voltage, specifically for: Decomposing the voltage time series by using a time series algorithm to obtain a trend subsequence of voltage daily changes, a periodic subsequence of voltage regularity changes, and a residual subsequence of voltage mutations; Based on the long short-term memory neural network, the transformer area voltage prediction model is constructed and obtained; Using the substation voltage prediction model, according to the trend subsequence and the residual subsequence, a trend prediction subsequence and a residual prediction subsequence are obtained; The predicted value of the substation voltage is determined according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence.

8. The voltage control device based on the power flow bidirectional line voltage regulator according to claim 7, characterized in that: The second processing module is used to determine the predicted value of the transformer area voltage according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence, and is specifically used to: The step of determining the predicted value of the transformer area voltage according to the period subsequence, the trend prediction subsequence and the residual prediction subsequence is implemented by the following formula: Wherein, U(t) is the predicted value of the voltage in the substation area; U season (t) is the periodic subsequence; predicting a subsequence for said trend; is the residual prediction subsequence.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the voltage control method based on the power flow bidirectional line voltage regulator according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the voltage control method based on the power flow bidirectional line voltage regulator according to any one of claims 1 to 5 is implemented.

Images