A regional power grid dispatching method and system based on multi-source data

Abstract

The present invention discloses a regional power grid dispatching method and system based on multi-source data, which relates to the technical field of power grid dispatching. It includes: first obtaining the regional power grid distribution information from the State Grid GIS platform, deploying a dispatching system in the cloud based on the OpenFMB framework, and collecting basic parameters, operation history, historical equipment status, historical environment, and historical power consumption information. Then, a power grid load constraint model is constructed, power limitation is performed to obtain node constraint information, and an LSTM model is used to predict future power consumption information. Finally, the dispatching strategy is determined by combining real-time information, node constraint information, and future power consumption information, such as starting SVG reactive power compensation or transferring load according to the power situation. The system includes a collection module, a main control module, a dispatching module, and a display module. Each module has a clear division of labor and cooperates to achieve power grid dispatching. This method and system effectively solve the problems of data transmission delay, high single-point failure risk, and low dispatching efficiency in centralized data storage and processing in power dispatching.

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, and particularly relates to a regional power grid scheduling method and system based on multi-source data. Background Art

[0002] In the field of power systems, the rationality and efficiency of regional power grid scheduling are crucial for the stability and reliability of power supply. The traditional centralized data storage and processing methods have exposed many problems when dealing with large-scale and complex power demands, such as data transmission delay, resulting in a lag in scheduling decisions; high single-point failure risk, and a single failure may affect the entire scheduling system; low scheduling efficiency, and it is difficult to quickly respond to changing power demands. These problems have severely restricted the development of regional power grid scheduling and urgently require new scheduling methods and systems to solve them.

[0003] When the existing regional power grid scheduling methods and systems deal with large-scale and complex power demands, they rely on empirical thresholds and cannot dynamically reflect the impact of equipment aging and environmental changes on the current-carrying capacity, resulting in an increase in the undetected rate of overload risks. Therefore, it is necessary to provide a regional power grid scheduling method and system based on multi-source data to solve the above-mentioned problems. Summary of the Invention

[0004] To solve the above technical problems, a regional power grid scheduling method and system based on multi-source data are provided. This technical solution solves the problem that the existing regional power grid scheduling methods and systems rely on empirical thresholds when dealing with large-scale and complex power demands, cannot dynamically reflect the impact of equipment aging and environmental changes on the current-carrying capacity, and result in an increase in the undetected rate of overload risks.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A regional power grid scheduling method based on multi-source data, comprising:

[0007] S1. Obtain the distribution information of the regional power grid, deploy a regional power grid scheduling system according to the distribution information of the regional power grid, and use the regional power grid scheduling system to collect the basic grid parameter data, grid operation historical information, grid equipment historical state information, and historical environment information of each node in the regional power grid;

[0008] Wherein, each node in the regional power grid is each feeder terminal in the regional power grid;

[0009] S2. Based on the basic grid parameter data, grid operation historical information, grid equipment historical state information, and historical environment information of each node, construct a grid load constraint model corresponding to each node;

[0010] S3. Perform power limitation on each node through the grid load constraint model to obtain power node constraint information;

[0011] S4. Obtain the historical power consumption information of each node in the regional power grid, import the historical power consumption information into the regional power grid dispatching system, and predict the future power consumption information of each node in the current regional power grid;

[0012] S5. Collect the real-time operation information, real-time status information of grid equipment, and real-time environment information of each node in the regional power grid, combine the power node constraint information corresponding to each node and the future power consumption information of each node in the current regional power grid to determine the optimal dispatching strategy, and then dispatch the regional power grid according to the optimal dispatching strategy.

[0013] In an alternative embodiment, step S1 specifically includes:

[0014] Obtain the three-dimensional geographic information of the transmission line from the State Grid GIS platform to determine the regional power grid distribution information;

[0015] Deploy the core server in the cloud according to the regional power grid distribution information, and build a regional power grid dispatching system on the core server based on the OpenFMB framework;

[0016] Use the regional power grid dispatching system to collect the basic grid parameter data, grid operation historical information, grid equipment historical status information, and historical environment information of all feeder terminals in the regional power grid as the basic grid parameter data, grid operation historical information, grid equipment historical status information, and historical environment information of each node in the regional power grid.

[0017] In an alternative embodiment, constructing a grid load constraint model corresponding to each node based on the basic grid parameter data, grid operation historical information, grid equipment historical status information, and historical environment information of each node specifically includes:

[0018] S2.1. Arbitrarily obtain two adjacent nodes and denote them as the first node and the second node;

[0019] S2.2. According to the basic grid parameter data of each node, obtain the wire material information, wire cross-sectional area, and laying method information between the first node and the second node. According to the grid operation historical information of each node, obtain the wire ampacity of the wire between the first node and the second node under standard conditions, and then determine the allowable wire ampacity between the first node and the second node.

[0020] The calculation formula for the allowable wire ampacity is:

[0021]

[0022] In the formula, is the allowable wire ampacity between the first node and the second node, is the wire current-carrying capacity between the first node and the second node under standard conditions, is the temperature correction coefficient, is the wire cross-sectional area correction coefficient, is the laying method correction coefficient, is the environmental correction coefficient;

[0023] S2.3. Construct a thermodynamic constraint model:

[0024]

[0025] In the formula, is the allowable current-carrying capacity of the wire between the first node and the second node, is the rated apparent power of the equipment at the first node, is the grid load limit voltage between the first node and the second node, is the temperature correction coefficient, is the historical ambient temperature, is the reference temperature, is the safe current-carrying capacity of the wire between the first node and the second node;

[0026] S2.4. Obtain the grid load limit voltage between the first node and the second node through the thermodynamic constraint model;

[0027] S2.5. According to the historical state information of the grid equipment at each node, obtain the historical load loss, rated capacity and maximum allowable temperature of the transformer winding between the first node and the second node, and then determine the thermal stability limit of the transformer between the first node and the second node;

[0028] The expression formula for the thermal stability limit of the transformer between the first node and the second node is:

[0029]

[0030] In the formula, is the historical load loss of the transformer between the first node and the second node, is the maximum allowable loss of the transformer between the first node and the second node, is the rated capacity of the transformer between the first node and the second node, is the maximum allowable temperature of the transformer winding between the first node and the second node, is the historical ambient temperature, is the loss coefficient;

[0031] S2.6. Obtain the maximum allowable loss of the transformer between the first node and the second node through the expression formula for the thermal stability limit of the transformer between the first node and the second node;

[0032] S2.7. Define the power grid load constraint model corresponding to the first node. The power grid load constraint model of the first node includes the calculation formula for the allowable current-carrying capacity of the wire, the thermodynamic constraint model, and the expression formula for the thermal stability limit of the transformer. After determining the calculation formula for the allowable current-carrying capacity of the wire, the thermodynamic constraint model, and the expression formula for the thermal stability limit of the transformer between the first node and the second node, complete the construction of the power grid load constraint model corresponding to the first node, and then construct the power grid load constraint model corresponding to each node in turn.

[0033] In an alternative embodiment, the power limit is applied to each node through the power grid load constraint model to obtain the power node constraint information, which specifically includes:

[0034] S3.1. Obtain the calculation formula for the allowable current-carrying capacity of the wire, the thermodynamic constraint model, and the expression formula for the thermal stability limit of the transformer corresponding to each node through the power grid load constraint model, and then obtain the power node constraint model:

[0035]

[0036] where is the stable limit limiting current of the d-th node, is the allowable current-carrying capacity of the wire of the d-th node, is the grid load limit voltage of the d-th node, is the maximum allowable loss of the transformer of the d-th node, is the load power factor;

[0037] S3.2. Obtain the line impedance and line reactance corresponding to the d-th node through the basic power grid parameter data of each node;

[0038] S3.3. Through the power node constraint model, combined with the line impedance and line reactance corresponding to the d-th node, obtain the power node constraint information corresponding to the d-th node:

[0039]

[0040] where is the measured real-time power of the line of the current d-th node, is the maximum power allowed by the thermal stability of the d-th node, is the line impedance corresponding to the d-th node, is the line reactance corresponding to the d-th node, , is the load power factor.

[0041] In an alternative embodiment, acquiring the historical power consumption information of each node in the regional power grid, importing the historical power consumption information into the regional power grid dispatching system, and predicting the future power consumption information of each node in the current regional power grid specifically includes:

[0042] Sequentially collecting the historical power consumption information of at least 7 days corresponding to each node through the feeder terminals of each node in the regional power grid, where the historical power consumption information includes the historical power, voltage, current, temperature, and holiday label within the past 24 hours;

[0043] Construct an LSTM model and train the LSTM model using the historical power consumption information to obtain a future power consumption prediction model;

[0044] Obtain the temperature and holiday label of the next 24 hours in the area where any node is located, and input the temperature and holiday label of the next 24 hours in the area where any node is located into the future power consumption prediction model to obtain the power prediction value of this node in the next 1 hour output by the future power consumption prediction model, thereby determining the future power consumption information of each node in the current regional power grid.

[0045] In an alternative embodiment, step S5 specifically includes:

[0046] Collect the operation real-time information, power grid equipment real-time status information, and real-time environment information corresponding to each node through the feeder terminals of each node in the regional power grid;

[0047] Obtain the power grid load constraint model corresponding to each node through the operation real-time information, power grid equipment real-time status information, and real-time environment information corresponding to each node;

[0048] Obtain the power node constraint model corresponding to each node through the power grid load constraint model corresponding to each node, and then obtain the line impedance and line reactance corresponding to each node through the basic power grid parameter data of each node, thereby obtaining the power node constraint information corresponding to each node;

[0049] Based on the future power consumption information of each node in the current regional power grid, determine the power prediction value of each node in the next 1 hour ;

[0050] Obtain the real-time line power corresponding to each node through the power node constraint information corresponding to each node and the maximum power allowed by thermal stability ;

[0051] If , then start the SVG reactive power compensation to improve the voltage stability;

[0052] If , the user load in the overload area corresponding to the node will be transferred to the adjacent line, and observe whether the users in the overload area corresponding to the node continue to be overloaded. If so, remotely cut off the non-critical load. If not, continue to monitor.

[0053] Furthermore, a regional power grid dispatching system based on multi-source data is proposed to implement the dispatching method as described above, including:

[0054] A collection module, which is used to obtain the distribution information of the regional power grid and collect the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information and historical environment information of each

[0055] node in the regional power grid, and is also used to collect the real-time operation information, real-time status information of power grid equipment and real-time environment information of each node in the regional power grid;

[0056] A main control module, which is used to preprocess the data and information collected by the collection module, and construct a power grid load constraint model corresponding to each node based on the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information and historical environment information of each node;

[0057] A dispatching module, which is used to limit the power of each node through the power grid load constraint model to obtain power node constraint information, and is also used to combine the power node constraint information corresponding to each node and the future power consumption information of each node in the current regional power grid to determine an optimal dispatching strategy, and then dispatch the regional power grid according to the optimal dispatching strategy;

[0058] A display module, which is used to display the collection process and results of the collection module, the data processing process and results of the main control module, the constraint process and results of the dispatching module, and the dispatching process and results of the dispatching module.

[0059] In an alternative embodiment, the collection module includes:

[0060] A first collection unit, which is used to obtain the distribution information of the regional power grid and collect the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information and historical environment information of each node in the regional power grid;

[0061] A second collection unit, which is used to collect the real-time operation information, real-time status information of power grid equipment and real-time environment information of each node in the regional power grid.

[0062] In an alternative embodiment, the main control module includes:

[0063] A data processing unit, which is used to preprocess the data and information collected by the acquisition module;

[0064] A model construction unit, which is used to construct a grid load constraint model corresponding to each node based on the basic grid parameter data, grid operation historical information, grid equipment historical status information, and historical environment information of each node.

[0065] In an alternative embodiment, the scheduling module includes:

[0066] A constraint unit, which is used to perform power limitation on each node through the grid load constraint model to obtain power node constraint information;

[0067] A scheduling unit, which is used to combine the power node constraint information corresponding to each node and the future power consumption information of each node in the current regional power grid to determine an optimal scheduling strategy, and then schedule the regional power grid according to the optimal scheduling strategy.

[0068] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0069] A regional power grid scheduling method and system based on multi-source data proposed in this solution, by integrating multi-dimensional data such as GIS three-dimensional geographic information, grid equipment historical status, and environmental temperature, constructs a node-level power node constraint model including conductor ampacity (including temperature / laying method correction), transformer thermal stability limit, and thermodynamic constraints, realizes the full-condition quantitative evaluation of grid equipment, does not rely on empirical thresholds during scheduling, dynamically reflects the impact of equipment aging and environmental changes on ampacity, and reduces the overload risk and missed inspection rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a flowchart of a regional power grid scheduling method based on multi-source data proposed in this solution;

[0071] Figure 2 It is a flowchart of the construction of the grid load constraint model in this solution;

[0072] Figure 3 It is a flowchart of obtaining the power node constraint information in this solution;

[0073] Figure 4 It is a system block diagram of a regional power grid scheduling system based on multi-source data proposed in this solution. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0074] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0075] Refer to Figure 1 - Figure 4 As shown, a regional power grid dispatching method based on multi-source data includes:

[0076] S1. Obtain the regional power grid distribution information, deploy the regional power grid dispatching system according to the regional power grid distribution information, and use the regional power grid dispatching system to collect the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information, and historical environment information of each node in the regional power grid;

[0077] Among them, each node in the regional power grid is each feeder terminal in the regional power grid;

[0078] S2. Based on the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information, and historical environment information of each node, construct a power grid load constraint model corresponding to each node;

[0079] S3. Perform power limitation on each node through the power grid load constraint model to obtain power node constraint information;

[0080] S4. Obtain the historical power consumption information of each node in the regional power grid, import the historical power consumption information into the regional power grid dispatching system, and predict the future power consumption information of each node in the current regional power grid;

[0081] S5. Collect the real-time operation information, real-time status information of power grid equipment, and real-time environment information of each node in the regional power grid, combine the power node constraint information corresponding to each node and the future power consumption information of each node in the current regional power grid, determine the optimal dispatching strategy, and then dispatch the regional power grid according to the optimal dispatching strategy.

[0082] Specifically, the feeder terminal is installed near the switch equipment of the distribution network feeder circuit and is used to monitor, control, and protect the feeder switch. It can collect operation parameters such as the voltage, current, and power of the feeder, realize functions such as fault detection, location, and isolation of the feeder, and remote control opening and closing of the switch, so as to improve the reliability and automation level of the distribution network.

[0083] Further, step S1 specifically includes:

[0084] Obtain the three-dimensional geographical information of the transmission line from the State Grid GIS platform to determine the regional power grid distribution information;

[0085] According to the regional power grid distribution information, deploy the core server in the cloud, and build a regional power grid dispatching system on the core server based on the OpenFMB framework;

[0086] Use the regional power grid dispatching system to collect the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information, and historical environment information of all feeder terminals within the regional power grid as the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information, and historical environment information of each node within the regional power grid.

[0087] Furthermore, based on the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information, and historical environment information of each node, construct a power grid load constraint model corresponding to each node, specifically including:

[0088] S2.1. Arbitrarily obtain two adjacent nodes and denote them as the first node and the second node;

[0089] S2.2. According to the basic power grid parameter data of each node, obtain the wire material information, wire cross-sectional area, and laying method information between the first node and the second node. According to the power grid operation historical information of each node, obtain the wire current-carrying capacity of the wire between the first node and the second node under standard conditions, and then determine the allowable wire current-carrying capacity between the first node and the second node.

[0090] The calculation formula for the allowable wire current-carrying capacity is:

[0091]

[0092] In the formula, is the allowable wire current-carrying capacity between the first node and the second node, is the wire current-carrying capacity of the wire between the first node and the second node under standard conditions, is the temperature correction coefficient, is the wire cross-sectional area correction coefficient, is the laying method correction coefficient, is the environment correction coefficient;

[0093] Specifically, the wire current-carrying capacity of the wire under standard conditions can refer to IEC 60364 or GB 50545, is the temperature correction coefficient, , where, is the conductor resistance temperature coefficient of the wire, is the actual environmental temperature in the historical environment information. is the wire cross-sectional area correction coefficient, which is related to the shape of the wire, such as a circular wire . is the laying method correction coefficient, such as an overhead line , a directly buried line . is the environment correction coefficient, which is related to wind speed, sunlight, etc., such as when there is no wind and no sunlight 。

[0094] For example, if a certain node uses an LGJ-120 type aluminum core steel stranded wire, its standard current-carrying capacity , assuming the environmental temperature in the historical environmental information , conductor resistance temperature coefficient , then 。

[0095] S2.3. Construct a thermodynamic constraint model:

[0096]

[0097] In the formula, is the allowable current-carrying capacity of the wire between the first node and the second node, is the rated apparent power of the equipment at the first node, is the grid load limit voltage between the first node and the second node, is the temperature correction coefficient, is the historical environmental temperature, is the reference temperature, is the safe current-carrying capacity of the wire between the first node and the second node;

[0098] Specifically, the safe current-carrying capacity of the wire is determined by the material characteristics of the wire, and the rated apparent power of the equipment at the first node is the rated apparent power of the transformer closest to the first node.

[0099] For example, the rated apparent power S max = 630 kVA of the transformer closest to the first node, and the allowable current-carrying capacity of the wire between the first node and the second node, reference temperature T ref = 20 °C, it is calculated that the grid load limit voltage V = 10 kV,

[0100] S2.4. Obtain the grid load limit voltage between the first node and the second node through the thermodynamic constraint model;

[0101] S2.5. According to the historical state information of the grid equipment at each node, obtain the historical load loss, rated capacity, and maximum allowable temperature of the transformer winding between the first node and the second node, and then determine the thermal stability limit of the transformer between the first node and the second node;

[0102] The expression formula for the thermal stability limit of the transformer between the first node and the second node is:

[0103]

[0104] In the formula, is the historical load loss of the transformer between the first node and the second node, is the maximum allowable loss of the transformer between the first node and the second node, is the rated capacity of the transformer between the first node and the second node, is the highest allowable temperature of the transformer winding between the first node and the second node, is the historical ambient temperature, is the loss coefficient;

[0105] Specifically, the historical load loss of the transformer between the first node and the second node is collected from the transformer closest to the first node. Similarly, the rated capacity of the transformer between the first node and the second node is also collected from the transformer closest to the first node.

[0106] For example, if a certain 10kV / 0.4kV transformer (S base = 1000kVA) closest to the first node, the historical ambient temperature 30 , and the historical load loss P loss = 12kW of the transformer between the first node and the second node: then P max = 3 ⋅ 1000 ⋅ (95 - 30) = 202,500W = 202.5kW. Since 12kW ≤ 202.5kW, the transformer is in a safe state.

[0107] S2.6. Obtain the maximum allowable loss of the transformer between the first node and the second node through the expression formula of the thermal stability limit of the transformer between the first node and the second node;

[0108] S2.7. Define the grid load constraint model corresponding to the first node. The grid load constraint model of the first node includes the calculation formula of the allowable current-carrying capacity of the wire, the thermodynamic constraint model, and the expression formula of the thermal stability limit of the transformer. After determining the calculation formula of the allowable current-carrying capacity of the wire, the thermodynamic constraint model, and the expression formula of the thermal stability limit of the transformer between the first node and the second node, complete the construction of the grid load constraint model corresponding to the first node, and successively construct the grid load constraint models corresponding to each node.

[0109] Furthermore, perform power limitation on each node through the grid load constraint model to obtain the power node constraint information, specifically including:

[0110] S3.1. Obtain the calculation formula of the allowable current-carrying capacity of the wire, the thermodynamic constraint model, and the expression formula of the thermal stability limit of the transformer corresponding to each node through the grid load constraint model, and then obtain the power node constraint model:

[0111]

[0112] Wherein, is the stable limit current of the d-th node, is the allowable current-carrying capacity of the wire of the d-th node, is the grid load limit voltage of the d-th node, is the maximum allowable loss of the transformer of the d-th node, is the load power factor;

[0113] For example, the wire between the first node and the second node: model LGJ-70 (standard current-carrying capacity I z0 = 320 A, temperature coefficient α = 0.004 / °C), ambient temperature: T = 35°C, transformer: capacity S = 630 kVA, load loss = 8 kW, power factor ,

[0114] Calculation: = 320⋅(1 + 0.004⋅15) ≈ 342 A, = 8 kW, = 10 kV,

[0115] .

[0116] S3.2. Obtain the line impedance and line reactance corresponding to the d-th node through the basic parameter data of the power grid of each node;

[0117] S3.3. Through the power node constraint model, combined with the line impedance and line reactance corresponding to the d-th node, obtain the power node constraint information corresponding to the d-th node:

[0118]

[0119] Wherein, is the measured real-time power of the line of the current d-th node, is the maximum power allowed by the thermal stability of the d-th node, is the line impedance corresponding to the d-th node, is the line reactance corresponding to the d-th node, , is the load power factor.

[0120] Specifically, the maximum thermal power allowed by the line (determined by the comprehensive effect of the wire current-carrying capacity and transformer loss, unit: kW), is the measured real-time power of the line of the current d-th node, and the heating power of the line is determined by the combined action of resistance and reactance:

[0121] , Among them, is the real-time line current of the current d-th node measured.

[0122] Furthermore, obtain the historical electricity consumption information of each node in the regional power grid, import the historical electricity consumption information into the regional power grid dispatching system, and predict the future electricity consumption information of each node in the current regional power grid, specifically including:

[0123] Collect the historical electricity consumption information of at least 7 days corresponding to each node in sequence through the feeder terminals of each node in the regional power grid. The historical electricity consumption information includes historical power, voltage, current, temperature, and holiday labels within the past 24 hours;

[0124] Construct an LSTM model, and use the historical electricity consumption information to train the LSTM model to obtain a future electricity consumption prediction model;

[0125] Obtain the temperature and holiday labels of the next 24 hours in the area where any node is located, and input the temperature and holiday labels of the next 24 hours in the area where any node is located into the future electricity consumption prediction model to obtain the power prediction value of this node in the next 1 hour output by the future electricity consumption prediction model, and then determine the future electricity consumption information of each node in the current regional power grid.

[0126] Furthermore, step S5 specifically includes:

[0127] Collect the operation real-time information, power grid equipment real-time status information, and real-time environment information corresponding to each node through the feeder terminals of each node in the regional power grid;

[0128] Obtain the power grid load constraint model corresponding to each node through the operation real-time information, power grid equipment real-time status information, and real-time environment information corresponding to each node;

[0129] Obtain the power node constraint model corresponding to each node through the power grid load constraint model corresponding to each node, and then obtain the line impedance and line reactance corresponding to each node through the basic power grid parameter data of each node, and further obtain the power node constraint information corresponding to each node;

[0130] Based on the future electricity consumption information of each node in the current regional power grid, determine the power prediction value of each node in the next 1 hour ;

[0131] Obtain the line real-time power corresponding to each node through the power node constraint information corresponding to each node and the maximum power allowed by thermal stability ;

[0132] If , then start SVG reactive power compensation to improve voltage stability;

[0133] If , transfer the user load in the overloaded area corresponding to this node to the adjacent line, and observe whether the users in the overloaded area corresponding to this node continue to be overloaded. If so, remotely cut off the non-critical load. If not, continue to monitor.

[0134] Specifically, the preferred scheduling strategy formulation needs to optimize scheduling by combining real-time data and prediction results. Obtain real-time data such as current voltage, current, and ambient temperature through the feeder terminal. For example, the real-time current of a certain line is 320A, exceeding the thermal stability limit of 300A, triggering an overload alarm. Constraint verification and strategy selection: When the voltage is unstable and the predicted power meets the conditions, start SVG reactive power compensation to increase the voltage. When the line is overloaded and the conditions are met, transfer the load in the overloaded area to the adjacent line and cut off the non-critical load (such as air conditioners). For example, when the feeder terminal of a certain node discovers that a certain line is predicted to be overloaded, automatically switch 100kW of load to the standby line to avoid tripping.

[0135] Furthermore, a regional power grid scheduling system based on multi-source data is proposed to implement the above scheduling method, including:

[0136] The acquisition module is used to obtain the distribution information of the regional power grid, collect the basic power grid parameter data, power grid operation historical information, power grid equipment historical state information, and historical environment information of each node in the regional power grid, and is also used to collect the real-time operation information, real-time state information of power grid equipment, and real-time environment information of each node in the regional power grid;

[0137] The main control module is used to preprocess the data and information collected by the acquisition module, and construct a power grid load constraint model corresponding to each node based on the basic power grid parameter data, power grid operation historical information, power grid equipment historical state information, and historical environment information of each node;

[0138] The scheduling module is used to limit the power of each node through the power grid load constraint model to obtain the power node constraint information, and is also used to determine the preferred scheduling strategy by combining the power node constraint information corresponding to each node and the future power consumption information of each node in the current regional power grid, and then schedule the regional power grid according to the preferred scheduling strategy;

[0139] The display module is used to display the acquisition process and results of the acquisition module, the data processing process and results of the main control module, the constraint process and results of the scheduling module, and the scheduling process and results of the scheduling module.

[0140] Furthermore, the acquisition module includes:

[0141] The first acquisition unit is used to obtain the regional power grid distribution information, and collect the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information, and historical environment information of each node in the regional power grid;

[0142] The second acquisition unit is used to collect the real-time operation information, real-time status information of power grid equipment, and real-time environment information of each node in the regional power grid.

[0143] Furthermore, the main control module includes:

[0144] The data processing unit is used to perform data preprocessing on the data and information collected by the acquisition module;

[0145] The model construction unit is used to construct a power grid load constraint model corresponding to each node based on the basic power grid parameter data, power grid operation historical information, power grid equipment historical status information, and historical environment information of each node.

[0146] Furthermore, the scheduling module includes:

[0147] The constraint unit is used to perform power limitation on each node through the power grid load constraint model to obtain power node constraint information;

[0148] The scheduling unit is used to combine the power node constraint information corresponding to each node and the future power consumption information of each node in the current regional power grid to determine an optimal scheduling strategy, and then schedule the regional power grid according to the optimal scheduling strategy.

[0149] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A regional power grid dispatching method based on multi-source data, characterized in that: include: S1. Obtain regional power grid distribution information, and deploy a regional power grid dispatching system based on the regional power grid distribution information, and use the regional power grid dispatching system to collect basic power grid parameter data, power grid operation history information, power grid equipment history status information, and history environment information of each node in the regional power grid; Wherein, each node in the regional power grid is each feeder terminal in the regional power grid; S2. Based on the basic parameter data of the power grid, the historical operation information of the power grid, the historical status information of the power grid equipment and the historical environmental information of each node, a power grid load constraint model corresponding to each node is constructed: S2.

1. Get any two adjacent nodes and record them as the first node and the second node; S2.

2. According to the basic parameter data of the power grid of each node, the material information, cross-sectional area and laying method information of the conductor between the first node and the second node are obtained. According to the power grid operation history information of each node, the current carrying capacity of the conductor between the first node and the second node under standard conditions is obtained, and then the allowable current carrying capacity of the conductor between the first node and the second node is determined; S2.3, construct a thermodynamic constraint model; S2.4, obtaining a power grid load limit voltage between the first node and the second node through a thermodynamic constraint model; S2.

5. According to the historical status information of the power grid equipment at each node, the historical load loss of the transformer between the first node and the second node, the rated capacity of the transformer and the maximum allowable temperature of the transformer winding are obtained, and then the thermal stability limit of the transformer between the first node and the second node is determined; S2.

6. Obtain the maximum allowable loss of the transformer between the first node and the second node by using the expression formula of the thermal stability limit of the transformer between the first node and the second node; S2.

7. Define a power grid load constraint model corresponding to the first node, wherein the power grid load constraint model of the first node includes a calculation formula for the allowable current carrying capacity of the conductor, a thermodynamic constraint model, and an expression formula for the thermal stability limit of the transformer. After determining the calculation formula for the allowable current carrying capacity of the conductor between the first node and the second node, the thermodynamic constraint model, and the expression formula for the thermal stability limit of the transformer, the construction of the power grid load constraint model corresponding to the first node is completed, and the power grid load constraint model corresponding to each node is constructed in turn; S3. Use the power grid load constraint model to limit the power of each node and obtain power node constraint information S4, obtaining historical power consumption information of each node in the regional power grid, importing the historical power consumption information into the regional power grid dispatching system, and predicting the future power consumption information of each node in the current regional power grid; S5. Collect the real-time operation information, real-time status information and real-time environmental information of each node in the regional power grid, combine the power node constraint information corresponding to each node and the future power consumption information of each node in the current regional power grid, determine the optimal scheduling strategy, and then schedule the regional power grid according to the optimal scheduling strategy.

2. A regional power grid dispatching method based on multi-source data according to claim 1, characterized in that: Step S1 specifically includes: Obtain three-dimensional geographic information of transmission lines from the State Grid GIS platform to determine regional power grid distribution information; According to the regional power grid distribution information, the core server is deployed in the cloud, and the regional power grid dispatching system is built on the core server based on the OpenFMB framework; The regional power grid dispatching system is used to collect the basic power grid parameter data, power grid operation history information, power grid equipment historical status information and historical environmental information of all feeder terminals in the regional power grid as the basic power grid parameter data, power grid operation history information, power grid equipment historical status information and historical environmental information of each node in the regional power grid.

3. A regional power grid dispatching method based on multi-source data according to claim 1, characterized in that: The grid load constraint model corresponding to each node is constructed based on the grid basic parameter data, grid operation history information, grid equipment history status information and history environment information of each node, specifically including: The calculation formula for the allowable current carrying capacity of the conductor is: In the formula, The allowable current carrying capacity of the wire between the first node and the second node, is the current carrying capacity of the wire between the first node and the second node under standard conditions, is the temperature correction coefficient, is the conductor cross-sectional area correction factor, is the correction factor for the laying method, is the environmental correction factor; The thermodynamic constraint model is constructed as follows: In the formula, The allowable current carrying capacity of the wire between the first node and the second node, is the rated apparent power of the equipment at the first node, is the grid load limit voltage between the first node and the second node, is the temperature correction coefficient, is the historical ambient temperature, is the reference temperature, The safe current carrying capacity of the wire between the first node and the second node; The thermal stability limit of the transformer between the first node and the second node is expressed as: In the formula, is the historical load loss of the transformer between the first node and the second node, is the maximum allowable loss of the transformer between the first node and the second node, is the rated capacity of the transformer between the first node and the second node, is the maximum allowable temperature of the transformer winding between the first node and the second node, is the historical ambient temperature, is the loss coefficient.

4. A regional power grid dispatching method based on multi-source data according to claim 3, characterized in that: The power restriction of each node is performed through the power grid load constraint model to obtain power node constraint information, specifically including: S3.

1. Obtain the calculation formula of the allowable current carrying capacity of the conductor corresponding to each node, the thermodynamic constraint model and the expression formula of the thermal stability limit of the transformer through the power grid load constraint model, and then obtain the power node constraint model: In the formula, is the stability limit current of the dth node, is the allowable current carrying capacity of the wire at the dth node, is the grid load limit voltage of the dth node, is the maximum allowable loss of the transformer at the dth node, is the load power factor; S3.2, obtaining the line impedance and line reactance corresponding to the dth node through the basic parameter data of the power grid of each node; S3.

3. Obtain the power node constraint information corresponding to the dth node by combining the line impedance and line reactance corresponding to the dth node through the power node constraint model: In the formula, is the measured real-time line power of the current d-th node, is the maximum power allowed for thermal stability of the dth node, is the line impedance corresponding to the dth node, is the line reactance corresponding to the dth node, , is the load power factor.

5. A regional power grid dispatching method based on multi-source data according to claim 1, characterized in that: The obtaining of historical power consumption information of each node in the regional power grid, importing the historical power consumption information into the regional power grid dispatching system, and predicting the future power consumption information of each node in the current regional power grid specifically includes: Through the feeder terminals of each node in the regional power grid, historical power consumption information corresponding to each node for at least 7 days is collected in sequence, and the historical power consumption information includes historical power, voltage, current, temperature and holiday tags within the past 24 hours; Build an LSTM model and use historical electricity consumption information to train the LSTM model to obtain a future electricity consumption prediction model; The temperature and holiday labels of the area where any node is located in the next 24 hours are obtained, and the temperature and holiday labels of the area where any node is located in the next 24 hours are input into the future power consumption prediction model to obtain the power prediction value of the node in the next hour output by the future power consumption prediction model, and then determine the future power consumption information of each node in the current regional power grid.

6. A regional power grid dispatching method based on multi-source data according to claim 4, characterized in that: Step S5 specifically includes: Through the feeder terminals of each node in the regional power grid, the real-time operation information, real-time status information of the power grid equipment and real-time environmental information corresponding to each node are collected; Obtain the grid load constraint model corresponding to each node through the real-time operation information, real-time status information of the grid equipment and real-time environmental information corresponding to each node; The power node constraint model corresponding to each node is obtained through the power grid load constraint model corresponding to each node, and then the line impedance and line reactance corresponding to each node are obtained through the basic parameter data of the power grid of each node, and then the power node constraint information corresponding to each node is obtained; Based on the future power consumption information of each node in the current regional power grid, determine the power forecast value of each node in the next hour ; Obtain the real-time power of the line corresponding to each node through the power node constraint information corresponding to each node and thermal stability allowable maximum power ; like , then start SVG reactive power compensation to improve voltage stability; like , then the user load in the overloaded area corresponding to the node is transferred to The adjacent lines of the node are monitored and the users in the overloaded area corresponding to the node are observed to see whether the overload continues. If so, the non-critical loads are remotely cut off. If not, the monitoring continues.

7. A regional power grid dispatching system based on multi-source data, characterized in that: A method for implementing a regional power grid dispatching method as claimed in any one of claims 1 to 6, comprising: The acquisition module is used to obtain regional power grid distribution information and collect information about each The basic parameter data of the node, the historical information of the grid operation, the historical status information of the grid equipment and the historical environmental information are also used to collect the real-time operation information, real-time status information and real-time environmental information of each node in the regional grid; A main control module, which is used to perform data preprocessing on the data and information collected by the collection module, and to build a power grid load constraint model corresponding to each node based on the basic parameter data of the power grid, the historical information of the power grid operation, the historical status information of the power grid equipment and the historical environmental information of each node; The scheduling module is used to limit the power consumption of each node through the power grid load constraint model. The power node constraint information is obtained by combining the power node constraint information corresponding to each node and the future power consumption information of each node in the current regional power grid to determine the optimal dispatching strategy, and then the regional power grid is dispatched according to the optimal dispatching strategy; The display module is used to display the acquisition process and results of the acquisition module, and to display the main The data processing process and results of the control module are used to display the constraint process and constraint results of the scheduling module, as well as the scheduling process and results of the scheduling module.

8. A regional power grid dispatching system based on multi-source data according to claim 7, characterized in that: The acquisition module comprises: The first acquisition unit is used to obtain regional power grid distribution information, collect regional power grid distribution information, Basic grid parameter data, grid operation history information, grid equipment history status information and historical environment information of each node in the grid; The second collection unit is used to collect real-time operation information of each node in the regional power grid, real-time status information of power grid equipment and real-time environmental information.

9. A regional power grid dispatching system based on multi-source data according to claim 7, characterized in that: The main control module comprises: A data processing unit is used to process the data and information collected by the acquisition module. Pretreatment; A model building unit, the model building unit is used to build a grid based on basic parameter data of each node, The grid operation history information, grid equipment status history information and historical environment information are used to build a grid load constraint model corresponding to each node.

10. A regional power grid dispatching system based on multi-source data according to claim 7, characterized in that: The scheduling module includes: The constraint unit is used to limit the power of each node through the power grid load constraint model. Control, obtain power node constraint information; The scheduling unit is used to combine the power node constraint information corresponding to each node and the current The future electricity consumption information of each node in the regional power grid is used to determine the optimal dispatching strategy, and then the regional power grid is dispatched according to the optimal dispatching strategy.

Images