Power grid data intelligent management system and method based on big data

Abstract

The invention relates to an intelligent power grid data management system and method based on big data, and the system is characterized in that an energy storage node management module is connected with a power utilization gap calculation module, the power utilization gap calculation module is connected with a power transmission line management module and an information judgment module, and the information judgment module is connected with a scheduling data management module; wherein the energy storage node management module is used for managing a discharge model of an energy storage node; the power transmission line management module is used for managing the relation of electric power loads between power distribution networks on the same power transmission line. The scheduling data management module is used for managing the function relationship between the load scheduling amount and the completion time; the power utilization gap calculation module is used for managing a gap power model corresponding to the power distribution area; the information judgment module is used for judging whether the scheduling time of the power utilization gap is longer than the time when the power utilization gap occurs. Compared with the prior art, the power utilization gap can be accurately predicted and estimated in time, and it is ensured that the power utilization gap is supplemented in time.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid big data processing, and in particular to a power grid data intelligent management system and method based on big data. Background Art

[0002] Due to the growing demand for electricity, the load pressure on traditional power transmission grids is increasing. With the development and popularization of new energy power generation technology and energy storage technology, the electricity generated by new energy power generation is used to supplement the traditional power transmission network.

[0003] The electricity generated by new energy in the prior art cannot completely cover the energy consumption of users. When the electricity generated by new energy is exhausted, it is necessary to readjust the power generation of traditional power generation to supplement the consumption in the power grid. However, traditional power generation methods such as coal-fired power and thermal power require a certain amount of adjustment time to adjust the power generation in the transmission network. If the electricity in the transmission network is not replenished in time, after the new energy storage device is disconnected, the power load in the distribution network will be greater than the power provided by the power grid, which will pose a safety hazard. Therefore, it is necessary to calculate and manage the power gap in a timely and accurate manner to avoid power accidents caused by the failure to meet the power load. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a big data-based intelligent power grid data management system and method, which can timely and accurately predict and estimate the electricity gap and ensure that the electricity gap is supplemented in time.

[0005] The purpose of the present invention can be achieved by the following technical solutions: an intelligent management system for power grid data based on big data, comprising an energy storage node management module, a transmission line management module, a scheduling data management module, a power consumption gap calculation module and an information judgment module, wherein the energy storage node management module is connected to the power consumption gap calculation module, the power consumption gap calculation module is respectively connected to the transmission line management module and the information judgment module, the information judgment module is connected to the scheduling data management module, and the energy storage node management module is used to manage the discharge model of the energy storage node;

[0006] The transmission line management module is used to manage the relationship between the electric power loads of the distribution networks on the same transmission line;

[0007] The scheduling data management module is used to manage the functional relationship between the load scheduling amount and the completion time;

[0008] The power consumption gap calculation module is used to manage the gap power model corresponding to the power distribution area;

[0009] The information determination module is used to determine whether the scheduling time of the power consumption gap is greater than the time when the power consumption gap occurs.

[0010] Furthermore, the energy storage node management module includes: a power consumption area management unit, a discharge data management unit and a discharge model management unit, wherein the power consumption area management unit is used to manage the connection information of the transmission lines in the power consumption area, the discharge data management unit is used to manage the discharge data of the new energy storage node, and the discharge model management unit is used to manage the discharge model of the new energy storage node.

[0011] Furthermore, the transmission line management module includes: a load sampling unit, a load collection unit and a load corresponding unit, wherein the load sampling unit is used to collect information on the distribution network obtaining electric energy from the transmission line, the load collection unit is used to collect load records of different distribution networks, and the load corresponding unit is used to obtain the minimum corresponding power under the load power conditions of a certain distribution network.

[0012] Furthermore, the scheduling data management module includes: a scheduling record collection unit and a function fitting unit, wherein the scheduling record collection unit is used to collect records of the amount of scheduling electric energy and the time spent in the scheduling process, and the function fitting unit is used to obtain a discharge model for constructing a new energy storage node.

[0013] Furthermore, the electricity gap calculation module includes: a remaining time management unit, a surplus power management unit and a gap power management unit, wherein the remaining time management unit is used to obtain the remaining working time of the energy storage node, the surplus power management unit is used to manage the surplus power provided by the distribution network, and the gap power management unit is used to calculate the gap power and the corresponding time through the gap power model.

[0014] Furthermore, the information judgment module includes: an objective function management unit, a prediction sampling unit and a gap judgment unit, wherein the objective function management unit is used to obtain the objective function, the prediction sampling unit is used to collect the predicted value information on the objective function, and the gap judgment unit is used to compare the scheduling time of the electricity gap with the time when the electricity gap occurs.

[0015] A method for intelligent management of power grid data based on big data, comprising the following steps:

[0016] Step S1: In a power consumption area including a transmission line and a distribution network, the power consumption area is connected to a power dispatching system, the power consumption area includes at least two distribution networks, a new energy storage node is set in the distribution network, historical discharge data of the new energy storage node is collected, and the relationship between the discharge power and the discharge duration of the new energy storage node is obtained;

[0017] Step S2: Collect historical power consumption data of the power consumption area, obtain the law of power load changes over time in each distribution network, and obtain the relationship between the power loads of the distribution networks connected to the same transmission line;

[0018] Step S3, collecting the electric energy dispatching records in the power consumption area, and fitting the historical records of different load dispatching amounts and corresponding load dispatching completion time to obtain the functional relationship between the load dispatching amount and the completion time;

[0019] Step S4: When the new energy storage node provides electric energy to the distribution network, a gap power model is established through the load of the current distribution network on the transmission line, the predicted value of the power load in the distribution network, and the remaining time for the new energy storage node to provide electric energy;

[0020] Step S5, predict the load gap in the distribution network through the gap power model, obtain the maximum value of the load gap in a detection cycle, obtain the scheduling time of the electric energy corresponding to the current time interval and the maximum value of the scheduling load gap when the maximum value occurs, and issue an alarm when the scheduling time is greater than the time interval.

[0021] Furthermore, the step S1 comprises:

[0022] Step S11: In the power consumption area, there is at least one transmission line, one of the transmission lines is recorded as a target transmission line, and at least two distribution networks are connected to the target transmission line;

[0023] Step S12: From the distribution networks connected to the target transmission line, select any one distribution network as the first distribution network, and the remaining distribution networks connected to the target transmission line as the second distribution network, and the connection position between the first distribution network and the target transmission line as the first connection position, and the connection position between the second distribution network and the target transmission line as the second connection position, and connect the new energy storage node to the power line connected to the corresponding distribution network at the first connection position or the second connection position;

[0024] Step S13: Take any new energy storage node in the distribution network as the target energy storage node, obtain the discharge time of the target energy storage node under the condition of discharge power w, collect the corresponding relationship between discharge power and discharge time of all new energy storage nodes in the power consumption area, and construct a discharge model of the new energy storage node.

[0025] Furthermore, the step S2 comprises:

[0026] Step S21: Obtain the instantaneous power consumption pm1 of the first power distribution network at a certain moment m1, form a sampling pair (m1, pm1), obtain several sampling pairs to form a power consumption sampling set, and obtain the functional relationship of the power consumption in the first power distribution network changing with time;

[0027] Step S22: When the new energy storage node does not provide electric energy to the distribution network, and the total load power on the target transmission line is E, obtain the load power of the first connection position and the load power of the second connection position at a certain moment, obtain the second connection position, when the load power is pd2, the records of all load powers of the first connection position, (pd11, pd2), (pd12, pd2), (pd13, pd2), ..., (pd1k, pd2), wherein pd11, pd12, pd13, ... and pd1k respectively represent the records of the 1st, 2nd, 3rd, ... and kth load powers corresponding to the first connection position when the load power of the second connection position is pd2;

[0028] Step S23: Obtain the minimum value from pd11, pd12, pd13, ... and pd1k and record it as pd1min, and use pd1min as the minimum corresponding power of pd2.

[0029] Furthermore, the step S3 comprises:

[0030] Step S31: Obtain the dispatch record of increasing the total load power of the target transmission line in the power consumption area from the power dispatch record, regard the power consumption area from the dispatch application to the dispatch completion as one power dispatch process, obtain the time length of each dispatch completion process, and obtain the corresponding total load power increase value of the target transmission line in each dispatch process;

[0031] Step S32: The time parameter and the total load power increase value of the target transmission line are used as two parameters of the coordinate system to establish a coordinate system, obtain the load power increase value pv corresponding to any scheduling process and the value of the time length for completing the scheduling process of any scheduling process as tv, mark the position of the point (tv, pv) in the coordinate system, and obtain a marked point;

[0032] Step S33: obtain a number of marked points, perform curve fitting on all the marked points, and obtain a functional relationship between the load scheduling amount and the completion time.

[0033] Furthermore, the step S4 comprises:

[0034] Step S41: when the new energy storage node in the first power distribution network provides electric energy for the first power distribution network, obtaining the discharge power w1 of the new energy node, and obtaining the remaining discharge time Tw1 of the new energy node under the condition of the discharge power w1;

[0035] Step S42: When the total load power on the target transmission line is E, the load power P1 of the current first connection position is obtained. When the load of the first connection position is P1, the minimum corresponding power of the second connection position is recorded as P2, and the surplus power G2 of the second distribution network is calculated, G2=P2+w2-U2, wherein w2 represents the discharge power of the new energy storage node in the second distribution network, and U2 represents the functional relationship between the power consumption in the second distribution network and time.

[0036] When the new energy storage node is put into power supply operation, the power input in the second power distribution network includes the power provided by the transmission line and the power provided by the new energy storage node;

[0037] U2 represents the actual power load in the second power distribution network, so U2=w2+P 2实 , where P 2实 represents the electric energy load actually obtained by the second distribution network from the target transmission line, where P2 represents the estimated value of the target transmission line under the load power condition actually obtained from the target transmission line by the first distribution network when the total load power is E, P2 = P 2实 +G2, the load obtained by the second distribution network from the target transmission line includes P 2实 and adjustable load G2. To ensure power safety, this solution adopts the most conservative estimation method for G2, so the minimum value corresponding to P1 in the historical data is used as P2;

[0038] When G2 is greater than 0, it means that there is power abandonment from the target transmission line to the second distribution network, and the load in the transmission line is not fully used. G2 can be used to supplement the power of the first distribution network. When G2 is less than 0, it means that due to the power supply of the new energy storage node in the first distribution network, the power of the new energy storage node in the first distribution network flows into the second distribution network through the node, and part of the power obtained from the transmission line in the second distribution network is provided by the new energy storage node in the first distribution network.

[0039] Step S43: Establishing a notch power model:

[0040]

[0041] Wherein, R represents the functional relationship of the gap electric power changing with time, wherein U1 represents the functional relationship of the electric power used in the first distribution network changing with time, and t represents the time variable in the functional relationship changing with time.

[0042] Furthermore, the step S5 comprises:

[0043] Step S51: setting a check period of time length T1 and a unit prediction interval of time length y0, y0<T1, obtaining a functional relationship of the notch power model with respect to time variation in any detection period, recorded as an objective function;

[0044] Step S52: In any detection cycle, when the predicted value of R is greater than 0 for the first time, the predicted value is recorded as r1, and the time interval between the predicted value and the current value is obtained, which is recorded as tr1;

[0045] Step S53: In any detection cycle, starting from r1, every time a unit prediction interval passes, the target function is sampled to obtain N consecutive prediction values ​​of R, where the prediction value of the Nth R is recorded as rN;

[0046] Step S54: Calculate the average value of the N predicted values. When the average value is greater than 0, obtain the maximum value rA among the N predicted values, and obtain the time interval between rA and the current value, which is recorded as TA.

[0047] Step S55: Substitute rA into the functional relationship between the power dispatching amount and the completion time to obtain the dispatching time T0 corresponding to the target transmission line power increase of rA. When T0>TA, an alarm is issued to the management user.

[0048] Compared with the prior art, the present invention has the following advantages:

[0049] The present invention designs an energy storage node management module, a transmission line management module, a scheduling data management module, a power gap calculation module and an information judgment module, and connects the energy storage node management module with the power gap calculation module, connects the power gap calculation module with the transmission line management module and the information judgment module respectively, and then connects the information judgment module with the scheduling data management module, uses the energy storage node management module to manage the discharge model of the energy storage node; uses the transmission line management module to manage the relationship between the power distribution network on the same transmission line; uses the scheduling data management module to manage the functional relationship between the load scheduling amount and the completion time; and then uses the power gap calculation module to manage the gap power model corresponding to the distribution area, and combines the information judgment module to judge whether the scheduling time of the power gap is greater than the time when the power gap occurs. In this way, the power gap can be predicted and estimated in a timely and accurate manner, ensuring that the power gap is replenished in a timely manner.

[0050] The present invention establishes a power consumption model in the distribution network, analyzes the power provided by the transmission line and the output degree of the new energy storage node to the load in the distribution network, and estimates the power consumption gap to reduce the problem of difficulty in estimating the power consumption gap when two power sources are used to supply power to the distribution network at the same time. Combined with the historical records of power dispatching, the adjustment time of the power gap is estimated, and a prompt is given when the power gap cannot be replenished in time, so that countermeasures can be taken in advance to reduce the occurrence of power accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0052] Figure 2 It is a schematic diagram of the method flow of the present invention;

[0053] Figure 3 A schematic diagram of a power grid structure in an embodiment;

[0054] Explanation of the markings in the figure: 1. Energy storage node management module, 2. Transmission line management module, 3. Dispatching data management module, 4. Electricity gap calculation module, 5. Information judgment module. DETAILED DESCRIPTION

[0055] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0056] Embodiment 1

[0057] like Figure 1 As shown, an intelligent management system for power grid data based on big data includes an energy storage node management module 1, a transmission line management module 2, a scheduling data management module 3, a power gap calculation module 4 and an information judgment module 5, wherein the energy storage node management module 1 is connected to the power gap calculation module 4, the power gap calculation module 4 is respectively connected to the transmission line management module 2 and the information judgment module 5, and the information judgment module 4 is connected to the scheduling data management module 3.

[0058] The energy storage node management module 1 is used to manage the discharge model of the energy storage node;

[0059] The transmission line management module 2 is used to manage the relationship between the electric power loads of the distribution networks on the same transmission line;

[0060] The scheduling data management module 3 is used to manage the functional relationship between the load scheduling amount and the completion time;

[0061] The power gap calculation module 4 is used to manage the gap power model corresponding to the power distribution area;

[0062] The information judgment module 5 is used to judge whether the scheduling time of the power shortage is greater than the time when the power shortage occurs.

[0063] Specifically, the energy storage node management module 1 includes: a power consumption area management unit, a discharge data management unit and a discharge model management unit, wherein the power consumption area management unit is used to manage the connection information of the transmission lines in the power consumption area, the discharge data management unit is used to manage the discharge data of the new energy storage node, and the discharge model management unit is used to manage the discharge model of the new energy storage node;

[0064] The power transmission line management module 2 includes: a load sampling unit, a load collection unit and a load corresponding unit, wherein the load sampling unit is used to collect information on the power distribution network obtaining electric energy from the power transmission line, the load collection unit is used to collect load records of different power distribution networks, and the load corresponding unit is used to obtain the minimum corresponding power under the load power condition of a certain power distribution network;

[0065] The scheduling data management module 3 includes: a scheduling record collection unit and a function fitting unit, wherein the scheduling record collection unit is used to collect records of the amount of scheduling electric energy and the time spent in the scheduling process, and the function fitting unit is used to obtain a discharge model for constructing a new energy storage node;

[0066] The power gap calculation module 4 includes: a remaining time management unit, a surplus power management unit and a gap power management unit, wherein the remaining time management unit is used to obtain the remaining working time of the energy storage node, the surplus power management unit is used to manage the surplus power provided by the distribution network, and the gap power management unit is used to calculate the gap power and the corresponding time through the gap power model;

[0067] The information judgment module 5 includes: an objective function management unit, a prediction sampling unit and a gap judgment unit, wherein the objective function management unit is used to obtain the objective function, the prediction sampling unit is used to collect the prediction value information on the objective function, and the gap judgment unit is used to compare the scheduling time of the power gap with the time when the power gap occurs.

[0068] Embodiment 2

[0069] Applying the system in the first embodiment above, a method for intelligent management of power grid data based on big data is implemented, such as Figure 2 As shown, the following steps are included:

[0070] Step S1: In a power consumption area including a transmission line and a distribution network, the power consumption area is connected to a power dispatching system, the power consumption area includes at least two distribution networks, a new energy storage node is set in the distribution network, historical discharge data of the new energy storage node is collected, and the relationship between the discharge power and discharge duration of the new energy storage node is obtained;

[0071] Wherein, step S1 comprises:

[0072] Step S11: In the power consumption area, there is at least one transmission line, one of the transmission lines is recorded as a target transmission line, and at least two distribution networks are connected to the target transmission line;

[0073] From the distribution networks connected to the target transmission line, select any distribution network as the first distribution network, use the remaining distribution networks connected to the target transmission line as the second distribution network, use the connection position between the first distribution network and the target transmission line as the first connection position, and the connection position between the second distribution network and the target transmission line as the second connection position, and connect the new energy storage node to the power line connected to the corresponding distribution network at the first connection position or the second connection position;

[0074] The distribution network is a power grid that distributes electricity locally or step by step according to voltage to various users through distribution facilities. In this scheme, it represents the power system network on the user side;

[0075] Step S13: taking any new energy storage node in the distribution network as the target energy storage node, obtaining the discharge duration of the target energy storage node under the condition of discharge power being w, collecting the corresponding relationship between the discharge power and discharge duration of all new energy storage nodes in the power consumption area, and constructing a discharge model of the new energy storage node;

[0076] By collecting the changing relationship between the power and time in the new energy storage node under constant power discharge conditions, the discharge model of the new energy storage node is obtained. The discharge model represents the remaining usage time of the new energy storage node.

[0077] like Figure 3 In the power consumption area shown, L represents the target transmission line, ES1 and ES2 represent two new energy storage nodes respectively, Use1 and Use2 represent the first distribution network and the second distribution network respectively, Port1 represents the first connection position, and Port2 represents the second connection position.

[0078] Step S2: Collect historical power consumption data of the power consumption area, obtain the law of power load changes over time in each distribution network, and obtain the relationship between the power loads of the distribution networks connected to the same transmission line;

[0079] Wherein, step S2 comprises:

[0080] Step S21: Obtain the instantaneous power consumption pm1 of the first power distribution network at a certain moment m1, form a sampling pair (m1, pm1), obtain several sampling pairs to form a power consumption sampling set, and obtain the functional relationship of the power consumption in the first power distribution network changing with time;

[0081] Step S22: When the new energy storage node does not provide electric energy to the distribution network, and the total load power on the target transmission line is E, obtain the load power of the first connection position and the load power of the second connection position at a certain moment, obtain the second connection position, when the load power is pd2, the records of all load powers of the first connection position, (pd11, pd2), (pd12, pd2), (pd13, pd2), ..., (pd1k, pd2), wherein pd11, pd12, pd13, ... and pd1k respectively represent the records of the 1st, 2nd, 3rd, ... and kth load powers corresponding to the first connection position when the load power of the second connection position is pd2;

[0082] Step S23: Obtain the minimum value from pd11, pd12, pd13, ... and pd1k and record it as pd1min, and use pd1min as the minimum corresponding power of pd2.

[0083] Step S3: Collecting the electric energy dispatching records in the power consumption area, and fitting the historical records of different load dispatching amounts and corresponding load dispatching completion time to obtain the functional relationship between the load dispatching amount and the completion time;

[0084] Wherein, step S3 comprises:

[0085] Step S31: Obtain the dispatch record of increasing the total load power of the target transmission line in the power consumption area from the power dispatch record, regard the power consumption area from the dispatch application to the dispatch completion as one power dispatch process, obtain the time length of each dispatch completion process, and obtain the corresponding total load power increase value of the target transmission line in each dispatch process;

[0086] Step S32: The time parameter and the total load power increase value of the target transmission line are used as two parameters of the coordinate system to establish a coordinate system, obtain the load power increase value pv corresponding to any scheduling process and the value of the time length for completing the scheduling process of any scheduling process as tv, mark the position of the point (tv, pv) in the coordinate system, and obtain a marked point;

[0087] Step S33: obtain a number of marked points, perform curve fitting on all the marked points, and obtain a functional relationship between the load scheduling amount and the completion time.

[0088] Step S4: When the new energy storage node provides electric energy to the distribution network, a gap power model is established through the load of the current distribution network on the transmission line, the predicted value of the power load in the distribution network, and the remaining time for the new energy storage node to provide electric energy;

[0089] Wherein, step S4 comprises:

[0090] Step S41: when the new energy storage node in the first power distribution network provides electric energy for the first power distribution network, obtaining the discharge power w1 of the new energy node, and obtaining the remaining discharge time Tw1 of the new energy node under the condition of the discharge power w1;

[0091] Step S42: When the total load power on the target transmission line is E, the load power P1 of the current first connection position is obtained. When the load of the first connection position is P1, the minimum corresponding power of the second connection position is recorded as P2, and the surplus power G2 of the second distribution network is calculated, G2=P2+w2-U2, wherein w2 represents the discharge power of the new energy storage node in the second distribution network, and U2 represents the functional relationship between the power consumption in the second distribution network and time.

[0092] Step S43: Establishing a notch power model:

[0093]

[0094] Wherein, R represents the functional relationship of the gap electric power changing with time, wherein U1 represents the functional relationship of the electric power used in the first distribution network changing with time, and t represents the time variable in the functional relationship changing with time;

[0095] In the embodiment, a function model of R and time is established, and the current time is taken as time point 0. The coordinate of the data value of R on the time axis is the time interval with the current time point.

[0096] Step S5: predicting the load gap in the distribution network through the gap power model, obtaining the maximum value of the load gap in a detection cycle, obtaining the time interval between the maximum value and the current value and the dispatching time of the electric energy corresponding to the maximum value of the dispatching load gap, and issuing an alarm when the dispatching time is greater than the time interval;

[0097] Wherein, step S5 comprises:

[0098] Step S51: setting a check period of time length T1 and a unit prediction interval of time length y0, y0<T1, obtaining a functional relationship of the notch power model with respect to time variation in any detection period, recorded as an objective function;

[0099] Step S52: In any detection cycle, when the predicted value of R is greater than 0 for the first time, the predicted value is recorded as r1, and the time interval between the predicted value and the current value is obtained, which is recorded as tr1;

[0100] Step S53: In any detection cycle, starting from r1, every time a unit prediction interval passes, the target function is sampled to obtain N consecutive prediction values ​​of R, where the prediction value of the Nth R is recorded as rN;

[0101] Step S54: Calculate the average value of the N predicted values. When the average value is greater than 0, obtain the maximum value rA among the N predicted values, and obtain the time interval between rA and the current value, which is recorded as TA.

[0102] Step S55: Substitute rA into the functional relationship between the power dispatching amount and the completion time to obtain the dispatching time T0 corresponding to the target transmission line power increase of rA. When T0>TA, an alarm is issued to the management user.

[0103] In summary, this scheme collects historical electricity consumption data of the power consumption area, obtains the law of power load changes over time in each distribution network, obtains the relationship between the power load of the distribution networks connected on the same transmission line, and then fits the historical records of different load dispatching amounts and the corresponding load dispatching completion time to obtain the functional relationship between the load dispatching amount and the completion time. Then, through the current load of the distribution network on the transmission line, as well as the predicted value of the power load in the distribution network and the remaining time for the new energy storage node to provide power, a gap power model is established. Finally, the load gap in the distribution network is predicted by the gap power model, and the time interval between the maximum value and the current time and the dispatching time of the power corresponding to the maximum value of the dispatching load gap are obtained. Applying this scheme to the actual power system can timely and accurately estimate the power gap, reduce the problem of difficult estimation of the power gap when two power sources are used to supply power to the distribution network at the same time, can accurately estimate the adjustment time of the power gap, and give a prompt when the power gap cannot be replenished in time, so that early response measures can be taken in advance to reduce the occurrence of power accidents.

Claims

1. A big data-based intelligent power grid data management system, characterized in that: It includes an energy storage node management module, a transmission line management module, a scheduling data management module, a power consumption gap calculation module and an information judgment module. The energy storage node management module is connected to the power consumption gap calculation module, and the power consumption gap calculation module is respectively connected to the transmission line management module and the information judgment module. The information judgment module is connected to the scheduling data management module. The energy storage node management module is used to manage the discharge model of the energy storage node; The transmission line management module is used to manage the relationship between the electric power loads of the distribution networks on the same transmission line; The scheduling data management module is used to manage the functional relationship between the load scheduling amount and the completion time; The power consumption gap calculation module is used to manage the gap power model corresponding to the power distribution area; The information determination module is used to determine whether the scheduling time of the power consumption gap is greater than the time when the power consumption gap occurs.

2. The intelligent management system for power grid data based on big data according to claim 1 is characterized in that: The energy storage node management module includes: a power consumption area management unit, a discharge data management unit and a discharge model management unit, wherein the power consumption area management unit is used to manage the connection information of the transmission lines in the power consumption area, the discharge data management unit is used to manage the discharge data of the new energy storage node, and the discharge model management unit is used to manage the discharge model of the new energy storage node; The transmission line management module includes: a load sampling unit, a load collection unit and a load corresponding unit, wherein the load sampling unit is used to collect information on the distribution network obtaining electric energy from the transmission line, the load collection unit is used to collect load records of different distribution networks, and the load corresponding unit is used to obtain the minimum corresponding power under the load power conditions of a certain distribution network.

3. The intelligent management system for power grid data based on big data according to claim 1 is characterized in that: The scheduling data management module includes: a scheduling record collection unit and a function fitting unit, wherein the scheduling record collection unit is used to collect records of the amount of scheduling electric energy and the time spent in the scheduling process, and the function fitting unit is used to obtain a discharge model for constructing a new energy storage node; The information judgment module includes: an objective function management unit, a prediction sampling unit and a gap judgment unit, wherein the objective function management unit is used to obtain the objective function, the prediction sampling unit is used to collect the prediction value information on the objective function, and the gap judgment unit is used to compare the scheduling time of the electricity gap with the time when the electricity gap occurs.

4. The intelligent management system for power grid data based on big data according to claim 1 is characterized in that: The electricity gap calculation module includes: a remaining time management unit, a surplus power management unit and a gap power management unit, wherein the remaining time management unit is used to obtain the remaining working time of the energy storage node, the surplus power management unit is used to manage the surplus power provided by the distribution network, and the gap power management unit is used to calculate the gap power and the corresponding time through the gap power model.

5. A method for intelligent management of power grid data based on big data, characterized in that: The following steps are involved: Step S1: In a power consumption area including a transmission line and a distribution network, the power consumption area is connected to a power dispatching system, the power consumption area includes at least two distribution networks, a new energy storage node is set in the distribution network, historical discharge data of the new energy storage node is collected, and the relationship between the discharge power and the discharge duration of the new energy storage node is obtained; Step S2: Collect historical power consumption data of the power consumption area, obtain the law of power load changes over time in each distribution network, and obtain the relationship between the power loads of the distribution networks connected to the same transmission line; Step S3, collecting the electric energy dispatching records in the power consumption area, and fitting the historical records of different load dispatching amounts and corresponding load dispatching completion time to obtain the functional relationship between the load dispatching amount and the completion time; Step S4: When the new energy storage node provides electric energy to the distribution network, a gap power model is established through the load of the current distribution network on the transmission line, the predicted value of the power load in the distribution network, and the remaining time for the new energy storage node to provide electric energy; Step S5, predict the load gap in the distribution network through the gap power model, obtain the maximum value of the load gap in a detection cycle, obtain the scheduling time of the electric energy corresponding to the current time interval and the maximum value of the scheduling load gap when the maximum value occurs, and issue an alarm when the scheduling time is greater than the time interval.

6. The method for intelligent management of power grid data based on big data according to claim 5, characterized in that: The step S1 comprises: Step S11: In the power consumption area, there is at least one transmission line, one of the transmission lines is recorded as a target transmission line, and at least two distribution networks are connected to the target transmission line; Step S12: From the distribution networks connected to the target transmission line, select any one distribution network as the first distribution network, and the remaining distribution networks connected to the target transmission line as the second distribution network, and the connection position between the first distribution network and the target transmission line as the first connection position, and the connection position between the second distribution network and the target transmission line as the second connection position, and connect the new energy storage node to the power line connected to the corresponding distribution network at the first connection position or the second connection position; Step S13: Take any new energy storage node in the distribution network as the target energy storage node, obtain the discharge time of the target energy storage node under the condition of discharge power w, collect the corresponding relationship between discharge power and discharge time of all new energy storage nodes in the power consumption area, and construct a discharge model of the new energy storage node.

7. The method for intelligent management of power grid data based on big data according to claim 6, characterized in that: The step S2 comprises: Step S21: Obtain the instantaneous power consumption pm1 of the first power distribution network at a certain moment m1, form a sampling pair (m1, pm1), obtain several sampling pairs to form a power consumption sampling set, and obtain the functional relationship of the power consumption in the first power distribution network changing with time; Step S22: When the new energy storage node does not provide electric energy to the distribution network, and the total load power on the target transmission line is E, obtain the load power of the first connection position and the load power of the second connection position at a certain moment, obtain the second connection position, when the load power is pd2, the records of all load powers of the first connection position, (pd11, pd2), (pd12, pd2), (pd13, pd2), ..., (pd1k, pd2), wherein pd11, pd12, pd13, ... and pd1k respectively represent the records of the 1st, 2nd, 3rd, ... and kth load powers corresponding to the first connection position when the load power of the second connection position is pd2; Step S23: Obtain the minimum value from pd11, pd12, pd13, ... and pd1k and record it as pd1min, and use pd1min as the minimum corresponding power of pd2.

8. The method for intelligent management of power grid data based on big data according to claim 7, characterized in that: The step S3 comprises: Step S31: Obtain the dispatch record of increasing the total load power of the target transmission line in the power consumption area from the power dispatch record, regard the power consumption area from the dispatch application to the dispatch completion as one power dispatch process, obtain the time length of each dispatch completion process, and obtain the corresponding total load power increase value of the target transmission line in each dispatch process; Step S32: The time parameter and the total load power increase value of the target transmission line are used as two parameters of the coordinate system to establish a coordinate system, obtain the load power increase value pv corresponding to any scheduling process and the value of the time length for completing the scheduling process of any scheduling process as tv, mark the position of the point (tv, pv) in the coordinate system, and obtain a marked point; Step S33: Obtain a number of marked points, perform curve fitting on all the marked points, and obtain a functional relationship between the load scheduling amount and the completion time.

9. The method for intelligent management of power grid data based on big data according to claim 8, characterized in that: The step S4 comprises: Step S41: when the new energy storage node in the first power distribution network provides electric energy for the first power distribution network, obtaining the discharge power w1 of the new energy node, and obtaining the remaining discharge time Tw1 of the new energy node under the condition of the discharge power w1; Step S42: When the total load power on the target transmission line is E, the load power P1 of the current first connection position is obtained. When the load of the first connection position is P1, the minimum corresponding power of the second connection position is recorded as P2, and the surplus power G2 of the second distribution network is calculated, G2=P2+w2-U2, wherein w2 represents the discharge power of the new energy storage node in the second distribution network, and U2 represents the functional relationship between the power consumption in the second distribution network and time. When the new energy storage node is put into power supply operation, the power input in the second power distribution network includes the power provided by the transmission line and the power provided by the new energy storage node; U2 represents the actual power load in the second power distribution network, so U2=w2+P 2实 , where P 2实 represents the electric energy load actually obtained by the second distribution network from the target transmission line, where P2 represents the estimated value of the target transmission line under the load power condition actually obtained from the target transmission line by the first distribution network when the total load power is E, P2 = P 2实 +G2, the load obtained by the second distribution network from the target transmission line includes P 2实 and adjustable load G2. To ensure power safety, this solution adopts the most conservative estimation method for G2, so the minimum value corresponding to P1 in the historical data is used as P2; When G2 is greater than 0, it means that there is power abandonment from the target transmission line to the second distribution network, and the load in the transmission line is not fully used. G2 can be used to supplement the power of the first distribution network. When G2 is less than 0, it means that due to the power supply of the new energy storage node in the first distribution network, the power of the new energy storage node in the first distribution network flows into the second distribution network through the node, and part of the power obtained from the transmission line in the second distribution network is provided by the new energy storage node in the first distribution network. Step S43: Establishing a notch power model: Wherein, R represents the functional relationship of the gap electric power changing with time, wherein U1 represents the functional relationship of the electric power used in the first distribution network changing with time, and t represents the time variable in the functional relationship changing with time.

10. The method for intelligent management of power grid data based on big data according to claim 9, characterized in that: The step S5 comprises: Step S51: setting a check period of time length T1 and a unit prediction interval of time length y0, y0<T1, obtaining a functional relationship of the notch power model with respect to time variation in any detection period, recorded as an objective function; Step S52: In any detection cycle, when the predicted value of R is greater than 0 for the first time, the predicted value is recorded as r1, and the time interval between the predicted value and the current value is obtained, which is recorded as tr1; Step S53: In any detection cycle, starting from r1, every time a unit prediction interval passes, the target function is sampled to obtain N consecutive prediction values ​​of R, where the prediction value of the Nth R is recorded as rN; Step S54: Calculate the average value of the N predicted values. When the average value is greater than 0, obtain the maximum value rA among the N predicted values, and obtain the time interval between rA and the current value, which is recorded as TA. Step S55: Substitute rA into the functional relationship between the power dispatching amount and the completion time to obtain the dispatching time T0 corresponding to the target transmission line power increase of rA. When T0>TA, an alarm is issued to the management user.

Images