Substation abnormal load adaptive regulation method, system, device and medium

Abstract

The application relates to a substation abnormal load self-adaptive regulation method, system, device and medium, the method comprising the following steps: obtaining substation state information, forming object state flow and topological constraint; generating a transferable load slice with minimum residence time based on the object state flow and the topological constraint, and performing thermal inertia correction prediction on a target channel corresponding to the transferable load slice; obtaining a thermal stability check result in combination with a prediction result and the minimum residence time; generating a candidate operation sequence and a corresponding rollback anchor point based on the thermal stability check result, the topological constraint and a regulation parameter; performing implementation judgment on the candidate operation sequence, executing a sequence passing the implementation judgment and limiting reverse action; monitoring an execution state; when abnormal load is continuous and a residence time length reaches the minimum residence time, restoring to a state before operation according to the rollback anchor point, and updating the regulation parameter according to an execution result. The application has the effect of improving regulation stability.

Description

Technical Field

[0001] This invention belongs to the technical field of power system operation control, and in particular relates to a method, system, equipment and medium for adaptive control of abnormal loads in substations. Background Technology

[0002] Currently, in substation operation scenarios involving fluctuating output from new energy sources, rotating shutdowns of main transformers, feeder transfers, and concurrent changes in large load users, substation load status is characterized by strong volatility, wide correlation range, and frequent changes in operating modes. When abnormal loads are transmitted between main transformers, busbar sections, and connecting feeders, the load transfer range, channel carrying capacity, continuous operating time, and recovery conditions are mutually constrained, placing high demands on the safety and stability of substation operation.

[0003] Existing methods for handling abnormal loads in substations typically determine load transfer actions based on the overall circuit load forecast and preset threshold judgment results. This method has a coarse control granularity and a low degree of matching between the forecast results and the actual operating status on site. This can easily cause the operating status after load transfer to deviate from expectations, resulting in unstable load control within the substation. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, equipment, and medium for adaptive control of abnormal loads in substations, so as to solve the technical problem that the matching degree between the existing abnormal load control actions and the actual operating state of substations is low.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for adaptive control of abnormal loads in a substation, the method comprising: Obtain substation status information, and form object state flow and topology constraints based on the substation status information; Based on the object state flow and the topology constraints, a transferable load slice with a minimum residence time is generated. Thermal inertia correction prediction is performed on the target channel corresponding to the transferable load slice according to the object state flow. Then, thermal stability verification results are obtained based on the correction prediction results and the minimum residence time. Obtain control parameters, and based on the thermal stability verification results, the topological constraints, and the control parameters, generate candidate operation sequences and corresponding backoff anchor points for each of the transferable load slices; The candidate operation sequence and the corresponding backoff anchor point are subject to adjustment sequence determination. The candidate operation sequence that passes the determination is executed, and the reverse action is performed on the transferable load slice according to the minimum dwell time limit. Monitor the execution status of the candidate operation sequence. When the execution status meets the conditions of continuous abnormal load and the residence time of the transferable load slice reaches the minimum residence time, restore the state to the state before the operation according to the rollback anchor point, record the execution result, and update the control parameters according to the execution result.

[0006] By adopting the above technical solutions, and by acquiring substation status information and forming object state flows and topological constraints, the operating status and electrical connection limitations of each object within the substation can be uniformly characterized, thereby improving the matching degree between the abnormal load control basis and the on-site operation mode. By generating transferable load slices with minimum residence time and combining them with thermal inertia correction prediction results for thermal stability verification, the load transfer granularity can be refined while judging the load-bearing status of the target channel during continuous transfer, thereby reducing the risk of thermal state exceeding limits after load transfer. By generating candidate operation sequences and corresponding rollback anchors based on thermal stability verification results, topological constraints, and control parameters, forward control actions can be associated with the pre-operation state and recovery relationship, thereby improving the pertinence of candidate operation sequences and the recoverability under abnormal conditions. By implementing and judging candidate operation sequences, performing reverse actions according to minimum residence time limits, and implementing rollback and updating control parameters according to the execution status, the operational oscillations caused by frequent reverse control can be reduced, and subsequent control basis can be corrected based on actual execution, thereby improving the stability and adaptability of abnormal load control.

[0007] In one example, the present invention can be further configured as follows: obtaining substation status information and forming object state flow and topology constraints based on the substation status information includes: Collect measurement data from the main transformer, busbar and feeder, and obtain the status of tie switches, protection actions, equipment temperature, environmental parameters, maintenance methods and recent operation records to obtain operating status data; Obtain a primary wiring diagram and use the operating status data and the primary wiring diagram as the substation status information; The operational status data is time-stamped, outlier removed, and confidence level marked. Based on the processed operational status data, the thermal state change rate, on / off status, maintenance constraints, and operation frequency of each object are determined. The processed operational status data is then combined with the determination results to obtain the object state stream. Based on the primary wiring diagram, the switch status, and the maintenance constraints, the electrical connection relationships and available communication relationships between each object are determined to obtain the topology state. Based on the topology state, the channel restrictions corresponding to load transfer out and load transfer in are determined to form the topology constraints.

[0008] By adopting the above technical solution, by collecting measurement data and equipment status information of main transformers, busbars and feeders, and performing time-scale alignment, outlier removal and reliability marking on the operating status data, and combining it with the primary wiring diagram to form object state flow and topology constraints, the deviation of multi-source data in sampling time, data quality and equipment correspondence can be reduced, thereby improving the accuracy of substation operating status description and load transfer channel limitation.

[0009] In one example, the present invention can be further configured as follows: generating a transferable load slice with a minimum residence time based on the object state flow and the topology constraints, performing thermal inertia correction prediction on the target channel corresponding to the transferable load slice according to the object state flow, and then obtaining a thermal stability verification result based on the correction prediction result and the minimum residence time, including: Extract feeder loads and branch switch states from the object state stream, obtain user groups and importance lists, and determine the electrical boundaries and user boundaries of the loads within the station based on the feeder loads, branch switch states, user groups, and topology constraints. The load within the station is split according to the electrical boundary and the user boundary. The source loop, target channel and user importance corresponding to the split load are determined according to the topology constraints and the importance list. The minimum dwell time corresponding to the split load is obtained. The source loop, the target channel, the user importance and the minimum dwell time are associated with the split load to obtain the transferable load slice. Extract the real-time current, equipment temperature, environmental quantity, thermal state change rate and operation frequency corresponding to the target channel from the object state stream, and determine the heat accumulation, cooling hysteresis and operation disturbance increment based on the extraction results to obtain the thermal inertia state; The corrected prediction result is obtained by predicting the thermal state of the target channel in multiple future time windows based on the thermal inertia state. The thermal stability of the target channel is verified based on the correction prediction result and the minimum dwell time to obtain the thermal stability verification result.

[0010] By adopting the above technical solution, the load within the station is split according to the electrical boundary and the user boundary, and the source circuit, target channel, user importance and minimum residence time are associated to form a transferable load slice. Multi-time window prediction and thermal stability verification are performed according to the thermal inertia state of the target channel. The independent transfer conditions of the load, the power supply requirements of the user and the continuous thermal carrying capacity of the target channel can be considered at the same time, thereby improving the rationality of the division of transferable load slices and the selection of target channels.

[0011] In one example, the present invention can be further configured as follows: the thermal stability verification of the target channel based on the correction prediction result and the minimum dwell time, to obtain the thermal stability verification result, includes: Extract the temperature rise trend and remaining margin of the target channel over multiple future time windows from the corrected prediction results; Based on the temperature rise trend and the remaining margin, the thermal stability state of the target channel within each time window is determined, and the time window determination result is obtained. According to the order of the time windows, the time window determination results corresponding to the continuous time windows are integrated to determine the duration for which the target channel continuously meets the thermal stability requirements; The duration is compared with the minimum residence time corresponding to the transferable load slice, and the thermal stability verification result is obtained based on the comparison result.

[0012] By adopting the above technical solution, by extracting the temperature rise trend and remaining margin of the target channel in multiple future time windows, the duration of continuously meeting the thermal stability requirements can be determined. By comparing the duration with the minimum residence time, it can be determined whether the target channel can maintain thermal stability during the residence period of the load slice that can be supplied, thereby reducing the risk of subsequent thermal overruns caused by load transfer based solely on the state at a single moment.

[0013] In one example, the present invention can be further configured as follows: the step of obtaining the control parameters, based on the thermal stability verification result, the topological constraints, and the control parameters, generating candidate operation sequences and corresponding backoff anchor points for each candidate operation sequence for the transferable load slice, includes: The control parameters are obtained by acquiring the conduction coefficient between each source loop and the target channel, as well as the slicing success rate corresponding to each load-transferable slice; Based on the topological constraints and the conduction coefficient, the predicted load change of the corresponding source circuit after the transferable load slice is transferred out and the predicted load change of the corresponding target channel after the transfer is in are determined, thus obtaining the channel influence; Based on the channel impact, the thermal stability verification result, and the slice success rate, each of the transferable load slices is screened, and based on the screening result, a candidate operation sequence is generated that includes at least one of the following actions: slice transfer, tie switch opening / closing, and bus section switching. Obtain the switch configuration, load distribution, and protection blocking status before the execution of each candidate operation sequence, and determine the recoverable path based on the topology constraints; The switch configuration, load distribution, protection lockout state, and recoverable path are bound to the corresponding candidate operation sequences to generate a backoff anchor point that corresponds one-to-one with each candidate operation sequence.

[0014] By adopting the above technical solution, the influence of the transfer of load slices on the channel from the load slices is determined based on the conduction coefficient. Candidate operation sequences are generated by combining the thermal stability verification results and the slice success rate. The switch configuration, load distribution, protection lockout status and recoverable path before the operation are bound as backoff anchor points. This can improve the matching degree between the candidate operation sequence and the actual load transfer relationship and operating constraints, thereby enhancing the effectiveness of the control operation and the traceability of abnormal recovery.

[0015] In one example, the present invention can be further configured as follows: the step of performing a control sequence determination on the candidate operation sequence and the corresponding backoff anchor point, executing the candidate operation sequence that passes the determination, and performing a reverse action on the transferable load slice according to the minimum dwell time limit, includes: The abnormal load corresponding to the candidate operation sequence is assessed based on the control parameters to obtain the abnormal risk, and the necessity of control is determined based on the abnormal risk. If the determination result of the necessity of regulation indicates that regulation is required, the candidate operation sequence is determined to have the conditions for execution based on the thermal stability verification result and the regulation parameters, and the executability determination result is obtained. If the executability judgment result indicates that the execution conditions are met, a recoverable path is extracted from the fallback anchor point, and the validity of the fallback anchor point and the reachability of the recoverable path are verified to obtain the reversibility judgment result. Based on the determination results of the necessity of regulation, the feasibility, and the reversibility, a determination result for the implementation of the regulation sequence is obtained, and the candidate operation sequence that is allowed to be implemented according to the determination result of the implementation of the regulation sequence is executed. Monitor the dwell time of the transferable load slice, and restrict reverse transfer and rollback actions for the transferable load slice when the dwell time does not reach the minimum dwell time.

[0016] By adopting the above technical solution, and by sequentially determining the necessity, feasibility, and reversibility of the control, and only executing the candidate operation sequence that is allowed to be implemented according to the control sequence implementation judgment, while restricting reverse transfer and backoff actions when the dwell time does not reach the minimum dwell time, unnecessary, unexecutable, or unreliable control operations can be avoided, thereby reducing the impact of frequent switching and repeated control on the stable operation of the substation.

[0017] In one example, the present invention can be further configured as follows: monitoring the execution status of the candidate operation sequence, when the execution status satisfies the condition of continuous abnormal load and the residence time of the transferable load slice reaches the minimum residence time, restoring to the pre-operation state according to the fallback anchor point, recording the execution result, and updating the control parameters according to the execution result, including: Monitor the load status, actual load changes of the source loop and target channel after the candidate operation sequence is executed, as well as the dwell time of the corresponding transferable load slice, and record the success or failure of the execution of the transferable load slice to obtain the execution status; Determine whether the abnormal load state continues based on the execution state. When the abnormal load state continues and the dwell time reaches the minimum dwell time, extract the recoverable path and pre-operation state information from the fallback anchor point. The system restores the system to the pre-operation state corresponding to the pre-operation state information according to the recoverable path, and records the rollback result when the rollback anchor point is called. Record the actual load changes, the success or failure of the execution of the transferable load slice, and the invocation status of the rollback anchor point, and record the rollback result when the rollback anchor point is invoked to obtain the execution result; The transmission coefficient and slicing success rate are extracted from the control parameters, and the predicted load change corresponding to the candidate operation sequence is obtained. The transmission coefficient is updated according to the deviation between the actual load change and the predicted load change, and the slicing success rate is updated according to the execution result to obtain the updated control parameters.

[0018] By adopting the above technical solution, by monitoring the actual load changes, slice dwell time and execution success or failure after the candidate operation sequence is executed, the state before the operation is restored according to the rollback anchor point when the abnormal load continues, and the transmission coefficient and slice success rate are updated according to the deviation between the actual load change and the predicted load change, a closed-loop feedback process covering control execution, abnormal recovery and parameter correction can be formed, thereby improving the accuracy and adaptability of subsequent abnormal load control results.

[0019] In a second aspect, the present invention provides an adaptive control system for abnormal loads in a substation, the system comprising: The state construction module is used to acquire substation state information and form object state flow and topology constraints based on the substation state information. The slice prediction module is used to generate a transferable load slice with a minimum residence time based on the object state flow and the topology constraints, perform thermal inertia correction prediction on the target channel corresponding to the transferable load slice according to the object state flow, and then obtain the thermal stability verification result based on the correction prediction result and the minimum residence time. The sequence generation module is used to acquire control parameters, and based on the thermal stability verification results, the topological constraints and the control parameters, generate candidate operation sequences and backoff anchor points corresponding to each candidate operation sequence for the transferable load slice. The implementation judgment module is used to perform control sequence implementation judgment on the candidate operation sequence and the corresponding backoff anchor point, execute the candidate operation sequence that passes the implementation judgment, and perform the reverse action on the transferable load slice according to the minimum residence time limit; The feedback update module is used to monitor the execution status of the candidate operation sequence. When the execution status meets the conditions of continuous abnormal load state and the residence time of the transferable load slice reaches the minimum residence time, the module restores the state before operation according to the rollback anchor point, records the execution result, and updates the control parameters according to the execution result.

[0020] By adopting the above technical solutions, and by acquiring substation status information and forming object state flows and topological constraints, the operating status and electrical connection limitations of each object within the substation can be uniformly characterized, thereby improving the matching degree between the abnormal load control basis and the on-site operation mode. By generating transferable load slices with minimum residence time and combining them with thermal inertia correction prediction results for thermal stability verification, the load transfer granularity can be refined while judging the load-bearing status of the target channel during continuous transfer, thereby reducing the risk of thermal state exceeding limits after load transfer. By generating candidate operation sequences and corresponding rollback anchors based on thermal stability verification results, topological constraints, and control parameters, forward control actions can be associated with the pre-operation state and recovery relationship, thereby improving the pertinence of candidate operation sequences and the recoverability under abnormal conditions. By implementing and judging candidate operation sequences, performing reverse actions according to minimum residence time limits, and implementing rollback and updating control parameters according to the execution status, the operational oscillations caused by frequent reverse control can be reduced, and subsequent control basis can be corrected based on actual execution, thereby improving the stability and adaptability of abnormal load control.

[0021] In a third aspect, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the aforementioned substation abnormal load adaptive control method.

[0022] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the aforementioned substation abnormal load adaptive control method. Attached Figure Description

[0023] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart of an adaptive control method for abnormal loads in a substation, as described in an embodiment of the present invention. Figure 2 This is a structural block diagram of the substation abnormal load adaptive control system in an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0024] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0025] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this invention is for describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0026] Example 1 like Figure 1 As shown, this invention discloses an adaptive control method for abnormal loads in substations, which specifically includes the following steps: S10: Obtain substation status information and form object state flow and topology constraints based on the substation status information.

[0027] Specifically, the operating status, equipment status, environmental status, and wiring relationships of each electrical object in the substation are organized according to a unified object identifier and a unified time base. The status data that changes over time is continuously arranged according to the corresponding electrical object to form an object status stream. At the same time, topological constraints are formed based on the current wiring relationship, equipment commissioning / decommissioning status, and operating mode to limit the load transfer direction, load transfer direction, and available channel range.

[0028] S20: Generate a transferable load slice with minimum residence time based on object state flow and topology constraints. Perform thermal inertia correction prediction on the target channel corresponding to the transferable load slice according to object state flow. Then, obtain the thermal stability verification result based on the correction prediction result and minimum residence time.

[0029] Specifically, based on the load distribution reflected by the object state flow and the electrical connection range reflected by the topology constraints, loads that can be independently transferred out and transferred in along available channels are organized into transferable load slices. The minimum dwell time required after the associated execution of each transferable load slice is determined. Then, the future operating state is corrected and predicted based on the current electrical state, thermal state, and recent operating state of the target channel, and it is determined whether the target channel can continuously meet the thermal stability requirements within the corresponding minimum dwell time.

[0030] S30: Obtain control parameters, and based on thermal stability verification results, topological constraints, and control parameters, generate candidate operation sequences and corresponding backoff anchor points for each transferable load slice.

[0031] Specifically, the control parameters used to describe the load transfer relationship between different source circuits and target channels, as well as the historical execution status of load slices that can be transferred, are read. The thermal stability verification results and the operating range allowed by the current topology are combined to generate candidate operation sequences with clear action order. At the same time, the running status and reverse recovery relationship before the implementation of each candidate operation sequence are saved to form backoff anchor points corresponding to the candidate operation sequences.

[0032] S40: Execute the control sequence implementation judgment for the candidate operation sequence and the corresponding backoff anchor point, execute the candidate operation sequence that passes the implementation judgment, and perform the reverse action for the transferable load slice according to the minimum residence time limit.

[0033] Specifically, the control sequence implementation judgment result is formed by combining the control requirements of the candidate operation sequence for abnormal load, the forward execution conditions of the candidate operation sequence, and the reverse recovery conditions corresponding to the rollback anchor point. Only the candidate operation sequence that is allowed to be implemented by the implementation judgment result is executed. After the transferable load slice completes the transfer, the dwell time is accumulated. Before the dwell time reaches the minimum dwell time, reverse transfer and rollback for the same transferable load slice are suppressed.

[0034] S50: Monitor the execution status of candidate operation sequences. When the execution status meets the requirements of continuous abnormal load state and the residence time of the load slice that can be transferred reaches the minimum residence time, restore the state to the state before operation according to the rollback anchor point, record the execution results, and update the control parameters according to the execution results.

[0035] Specifically, the load, topology, and thermal status are continuously collected after the candidate operation sequence is implemented, and an execution status is formed. When the execution status reflects that the abnormal load has not recovered within the continuous monitoring time window and the available load slice has met the minimum residence time, the corresponding rollback anchor point is called to restore the running status before the candidate operation sequence was executed. At the same time, the load transfer, slice execution, and rollback recovery results are recorded, and the recorded results are used to correct the control parameters used in subsequent control.

[0036] In one embodiment, step S10, namely acquiring substation status information and forming object state flow and topology constraints based on the substation status information, includes: S11: Collect measurement data from the main transformer, busbar and feeder, and obtain the status of tie switches, protection actions, equipment temperature, environmental parameters, maintenance methods and recent operation records to obtain operating status data.

[0037] Specifically, the current, voltage, active power, and reactive power of each main transformer, bus, and feeder are collected according to the preset sampling period. Each measurement data is associated with the corresponding equipment number, sampling time, and data source. At the same time, the open / closed status of the tie switch, the operation and blocking status of the protection device, the temperature of the main transformer and conductor, the ambient temperature in the station, the current maintenance mode, and the switch operation records within the preset historical period are read. The measurement information and status information corresponding to the same sampling time are encapsulated into operating status data. Among them, the recent operation records at least represent the operation object, operation direction, operation time, and the cumulative number of operations within the preset time window.

[0038] S12: Obtain the primary wiring diagram and use the operating status data and the primary wiring diagram as substation status information.

[0039] Specifically, the primary wiring diagram and its version identifier corresponding to the current substation are read. The electrical objects and connection endpoints corresponding to the main transformer, busbar, feeder, busbar sectionalizing switch and tie switch are identified from the primary wiring diagram. The electrical object numbers in the primary wiring diagram are matched with the equipment numbers carried in the operating status data. The matched operating status data, primary wiring diagram and current operating mode identifier are combined into the substation status information at the same time.

[0040] S13: Perform time-scale alignment, outlier removal, and reliability marking on the operating status data. Based on the processed operating status data, determine the thermal state change rate, on / off status, maintenance constraints, and operation frequency of each object. Combine the processed operating status data with the determined results to obtain the object state flow.

[0041] Specifically, operational status data from different sampling periods and data sources are mapped to a unified time axis. Timestamp matching is performed on measurement and status data of the same electrical object within the same time window. Data exceeding the equipment's allowable range, exhibiting abnormal rates of change, or inconsistent with adjacent measurements are marked as anomalies and removed from the valid calculation data. Reliability tags are written to retained data based on data integrity, timeliness, and multi-source consistency. The thermal state change rate is calculated based on the equipment temperature at adjacent times and calculated according to formula x. i (t)=[I i (t),U i (t),P i (t),Qi (t),T i (t),dT i / dt,S i (t),B i (t),Nop i (t),E(t),Rm i [(t)] Construct the object state vector of electrical object i at time t, where I i (t) represents the current, U i (t) represents the voltage, P i (t) represents the active power, Q i (t) represents reactive power, T i (t) represents the equipment temperature, dT i / dt is the rate of change of thermal state, S i (t) represents the switch state, B i (t) indicates a protective action or locked state, Nop i (t) represents the operation frequency within the preset time window, E(t) represents the environmental variable, and Rm i (t) represents the maintenance constraint corresponding to the maintenance method. The object state vectors of each electrical object are combined in chronological order to obtain the object state flow X(t).

[0042] S14: Determine the electrical connection relationships and available communication relationships between each object based on the primary wiring diagram, switch status, and maintenance constraints to obtain the topology status, and determine the corresponding channel restrictions for load transfer out and load transfer in based on the topology status to form topology constraints.

[0043] Specifically, the static connection relationships between each main transformer, busbar, feeder, and tie switch are determined based on the primary wiring diagram. Then, electrical connections that are in the open state are deleted and electrical connections that are in the closed state are connected based on the current switch status. Maintenance constraints are used to exclude maintenance equipment and connection paths formed through maintenance equipment, resulting in a topology state matrix G(t) reflecting the current operating mode, where matrix elements G... ij (t) characterizes whether electrical object i and electrical object j form a valid electrical connection at time t. Based on the topology state matrix, search for the connection path between each source circuit and the backup target channel. Combined with the operable state of the tie switch, the protection lockout state, the equipment maintenance state, and the load transfer direction, determine the source circuits that can be transferred out, the target channels that can be transferred in, and the electrical objects that are prohibited from passing through, thus forming topology constraints.

[0044] In one embodiment, in step S20, a transferable load slice with a minimum dwell time is generated based on the object state flow and topological constraints. Thermal inertia correction prediction is performed on the target channel corresponding to the transferable load slice according to the object state flow. Then, thermal stability verification results are obtained based on the correction prediction results and the minimum dwell time, including: S21: Extract feeder load and branch switch status from the object state stream, obtain user grouping and importance list, and determine the electrical boundary and user boundary of the load in the station based on feeder load, branch switch status, user grouping and topology constraints.

[0045] Specifically, the active load, reactive load, and branch switch status of each feeder and feeder branch at the current moment are read from the object state stream. The load range that is in the same closed switch section and can be transferred out or into as a whole through the same set of switch actions is determined as the electrical boundary. The user grouping results and importance list are read, and users with the same or compatible power supply continuity requirements, user categories, and importance levels are organized into user sets. The user boundary is determined based on the principle of not splitting user sets that need to maintain a common power supply relationship. Then, the existence of available transfer paths and target channels for the loads corresponding to the electrical boundary is verified according to the topology constraints, so as to obtain the substation load boundary that simultaneously satisfies the electrical connection relationship and the user power supply relationship.

[0046] S22: Split the load within the station according to the electrical boundary and the user boundary. Determine the source circuit, target channel and user importance corresponding to the split load according to the topology constraints and importance list. Obtain the minimum residence time corresponding to the split load. Associate the source circuit, target channel, user importance and minimum residence time with the split load to obtain the load slice that can be supplied.

[0047] Specifically, the load within the station is initially segmented according to electrical boundaries, and then the load segments spanning different user groups are further subdivided according to user boundaries. This ensures that each subdivided load can be independently transferred by a defined switch combination without disrupting the shared power supply relationship of important users. The source circuit is determined based on the feeder where the load was located before being transferred out. The target channel is determined based on the backup path connected to the source circuit and having remaining carrying capacity in the topology constraints. The user importance of the users included in the load is determined based on the importance list. The minimum dwell time is determined based on the maintenance requirements in the station's control procedures that match the load capacity, user importance, target channel, and operation type. Finally, the process is performed according to formula z. s =[src s ,dst s ,p s ,q s grade s , anchor s Constructing load slicing that can be transferred s , where src s dst is the source loop identifier. s p is the target channel identifier. s For the active load of the slice, q s For slice reactive load, grade sBased on user importance, For minimum dwell time, anchor s An anchor point identifier field is used to associate subsequent rollback anchor points. The anchor point identifier field is written with the corresponding identifier when the candidate operation sequence is bound to the rollback anchor point. Each loadable slice combination is a slice set Z(t).

[0048] S23: Extract the real-time current, equipment temperature, environmental quantity, thermal state change rate and operation frequency corresponding to the target channel from the object state flow, and determine the heat accumulation, cooling hysteresis and operation disturbance increment based on the extraction results to obtain the thermal inertia state.

[0049] Specifically, based on the target channel identifier, the real-time current, current equipment temperature, ambient temperature, thermal state change rate, and operation frequency within a preset historical time window corresponding to the main transformer, bus, and conductor within the target channel are extracted from the object state stream. The degree of heat accumulation of the target channel under the current load is determined based on the real-time current and current equipment temperature. The cooling hysteresis that has not been released after the load is reduced is determined based on the direction of change of equipment temperature relative to ambient temperature and the thermal state change rate. The operation disturbance increment is determined based on the number and timing of recent switching, transfer, and opening / closing operations. The heat accumulation, cooling hysteresis, and operation disturbance increment are associated with the electrical objects within the target channel to obtain the thermal inertia state h(t). The thermal inertia state is used to characterize the historical thermal effects that the electrical objects still retain beyond the current.

[0050] S24: Predict the thermal state of the target channel in multiple future time windows based on the thermal inertia state, and obtain the corrected prediction results.

[0051] Specifically, the object state sequence of k consecutive sampling times prior to the current time, the current topological state matrix, and environmental quantities are used as the basic prediction inputs. The thermal state change rate and recent operation frequency are used to perform thermal inertia correction on the basic prediction results, according to the formula... (t+τ)=F θ (X i (tk:t),G(t),E(t))+α i ·dT i / dt+β i ·Nop i (t) Calculate the corrected predicted current for electrical object i in the future time interval τ, where (t+τ) is the correction prediction current, F θ For the basic prediction mapping with parameter θ, X i (tk:t) represents electrical object i from time t. The object state sequence from time k to time t, G(t) is the current topological state matrix, E(t) is the current environmental variable, and α idT is the correction factor for the rate of change of thermal state. i / dt is the current rate of change of thermal state, β i Nop is the operating disturbance correction factor. i (t) represents the recent operating frequency. By changing τ, we obtain the corrected predicted current corresponding to multiple future time windows. Combined with the thermal inertia state, we form a corrected predicted result that includes the predicted current, the predicted temperature change direction, and the load margin.

[0052] S25: Perform thermal stability verification on the target channel based on the correction prediction results and minimum residence time to obtain the thermal stability verification results.

[0053] Specifically, the correction prediction results corresponding to multiple time windows of the target channel are read, and the prediction time range that needs to be continuously covered is determined according to the minimum residence time corresponding to the load slice that can be supplied. It is then determined whether the target channel continuously meets the equipment current and temperature operating boundaries within the corresponding prediction time range. The judgment states that the thermal stability requirements are continuously met, the thermal stability requirements are not continuously met, and the prediction time range is insufficient to cover the minimum residence time are written into the thermal stability verification results.

[0054] In one embodiment, step S25, namely, performing thermal stability verification on the target channel based on the correction prediction result and the minimum dwell time, to obtain the thermal stability verification result, includes: S251: Extract the temperature rise trend and remaining margin of the target channel over multiple future time windows from the correction prediction results.

[0055] Specifically, the corrected predicted current, predicted temperature, and allowable current and allowable temperature of the corresponding equipment are read according to each electrical object and each prediction time window in the target channel. The direction and magnitude of the predicted temperature change in adjacent prediction time windows are taken as the temperature rise trend. The difference between the allowable current and the corrected predicted current, and the difference between the allowable temperature and the predicted temperature are taken as the margin. The margin with the smallest value among each electrical object is used to characterize the overall margin of the target channel in the corresponding time window.

[0056] S252: Determine the thermal stability of the target channel within each time window based on the temperature rise trend and remaining margin, and obtain the time window determination result.

[0057] Specifically, for each prediction time window, the temperature rise trend and remaining margin corresponding to the target channel are jointly judged. When the remaining margin is greater than or equal to the preset safety margin and the temperature rise trend does not indicate that the equipment temperature will exceed the allowable temperature in the subsequent time window, the corresponding time window is marked as meeting the thermal stability requirements. When the remaining margin is less than the preset safety margin or the temperature rise trend indicates that the equipment temperature will continue to rise and will exceed the allowable temperature, the corresponding time window is marked as not meeting the thermal stability requirements. The judgment results of each electrical object are taken according to the most stringent state of the target channel to obtain the time window judgment results corresponding to each time window.

[0058] S253: Integrate the time window judgment results corresponding to the consecutive time windows according to the order of each time window to determine the duration for which the target channel continuously meets the thermal stability requirements.

[0059] Specifically, the time window determination results are read in order of the predicted time window being closest to the current time. Starting from the first time window after the current time, the time windows that meet the thermal stability requirements are continuously counted. When the first time window that does not meet the thermal stability requirements is encountered, the count is stopped. The product of the number of time windows that continuously meet the thermal stability requirements and the duration of a single time window is determined as the duration of the target channel continuously meeting the thermal stability requirements. The corresponding start time, end time, and restrictive electrical objects are written into the duration record.

[0060] S254: Compare the duration with the minimum residence time corresponding to the load transferable slice, and obtain the thermal stability verification result based on the comparison result.

[0061] Specifically, read the minimum residence time in the transferable load slice. The duration for which the target channel continuously meets the thermal stability requirements is compared with the minimum dwell time. When the duration is greater than or equal to the minimum dwell time, the corresponding transferable load slice and the target channel are marked as having passed the thermal stability test. When the duration is less than the minimum dwell time, the corresponding transferable load slice and the target channel are marked as having failed the thermal stability test. The duration difference, the first time window in which the thermal stability requirements are not met, and the corresponding restrictive electrical object are recorded to obtain the thermal stability test result.

[0062] In one embodiment, step S30 involves obtaining control parameters, and based on the thermal stability verification results, topological constraints, and control parameters, generating candidate operation sequences and corresponding backoff anchor points for each transferable load slice, including: S31: Obtain the conduction coefficient between each source circuit and the target channel, as well as the slice success rate corresponding to each load-transferable slice, to obtain the control parameters.

[0063] Specifically, based on the source loop identifier and the target channel identifier, the relationship between the actual load change and the planned load change recorded in the historical load transfer process of the corresponding channel is read to obtain the transmission coefficient ρ, which characterizes the ease with which the load is transferred from the source loop and transmitted along the target channel. ij Based on the available load slice identifier, the historical execution count, successful completion count, abnormal termination count, and rollback anchor call count of the corresponding slice are read to obtain the slice success rate Succ, which characterizes the probability that the available load slice will complete the expected transfer action. s The conduction coefficients of each source circuit and the target channel, as well as the slicing success rate of each load-transferable slice, are combined into control parameters.

[0064] S32: Based on topological constraints and transmission coefficients, determine the predicted load change of the corresponding source circuit after the load slice is transferred out and the predicted load change of the corresponding target channel after it is transferred in, and obtain the channel influence.

[0065] Specifically, the source loop, target channel, and effective connection relationship between them are determined based on topological constraints, and then calculated according to formula Y. ij (t)=G ij (t)·ρ ij ·ψ ij Calculate the topological propagation tensor, where Y ij (t) represents the topological conduction value from electrical object i to electrical object j at time t, G ij (t) represents the connection state between electrical object i and electrical object j in the topological state matrix, ρ ij ψ is the conduction coefficient corresponding to the connection relationship. ij Based on the constraint correction coefficients determined according to the maintenance method, the operable status of the tie switch, the protection lockout status, and the availability of the channel, the active and reactive loads of the load slices that can be transferred are mapped to the source circuit and the target channel according to the topology conduction tensor. The predicted load reduction of the source circuit after the slice is transferred out and the predicted load increase of the target channel after the slice is transferred in are determined. The affected electrical objects, the predicted load change direction, the predicted load change amount, and the conduction path are combined into the channel influence.

[0066] S33: Based on the channel impact, thermal stability verification results and slice success rate, each load transferable slice is screened, and a candidate operation sequence containing at least one of the following actions is generated based on the screening results: slice transfer, tie switch opening / closing, and bus section switching.

[0067] Specifically, based on the impact of the channel, it is determined whether the transferable load slice can reduce the load of the abnormal source circuit after being transferred out, and whether the transfer will cause new load over-limits in the target channel. Transferable load slices that cannot reduce abnormal loads or will cause load over-limits in the target channel are eliminated. Based on the thermal stability verification results, transferable load slices that cannot continuously meet the thermal stability requirements within the minimum residence time are eliminated. Then, the retained transferable load slices are sorted according to the slice success rate. According to the current switch configuration and topology constraints, the tie switch closing and opening, bus section switching and related load switching actions required to complete the slice transfer are determined. Each action is arranged in order of satisfying interlocking relationships and sequential dependencies, generating one or more candidate operation sequences.

[0068] S34: Obtain the switch configuration, load distribution, and protection blocking status before the execution of each candidate operation sequence, and determine the recoverable path based on topology constraints.

[0069] Specifically, before executing a candidate operation sequence, the current open / closed positions of tie switches, branch switches, and bus section switches related to the candidate operation sequence are recorded. The current load distribution corresponding to each source circuit, target channel, main transformer, and bus is also recorded. The activation, deactivation, operation, and blocking status of protection devices are also recorded. The recorded content is associated with the version identifier of the current topology state matrix to form a snapshot of the field before the operation. Then, based on the topology constraints, the target topology state of the candidate operation sequence is reverse-searched to find an action path that can restore the topology state before the operation. The operability of switches, equipment maintenance status, and protection blocking conditions in the reverse path are verified to obtain a recoverable path.

[0070] S35: Bind the switch configuration, load distribution, protection blocking status, and recoverable path to the corresponding candidate operation sequence to generate a backoff anchor point that corresponds one-to-one with each candidate operation sequence.

[0071] Specifically, a unique sequence identifier is assigned to each candidate operation sequence. The corresponding pre-operation switch configuration, pre-operation load distribution, pre-operation protection lockout status, topology version, recoverable path, associated transferable load slice identifier, and minimum dwell time are written into the same rollback record. The rollback record identifier is then written into the anchor field of the transferable load slice. s , forming a backtracking anchor point r a A candidate operation sequence is bound to only one rollback anchor point for restoring the state before the corresponding operation. A rollback anchor point establishes a one-to-one correspondence with the corresponding candidate operation sequence through the candidate operation sequence identifier.

[0072] In one embodiment, step S40 involves determining the implementation sequence of the candidate operation sequence and its corresponding rollback anchor point, executing the candidate operation sequence that passes the implementation determination, and performing a reverse action on the transferable load slice according to the minimum dwell time limit, including: S41: Based on the control parameters, perform a risk assessment on the abnormal load corresponding to the candidate operation sequence to obtain the abnormal risk, and determine the control necessity judgment result based on the abnormal risk.

[0073] Specifically, the conduction coefficients between the source loop and adjacent channels are extracted from the control parameters to form the corresponding topological conduction tensor. This tensor is then combined with the load exceedance degree of the abnormal object, the abnormal propagation state of adjacent objects, the remaining load margin, the thermal state, and the recent operating frequency, according to formula R... i =σ(a1· +a2·Σ j Y ij (t)·Over j +a3·(1-M i )+a4·Hot i +a5·OpFreq i ) Calculate the abnormal risk of electrical object i, where R i For the abnormal risk score, σ is a function that maps the weighted result to a preset risk range, and a1 to a5 are the weights of each risk factor. Y represents the probability of load exceeding the limit for electrical object i. ij (t) represents the topological conduction value from electrical object i to adjacent electrical object j, Over j M represents the degree of limit violation for adjacent electrical objects j. i To normalize the remaining carrying capacity margin, Hot i OpFreq is the amount of thermal risk determined based on the current temperature and the rate of change of thermal state. i The operational risk level corresponding to the recent frequency of operations is used to compare the abnormal risk score with the corresponding risk range to obtain the determination of the necessity of control, whether it needs to be adjusted, postponed for observation, or not.

[0074] S42: If the necessity judgment result indicates that regulation is required, determine whether the candidate operation sequence has the conditions for execution based on the thermal stability verification result and the regulation parameter, and obtain the executability judgment result.

[0075] Specifically, when the necessity judgment result indicates that regulation is required, the thermal stability verification results and slice success rates corresponding to each transferable load slice involved in the candidate operation sequence are read. The verification checks whether all slices included in the candidate operation sequence have available source loops and target channels, whether they can all meet thermal stability requirements within the minimum dwell time, whether they meet the power supply constraints of important users, and whether the slice success rate meets the corresponding execution requirements. The verification items are then summarized according to the candidate operation sequence to obtain the slice executability rate F. sWhen all necessary slices and necessary actions in a candidate operation sequence meet the execution requirements, the candidate operation sequence is determined to be executable. When any necessary slice or necessary action does not meet the execution requirements, the candidate operation sequence is determined to be non-executable, and the executability judgment result is obtained.

[0076] S43: If the executability judgment result indicates that the execution conditions are met, extract the recoverable path from the fallback anchor point, verify the validity of the fallback anchor point and the reachability of the recoverable path, and obtain the reversibility judgment result.

[0077] Specifically, when the executability judgment result indicates that the candidate operation sequence meets the execution conditions, the corresponding rollback anchor point is read according to the candidate operation sequence identifier. The pre-operation topology version, switch configuration, load distribution, protection interlocking status, and recoverable path are extracted from the rollback anchor point. The completeness of the rollback anchor point record, the consistency between the topology version corresponding to the rollback anchor point and the current execution basis, and the availability of the pre-operation status information are verified to obtain the rollback anchor point validity A. r Then, along the recoverable path, check item by item whether the switches involved in the reverse action can be operated, whether the load after reverse recovery meets the channel bearing requirements, whether the maintenance equipment is isolated, and whether the protection interlocking conditions allow recovery. When the back-off anchor point is valid and all reverse actions in the recoverable path can be reached, the candidate operation sequence is determined to be reversible; otherwise, the candidate operation sequence is determined to be non-reversible, and the reversibility judgment result is obtained.

[0078] S44: Based on the results of the necessity, feasibility and reversibility of the regulation, obtain the implementation decision of the regulation sequence, and execute the candidate operation sequence that is allowed to be implemented according to the results of the implementation decision of the regulation sequence.

[0079] Specifically, the abnormal risk score, slice executability, fallback anchor validity, data quality score, and recent operation frequency are mapped to the execution mode according to the formula Mode=g(R). i ,F s A r Q data Nop i The execution mode is determined by the sequence {automatic execution, manual review, delayed observation, and lockout rollback}, where Mode is the result of the control sequence implementation decision, g is the execution mode mapping rule, and R is the control sequence implementation decision. i For anomaly risk scoring, F s For slice executability, A r To determine the validity of the backtracking anchor point, Q data To form a data quality score based on data integrity, timeliness, and consistency, Nop iBased on recent operation frequency, automatic execution is determined when the abnormal risk is within the controllable range, the slice executability rate meets the execution requirements, the rollback anchor point is effective, the data quality meets the standards, and the recent operation frequency does not exceed the limit. When the risk is in the gray zone or the candidate operation sequence involves important users, manual review is determined. When the predicted state is unstable but has not yet exceeded the limit, delayed observation is determined. When interlocking, load bearing, thermal stability, or rollback reachability verification fails, lockout rollback is determined. The candidate operation sequence corresponding to the automatic execution mode is executed according to the action order recorded in the candidate operation sequence. The manual review mode processes according to the review results after obtaining the review results.

[0080] S45: Monitor the dwell time of the transferable load slice. If the dwell time does not reach the minimum dwell time, restrict the reverse transfer action and rollback action for the transferable load slice.

[0081] Specifically, the dwell time is calculated continuously from the moment the load slice is transferred to the target channel. Simultaneously, the number of operations on the same electrical object is counted within the sliding operation time window, and calculated according to the formula Nop. i (t,t+T w )≤N max And Δt≥ Implement anti-oscillation constraints, where Nop i (t,t+T w Let i be an electrical object at time t to time t+T. w The number of operations between, T w To perform the statistical time window, N max The maximum number of operations allowed within the statistical time window is Δt, where Δt is the time interval between two consecutive reverse actions for the same transferable load slice. The minimum dwell time is set for the load slice that can be transferred. When the dwell time is less than the minimum dwell time or the number of operations reaches the maximum number of operations, it is prohibited to generate and execute reverse transfer actions and rollback actions for the same load slice. When the dwell time reaches the minimum dwell time, the execution status is used to determine whether to allow the implementation of reverse actions.

[0082] In one embodiment, in step S50, the execution status of the candidate operation sequence is monitored. When the execution status satisfies the condition of continuous abnormal load and the dwell time of the load slice that can be transferred reaches the minimum dwell time, the state is restored to the state before the operation according to the rollback anchor point, the execution result is recorded, and the control parameters are updated according to the execution result, including: S51: Monitor the load status, actual load changes of the source loop and target channel after the candidate operation sequence is executed, as well as the dwell time of the corresponding transferable load slice, and record the success or failure of the execution of the transferable load slice to obtain the execution status.

[0083] Specifically, after the candidate operation sequence begins execution, the instruction issuance time, status feedback time, and actual opening / closing position of each switch action are recorded according to the action sequence. The current, active power, reactive power, equipment temperature, and thermal state change rate of the source circuit and target channel are continuously collected. The measured values ​​after execution are compared with the corresponding measured values ​​in the field snapshot before execution to obtain the actual load reduction of the source circuit and the actual load increase of the target channel. The successful execution condition is that the transferable load slice is actually transferred to the target channel and the relevant switch status is consistent with the target status of the candidate operation sequence. The slice execution success, execution failure, or partial completion status is recorded. At the same time, the slice dwell time is accumulated. The load status, actual load change, slice dwell time, slice execution success or failure, and the current topology version are combined into the execution status.

[0084] S52: Determine whether the abnormal load state continues based on the execution status. If the abnormal load state continues and the dwell time reaches the minimum dwell time, extract the recoverable path and the state information before the operation from the rollback anchor point.

[0085] Specifically, based on the execution status, it continuously judges whether the load of the abnormal source circuit has fallen back to the safe operating range, whether the target channel has generated new load or thermal state exceeding the limit, and whether the equipment temperature has entered the recovery trend according to the correction prediction results. When the abnormal source circuit has not recovered to the safe operating range or the target channel continues to be in the exceeding limit state within multiple consecutive monitoring time windows, it is determined that the abnormal load state continues. Then, the current dwell time is compared with the minimum dwell time. When the abnormal load state continues and the dwell time has reached the minimum dwell time, the corresponding backoff anchor point is called according to the candidate operation sequence identifier. The recoverable path composed of reverse recovery actions and the pre-operation state information composed of switch configuration, load distribution, protection interlocking status and topology version are extracted from the backoff anchor point.

[0086] S53: Restore to the pre-operation state corresponding to the pre-operation state information according to the recoverable path, and record the rollback result when calling the rollback anchor point.

[0087] Specifically, switch restoration and load migration are performed item by item according to the reverse action sequence recorded in the recoverable path. Before each reverse action is executed, the current switch state is checked to see if it is consistent with the previous state in the recoverable path. After each reverse action is executed, the actual switch feedback is read and the temporary topology state is updated until the switch configuration is restored to the switch configuration before operation, the load distribution is restored to the load distribution before operation, and the protection blocking state is consistent with the state information before operation. During the rollback process, it is recorded whether each reverse action is executed successfully, whether the restored topology corresponds to the topology version before operation, whether the source loop and target channel are restored to the allowable operating range, and whether there is manual intervention. The completion status of all reverse actions and the final restoration status are combined into the rollback result.

[0088] S54: Record the actual load changes, the success or failure of the execution of the load slice that can be transferred, and the calling status of the rollback anchor point. When the rollback anchor point is called, record the rollback result and obtain the execution result.

[0089] Specifically, execution records are established using candidate operation sequence identifiers and transferable load slice identifiers. The predicted load changes, actual load changes, slice execution success or failure, slice dwell time, topology status before and after operation, equipment temperature recovery curve, whether the rollback anchor point is called, the rollback anchor point call time, rollback result, and manual review or correction content are written into the execution record. When the rollback anchor point is not called, the rollback anchor point call status is recorded as not called. When the rollback anchor point is called, the rollback success, rollback failure, or partial recovery status is written synchronously to obtain the execution result that can reflect the forward execution and reverse recovery of the candidate operation sequence.

[0090] S55: Extract the transmission coefficient and slice success rate from the control parameters, obtain the predicted load change corresponding to the candidate operation sequence, update the transmission coefficient according to the deviation between the actual load change and the predicted load change, update the slice success rate according to the execution result, and obtain the updated control parameters.

[0091] Specifically, the original conduction coefficients of the source loops and target channels involved in the candidate operation sequences are read from the control parameters. and the success rate of the original slice corresponding to the load transferable slice. The transmission deviation e is calculated based on the actual load change in the execution results and the predicted load change corresponding to the candidate operation sequence. flow The execution feedback deviation e is generated based on whether the slice was successfully completed, whether a rollback was triggered, and whether the rollback was successful. exec According to the formula = +η1·e flow , = +η2·e exec θ new =θ old -η3·grad(Loss) performs a closed-loop update, where and These are the conduction coefficients before and after the update, respectively. and These represent the slice success rates before and after the update, respectively. η1 is the update step size for the conduction coefficient, η2 is the update step size for the slice success rate, and e flow e represents the deviation of actual load change from predicted load change. exec θ is the execution feedback quantity formed based on the slice execution and rollback results. old and θnew The prediction parameters before and after the update are respectively, η3 is the step size of the prediction parameter update, and grad(Loss) is the gradient obtained based on the loss between the prediction result and the actual result. The updated conduction coefficient and the slice success rate are then combined to form the updated control parameters, and the updated prediction parameters are used for the thermal inertia correction prediction of the next control cycle.

[0092] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiments, the present invention also provides a substation abnormal load adaptive control system, comprising: The state construction module is used to obtain substation state information and form object state flow and topology constraints based on the substation state information. The slice prediction module is used to generate transferable load slices with minimum residence time based on object state flow and topology constraints. It performs thermal inertia correction prediction on the target channel corresponding to the transferable load slice according to object state flow, and then obtains thermal stability verification results based on the correction prediction results and minimum residence time. The sequence generation module is used to obtain control parameters, and based on the thermal stability verification results, topological constraints and control parameters, it generates candidate operation sequences and corresponding backoff anchor points for each candidate operation sequence for the transferable load slice. The implementation judgment module is used to perform control sequence implementation judgment on candidate operation sequences and corresponding backoff anchor points, execute candidate operation sequences that pass the implementation judgment, and perform reverse actions on the transferable load slices according to the minimum residence time limit. The feedback update module is used to monitor the execution status of candidate operation sequences. When the execution status meets the requirements of continuous abnormal load state and the residence time of the load slice that can be transferred reaches the minimum residence time, the module restores the state before the operation according to the rollback anchor point, records the execution results, and updates the control parameters according to the execution results.

[0093] Optionally, the state building module includes: The status acquisition submodule is used to collect measurement data from the main transformer, busbar and feeder, and obtain the status of tie switch, protection action, equipment temperature, environmental quantity, maintenance method and recent operation record to obtain operating status data; The information collection submodule is used to acquire the primary wiring diagram and use the operating status data and the primary wiring diagram as substation status information. The State Flow submodule is used to perform time-stamp alignment, outlier removal, and confidence marking on the running state data. Based on the processed running state data, it determines the thermal state change rate, on / off state, maintenance constraints, and operation frequency of each object. The processed running state data is then combined with the determined results to obtain the object state flow. The topology construction submodule is used to determine the electrical connection relationships and available communication relationships between objects based on the primary wiring diagram, switch status and maintenance constraints, obtain the topology status, and determine the corresponding channel restrictions for load transfer out and load transfer in based on the topology status, thus forming topology constraints.

[0094] Optionally, the tile prediction module includes: The boundary determination submodule is used to extract feeder load and branch switch status from the object state stream, obtain user groups and importance lists, and determine the electrical boundary and user boundary of the load in the station based on the feeder load, branch switch status, user groups and topology constraints. The load slicing generation submodule is used to split the load within the station according to the electrical boundary and the user boundary. Based on the topology constraints and the importance list, it determines the source loop, target channel and user importance corresponding to the split load, obtains the minimum dwell time corresponding to the split load, and associates the source loop, target channel, user importance and minimum dwell time with the split load to obtain the load slice that can be supplied. The thermal extraction submodule is used to extract the real-time current, equipment temperature, environmental quantity, thermal state change rate and operation frequency corresponding to the target channel from the object state stream. Based on the extraction results, the thermal accumulation, cooling hysteresis and operation disturbance increment are determined to obtain the thermal inertia state. The thermal prediction submodule is used to predict the thermal state of the target channel in multiple future time windows based on the thermal inertia state, and obtain the corrected prediction results. The stability verification submodule is used to perform thermal stability verification on the target channel based on the correction prediction results and the minimum dwell time, and obtain the thermal stability verification results.

[0095] Optional, the stability verification submodule includes: The trend extraction unit is used to extract the temperature rise trend and remaining margin of the target channel over multiple future time windows from the corrected prediction results. The window determination unit is used to determine the thermal stability state of the target channel in each time window based on the temperature rise trend and remaining margin, and to obtain the time window determination result. The duration determination unit is used to integrate the time window determination results corresponding to the continuous time windows according to the order of each time window, and determine the duration for which the target channel continuously meets the thermal stability requirements. The result generation unit is used to compare the duration with the minimum residence time corresponding to the transferable load slice, and obtain the thermal stability verification result based on the comparison result.

[0096] Optionally, the sequence generation module includes: The parameter acquisition submodule is used to obtain the conduction coefficient between each source circuit and the target channel, as well as the slice success rate corresponding to each load-transferable slice, and to obtain the control parameters. The influence prediction submodule is used to determine the predicted load change of the corresponding source circuit after the transferable load slice is transferred out and the predicted load change of the corresponding target channel after the transfer is in, based on topological constraints and transmission coefficients, and thus obtain the channel influence. The sequence filtering submodule is used to filter each transferable load slice based on channel influence, thermal stability verification results and slice success rate, and generate a candidate operation sequence that includes at least one of the following actions: slice transfer, tie switch opening and closing, and bus section switching. The path determination submodule is used to obtain the switch configuration, load distribution and protection blocking status before the execution of each candidate operation sequence, and to determine the recoverable path based on topology constraints. The anchor point generation submodule is used to bind the switch configuration, load distribution, protection blocking status, and recoverable path to the corresponding candidate operation sequence, and generate a backoff anchor point that corresponds one-to-one with each candidate operation sequence.

[0097] Optionally, the implementation decision module includes: The risk assessment submodule is used to assess the abnormal loads corresponding to candidate operation sequences based on the control parameters, obtain the abnormal risks, and determine the control necessity judgment results based on the abnormal risks. The execution judgment submodule is used to determine whether the candidate operation sequence has the conditions for execution based on the thermal stability verification result and the control parameters when the control necessity judgment result indicates that control is required, and to obtain the executability judgment result. The reversibility verification submodule is used to extract recoverable paths from the fallback anchors when the executability judgment result indicates that the execution conditions are met, and to verify the validity of the fallback anchors and the reachability of the recoverable paths to obtain the reversibility judgment result. The sequence execution submodule is used to obtain the control sequence implementation judgment result based on the control necessity judgment result, the executability judgment result, and the reversibility judgment result, and to execute the candidate operation sequence that is allowed to be implemented according to the control sequence implementation judgment result; The reverse limiting submodule is used to monitor the dwell time of the transferable load slice. When the dwell time does not reach the minimum dwell time, it restricts the reverse transfer and rollback actions for the transferable load slice.

[0098] Optional, the feedback update module includes: The status monitoring submodule is used to monitor the load status, actual load changes of the source loop and target channel after the execution of the candidate operation sequence, as well as the dwell time of the corresponding transferable load slice, and record the success or failure of the execution of the transferable load slice to obtain the execution status. The rollback extraction submodule is used to determine whether the abnormal load state continues based on the execution status. When the abnormal load state continues and the dwell time reaches the minimum dwell time, it extracts the recoverable path and the state information before the operation from the rollback anchor point. The state recovery submodule is used to restore the state to the state before the operation according to the recoverable path, and to record the rollback result when the rollback anchor is called. The results recording submodule is used to record actual load changes, the success or failure of the execution of available load slices, and the calling status of rollback anchors. When a rollback anchor is called, the rollback result is recorded to obtain the execution result. The parameter update submodule is used to extract the transmission coefficient and slice success rate from the control parameters, obtain the predicted load change corresponding to the candidate operation sequence, update the transmission coefficient according to the deviation between the actual load change and the predicted load change, and update the slice success rate according to the execution result to obtain the updated control parameters.

[0099] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing an adaptive control method for abnormal loads in substations; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0100] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the substation abnormal load adaptive control method of Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0101] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0102] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0103] The memory 101 in the electronic device 100 stores multiple instructions to implement a substation abnormal load adaptive control method, and the processor 102 can execute multiple instructions to achieve the following: Obtain substation status information and form object state flow and topology constraints based on the substation status information; Based on object state flow and topology constraints, a transferable load slice with minimum residence time is generated. Thermal inertia correction prediction is performed on the target channel corresponding to the transferable load slice according to the object state flow. Then, thermal stability verification results are obtained based on the correction prediction results and minimum residence time. Obtain control parameters, and based on thermal stability verification results, topological constraints, and control parameters, generate candidate operation sequences and corresponding backoff anchor points for each candidate operation sequence for the transferable load slice; The candidate operation sequence and its corresponding rollback anchor point are controlled and determined. The candidate operation sequence that passes the determination is executed, and the reverse action is performed on the transferable load slice according to the minimum residence time limit. Monitor the execution status of candidate operation sequences. When the execution status meets the requirements of continuous abnormal load state and the residence time of the load slice that can be transferred reaches the minimum residence time, restore the state to the state before the operation according to the rollback anchor point, record the execution results, and update the control parameters according to the execution results.

[0104] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0105] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0107] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0108] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0109] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for adaptive control of abnormal loads in a substation, characterized in that, The method includes: Obtain substation status information, and form object state flow and topology constraints based on the substation status information; Based on the object state flow and the topology constraints, a transferable load slice with a minimum residence time is generated. Thermal inertia correction prediction is performed on the target channel corresponding to the transferable load slice according to the object state flow. Then, thermal stability verification results are obtained based on the correction prediction results and the minimum residence time. Obtain control parameters, and based on the thermal stability verification results, the topological constraints, and the control parameters, generate candidate operation sequences and corresponding backoff anchor points for each of the transferable load slices; The candidate operation sequence and the corresponding backoff anchor point are subject to adjustment sequence determination. The candidate operation sequence that passes the determination is executed, and the reverse action is performed on the transferable load slice according to the minimum dwell time limit. Monitor the execution status of the candidate operation sequence. When the execution status meets the conditions of continuous abnormal load and the residence time of the transferable load slice reaches the minimum residence time, restore the state to the state before the operation according to the rollback anchor point, record the execution result, and update the control parameters according to the execution result.

2. The substation abnormal load adaptive control method according to claim 1, characterized in that, The process of acquiring substation status information and forming object state flow and topology constraints based on the substation status information includes: Collect measurement data from the main transformer, busbar and feeder, and obtain the status of tie switches, protection actions, equipment temperature, environmental parameters, maintenance methods and recent operation records to obtain operating status data; Obtain a primary wiring diagram, and use the operating status data and the primary wiring diagram as the substation status information; The operational status data is time-stamped, outlier removed, and confidence level marked. Based on the processed operational status data, the thermal state change rate, on / off status, maintenance constraints, and operation frequency of each object are determined. The processed operational status data is then combined with the determination results to obtain the object state stream. Based on the primary wiring diagram, the switch status, and the maintenance constraints, the electrical connection relationships and available communication relationships between each object are determined to obtain the topology state. Based on the topology state, the channel restrictions corresponding to load transfer out and load transfer in are determined to form the topology constraints.

3. The substation abnormal load adaptive control method according to claim 1, characterized in that, The process of generating a transferable load slice with a minimum dwell time based on the object state flow and the topology constraints, performing thermal inertia correction prediction on the target channel corresponding to the transferable load slice according to the object state flow, and then obtaining the thermal stability verification result based on the correction prediction result and the minimum dwell time includes: Extract feeder loads and branch switch states from the object state stream, obtain user groups and importance lists, and determine the electrical boundaries and user boundaries of the loads within the station based on the feeder loads, branch switch states, user groups, and topology constraints. The load within the station is split according to the electrical boundary and the user boundary. The source loop, target channel and user importance corresponding to the split load are determined according to the topology constraints and the importance list. The minimum dwell time corresponding to the split load is obtained. The source loop, the target channel, the user importance and the minimum dwell time are associated with the split load to obtain the transferable load slice. Extract the real-time current, equipment temperature, environmental quantity, thermal state change rate and operation frequency corresponding to the target channel from the object state stream, and determine the heat accumulation, cooling hysteresis and operation disturbance increment based on the extraction results to obtain the thermal inertia state; The corrected prediction result is obtained by predicting the thermal state of the target channel in multiple future time windows based on the thermal inertia state. The thermal stability of the target channel is verified based on the correction prediction result and the minimum dwell time to obtain the thermal stability verification result.

4. The substation abnormal load adaptive control method according to claim 3, characterized in that, The step of performing thermal stability verification on the target channel based on the correction prediction result and the minimum dwell time to obtain the thermal stability verification result includes: Extract the temperature rise trend and remaining margin of the target channel over multiple future time windows from the corrected prediction results; Based on the temperature rise trend and the remaining margin, the thermal stability state of the target channel within each time window is determined, and the time window determination result is obtained. According to the order of the time windows, the time window determination results corresponding to the continuous time windows are integrated to determine the duration for which the target channel continuously meets the thermal stability requirements; The duration is compared with the minimum residence time corresponding to the transferable load slice, and the thermal stability verification result is obtained based on the comparison result.

5. The substation abnormal load adaptive control method according to claim 1, characterized in that, The acquisition of control parameters, based on the thermal stability verification results, the topological constraints, and the control parameters, involves generating candidate operation sequences and corresponding backoff anchor points for each transferable load slice, including: The control parameters are obtained by acquiring the conduction coefficient between each source loop and the target channel, as well as the slicing success rate corresponding to each load-transferable slice; Based on the topological constraints and the conduction coefficient, the predicted load change of the corresponding source circuit after the transferable load slice is transferred out and the predicted load change of the corresponding target channel after the transfer is in are determined, thus obtaining the channel influence. Based on the channel impact, the thermal stability verification result, and the slice success rate, each of the transferable load slices is screened, and based on the screening result, a candidate operation sequence is generated that includes at least one of the following actions: slice transfer, tie switch opening / closing, and bus section switching. Obtain the switch configuration, load distribution, and protection blocking status before the execution of each candidate operation sequence, and determine the recoverable path based on the topology constraints; The switch configuration, load distribution, protection lockout state, and recoverable path are bound to the corresponding candidate operation sequences to generate a backoff anchor point that corresponds one-to-one with each candidate operation sequence.

6. The substation abnormal load adaptive control method according to claim 1, characterized in that, The step of determining the adjustment sequence for the candidate operation sequence and the corresponding rollback anchor point, and executing the candidate operation sequence that passes the determination, includes the following reverse action for the transferable load slice according to the minimum dwell time limit: The abnormal load corresponding to the candidate operation sequence is assessed based on the control parameters to obtain the abnormal risk, and the necessity of control is determined based on the abnormal risk. If the determination result of the necessity of regulation indicates that regulation is required, the candidate operation sequence is determined to have the conditions for execution based on the thermal stability verification result and the regulation parameters, and the executability determination result is obtained. If the executability judgment result indicates that the execution conditions are met, a recoverable path is extracted from the fallback anchor point, and the validity of the fallback anchor point and the reachability of the recoverable path are verified to obtain the reversibility judgment result. Based on the determination results of the necessity of regulation, the feasibility, and the reversibility, a determination result for the implementation of the regulation sequence is obtained, and the candidate operation sequence that is allowed to be implemented according to the determination result of the implementation of the regulation sequence is executed. Monitor the dwell time of the transferable load slice, and restrict reverse transfer and rollback actions for the transferable load slice when the dwell time does not reach the minimum dwell time.

7. The substation abnormal load adaptive control method according to claim 1, characterized in that, The monitoring of the execution status of the candidate operation sequence, when the execution status meets the conditions of continuous abnormal load state and the residence time of the transferable load slice reaches the minimum residence time, restores the state to the pre-operation state according to the rollback anchor point, records the execution result, and updates the control parameters according to the execution result, including: Monitor the load status, actual load changes of the source loop and target channel after the candidate operation sequence is executed, as well as the dwell time of the corresponding transferable load slice, and record the success or failure of the execution of the transferable load slice to obtain the execution status; Determine whether the abnormal load state continues based on the execution state. When the abnormal load state continues and the dwell time reaches the minimum dwell time, extract the recoverable path and pre-operation state information from the fallback anchor point. The system restores the system to the pre-operation state corresponding to the pre-operation state information according to the recoverable path, and records the rollback result when the rollback anchor point is called. Record the actual load changes, the success or failure of the execution of the transferable load slice, and the invocation status of the rollback anchor point, and record the rollback result when the rollback anchor point is invoked to obtain the execution result; The transmission coefficient and slicing success rate are extracted from the control parameters, and the predicted load change corresponding to the candidate operation sequence is obtained. The transmission coefficient is updated according to the deviation between the actual load change and the predicted load change, and the slicing success rate is updated according to the execution result to obtain the updated control parameters.

8. A substation abnormal load adaptive control system, characterized in that, The system includes: The state construction module is used to acquire substation state information and form object state flow and topology constraints based on the substation state information. The slice prediction module is used to generate a transferable load slice with a minimum residence time based on the object state flow and the topology constraints, perform thermal inertia correction prediction on the target channel corresponding to the transferable load slice according to the object state flow, and then obtain the thermal stability verification result based on the correction prediction result and the minimum residence time. The sequence generation module is used to acquire control parameters, and based on the thermal stability verification results, the topological constraints and the control parameters, generate candidate operation sequences and backoff anchor points corresponding to each candidate operation sequence for the transferable load slice. The implementation judgment module is used to perform control sequence implementation judgment on the candidate operation sequence and the corresponding backoff anchor point, execute the candidate operation sequence that passes the implementation judgment, and perform the reverse action on the transferable load slice according to the minimum residence time limit; The feedback update module is used to monitor the execution status of the candidate operation sequence. When the execution status meets the conditions of continuous abnormal load state and the residence time of the transferable load slice reaches the minimum residence time, the module restores the state before operation according to the rollback anchor point, records the execution result, and updates the control parameters according to the execution result.

9. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the substation abnormal load adaptive control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the substation abnormal load adaptive control method as described in any one of claims 1 to 7.

Images