Power distribution network active and reactive cooperation voltage control method and system

Abstract

The invention discloses an active and reactive cooperative voltage control method and system for a power distribution network, and relates to the technical field of real-time data collection and state sensing processing, and the method comprises the steps: collecting the operation data of the power distribution network in real time through sensors disposed at all nodes of the power distribution network; the power distribution network state real-time monitoring module, the decision model, the distributed execution module and the collaborative visualization module are arranged, meanwhile, the whole network operation state, the control strategy and the execution result are displayed in a centralized visualization mode, active resources are coordinated when the operation state, the control strategy and the execution result are invalid, the response speed is increased, the collaborative visualization module provides a graphical interface, and the operation efficiency is improved. According to the technical scheme, the whole-network operation state, the control strategy and the execution result are displayed in real time, workers are helped to rapidly identify problems and manage, visualize and store collaborative voltage control data and corresponding analysis results, collaborative voltage control management can be achieved through cloud management and control of the Internet of Things, and the intelligent level of collaborative voltage control management is improved.

Description

Technical Field

[0001] This invention relates to the technical field, specifically to a method and system for coordinated active and reactive power voltage control in power distribution networks. Background Technology

[0002] In distribution network operation, voltage stability is a key factor in ensuring power quality, equipment safety, and energy efficiency. Traditional distribution network voltage control methods mainly rely on the independent operation of local regulating equipment (such as capacitor banks and on-load tap-changing transformers), lacking system-level coordination and intelligent decision-making capabilities.

[0003] Chinese Patent Publication No. CN 120474033 A discloses a voltage control system for wind-solar-storage synergy, including a wind power generation module, a photovoltaic power generation module, a hybrid energy storage system, and an intelligent control center. The wind power generation module and the photovoltaic power generation module are connected to the power grid in parallel. The intelligent control center monitors voltage fluctuations in real time and dynamically adjusts the charging and discharging strategy of the hybrid energy storage system according to the voltage fluctuations to maintain grid voltage stability and ensure power quality. The intelligent control center uses a multi-objective optimization algorithm to accurately predict wind and photovoltaic power generation and optimize charging and discharging commands based on the energy storage status. This invention constructs a multi-level collaborative control architecture, optimizes energy storage response through adaptive algorithms, and enhances voltage transient support capabilities by combining SVPWM technology, effectively coping with wind and solar power generation fluctuations and ensuring stable grid operation.

[0004] However, the above solution still has the following shortcomings:

[0005] Adjusting only a single node or device cannot achieve cross-regional coordination of active and reactive power, resulting in frequent voltage fluctuations and high network losses.

[0006] Relying heavily on static models and historical data, and lacking deep learning and dynamic optimization of real-time data, the traditional control model is difficult to adapt to the changing load and power output fluctuations as the distributed power generation becomes more complex with the popularization of distributed power sources.

[0007] Most systems lack centralized visual monitoring and real-time early warning functions, making it difficult for staff to fully grasp the status of the power grid and respond to abnormal situations in a timely manner, which increases operational risks and causes many inconveniences.

[0008] Therefore, this invention requires the design of a method and system for coordinated active and reactive power voltage control in power distribution networks to solve the aforementioned problems. Summary of the Invention

[0009] The purpose of this invention is to provide an intelligent collaborative voltage control system to solve the above-mentioned problems. This system can integrate real-time data, machine learning algorithms, and distributed execution units to achieve collaborative optimization of active and reactive power, improve voltage stability, reduce network losses, and enhance system security and monitorability, thus solving the problems mentioned in the background art.

[0010] To address the above problems, the present invention provides a technical solution:

[0011] A method for coordinated active and reactive power voltage control in a power distribution network includes the following specific steps:

[0012] S1. Real-time data acquisition and status awareness processing: Real-time acquisition of power grid operation data through sensors deployed at various nodes of the distribution network;

[0013] S2. Construction and optimization of collaborative decision-making model based on big data learning: Based on the real-time data and historical data collected in step S1, machine learning algorithms are used for training and learning to generate a collaborative control decision-making model with the comprehensive goal of maintaining voltage stability and reducing grid loss, and the decision-making model is continuously optimized based on grid feedback.

[0014] S3. Distributed collaborative control execution and visualization processing: The control commands generated by the decision model in step S2 are sent to each distributed execution unit through the communication network to coordinate the adjustment of the tap changer of the on-load tap changer, the switching of capacitor banks, the static var compensator, and the active and reactive power output of the distributed power source.

[0015] S4. Simultaneously, the overall network operation status, control strategies, and execution results are centrally visualized and displayed.

[0016] In a preferred embodiment of the present invention, the collaborative control decision model in step S2 is a multi-objective optimization model, and its objective function is expressed as follows:

[0017] MinF=ω1*Σ(Ui-Uref)^2+ω2*Ploss

[0018] Where Ui represents the real-time voltage of node i, Uref represents the rated reference voltage, Ploss represents the total active power loss of the system, and ω1 and ω2 are weighting coefficients used to balance the optimization priority of voltage deviation and network loss.

[0019] In a preferred embodiment of the present invention, step S2, which involves training and learning using machine learning algorithms, specifically includes: employing a deep reinforcement learning algorithm, using the power distribution network operating environment as the learning environment for the agent, and using voltage over-limit penalties, equipment operation costs, and network loss costs as reward functions, and training the agent to obtain the optimal control strategy through continuous interaction with the environment.

[0020] In a preferred embodiment of the present invention, the reward function R is designed as follows:

[0021] R=-α*Σ|Ui-Ulim|-β*Σ|ΔC|-γ*Ploss

[0022] Wherein, when the node voltage Ui exceeds the limit, Ulim is the upper or lower limit of the voltage; otherwise, this term is zero; ΔC represents the number of times the reactive power compensation equipment or transformer tap changer operates; Ploss is the system network loss; α, β, γ are the weighting coefficients of each penalty term.

[0023] In a preferred embodiment of the present invention, the data in step S1 includes node voltage, branch current, active power, reactive power, load rate, and distributed power output; the coordinated adjustment in step S3 includes prioritizing the use of nearby reactive power compensation resources for adjustment when a local voltage over-limit occurs; and coordinating and controlling the active power resources in adjacent areas when reactive power resources are exhausted or insufficient, thereby achieving coordinated support of active and reactive power in time and space.

[0024] A distribution network active and reactive power coordinated voltage control system is disclosed. The voltage control system includes a distribution network status real-time monitoring module, a decision model, a distributed execution module, and a coordinated visualization module. Staff can log in to the coordinated visualization module to access the voltage control system and view the real-time operating data of the distribution network status real-time monitoring module, the decision model, and the distributed execution module.

[0025] In a preferred embodiment of the present invention, the real-time monitoring module for distribution network status includes a real-time monitoring unit for distribution network status, a communication network unit, and a control mode authentication unit. The real-time monitoring unit for distribution network status and the control mode authentication unit are bidirectionally connected, and the communication network unit is integrated inside the real-time monitoring unit for distribution network status.

[0026] The main task of the real-time monitoring unit for distribution network status is to collect and monitor the operating status of the distribution network in real time. The real-time collected data includes key power grid parameters such as voltage, current, power, frequency, and load.

[0027] The real-time monitoring unit for the power distribution network status is also used to provide real-time data on various nodes, equipment, and lines of the power grid, so that other modules such as optimization control units and decision models can make corresponding control decisions based on this data.

[0028] The communication network unit is used for data transmission and communication between different devices, monitoring units and control systems in the power distribution network to ensure accurate and timely data transmission.

[0029] The control mode authentication unit is used to authenticate and verify various control modes in the power distribution network control system to ensure that only authenticated and legitimate control modes can be used in the system.

[0030] In a preferred embodiment of the present invention, the decision model includes a big data learning unit, a decision model generation unit, and a decision model optimization unit. The output of the big data learning unit is communicatively connected to the input of the decision model generation unit, and the output of the decision model generation unit is communicatively connected to the input of the decision model optimization unit.

[0031] The big data learning unit is used to extract valuable information from a large amount of data in the operation of the power distribution network, and to discover potential patterns and trends through data analysis and learning algorithms. The data includes voltage, current, power, equipment status, load changes, etc.

[0032] The decision model generation unit is used to construct a decision model for power grid control based on the data analysis results provided by the big data learning unit. By considering various operating parameters and control objectives of the power grid, it provides a basis for system decision-making. The operating parameters include voltage, current, power, load, etc., and the control objectives include voltage stability, energy efficiency, reactive power optimization, etc.

[0033] The decision model optimization unit is used to continuously optimize and adjust the existing decision model based on actual power grid operation feedback, so as to improve the operating efficiency and stability of the power grid and enable the power grid to achieve more precise voltage regulation and power distribution under different load conditions.

[0034] In a preferred embodiment of the present invention, the distributed execution module includes a distributed execution unit, a power distribution network data center, and a response optimization unit, wherein both the distributed execution unit and the response optimization unit are bidirectionally connected to the power distribution network data center.

[0035] The distributed execution unit is used to perform specific voltage control operations in various areas of the distribution network by coordinating with other execution units, so as to ensure that each node in the distribution network can adjust the active and reactive power as needed and keep the voltage within a reasonable range.

[0036] The distributed execution unit is also used to support data acquisition, providing real-time data support for subsequent optimization control and decision-making;

[0037] The power distribution network data center is used to collect and manage real-time data from the entire power distribution network. The real-time data includes the acquisition, storage and processing of various electrical parameters such as voltage, current, power and frequency.

[0038] The response optimization unit is used to optimize the response strategy of the distribution network based on the data collected by the distribution network data center and the operating status of the power grid.

[0039] The collaborative visualization module includes an algorithm collaboration unit, a distributed visualization unit, and other collaborative control units. The outputs of the algorithm collaboration unit and other collaborative control units are all communicatively connected to the input of the distributed visualization unit.

[0040] The algorithm coordination unit is used to process data information from various distributed execution units, distribution network data centers and other modules. It optimizes the active and reactive power coordinated voltage control of the distribution network through algorithms, including optimal control algorithms, prediction algorithms, fault diagnosis algorithms, etc., to solve voltage control problems in the power grid and ensure voltage stability and energy efficiency during system operation.

[0041] The distributed visualization unit is used to graphically display the status of each distributed execution unit and monitoring data in the power grid to the staff, so as to understand the operation of the power grid, the execution status of control strategies and possible problems in real time.

[0042] The other collaborative control units are mainly responsible for various collaborative tasks and optimization adjustments in the system, and perform precise control of power grid equipment based on the input signals provided by the distributed execution unit and the algorithm collaboration unit.

[0043] In a preferred embodiment of the present invention, the voltage control system further includes a safety early warning management module, which includes a field remote early warning unit and a safety risk control unit, and the field remote early warning unit and the safety risk control unit are bidirectionally connected.

[0044] The on-site remote early warning unit is used to identify the voltage, current and other related parameters detected in the power distribution network, identify abnormal states or potential safety risks, and trigger an early warning signal when the operating status of the equipment or power grid is detected to be abnormal.

[0045] The safety risk control unit is used to analyze the safety status of the system based on field data, determine whether there are potential fault risks, overload risks, equipment failures, etc., and automatically adjust the active and reactive power of the distribution network and regulate the voltage when a safety risk is detected to avoid system collapse or equipment damage.

[0046] The beneficial effects of this invention are as follows: By setting up a real-time monitoring module for distribution network status, a decision-making model, a distributed execution module, and a collaborative visualization module, this invention constructs a complete voltage control system. In actual use, sensors deployed at various nodes of the distribution network collect real-time power grid operation data. Based on the collected real-time and historical data, machine learning algorithms are used for training and learning to generate a collaborative control decision-making model with the comprehensive goal of maintaining voltage stability and reducing network losses. The decision-making model is continuously optimized based on power grid feedback. The control commands generated by the decision-making model are sent to each distributed execution unit through the communication network to coordinate the adjustment of the tap changers of on-load tap changers, capacitor bank switching, static var compensators, and the active and reactive power outputs of distributed power sources. At the same time, the overall network operation status, control strategies, and execution results are centrally visualized. When ineffective, active power resources are coordinated to improve response speed. The collaborative visualization module provides a graphical interface to display the overall network operation status, control strategies, and execution results in real time, helping staff to quickly identify problems. It manages, visualizes, and stores collaborative voltage control data and corresponding analysis results, which helps to realize collaborative voltage control management through IoT cloud management and improve the intelligence level of collaborative voltage control management. Attached Figure Description

[0047] For ease of explanation, the present invention will be described in detail below with reference to specific embodiments and accompanying drawings.

[0048] Figure 1 This is a flowchart of a method and system for coordinated active and reactive power voltage control in a power distribution network according to the present invention.

[0049] Figure 2 This is the overall system topology diagram of the active and reactive power coordinated voltage control method and system for power distribution networks according to the present invention. Detailed Implementation

[0050] like Figure 1 and Figure 2 As shown, the specific implementation adopts the following technical solution:

[0051] This invention provides a technical solution: a distribution network active and reactive power coordinated voltage control system. The voltage control system includes a distribution network status real-time monitoring module, a decision model, a distributed execution module, and a coordinated visualization module. Staff can log in to the coordinated visualization module to access the internal workings of the voltage control system and view the real-time operating data of the distribution network status real-time monitoring module, the decision model, and the distributed execution module one by one.

[0052] Real-time monitoring of power distribution network status

[0053] S101. The real-time monitoring module for the distribution network status is used to collect power grid operation data in real time through sensors deployed at each node of the distribution network, and to preprocess and perceive the data status.

[0054] S102. The real-time monitoring module for distribution network status includes a real-time monitoring unit for distribution network status, a communication network unit, and a control mode authentication unit. It maintains a bidirectional communication connection between the real-time monitoring unit for distribution network status and the control mode authentication unit. The communication network unit is integrated inside the real-time monitoring unit for distribution network status.

[0055] S103, Intelligent Voltage Control System Control Distribution Network Status Real-time Monitoring Unit collects and monitors the operating status of the distribution network in real time, including key grid parameters such as voltage, current, power, frequency, and load.

[0056] S104, The intelligent voltage control system control distribution network status real-time monitoring unit provides real-time data on various nodes, equipment and lines of the power grid so that other modules such as decision models and distributed execution modules can make corresponding control decisions based on this data;

[0057] S105, the intelligent voltage control system control distribution network status real-time monitoring unit integrates various sensors and monitoring equipment to collect electrical parameters of the distribution network in real time and transmit these data to the distribution network data center or other decision modules for analysis;

[0058] S106, The intelligent voltage control system control communication network unit is responsible for data transmission and communication between different devices, monitoring units and control systems in the distribution network, ensuring the accurate and timely transmission of data;

[0059] S107, the intelligent voltage control system communication network unit supports various data protocols, such as Modbus, DNP3, IEC 61850, etc., to be compatible with the communication requirements of different devices and systems;

[0060] S108, Intelligent Voltage Control System Control Mode Authentication Unit, authenticates and verifies various control modes in the distribution network control system to ensure that only certified and legal control modes can be applied in the system.

[0061] S109, Intelligent Voltage Control System Control Mode Certification Unit: In the process of automatic control of the distribution network, the unit executes a strict certification process to adjust different control strategies to ensure compliance with the system's safety, stability, and compliance requirements.

[0062] Construction and optimization of collaborative decision-making models

[0063] S201. The decision model is used to train and learn based on real-time data and historical data using machine learning algorithms to generate a collaborative control decision model with the comprehensive goal of maintaining voltage stability and reducing grid losses, and to continuously optimize the decision model based on grid feedback.

[0064] S202. The decision model includes a big data learning unit, a decision model generation unit, and a decision model optimization unit. The output of the big data learning unit is kept in communication with the input of the decision model generation unit, and the output of the decision model generation unit is kept in communication with the input of the decision model optimization unit.

[0065] S203, the intelligent voltage control system controls the big data learning unit to extract valuable information from a large amount of data in the operation of the distribution network, and discovers potential patterns and trends through data analysis and learning algorithms. The data includes voltage, current, power, equipment status, load changes, etc.

[0066] S204 The intelligent voltage control system's big data learning unit adopts a deep reinforcement learning algorithm, using the distribution network operating environment as the learning environment for the intelligent agent, and using voltage over-limit penalties, equipment action costs, and network loss costs as reward functions. Through continuous interaction with the environment, the intelligent agent is trained to obtain the optimal control strategy.

[0067] S205, the intelligent voltage control system control decision model generation unit constructs a decision model for power grid control based on the data analysis results provided by the big data learning unit. By considering various operating parameters and control objectives of the power grid, it provides a basis for system decision-making. The operating parameters include voltage, current, power, load, etc., and the control objectives include voltage stability, energy efficiency, reactive power optimization, etc.

[0068] S206, the intelligent voltage control system control decision model generation unit generates decision rules and control strategies that adapt to different operating conditions based on machine learning algorithms or optimization algorithms, ensuring that the distribution network can operate stably in various environments;

[0069] S207, the intelligent voltage control system control decision model optimization unit continuously optimizes and adjusts the existing decision model based on actual power grid operation feedback, so as to improve the operating efficiency and stability of the power grid and enable the power grid to achieve more precise voltage regulation and power distribution under different load conditions.

[0070] S208, the intelligent voltage control system control decision model optimization unit, refines and adjusts the decision model through real-time data, system feedback, and algorithm optimization methods to ensure that the power grid control system can cope with constantly changing demands and operating environments.

[0071] Distributed collaborative control execution

[0072] S301. The distributed execution module is used to send the control commands generated by the decision model to each distributed execution unit through the communication network, and coordinate the adjustment of the tap changer of the on-load tap changer, the switching of the capacitor bank, the static var compensator and the active and reactive power output of the distributed power source.

[0073] S302, The distributed execution module includes a distributed execution unit, a power distribution network data center, and a response optimization unit, and both the distributed execution unit and the response optimization unit maintain bidirectional communication connections with the power distribution network data center;

[0074] S303, the intelligent voltage control system controls the distributed execution unit to perform specific voltage control operations in various areas of the distribution network through coordination with other execution units, ensuring that each node in the distribution network can adjust active and reactive power as needed to keep the voltage within a reasonable range;

[0075] S304, the intelligent voltage control system controls the distributed execution unit to support data acquisition, providing real-time data support for subsequent optimization control and decision-making;

[0076] S305 The intelligent voltage control system controls the distribution network data center to collect and manage real-time data from the entire distribution network. The real-time data includes the acquisition, storage and processing of various electrical parameters such as voltage, current, power and frequency.

[0077] S306, the intelligent voltage control system controls the distribution network data center to analyze power grid operation data and promptly detect potential power grid problems, such as voltage instability and equipment failure.

[0078] S307, the intelligent voltage control system controls the data center of the distribution network to work in coordination with other units, and transmits key data to relevant modules for decision-making and response;

[0079] S308, the intelligent voltage control system control response optimization unit optimizes the response strategy of the distribution network based on the data collected by the distribution network data center and the operating status of the power grid;

[0080] S309, the intelligent voltage control system control response optimization unit adjusts and optimizes the voltage control strategy in real time, including adjusting the output of active and reactive power, allocating reactive power, activating backup power or adjusting voltage control equipment, etc., to ensure that the distribution network system can maintain voltage stability without overload.

[0081] When a local voltage exceeds the limit, the S310 intelligent voltage control system control response optimization unit prioritizes calling the nearest reactive power compensation resources for adjustment; when the reactive power resources are exhausted or the effect is insufficient, it then coordinates the control of the active power resources in the adjacent area to achieve coordinated support of active and reactive power in time and space.

[0082] Collaborative visualization and monitoring

[0083] S401, The collaborative visualization module is used to centrally visualize and display the overall network operation status, control strategies, and execution results;

[0084] S402, The collaborative visualization module includes an algorithm collaboration unit, a distributed visualization unit, and other collaborative control units, and the output terminals of the algorithm collaboration unit and other collaborative control units are all connected to the input terminal of the distributed visualization unit.

[0085] S403, the intelligent voltage control system control algorithm coordination unit processes data information from various distributed execution units, distribution network data centers and other modules, and optimizes the active and reactive power coordinated voltage control of the distribution network through algorithms. The algorithms include optimal control algorithms, prediction algorithms, fault diagnosis algorithms, etc., to solve voltage control problems in the power grid and ensure voltage stability and energy efficiency during system operation.

[0086] S404, the intelligent voltage control system control algorithm coordination unit adjusts in real time according to changes in the external environment or load to ensure that the algorithm output can minimize energy loss and failure.

[0087] The S405 intelligent voltage control system's distributed visualization unit graphically displays the status of each distributed execution unit and monitoring data in the power grid to the operator, enabling real-time understanding of the power grid's operation, control strategy execution status, and potential problems.

[0088] The S406 intelligent voltage control system's distributed visualization unit provides a centralized visualization platform that supports real-time updates, helping staff monitor the real-time status of various nodes in the power grid.

[0089] S407, the intelligent voltage control system, controls other collaborative control units and is mainly responsible for various collaborative operations and optimization adjustments in the system. It performs precise control of power grid equipment based on the input signals provided by the distributed execution unit and the algorithm collaboration unit.

[0090] The S408 intelligent voltage control system controls other collaborative control units to perform multi-level control, such as load sharing between areas and rational allocation of reactive power, in order to maximize the overall voltage stability and energy efficiency of the system.

[0091] Safety early warning management

[0092] S501, The voltage control system further includes a safety early warning management module. The intelligent voltage control system controls the safety early warning management module to monitor the safety risks in the power distribution network in real time and issue an early warning when an abnormality is detected.

[0093] S502, The safety early warning management module includes a field remote early warning unit and a safety risk control unit, and maintains a two-way communication connection between the field remote early warning unit and the safety risk control unit;

[0094] The S503 intelligent voltage control system controls the field remote early warning unit to identify the voltage, current and other related parameters detected in the distribution network, identify abnormal states or potential safety risks, and trigger an early warning signal when the operating status of the equipment or the power grid is detected to be abnormal.

[0095] S504, the intelligent voltage control system controls the remote early warning unit to notify remote and on-site personnel to intervene;

[0096] The S505 intelligent voltage control system safety risk control unit analyzes the system's safety status based on field data, determines whether there are potential fault risks, overload risks, equipment failures, etc., and automatically adjusts the active and reactive power of the distribution network to regulate voltage when a safety risk is detected, so as to avoid system collapse or equipment damage.

[0097] S506, the intelligent voltage control system's safety risk control unit, immediately triggers an alarm and takes control measures when a risk is assessed as high-risk, such as automatically cutting off power, starting backup equipment, and dispatching personnel to handle the situation. It records each safety risk and control operation to facilitate post-event analysis, improvement, and the development of more effective safety plans.

[0098] The deep reinforcement learning reward function (R = -α*Σ|Ui-Ulim| - β*Σ|ΔC| - γ*Ploss) of this invention is specifically designed for the specific technical problem of distribution network voltage control. It simultaneously considers voltage deviation, equipment operating costs and network losses. This multi-objective trade-off model design is non-obvious.

[0099] The state space of the deep reinforcement learning agent includes the voltage of each node, active and reactive power, load rate, etc., and the action space includes the transformer tap position, capacitor bank switching status, distributed power factor command, etc.

[0100] Example 1: Rapid Voltage Control to Cope with Sudden Increases in Local Load

[0101] 1. Scene Description:

[0102] During the evening peak electricity consumption period, a 10kV feeder (containing 15 nodes) in a city's power distribution network experienced a surge in load at node 7 from 800kW to 1200kW within 2 minutes due to concentrated power consumption by a large commercial complex. Consequently, the voltage at this node rapidly dropped from 0.98pu (per unit value) to 0.92pu (the national standard lower limit is 0.93pu), posing a risk of voltage exceeding the limit. Furthermore, the network loss in this area increased from 25kW to 32kW.

[0103] 2. System operation process and data analysis:

[0104] S1. Real-time monitoring and sensing:

[0105] The voltage and current sensors deployed at node 7 were the first to detect voltage dips and power changes;

[0106] The real-time monitoring module for the power distribution network status completes data collection within 5 seconds and confirms that it is currently in automatic collaborative control mode through the control mode authentication unit;

[0107] The communication network unit uploads alarm data and real-time operation data packets (including node 7 voltage 0.92pu, load 1200kW, regional network loss 32kW) to the decision model and distribution network data center via the IEC61850 protocol;

[0108] S2, Intelligent Decision-Making and Optimization:

[0109] After receiving real-time data, the decision model immediately starts the big data learning unit. Based on training in similar historical scenarios, the deep reinforcement learning agent calculates the optimal strategy within 1 second.

[0110] The reward function R = -0.7 * |0.92 - 0.93| - 0.2 * 1 - 0.1 * 32 calculates that the reward value for the current state is negative, triggering a control action.

[0111] The decision model generation unit outputs control instructions: prioritize the activation of capacitor bank C1 near node 6 (providing 300kvar reactive power compensation), as this is the fastest reactive power support method. The model predicts that this operation can boost the voltage to 0.945pu, but it still does not fully meet the target.

[0112] S3, Collaborative Control Execution:

[0113] After receiving the instruction, the distributed execution module fine-tunes the response optimization unit and completes the switching of capacitor bank C1 within 2 seconds.

[0114] Monitoring data showed that the voltage rose to 0.944 pu, which was basically consistent with the prediction, but still exceeded the limit. The decision model then activated the second strategy: coordinated control of the distributed photovoltaic inverter located at node 8, adjusted its power factor from 0.98 (lagging) to 0.90 (lagging), and generated an additional 150 kvar of reactive power.

[0115] After execution, the voltage at node 7 stabilized at 0.965 pu, successfully exiting the over-limit region. The entire adjustment process was completed within 10 seconds.

[0116] S4. Visualization and Early Warning:

[0117] On the collaborative visualization module, the color of node 7 changes from red, representing an alarm, to green, representing normal operation, and a voltage recovery curve and policy execution log are generated.

[0118] Since the entire process was completed automatically and quickly by the system, the safety warning management module only recorded minor voltage over-limit events and archived them automatically, without triggering high-level alarms that would disturb staff.

[0119] index Before control After control Improvement effect Node 7 voltage (pu) 0.92 (out of limit) 0.964 (normal) Improved by 4.9%, resolving over-limit issues. Regional network loss (KW) 32 28 Reduced by 12.5% Response and adjustment time - <10 seconds Far exceeding human response speed Control equipment operation - Capacitor switching and inverter regulation Coordination of active and reactive power to avoid excessive operation of a single device.

[0120] Example 2: Network Voltage Optimization and Early Warning under Distributed Power Generation Fluctuations

[0121] 1. Scene Description:

[0122] At midday, in a distribution network area with a high proportion of distributed photovoltaic power, the total photovoltaic output fluctuated from 2MW to 1.2MW within 5 minutes due to sudden cloud cover. This caused the voltage at the end nodes 12, 13, and 14 of the line to drop from 1.02pu to 0.94pu (exceeding the limit). At the same time, the system power flow reversed, and the network loss increased from 40kW to 55kW.

[0123] 2. System operation process and data analysis:

[0124] S1. Real-time monitoring and sensing:

[0125] The monitoring units of multiple nodes simultaneously captured the reverse changes in power and voltage, and the real-time monitoring unit of the distribution network status determined that this was a regional voltage problem caused by source-side fluctuations.

[0126] S2, Intelligent Decision-Making and Optimization:

[0127] The multi-objective optimization function of the decision model is initiated: MinF=0.6*Σ(Ui-1.00)^2+0.4*55. After calculation, the model finds that reactive power regulation alone is insufficient to support the voltage.

[0128] The decision model generation unit generates a collaborative control instruction package:

[0129] Instruction 1: Adjust the tap changer of the on-load tap-changing transformer (OLTC) to change the turns ratio from 1.025 to 1.050;

[0130] Instruction 2: Activate capacitor banks C2 and C3 at nodes 11 and 13 (total 500kvar);

[0131] Instruction 3 (Active Power Support): Slightly reduce the non-critical interruptible load (such as electric vehicle charging piles) in the area by 50kW, and adjust the photovoltaic inverters that are still generating electricity so that they generate an additional 100kvar of reactive power while generating active power.

[0132] S3, Collaborative Control Execution:

[0133] The distributed execution unit executes in the order of reactive power first, then active power. After the OLTC and capacitors are activated, the node voltage rises back to 0.95-0.96 pu, but does not fully recover.

[0134] The response optimization unit then executes instruction 3 to provide coordinated support for active power, thereby further supporting the voltage.

[0135] S4. Visualization and Early Warning:

[0136] During the control process, the collaborative visualization module generated a full-network voltage heat map, clearly showing the process of the voltage dip area gradually shrinking from the end;

[0137] When the voltage first exceeds the limit, the safety early warning management module pushes a regional voltage over-limit alarm to the mobile APP of the operation and maintenance personnel. When the system executes the active power support strategy, due to the involvement of load control, the module pushes confirmation information for the execution of active power coordinated control again and automatically generates a risk analysis report, recording that the root cause of this fluctuation is a sudden drop in photovoltaic output.

[0138] index Before control After control Improvement effect Node 7 voltage (pu) 0.94 (out of limit) 0.98 (normal) Improved by 4.3%, resolving over-limit issues. Regional network loss (KW) 56 48 Decreased by 12.9% Response and adjustment time - Fully automated collaborative control requires personnel monitoring and confirmation. Multi-resource collaboration yields significant results. Control equipment operation Manual analysis and operation are required one by one. Capacitor switching and inverter regulation Reduce troubleshooting time and human error

[0139] Specifically, in practical applications, multiple collaborative visualization modules are used in conjunction with the real-time monitoring module for distribution network status, the decision model, and the distributed execution module. These multiple collaborative visualization modules are located in different geographical locations. This invention constructs a complete voltage control system by setting up the real-time monitoring module for distribution network status, the decision model, the distributed execution module, and the collaborative visualization module. In actual use, sensors deployed at various nodes of the distribution network collect real-time data on the operation of the power grid. Based on the collected real-time and historical data, machine learning algorithms are used for training and learning to generate a collaborative control decision model with the comprehensive goal of maintaining voltage stability and reducing network losses. The decision model is continuously optimized based on power grid feedback. The control commands generated by the decision model are sent to each distributed execution unit through the communication network to coordinate the adjustment of the tap changers of on-load tap changers, capacitor bank switching, static var compensators, and the active and reactive power outputs of distributed power sources. At the same time, the overall network operation status, control strategies, and execution results are centrally visualized.

[0140] Modular design and intelligent algorithms have brought about the following significant benefits:

[0141] Through real-time data acquisition and collaborative decision-making models, the system can quickly detect voltage deviations and dynamically adjust active and reactive power, keeping voltage fluctuations within ±2% of the rated value, significantly reducing voltage over-limit events. Utilizing a multi-objective optimization model, the system minimizes total active power losses while maintaining voltage stability. Through spatiotemporal collaborative support of active and reactive power, it prioritizes the use of nearby reactive resources when local voltage over-limits occur, and only coordinates active resources when ineffective, improving response speed. The collaborative visualization module provides a graphical interface to display the real-time network operation status, control strategies, and execution results, helping staff quickly identify problems. It manages, visualizes, and stores collaborative voltage control data and corresponding analysis results, facilitating collaborative voltage control management through IoT cloud management and control, and improving the intelligence level of collaborative voltage control management.

[0142] Those skilled in the art will recognize that the modules and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0143] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, equipment, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0144] In the embodiments provided in this application, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or equipment, and may be electrical, mechanical, or other forms.

[0145] The modules for real-time monitoring of power grid status, decision-making models, distributed execution, and collaborative visualization may or may not be physically separate. The components displayed as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0146] Furthermore, it should be noted that the combination of the various technical features in this case is not limited to the combination methods described in the claims of this case or the combination methods described in the specific embodiments. All technical features described in this case can be freely combined or combined in any way, unless there is a contradiction between them.

[0147] It should be noted that the above examples are merely specific embodiments of the present invention, and the present invention is obviously not limited to the above embodiments, with many similar variations. All modifications that can be directly derived or conceived by those skilled in the art from the content disclosed in this invention should fall within the protection scope of this invention.

[0148] The above are merely preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for coordinated active and reactive power voltage control in a power distribution network, characterized in that, The specific steps include the following: S1. Real-time data acquisition and status awareness processing: Real-time acquisition of power grid operation data through sensors deployed at various nodes of the distribution network; S2. Construction and optimization of collaborative decision-making model based on big data learning: Based on the real-time data and historical data collected in step S1, machine learning algorithms are used for training and learning to generate a collaborative control decision-making model with the comprehensive goal of maintaining voltage stability and reducing grid loss, and the decision-making model is continuously optimized based on grid feedback. S3. Distributed collaborative control execution and visualization processing: The control commands generated by the decision model described in step S2 are sent to each distributed execution unit through the communication network to coordinate the adjustment of the tap changer of the on-load tap changer, the switching of capacitor banks, the static var compensator, and the active and reactive power output of the distributed power source. S4. Simultaneously, the overall network operation status, control strategies, and execution results are centrally visualized and displayed.

2. The method for coordinated active and reactive power voltage control in a distribution network according to claim 1, characterized in that: The collaborative control decision model in step S2 is a multi-objective optimization model, and its objective function is expressed as: MinF=ω1*Σ(Ui-Uref)^2+ω2*Ploss Where Ui represents the real-time voltage of node i, Uref represents the rated reference voltage, Ploss represents the total active power loss of the system, and ω1 and ω2 are weighting coefficients used to balance the optimization priority of voltage deviation and network loss.

3. The method for coordinated active and reactive power voltage control in a distribution network according to claim 1, characterized in that: In step S2, training and learning using machine learning algorithms specifically includes: using a deep reinforcement learning algorithm, taking the power distribution network operating environment as the learning environment for the agent, and using voltage over-limit penalties, equipment operation costs, and network loss costs as reward functions. By continuously interacting with the environment, the agent is trained to obtain the optimal control strategy.

4. The method for coordinated active and reactive power voltage control in a distribution network according to claim 1, characterized in that: The reward function R is designed as follows: R=-α*Σ|Ui-Ulim|-β*Σ|ΔC|-γ*Ploss Wherein, when the node voltage Ui exceeds the limit, Ulim is the upper or lower limit of the voltage; otherwise, this term is zero; ΔC represents the number of times the reactive power compensation equipment or transformer tap changer operates; Ploss is the system network loss; α, β, γ are the weighting coefficients of each penalty term.

5. The method for coordinated active and reactive power voltage control in a distribution network according to claim 1, characterized in that: The data in step S1 includes node voltage, branch current, active power, reactive power, load rate, and distributed power output; the coordinated adjustment in step S3 includes prioritizing the use of nearby reactive power compensation resources for adjustment when a local voltage exceeds the limit; when reactive power resources are exhausted or insufficient, the active power resources in adjacent areas are coordinated and controlled to achieve coordinated support of active and reactive power in time and space.

6. A distribution network active and reactive power coordinated voltage control system, used to implement the distribution network active and reactive power coordinated voltage control method as described in any one of claims 1-5, characterized in that: The voltage control system includes a real-time monitoring module for distribution network status, a decision model, a distributed execution module, and a collaborative visualization module. Staff can log in to the collaborative visualization module to access the voltage control system and view the real-time operating data of the real-time monitoring module for distribution network status, the decision model, and the distributed execution module.

7. A power distribution network active and reactive power coordinated voltage control system according to claim 6, characterized in that: The real-time monitoring module for distribution network status includes a real-time monitoring unit for distribution network status, a communication network unit, and a control mode authentication unit. The real-time monitoring unit for distribution network status and the control mode authentication unit are bidirectionally connected, and the communication network unit is integrated inside the real-time monitoring unit for distribution network status. The main task of the real-time monitoring unit for distribution network status is to collect and monitor the operating status of the distribution network in real time. The communication network unit is used for data transmission and communication between different devices, monitoring units and control systems in the power distribution network; The control mode authentication unit is used to authenticate and verify various control modes in the power distribution network control system.

8. A power distribution network active and reactive power coordinated voltage control system according to claim 6, characterized in that: The decision model includes a big data learning unit, a decision model generation unit, and a decision model optimization unit. The output of the big data learning unit is communicatively connected to the input of the decision model generation unit, and the output of the decision model generation unit is communicatively connected to the input of the decision model optimization unit. The big data learning unit is used to extract valuable information from a large amount of data in the operation of the power distribution network, and to discover potential patterns and trends through data analysis and learning algorithms. The decision model generation unit is used to construct a decision model for power grid control based on the data analysis results provided by the big data learning unit. The decision model optimization unit is used to continuously optimize and adjust the existing decision model based on actual power grid operation feedback.

9. A power distribution network active and reactive power coordinated voltage control system according to claim 6, characterized in that: The distributed execution module includes a distributed execution unit, a power distribution network data center, and a response optimization unit. Both the distributed execution unit and the response optimization unit are bidirectionally connected to the power distribution network data center. The distributed execution unit is used to perform specific voltage control operations in various areas of the power distribution network by coordinating with other execution units; The power distribution network data center is used to collect and manage real-time data from the entire power distribution network. The real-time data includes the acquisition, storage and processing of various electrical parameters such as voltage, current, power and frequency. The response optimization unit is used to optimize the response strategy of the distribution network based on the data collected by the distribution network data center and the operating status of the power grid. The collaborative visualization module includes an algorithm collaboration unit, a distributed visualization unit, and other collaborative control units. The outputs of the algorithm collaboration unit and other collaborative control units are all communicatively connected to the input of the distributed visualization unit. The algorithm coordination unit is used to process data information from various distributed execution units, distribution network data centers and other modules, and to optimize the active and reactive power coordinated voltage control of the distribution network through algorithms. The distributed visualization unit is used to display the status of each distributed execution unit and monitoring data in the power grid to the staff in a graphical way; The other collaborative control units are mainly responsible for various collaborative tasks and optimization adjustments in the system, and perform precise control of power grid equipment based on the input signals provided by the distributed execution unit and the algorithm collaboration unit.

10. A power distribution network active and reactive power coordinated voltage control system according to claim 6, characterized in that: The voltage control system also includes a safety early warning management module, which includes a field remote early warning unit and a safety risk control unit, and the field remote early warning unit and the safety risk control unit are bidirectionally connected. The on-site remote early warning unit is used to identify the voltage, current and other related parameters detected in the power distribution network, and to identify abnormal states or potential safety risks. The safety risk control unit is used to analyze the safety status of the system based on on-site data and determine whether there are potential risks of failure, overload, equipment failure, etc.

Images