Power transmission line dynamic capacity increasing method and system based on distributed cooperation

Abstract

The invention discloses a power transmission line dynamic capacity increasing method and system based on distributed collaboration. The method specifically comprises the following steps: acquiring operation data and meteorological data of each node on a power transmission line in real time; preprocessing the collected operation data and meteorological data; based on the preprocessed data, solving a transient heat balance model by using a steady-state condition, and calculating the maximum allowable current-carrying capacity according to a solving result; fusing the maximum allowable current-carrying capacity of each node by adopting a distributed cooperation method to obtain a global maximum current-carrying capacity; solving a load prediction value at a future moment, and generating a global regulation and control strategy in combination with the global maximum current-carrying capacity; and dynamically adjusting the working state of the field equipment according to the global regulation and control strategy to obtain a dynamic capacity increasing result of the power transmission line, thereby realizing the dynamic capacity increasing of the power transmission line based on distributed coordination. Dynamic calculation and real-time regulation and control of the maximum safe current-carrying capacity of the power transmission line are realized, so that the invisible capacity of the existing line is fully released, and the requirements of safe and economic operation of a power grid are met.

Description

Technical Field

[0001] The present invention belongs to the field of power system operation management and intelligent control technology, and more specifically, relates to a method and system for dynamic capacity expansion of transmission lines based on distributed collaboration. Background Art

[0002] With rising electricity demand and the large-scale integration of renewable energy sources, traditional transmission lines are facing increasing operational pressure. Traditional dynamic capacity expansion methods, based on steady-state thermal balance models, assume constant environmental parameters and are unable to respond in real time to transient changes such as sudden wind speed changes and temperature fluctuations. Furthermore, most existing transmission lines operate according to fixed, static design capacities, often with a large safety margin to ensure safety. However, under normal operating conditions, the actual current carrying capacity of the lines is far below the design value, resulting in low resource utilization. The lack of proactive optimization based on load forecasting makes it difficult to cope with the randomness of renewable energy output. Furthermore, the construction of new transmission lines is constrained by limited land availability, high investment costs, and long construction periods. Therefore, achieving dynamic capacity expansion on existing lines has become a key issue in optimizing grid operations.

[0003] Currently, existing technologies primarily rely on centralized online monitoring systems, which collect data on conductor temperature, ambient temperature, wind speed, and load, and use thermal balance models or empirical formulas to calculate the maximum current carrying capacity of transmission lines. However, centralized systems suffer from issues such as data transmission delays, single points of failure, and an inability to fully reflect regional meteorological variations. These issues lead to conservative calculation results and untimely responses, making it difficult to fully realize the hidden capacity of the lines. Furthermore, some systems lack effective fault tolerance measures when data is missing or abnormal, which can easily affect the overall operational safety of the system. Summary of the Invention

[0004] In order to address the shortcomings of the existing technology, the present invention provides a method and system for dynamic capacity expansion of transmission lines based on distributed collaboration. Edge intelligence technology is used to delegate data collection and preliminary decision-making to various monitoring nodes along the transmission line. Through hierarchical collaborative calculation, dynamic measurement of the global optimal current carrying capacity is achieved, and dynamic control strategies are generated using intelligent prediction algorithms and sent to on-site control equipment to form a closed-loop control. This can fully reflect the differences in local operating conditions in various regions, and automatically activate backup plans when data is abnormal, ensuring stable, safe and economical operation of the system.

[0005] The present invention adopts the following technical solutions.

[0006] A first aspect of the present invention provides a method for dynamically increasing the capacity of a transmission line based on distributed collaboration, comprising:

[0007] Real-time collection of operating data and meteorological data of each node on the transmission line;

[0008] Pre-process the collected operational data and meteorological data;

[0009] Based on the pre-processed data, the transient heat balance model is solved using steady-state conditions, and the maximum allowable current carrying capacity is calculated based on the solution;

[0010] The distributed coordination method is used to merge the maximum allowable current carrying capacity of each node to obtain the global maximum current carrying capacity;

[0011] Solve the load forecast value at the future moment, combine it with the global maximum current carrying capacity, and generate the global control strategy;

[0012] According to the global control strategy, the working status of the on-site equipment is dynamically adjusted to obtain the result of dynamic capacity expansion of the transmission line, thereby realizing dynamic capacity expansion of the transmission line based on distributed collaboration.

[0013] Preferably, the method of solving the transient heat balance model based on the preprocessed data using steady-state conditions and calculating the maximum allowable current carrying capacity according to the solution includes:

[0014] Combined with the pre-processed data, a transient heat balance model is constructed;

[0015] According to the balance between heat generation and heat dissipation under steady-state conditions, the constraint conditions of heat and heat dissipation balance are constructed;

[0016] Solve the transient temperature difference based on the constraints of heat and heat dissipation balance and the transient heat balance model;

[0017] When the current conductor temperature is at the highest temperature allowed to be reached by the conductor under safe operating conditions, the maximum allowable current carrying capacity of this node is solved based on the transient temperature difference.

[0018] Preferably, the transient heat balance model specifically includes:

[0019] The sum of the current ambient temperature and the temperature rise caused by the load, minus the temperature drop due to heat dissipation, equals the current conductor temperature.

[0020] Preferably, when the current conductor temperature is at the maximum temperature allowed to be reached by the conductor under safe operating conditions, solving the maximum allowable current carrying capacity of the node according to the transient temperature difference specifically includes:

[0021] Replace the current conductor temperature in the transient temperature difference formula with the maximum temperature allowed for the conductor under safe operating conditions, and subtract the current ambient temperature to obtain the maximum temperature difference at this node.

[0022] The maximum heat dissipation per unit time is obtained by multiplying the convection heat transfer coefficient, the effective heat dissipation surface area of ​​the conductor, and the maximum temperature difference of this node;

[0023] Divide the maximum heat dissipation per unit time by the wire resistance and take the square root to obtain the maximum allowable current carrying capacity of this node.

[0024] Preferably, the method of adopting a distributed collaborative method to merge the maximum allowable current carrying capacity of each node to obtain the global maximum current carrying capacity specifically includes:

[0025] Each node transmits the maximum allowable current carrying capacity and node weight calculated locally to the adjacent nodes through the distributed communication network;

[0026] Each node uses the maximum allowable current carrying capacity and node weight received from adjacent nodes and performs weighted fusion with its own maximum allowable current carrying capacity and node weight to obtain the current global current carrying capacity;

[0027] Each node uses an iterative weighted average algorithm to repeatedly iterate and calculate the current global current carrying capacity until the current global current carrying capacity calculation results of all nodes converge to a global consistency, forming a global optimal safe current carrying capacity value, which is set as the global maximum current carrying capacity.

[0028] Preferably, the method of solving the load forecast value at the future moment and combining it with the global maximum current carrying capacity to generate a global control strategy specifically includes:

[0029] Input historical data and real-time data into the load forecasting model for prediction, and solve the load forecast value at the future time t+τ;

[0030] The global maximum current carrying capacity and the load forecast value at the future time t+τ are input into the pre-trained mapping function to generate a global control strategy.

[0031] Preferably, the step of inputting historical data and real-time data into a load forecasting model for forecasting to obtain a load forecast value at a future time t+τ specifically includes:

[0032] Construct the historical load and environmental data matrix from time t to time t+τ;

[0033] The data matrix is ​​input into the convolutional neural network to extract the local spatiotemporal characteristics of the load;

[0034] Input the local spatiotemporal characteristics of the load into the long-short term neural network to capture the long-short time series dependency characteristics of the load;

[0035] The long and short time series dependency features of the load are input into the support vector machine for correction to obtain the load forecasting results.

[0036] Preferably, the global maximum current carrying capacity and the load forecast value at the future time t+τ are input into a pre-trained mapping function to generate a global control strategy, which specifically includes:

[0037] Inputting the global maximum current carrying capacity, the load forecast value at the future time t+τ and the transformer tap data into the first mapping function to obtain the transformer tap adjustment value;

[0038] The global maximum current carrying capacity, the load forecast value at the future time t+τ, and the line tension data are input into the second mapping function to obtain the line tension adjustment amplitude;

[0039] The global maximum current carrying capacity, the load forecast value at the future time t+τ, and the auxiliary cooling device data are input into the third mapping function to obtain the auxiliary cooling device start and stop signal;

[0040] The transformer tap adjustment amount, line tension adjustment amplitude and auxiliary cooling device start and stop signals are combined to generate a global control strategy.

[0041] Preferably, dynamically adjusting the working state of the on-site equipment according to the global control strategy to obtain the result of dynamic capacity increase of the transmission line specifically includes:

[0042] Distribute the global control strategy to all on-site devices;

[0043] The field device dynamically adjusts the working state of the field device according to the received global control strategy to obtain the adjustment result of the field device;

[0044] Based on the adjustment results of on-site equipment and real-time monitoring data, the distributed collaborative solution process of global maximum current carrying capacity and load forecast is repeated to generate an optimized global control strategy. Then, the on-site equipment is adjusted to form a closed-loop control. Through multiple closed-loop controls, the dynamic capacity expansion results of the transmission line are obtained.

[0045] The second aspect of the present invention provides a system for dynamically increasing the capacity of a transmission line based on distributed collaboration, which runs the method for dynamically increasing the capacity of a transmission line based on distributed collaboration described in the first aspect of the present invention, specifically comprising:

[0046] Data acquisition module, used to collect real-time operating data and meteorological data of each node on the transmission line;

[0047] Preprocessing module, used to preprocess the collected operation data and meteorological data;

[0048] The maximum allowable current carrying capacity solving module is used to solve the transient heat balance model based on the pre-processed data using steady-state conditions and calculate the maximum allowable current carrying capacity based on the solution results;

[0049] The global maximum current carrying capacity solving module is used to integrate the maximum allowable current carrying capacity of each node using a distributed collaborative method to obtain the global maximum current carrying capacity;

[0050] The global control strategy generation module is used to solve the load forecast value at the future moment and generate the global control strategy based on the global maximum current carrying capacity;

[0051] The dynamic capacity expansion module is used to dynamically adjust the working status of on-site equipment according to the global control strategy, obtain the result of dynamic capacity expansion of the transmission line, and realize dynamic capacity expansion of the transmission line based on distributed collaboration.

[0052] The third aspect of the present invention proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is loaded into the processor, the method for dynamic capacity expansion of transmission lines based on distributed collaboration according to the first aspect of the present invention is implemented.

[0053] The fourth aspect of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method for dynamic capacity expansion of transmission lines based on distributed collaboration according to the first aspect of the present invention.

[0054] Compared with the prior art, the beneficial effects of the present invention include at least:

[0055] 1) This method collects real-time changes in environmental parameters and operating data, responds to environmental fluctuations in real time through a transient thermal balance model, replaces the fixed assumptions of traditional steady-state models, and dynamically calculates the maximum allowable current carrying capacity of the line. Based on safety constraints such as transient temperature rise and sag constraints, the current carrying capacity is adjusted in real time, instantly releasing hidden capacity, avoiding overload risks caused by environmental changes, enhancing grid flexibility and environmental adaptability, and reducing resource waste caused by conservative design.

[0056] For example, but not limited to, when the ambient temperature of the line suddenly rises at noon, the carrying capacity is calculated and predicted in real time. At this time, the carrying capacity is too large, exceeding the national standard of 80 degrees. Assuming that the environmental parameters are constant, it is unable to reflect the actual dynamic changes, resulting in conservative calculation of the carrying capacity. The steady state cannot solve this problem. The present invention converts the steady state into a transient state, and dynamically reduces the carrying capacity by generating a control strategy based on the real-time changes in the environment. In the afternoon, the ambient temperature of the line is monitored to drop in real time. The carrying capacity is obtained through real-time calculation and prediction. The carrying capacity is too low, and a control strategy is generated to dynamically increase the carrying capacity, thereby realizing dynamic capacity expansion.

[0057] 2) By predicting future short-term loads and combining them with real-time current-carrying capacity to dynamically adjust control strategies, line operating parameters are optimized and equipment status (such as, but not limited to, taps, tension, and cooling devices) is adjusted in advance to avoid emergency load reductions or power outages caused by sudden load increases. Furthermore, based on the predicted results, equipment status is adjusted only when needed, improving the overall resource utilization and economic efficiency of the power grid. For example, but not limited to, cooling devices are activated or tensioned only when needed, reducing energy consumption and equipment losses. Cooling devices are shut down at night when temperatures are low, saving energy and optimizing operating costs.

[0058] 3) This invention achieves this by integrating the local maximum current capacity of each node in a distributed, collaborative manner. This transmits the maximum allowable current capacity of each node to adjacent nodes via a distributed communication network, eliminating data transmission delays. In the event of a single point of failure, the system redetermines the global maximum current capacity through distributed collaborative calculations across all remaining nodes, ensuring control continuity and preventing a single node failure from limiting global capacity. This improves the system's response rate and fault tolerance. For example, but not limited to, when a node fails, other nodes can still contribute capacity.

[0059] 4) After the equipment is adjusted, the capacity expansion effect is verified through monitoring data, the prediction model parameters are updated, and the accuracy of subsequent strategies is improved. The present invention continuously corrects model errors through closed-loop feedback, achieving real-time self-correction and optimization of transmission line field equipment, ensuring the safety and reliability of the capacity expansion process, and improving the robustness and accuracy of the capacity expansion process. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a schematic diagram of the overall structure of a system provided in accordance with an embodiment of the present invention;

[0061] Figure 2 It is a schematic diagram of a fault detection and fault tolerance mechanism provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. The described embodiments are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0063] like Figure 1 As shown, embodiment 1 of the present invention provides a method for dynamic capacity expansion of a transmission line based on distributed collaboration, comprising the following steps:

[0064] Step 1: collect the operating data and meteorological data of each node on the transmission line in real time, wherein the operating data includes conductor temperature, load and conductor temperature rise data, and the meteorological data includes ambient temperature and wind speed.

[0065] In a preferred but non-limiting embodiment of the present invention, step 1 comprises:

[0066] In a certain urban regional power grid, a transmission line with a total length of approximately 250 kilometers was selected as the target. Multiple online monitoring and control nodes were deployed in key areas along the transmission line, such as but not limited to substations, line nodes, and key load areas. Each node is equipped with meteorological monitoring, conductor temperature detection, conductor sag detection, and load detection sensors. The meteorological monitoring sensor is used to monitor wind speed and ambient temperature; the conductor temperature detection sensor is used to monitor conductor temperature; the load detection sensor is used to monitor load; and the conductor sag detection sensor is used to monitor conductor temperature rise. The data collected by each sensor includes device identification, collection time, and corresponding measurement value.

[0067] Step 2: Preprocess the operating data and meteorological data collected in step 1.

[0068] In a preferred but non-limiting embodiment of the present invention, step 2 comprises:

[0069] The collected data are filtered, denoised, normalized and time synchronized.

[0070] Step 3: Based on the data preprocessed in step 2, the transient heat balance model is solved using steady-state conditions, and the maximum allowable current carrying capacity is calculated according to the solution.

[0071] In a preferred but non-limiting embodiment of the present invention, step 3 comprises:

[0072] Step 3.1: Combine the preprocessed data to construct a transient heat balance model, which is expressed as the following formula:

[0073] T(t)=T ambient (t)+ΔT load (t)-ΔT cooling (t) (1)

[0074] in,

[0075] T(t) represents the current conductor temperature, T ambient (t) represents the current ambient temperature, ΔT load (t) represents the temperature rise caused by the load, where the temperature rise caused by the load is ΔT load (t) is derived from Joule's law and expressed as follows:

[0076] ΔT load (t) = Q / C (2)

[0077] Where,

[0078] Q represents the heat generated per unit time and is expressed by the following formula:

[0079] Q=I(t) 2 RΔt (3)

[0080] Where,

[0081] I(t) represents the real-time current, R represents the wire resistance, Δt represents the time step, and C represents the wire heat capacity, which is expressed as follows:

[0082] C=mc (4)

[0083] Where,

[0084] m represents the mass of the wire, and c represents the specific heat capacity of the wire.

[0085] ΔT cooling (t) represents the heat dissipation temperature drop, which is estimated based on wind speed, local environmental conditions and Newton's law of cooling and is expressed as follows:

[0086] ΔT cooling (t) = Q conv / C (5)

[0087] Where,

[0088] Q ccnv It represents the heat dissipation per unit time and is expressed by the following formula:

[0089] Q conv =A(T(t)-T ambient (t)) (6)

[0090] Where,

[0091] h represents the convection heat transfer coefficient, which is affected by wind speed and conductor surface roughness.

[0092] A represents the effective heat dissipation surface area of ​​the wire.

[0093] Step 3.2: Based on the balance between heat generation and heat dissipation under steady-state conditions, the constraint condition for the balance between heat generation and heat dissipation is constructed and expressed as the following formula:

[0094] I(t) 2 R=A(T(t)-T ambient (t)) (7)

[0095] Step 3.3, according to the constraints of heat and heat dissipation balance in step 3.2 and the transient heat balance model in step 3.1, solve the transient temperature difference T(t)-T ambient (t), the transient temperature difference is expressed by the following formula:

[0096] T(t)-T ambient (t)=I(t) 2 R / A (8)

[0097] Step 3.4: When the current conductor temperature is at the maximum temperature T that the conductor can reach under safe operating conditions,max When the maximum allowable current carrying capacity I of this node is solved according to the transient temperature difference in step 3.3 max , specifically including:

[0098] Replace the current conductor temperature in the transient temperature difference formula with the maximum temperature allowed for the conductor under safe operating conditions, and subtract the current ambient temperature to obtain the maximum temperature difference at this node.

[0099] The maximum heat dissipation per unit time is obtained by multiplying the convection heat transfer coefficient, the effective heat dissipation surface area of ​​the conductor, and the maximum temperature difference of this node;

[0100] Divide the maximum heat dissipation per unit time by the wire resistance and take the square root to obtain the maximum allowable current carrying capacity of this node, which is expressed as the following formula:

[0101]

[0102] The edge controller obtains the maximum allowable current carrying capacity of the node based on the calculation results, and uploads the results to the central distributed collaborative computing platform through a high-speed data channel.

[0103] Step 4: Use the distributed collaboration method to merge the maximum allowable current carrying capacity of each node obtained in step 3 to obtain the global maximum current carrying capacity.

[0104] In a preferred but non-limiting embodiment of the present invention, step 4 comprises:

[0105] Each node transmits the maximum allowable current carrying capacity and node weight calculated locally to the adjacent nodes through the distributed communication network;

[0106] Each node uses the maximum allowable current carrying capacity and node weight received from adjacent nodes and performs weighted fusion with its own maximum allowable current carrying capacity and node weight to obtain the current global current carrying capacity;

[0107] Each node uses an iterative weighted average algorithm to repeatedly iterate and calculate the current global current carrying capacity until the current global current carrying capacity calculation results of all nodes converge to a global consistency, forming a global optimal safe current carrying capacity value, which is set as the global maximum current carrying capacity.

[0108] Further preferably, the specific calculation process of the global maximum current carrying capacity includes:

[0109] Multiply the maximum allowable current carrying capacity of each node by the node weight of the corresponding node, and then add the weighted results of all nodes to obtain the weighted sum of the maximum allowable current carrying capacity of all nodes and their corresponding weights;

[0110] Find the sum of the weights of all nodes;

[0111] Divide the weighted sum by the sum of all node weights to get the global maximum current carrying capacity, which is expressed as follows:

[0112] I maxglobal (t)=∑w i I max,i (t) / ∑w i (10)

[0113] Where,

[0114] I maxglobal (t) represents the global maximum current carrying capacity,

[0115] w i represents the node weight of the i-th node,

[0116] I max,i (t) represents the maximum allowable current carrying capacity of the i-th node.

[0117] Step 5: Calculate the load forecast value at the future time t+τ, and combine it with the global maximum current carrying capacity obtained in step 4 to generate a global control strategy.

[0118] In a preferred but non-limiting embodiment of the present invention, step 5 comprises:

[0119] Step 5.1: Input historical data and real-time data into the load forecasting model to calculate the load forecast value L at the future time t+τ. pred (t+τ).

[0120] Further preferably, step 5.1 includes:

[0121] Input historical data and real-time data into the load forecasting model for prediction, and solve the load forecast value L at the future time t+τ pred (t+τ), the prediction formula is expressed as follows:

[0122] L pred (t+τ)=F(L(t),L(t-Δt),…,L(t-nΔt)) (11)

[0123] Where,

[0124] L pred (t+τ) represents the load forecast value at the future time t+τ,

[0125] L(t-nΔt) represents the sampled load value at time t-nΔt,

[0126] τ represents the prediction delay,

[0127] Δt represents the sampling interval from time t to time t+τ,

[0128] n represents the number of samples from time t to time t+τ,

[0129] F(·) represents a load forecasting model, such as, but not limited to, a statistical model (e.g., autoregressive integrated moving average (ARIMA)) or a machine learning model (e.g., long short-term memory (LSTM) network, recurrent neural network) to extract load variation trends, periodic characteristics, and environmental impact coefficients;

[0130] The present invention uses convolutional neural network, long short-term memory network and support vector machine to predict the load in the future time t+τ, and constructs the load prediction model F(·). Therefore, the load prediction value L in the future time t+τ is pred (t+τ) can be described as:

[0131] Construct the historical load and environmental data matrix from time t to time t+τ;

[0132] The data matrix is ​​input into the convolutional neural network to extract the local spatiotemporal characteristics of the load;

[0133] Input the local spatiotemporal characteristics of the load into the long-short term neural network to capture the long-short time series dependency characteristics of the load;

[0134] The long and short time series dependency features of the load are input into the support vector machine for correction to obtain the load forecast result, which is expressed as the following formula:

[0135] L pred (t+τ)=SVM[LSTM(CNN(X(t,τ)))] (12)

[0136] X(t,τ) represents the historical load and environmental data matrix from time t to t+τ, X(t,τ) = L(t), L(t-Δt), …, L(t-nΔt);

[0137] CNN(·) represents convolutional neural network, which is used to extract local spatiotemporal features;

[0138] LSTM(·) represents a long short-term neural network, which is used to capture long- and short-term temporal dependencies;

[0139] SVM[·] represents support vector machine, which is used to correct and optimize the prediction results. It can be seen that the load forecasting model F(·) corresponds to SVM[LSTM(CNN(·))] here.

[0140] In step 5.2, the global maximum current carrying capacity and the load forecast value at the future time t+τ are input into the pre-trained mapping function to generate a global control strategy.

[0141] Further preferably, step 5.2 includes:

[0142] Generate a global control strategy, expressed as the following formula:

[0143] S(t)=g(I maxglobal (t),I pred (t+τ)) (12)

[0144] Where,

[0145] S(t) represents the control strategy,

[0146] I maxglobal (t) represents the global maximum current carrying capacity,

[0147] g represents a mapping function, such as but not limited to a neural network, support vector machine regression, logistic regression, or decision tree.

[0148] Based on the prediction results, the mapping function g(·) is combined with the current global safe ampacity to calculate and generate the control strategy S(t). By issuing instructions, the transformer taps, line tension, and cooling devices are adjusted, thereby dynamically increasing the capacity while ensuring the conductor temperature, sag, and safety margin.

[0149] More preferably, a global control strategy is generated according to the transformer tap adjustment amount, the line tension adjustment amplitude, and the auxiliary cooling device start / stop signal, specifically including:

[0150] Inputting the global maximum current carrying capacity, the load forecast value at the future time t+τ and the transformer tap data into the first mapping function to obtain the transformer tap adjustment value;

[0151] The global maximum current carrying capacity, the load forecast value at the future time t+τ, and the line tension data are input into the second mapping function to obtain the line tension adjustment amplitude;

[0152] The global maximum current carrying capacity, the load forecast value at the future time t+τ, and the auxiliary cooling device data are input into the third mapping function to obtain the auxiliary cooling device start and stop signal;

[0153] The transformer tap adjustment amount, line tension adjustment amplitude and auxiliary cooling device start and stop signals are combined to generate a global control strategy.

[0154] The voltage is adjusted according to the transformer tap adjustment ΔV to optimize the line current distribution;

[0155] Mechanical adjustment based on line tension adjustment amplitude ΔTens to reduce conductor sag and optimize heat dissipation;

[0156] According to the auxiliary cooling device start / stop signal CoolingOn / Off, combined with the real-time temperature control cooling system startup, the control strategy is expressed as the following formula:

[0157] S(t)={ΔV,ΔTens,CoolingOn / Off} (13)

[0158] Where,

[0159] The transformer tap adjustment value ΔV, the line tension adjustment amplitude ΔTens, and the auxiliary cooling device start / stop signal CoolingOn / Off are expressed as follows:

[0160]

[0161] Where,

[0162] f1 represents a first mapping function, such as but not limited to a neural network mapping function, which uses a neural network to predict the optimal transformer tap adjustment ΔV, with the goal of minimizing the risk of line overload;

[0163] f2 represents a second mapping function, such as but not limited to a support vector machine mapping function, which outputs a line tension adjustment amplitude ΔTens through support vector machine regression to ensure that the conductor sag is less than a set sag threshold;

[0164] f3 represents a third mapping function, such as but not limited to a logistic regression or decision tree mapping function, which generates a binary signal based on the logistic regression or decision tree to trigger the start and stop of the cooling device; f1, f2, and f3 are all determined by a pre-trained model;

[0165] ζ1 represents the transformer tap data, including the current tap level of the transformer and line impedance parameters;

[0166] ζ2 represents the line tension data, including conductor material properties and sag safety threshold;

[0167] ζ3 represents the auxiliary cooling device data, including the conductor temperature and heat dissipation efficiency parameters.

[0168] Step 6: Based on the global control strategy, dynamically adjust the working status of the on-site equipment to obtain the result of dynamic capacity expansion of the transmission line. By dynamically adjusting the working status of the on-site equipment, the transmission line is dynamically expanded to improve the instantaneous current carrying capacity of the line, thereby realizing dynamic capacity expansion of the transmission line based on distributed collaboration.

[0169] In a preferred but non-limiting embodiment of the present invention, step 6 comprises:

[0170] Step 6.1: The global control strategy S(t) is uniformly distributed to all field devices (such as transformer taps, line tension regulators, auxiliary cooling devices, etc.) through the distributed communication network.

[0171] Step 6.2: The field device dynamically adjusts its working state according to the received global control strategy;

[0172] Further preferably, step 6.2 includes:

[0173] Field equipment automatically adjusts taps based on transformer tap adjustment to achieve voltage optimization;

[0174] On-site equipment adjusts line tension according to line tension adjustment instructions, and the on-site mechanical system adjusts line tension to reduce sag and improve heat dissipation conditions;

[0175] The on-site auxiliary cooling device starts or stops working according to the cooling start and stop signal to control the conductor temperature.

[0176] In step 6.3, based on the adjustment results of the on-site equipment in step 6.2 and the real-time monitoring data, the distributed collaborative solution process for the global maximum current carrying capacity and load forecast is repeated to generate an optimized global control strategy. The on-site equipment is then adjusted to form a closed-loop control. Through multiple closed-loop controls, the system increases the maximum allowable current carrying capacity of the line in real time under safety constraints such as conductor temperature and sag. The global maximum current carrying capacity gradually approaches the physical limit current carrying capacity of the line, obtaining the dynamic capacity increase result of the transmission line and realizing a continuous optimization closed loop of dynamic capacity increase.

[0177] The generated control strategy S(t) includes control parameters such as transformer tap adjustment, line tension regulation, and auxiliary cooling start and stop. It is sent to the on-site control equipment in an encrypted manner through the control command transmission unit for execution. After execution, the on-site equipment automatically adjusts the parameters. The control results and real-time status are collected again by sensors and fed back to the central control unit in real time, forming a complete closed-loop control and achieving real-time self-correction and optimization. The control strategy is issued and executed in real time, and the adjustment effect is verified through closed-loop feedback, thereby fully releasing the invisible capacity of the transmission line and achieving the purpose of dynamic capacity expansion. This closed-loop feedback and continuous adjustment mechanism is the core of the "dynamic" control strategy of the present invention, enabling the transmission line to continuously achieve the effective release of invisible capacity while meeting safety constraints.

[0178] like Figure 2As shown, when a monitoring node experiences sensor failure, data collection anomalies, or communication link interruption, the system immediately triggers a fault detection mechanism. Each node has a built-in communication status monitoring module that monitors data transmission delay and packet loss in real time. By comparing the set checksum with redundant data, the collected data is determined to be abnormal. When a single node failure is detected, the system automatically activates a backup plan, using data from adjacent nodes or backup sensors to fill the gap. During global data fusion, data from each node is weighted averaged. If a node's data is abnormal, its weight is automatically reduced. In the local decision-making module, when data anomalies or communication failures are detected, the node switches to a pre-set fault-tolerant state, adaptively estimating data using historical data and data from neighboring nodes to ensure uninterrupted local decision-making. During a fault, the central control unit makes real-time compensation adjustments based on feedback data, ensuring the continuity and stability of the overall control strategy, thereby enabling dynamic capacity expansion control of the transmission line unaffected by single-node failures. During a fault, the communication links between the node, adjacent nodes, and the central control platform are monitored in real time. When data collection anomalies are detected, transmission delays exceed the set threshold, or information between nodes is inconsistent, the system immediately determines that a fault has occurred, automatically marks the data anomaly and issues an early warning. The system activates fault-tolerant mode and automatically calls backup sensors or adjacent node data for supplementary information to ensure uninterrupted transmission of local information. When node communication is interrupted or data is abnormal, each node will switch to a preset fault-tolerant control strategy to ensure that local monitoring and decision-making functions are not affected. When the central control platform performs global collaborative calculations, it sets fault-tolerant weights for data from each node. When data from a node is missing, the weight of the node is automatically reduced, and backup data or data from adjacent nodes are used to fill the gap to ensure continuous and stable operation of the entire system.

[0179] Embodiment 2 of the present invention provides a system for dynamically increasing the capacity of a power transmission line based on distributed collaboration, and executes the method for dynamically increasing the capacity of a power transmission line based on distributed collaboration described in embodiment 1, including:

[0180] Data acquisition module, used to collect real-time operating data and meteorological data of each node on the transmission line;

[0181] Preprocessing module, used to preprocess the collected operation data and meteorological data;

[0182] The maximum allowable current carrying capacity solving module is used to solve the transient heat balance model based on the pre-processed data using steady-state conditions and calculate the maximum allowable current carrying capacity based on the solution results;

[0183] The global maximum current carrying capacity solving module is used to integrate the maximum allowable current carrying capacity of each node using a distributed collaborative method to obtain the global maximum current carrying capacity;

[0184] The global control strategy generation module is used to solve the load forecast value at the future moment and generate the global control strategy based on the global maximum current carrying capacity;

[0185] The dynamic capacity expansion module is used to dynamically adjust the working status of on-site equipment according to the global control strategy, obtain the result of dynamic capacity expansion of the transmission line, and realize dynamic capacity expansion of the transmission line based on distributed collaboration.

[0186] Embodiment 3 of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is loaded into the processor, a method for dynamically increasing the capacity of a transmission line based on distributed collaboration according to embodiment 1 is implemented.

[0187] Embodiment 4 of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements a method for dynamic capacity expansion of transmission lines based on distributed collaboration according to embodiment 1.

[0188] Compared with the prior art, the beneficial effects of the present invention include at least:

[0189] 1) This method collects real-time changes in environmental parameters and operating data, responds to environmental fluctuations in real time through a transient thermal balance model, replaces the fixed assumptions of traditional steady-state models, and dynamically calculates the maximum allowable current carrying capacity of the line. Based on safety constraints such as transient temperature rise and sag constraints, the current carrying capacity is adjusted in real time, instantly releasing hidden capacity, avoiding overload risks caused by environmental changes, enhancing grid flexibility and environmental adaptability, and reducing resource waste caused by conservative design.

[0190] For example, but not limited to, when the ambient temperature of the line suddenly rises at noon, the carrying capacity is calculated and predicted in real time. At this time, the carrying capacity is too large, exceeding the national standard of 80 degrees. Assuming that the environmental parameters are constant, it is unable to reflect the actual dynamic changes, resulting in conservative calculation of the carrying capacity. The steady state cannot solve this problem. The present invention converts the steady state into a transient state, and dynamically reduces the carrying capacity by generating a control strategy based on the real-time changes in the environment. In the afternoon, the ambient temperature of the line is monitored to drop in real time. The carrying capacity is obtained through real-time calculation and prediction. The carrying capacity is too low, and a control strategy is generated to dynamically increase the carrying capacity, thereby realizing dynamic capacity expansion.

[0191] 2) By predicting future short-term loads and combining them with real-time current-carrying capacity to dynamically adjust control strategies, line operating parameters are optimized and equipment status (such as, but not limited to, taps, tension, and cooling devices) is adjusted in advance to avoid emergency load reductions or power outages caused by sudden load increases. Furthermore, based on the predicted results, equipment status is adjusted only when needed, improving the overall resource utilization and economic efficiency of the power grid. For example, but not limited to, cooling devices are activated or tensioned only when needed, reducing energy consumption and equipment losses. Cooling devices are shut down at night when temperatures are low, saving energy and optimizing operating costs.

[0192] 3) This invention achieves this by integrating the local maximum current capacity of each node in a distributed, collaborative manner. This transmits the maximum allowable current capacity of each node to adjacent nodes via a distributed communication network, eliminating data transmission delays. In the event of a single point of failure, the system redetermines the global maximum current capacity through distributed collaborative calculations across all remaining nodes, ensuring control continuity and preventing a single node failure from limiting global capacity. This improves the system's response rate and fault tolerance. For example, but not limited to, when a node fails, other nodes can still contribute capacity.

[0193] 4) After the equipment is adjusted, the capacity expansion effect is verified through monitoring data, the prediction model parameters are updated, and the accuracy of subsequent strategies is improved. The present invention continuously corrects model errors through closed-loop feedback, achieving real-time self-correction and optimization of transmission line field equipment, ensuring the safety and reliability of the capacity expansion process, and improving the robustness and accuracy of the capacity expansion process.

[0194] The present disclosure may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0195] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for dynamic capacity expansion of power transmission lines based on distributed collaboration, characterized by: Real-time collection of operating data and meteorological data of each node on the transmission line; Pre-process the collected operational data and meteorological data; Based on the pre-processed data, the transient heat balance model is solved using steady-state conditions, and the maximum allowable current carrying capacity is calculated based on the solution; The distributed coordination method is used to merge the maximum allowable current carrying capacity of each node to obtain the global maximum current carrying capacity; Solve the load forecast value at the future moment, combine it with the global maximum current carrying capacity, and generate the global control strategy; According to the global control strategy, the working status of the on-site equipment is dynamically adjusted to obtain the result of dynamic capacity increase of the transmission line.

2. The method for dynamic capacity expansion of power transmission lines based on distributed collaboration according to claim 1, characterized in that: The method of solving the transient heat balance model based on the pre-processed data using steady-state conditions and calculating the maximum allowable current carrying capacity according to the solution includes: Combined with the pre-processed data, a transient heat balance model is constructed; According to the balance between heat generation and heat dissipation under steady-state conditions, the constraint conditions of heat and heat dissipation balance are constructed; Solve the transient temperature difference based on the constraints of heat and heat dissipation balance and the transient heat balance model; When the current conductor temperature is at the highest temperature allowed to be reached by the conductor under safe operating conditions, the maximum allowable current carrying capacity of this node is solved based on the transient temperature difference.

3. The method for dynamic capacity expansion of power transmission lines based on distributed collaboration according to claim 2, characterized in that: The transient heat balance model specifically includes: The sum of the current ambient temperature and the temperature rise caused by the load, minus the temperature drop due to heat dissipation, equals the current conductor temperature.

4. The method for dynamic capacity expansion of power transmission lines based on distributed collaboration according to claim 2, characterized in that: When the current conductor temperature is at the maximum temperature allowed to be reached by the conductor under safe operating conditions, solving the maximum allowable current carrying capacity of the node according to the transient temperature difference specifically includes: Replace the current conductor temperature in the transient temperature difference formula with the maximum temperature allowed for the conductor under safe operating conditions, and subtract the current ambient temperature to obtain the maximum temperature difference at this node. The maximum heat dissipation per unit time is obtained by multiplying the convection heat transfer coefficient, the effective heat dissipation surface area of ​​the conductor, and the maximum temperature difference of this node; Divide the maximum heat dissipation per unit time by the wire resistance and take the square root to obtain the maximum allowable current carrying capacity of this node.

5. The method for dynamic capacity expansion of power transmission lines based on distributed collaboration according to claim 1, characterized in that: The distributed collaborative method is used to merge the maximum allowable current carrying capacity of each node to obtain the global maximum current carrying capacity, specifically including: Each node transmits the maximum allowable current carrying capacity and node weight calculated locally to the adjacent nodes through the distributed communication network; Each node uses the maximum allowable current carrying capacity and node weight received from adjacent nodes and performs weighted fusion with its own maximum allowable current carrying capacity and node weight to obtain the current global current carrying capacity; Each node uses an iterative weighted average algorithm to repeatedly iterate and calculate the current global current carrying capacity until the current global current carrying capacity calculation results of all nodes converge to a global consistency, forming a global optimal safe current carrying capacity value, which is set as the global maximum current carrying capacity.

6. The method for dynamic capacity expansion of power transmission lines based on distributed collaboration according to claim 1, characterized in that: The load forecast value at the future moment is solved and combined with the global maximum current carrying capacity to generate a global control strategy, specifically including: Input historical data and real-time data into the load forecasting model for prediction, and solve the load forecast value at the future time t+τ; The global maximum current carrying capacity and the load forecast value at the future time t+τ are input into the pre-trained mapping function to generate a global control strategy.

7. The method for dynamic capacity expansion of power transmission lines based on distributed collaboration according to claim 6, characterized in that: Inputting historical data and real-time data into the load forecasting model for forecasting and solving the load forecast value at the future time t+τ specifically includes: Construct the historical load and environmental data matrix from time t to time t+τ; The data matrix is ​​input into the convolutional neural network to extract the local spatiotemporal characteristics of the load; Input the local spatiotemporal characteristics of the load into the long-short term neural network to capture the long-short time series dependency characteristics of the load; The long and short time series dependency features of the load are input into the support vector machine for correction to obtain the load forecasting results.

8. The method for dynamic capacity expansion of power transmission lines based on distributed collaboration according to claim 6, characterized in that: The global maximum current carrying capacity and the load forecast value at the future time t+τ are input into a pre-trained mapping function to generate a global control strategy, specifically including: Inputting the global maximum current carrying capacity, the load forecast value at the future time t+τ and the transformer tap data into the first mapping function to obtain the transformer tap adjustment value; The global maximum current carrying capacity, the load forecast value at the future time t+τ, and the line tension data are input into the second mapping function to obtain the line tension adjustment amplitude; The global maximum current carrying capacity, the load forecast value at the future time t+τ, and the auxiliary cooling device data are input into the third mapping function to obtain the auxiliary cooling device start and stop signal; The transformer tap adjustment amount, line tension adjustment amplitude and auxiliary cooling device start and stop signals are combined to generate a global control strategy.

9. The method for dynamic capacity expansion of power transmission lines based on distributed collaboration according to claim 1, characterized in that: The method of dynamically adjusting the working status of the on-site equipment according to the global control strategy to obtain the result of dynamic capacity increase of the transmission line specifically includes: Distribute the global control strategy to all on-site devices; The field device dynamically adjusts the working state of the field device according to the received global control strategy to obtain the adjustment result of the field device; Based on the adjustment results of on-site equipment and real-time monitoring data, the distributed collaborative solution process of global maximum current carrying capacity and load forecast is repeated to generate an optimized global control strategy. Then, the on-site equipment is adjusted to form a closed-loop control. Through multiple closed-loop controls, the dynamic capacity expansion results of the transmission line are obtained.

10. A system for dynamically increasing the capacity of a power transmission line based on distributed collaboration, which runs a method for dynamically increasing the capacity of a power transmission line based on distributed collaboration according to any one of claims 1 to 9, characterized in that: Data acquisition module, used to collect real-time operating data and meteorological data of each node on the transmission line; Preprocessing module, used to preprocess the collected operation data and meteorological data; The maximum allowable current carrying capacity solving module is used to solve the transient heat balance model based on the pre-processed data using steady-state conditions and calculate the maximum allowable current carrying capacity based on the solution results; The global maximum current carrying capacity solving module is used to integrate the maximum allowable current carrying capacity of each node using a distributed collaborative method to obtain the global maximum current carrying capacity; The global control strategy generation module is used to solve the load forecast value at the future moment and generate the global control strategy based on the global maximum current carrying capacity; The dynamic capacity expansion module is used to dynamically adjust the working status of the on-site equipment according to the global control strategy to obtain the result of dynamic capacity expansion of the transmission line.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is loaded into a processor, a method for dynamic capacity increase of a transmission line based on distributed collaboration according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, a method for dynamic capacity increase of a transmission line based on distributed collaboration according to any one of claims 1 to 9 is implemented.

Images