Method for reducing line loss and improving power supply reliability based on Internet of Things

Abstract

The invention discloses a method for reducing line loss and improving power supply reliability based on the Internet of Things, and the method comprises the steps: carrying out the full-dimension load and line state monitoring: deploying an Internet of Things sensor, constructing an end-to-end monitoring network, and collecting key parameters in real time; a low-delay and wide-coverage data channel is constructed; a layered communication architecture is adopted, and efficient data transmission is realized; the real-time analysis and intelligent decision engine is used for constructing a load-line-equipment three-dimensional data model based on a cloud end and an edge platform, and realizing line loss real-time diagnosis, load prediction, situation awareness and rapid fault positioning; dynamic optimization and self-healing control: based on a data layer analysis result, source-network-load coordinated regulation and control are realized through an Internet of Things terminal, line loss is reduced, and stable power supply is guaranteed; user interaction and global optimization: realizing power grid-user interaction and peak load shifting through a user-side Internet of Things terminal to reduce the pressure of a power system; the system has the advantages of being capable of reducing line loss, guaranteeing power supply reliability, having various functions and being good in comprehensive application effect.

Description

Technical Field

[0001] This invention belongs to the field of Internet of Things (IoT) application technology, specifically relating to a method for reducing line loss and improving power supply reliability based on IoT. Background Technology

[0002] The Internet of Things (IoT) refers to the use of various information sensors, radio frequency identification (RFID) technology, global positioning systems (GPS), infrared sensors, laser scanners, and other devices and technologies to collect real-time information on any object or process that needs to be monitored, connected, or interacted with. This information includes sound, light, heat, electricity, mechanics, chemistry, biology, location, and other necessary data. Through various possible network access methods, ubiquitous connections between things and between things and people are achieved, enabling intelligent perception, identification, and management of objects and processes.

[0003] Currently, the application of IoT technology in power systems is maturing from concept. For example, in reducing line losses, it is gradually shifting from extensive management to precise governance. By deploying IoT sensors, it achieves second-level data collection of line losses in distribution areas, real-time analysis of line loss rate changes, and precise location of abnormally high-loss areas caused by electricity theft or equipment failure. In improving power supply reliability, it is gradually shifting from passive response to proactive defense, building a comprehensive sensing network, shortening fault location time, and transforming user-reported repairs into proactive handling. However, problems exist such as limited application effectiveness, poor overall application results, and low application efficiency, which are not conducive to the comprehensive management of power system problems. To solve these problems, it is necessary to develop an IoT-based method for reducing line losses and improving power supply reliability. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide an Internet of Things-based method for reducing line loss and improving power supply reliability, which can reduce line loss, ensure power supply reliability, and has multiple functions and good comprehensive application effects.

[0005] The objective of this invention is achieved as follows: a method for reducing line loss and improving power supply reliability based on the Internet of Things, comprising the following steps:

[0006] (1) Full-dimensional load and line status monitoring: By deploying IoT sensors, an end-to-end monitoring network is built to realize the real-time collection of key parameters, providing a data foundation for subsequent analysis and control;

[0007] (2) Construct a low-latency and wide-coverage data channel: Adopt a hierarchical communication architecture to achieve efficient data transmission in areas with different distances;

[0008] (3) Real-time analysis and intelligent decision engine: Based on cloud and edge platforms, a three-dimensional data model of load-line-equipment is constructed to realize real-time line loss diagnosis, load prediction and situational awareness, and rapid fault location;

[0009] (4) Dynamic optimization and self-healing control: Based on the analysis results of the data layer, source-grid-load coordinated regulation is realized through IoT terminals to reduce line loss and ensure stable power supply;

[0010] (5) User interaction and global optimization: Through the user-side IoT terminal, the power grid-user interaction is realized, and peak shaving and valley filling are carried out to reduce the pressure on the power system.

[0011] Preferably, the comprehensive load and line status monitoring includes the following steps:

[0012] (1) Load node monitoring: Three-phase intelligent power transmitters are deployed at distribution transformers, branch lines and user incoming lines to collect current, voltage, active power, reactive power and power factor in real time and accurately capture load fluctuations;

[0013] (2) Line status monitoring: Install temperature sensors, insulation monitors and micro-meteorological sensors at key locations to monitor line heating, insulation aging and icing / galloping status in real time, and identify abnormal sources of line loss. Key locations include line towers and cable joints.

[0014] (3) Topology node monitoring: Install status sensors on key equipment to record the opening and closing positions and the number of actions, providing equipment status data for fault location and self-healing control.

[0015] Preferably, the construction of a low-latency and wide-coverage data channel specifically involves:

[0016] (1) Within the transformer area, NB-IoT / LoRa narrowband Internet of Things technology is used to transmit sensor data;

[0017] (2) Real-time control commands are transmitted via a 5G private network between lines and substations;

[0018] (3) In the core network, local data is preprocessed by edge computing nodes and then uploaded to the cloud platform to reduce data transmission pressure.

[0019] Preferably, the real-time analysis and intelligent decision-making engine includes the following steps:

[0020] (1) Real-time line loss diagnosis: Calculate the theoretical line loss and actual line loss of each line, locate abnormal line loss areas, including three-phase imbalance, leakage of electricity and excessive reactive power loss areas; automatically mark high loss transformer areas / lines, and analyze the triggering causes, including overload, joint oxidation and insufficient reactive power compensation;

[0021] (2) Load forecasting and situational awareness: Combining historical load data, real-time load fluctuations and external factors, the machine learning model LSTM is used to predict the load trend in the next 15 minutes to 2 hours; potential overload points and three-phase imbalance critical points are identified and early warnings are given.

[0022] (3) Rapid fault location: Based on the characteristics of sudden current drop, voltage loss and sudden temperature rise of the line collected by the sensor, combined with the topology, the fault type and precise location are located; based on whether the reclosing is successful, permanent faults and transient faults are distinguished, providing a basis for subsequent control.

[0023] Preferably, the dynamic optimization and self-healing control includes the following steps:

[0024] (1) Dynamic load distribution to reduce transmission loss: For three-phase imbalance, the load distribution of each phase is adjusted in real time by intelligent circuit breakers to make the three-phase current deviation ≤5% and reduce the unbalanced line loss; For overloaded lines, the load of the overloaded line is transferred to the parallel light-load line through automatic switching of tie switches to avoid the increase in resistance caused by overload; For reactive power loss, intelligent reactive power compensation devices are installed in the transformer area / line, and the capacitor / reactor is automatically switched according to the real-time power factor, with a target of ≥0.95, to reduce reactive current transmission loss.

[0025] (2) Fault self-healing to improve power supply reliability: For momentary faults, power supply is quickly restored through reclosing to avoid unnecessary power outages; for permanent faults, the platform automatically isolates the faulty section and supplies non-faulty areas through backup lines, reducing the power outage range to the smallest unit and shortening the recovery time from the traditional hour level to the minute level; for important load users, a priority power supply strategy is preset, and power is supplied through energy storage power supply or backup lines in the event of a fault, achieving zero power outages.

[0026] (3) Proactive maintenance to prevent line loss deterioration: Based on long-term line monitoring data, assess the aging of the line and arrange maintenance in advance to avoid leakage loss caused by insulation degradation; for high-loss users, monitor the power consumption curve in real time through smart meters, trigger inspection and early warning when abnormalities occur to reduce management line loss.

[0027] Preferably, the user interaction and global optimization include the following steps:

[0028] (1) Guide off-peak electricity consumption: Before the peak load, push load warnings to high-energy-consuming users through smart meters or smart home devices, and reduce the load by using electricity price incentives or automatic control;

[0029] (2) Distributed energy coordination: During peak load periods, user-side distributed energy is connected and its reverse power supply is scheduled through the Internet of Things platform to reduce the power supply pressure on the main grid and reduce long-distance transmission line loss.

[0030] Due to the adoption of the above technical solutions, the beneficial effects of this invention are as follows: Based on IoT sensors and IoT terminals, this invention employs full-dimensional load and line status monitoring, as well as a hierarchical communication architecture and edge computing nodes. It efficiently transmits monitoring data to the cloud for analysis, enabling real-time diagnosis of line losses, real-time prediction of load and its development trends, and real-time rapid fault location and handling. Then, based on the analysis results, it performs source-grid-load coordinated regulation to reduce line losses, quickly handle faults, improve operation and maintenance capabilities, and fully guarantee power supply. Simultaneously, through user interaction and global optimization, this invention smooths and fills peak and valley loads in the power grid, reducing system power supply pressure and further ensuring power supply reliability. In summary, this invention has the advantages of reducing line losses, ensuring power supply reliability, diverse functions, and good comprehensive application effects. Detailed Implementation

[0031] The technical solution of the present invention will be further described in detail below through embodiments.

[0032] This invention provides a method for reducing line loss and improving power supply reliability based on the Internet of Things, comprising the following steps:

[0033] (I) Full-dimensional load and line status monitoring: By deploying IoT sensors, an end-to-end monitoring network is built to realize the real-time collection of key parameters, providing a data foundation for subsequent analysis and control.

[0034] (1) Load node monitoring: Deploy three-phase intelligent power transmitters at distribution transformers, branch lines and user incoming lines (especially high energy-consuming users and important load users) to collect load parameters such as current, voltage, active power, reactive power and power factor in real time, accurately capture load fluctuations, such as morning and evening peak hours, industrial start-up and shutdown, etc., and provide data support for dealing with large load fluctuations in the later stage.

[0035] (2) Line status monitoring: Temperature sensors, insulation monitors and micro-meteorological sensors are installed at key locations such as line towers and cable joints to monitor the line heating, insulation aging and icing / galloping status in real time and identify abnormal sources of line loss.

[0036] (3) Topology node monitoring: Install status sensors on key equipment such as switches and circuit breakers to record the opening and closing positions and the number of actions, providing equipment status data for fault location and self-healing control.

[0037] (ii) Constructing a low-latency and wide-coverage data channel: Adopting a hierarchical communication architecture to achieve efficient data transmission within different distance areas.

[0038] (1) Within the transformer area, NB-IoT / LoRa narrowband Internet of Things technology is used to transmit sensor data, which has low power consumption, wide coverage, and ensures data integrity;

[0039] (2) Between lines and substations, 5G private network is used to transmit real-time control commands with low latency, ensuring millisecond-level response.

[0040] (3) In the core network, local data is preprocessed (such as noise removal) through edge computing nodes before being uploaded to the cloud platform to reduce data transmission pressure.

[0041] (III) Real-time analysis and intelligent decision engine: Based on cloud and edge platforms, a three-dimensional data model of load-line-equipment is constructed to realize real-time line loss diagnosis, load prediction and situational awareness, and rapid fault location.

[0042] (1) Real-time line loss diagnosis: Calculate the theoretical line loss and actual line loss of each line (i.e., the active power loss collected in real time), locate abnormal line loss areas, including three-phase unbalanced areas, areas of electricity theft and leakage, and areas with excessive reactive power loss; automatically mark high-loss transformer areas / lines, and analyze the triggering causes, including overload, joint oxidation, and insufficient reactive power compensation.

[0043] Theoretical line loss is calculated based on parameters such as line resistance and current: For a three-phase balanced circuit, the theoretical line loss on the bus is the sum of the three-phase losses, and the formula simplifies to:

[0044] P 总 =3×I 2 ×R;

[0045] In the formula, R is the line resistance. When the three-phase current is balanced, the current in each phase is I, therefore the total loss P is... 总 It can be a single-phase weighted sum.

[0046] Among them, the abnormal line loss area caused by three-phase imbalance is defined as the area where the actual line loss is greater than the theoretical line loss and fluctuates significantly with load changes, and the three-phase current difference is large, that is, the imbalance degree is >10%.

[0047] By monitoring the current of each phase in real time using a three-phase smart meter or current sensor, the three-phase imbalance can be calculated using the following formula:

[0048]

[0049] Among them, the abnormal line loss area caused by electricity theft and leakage is defined as the area where the actual line loss is significantly greater than the theoretical line loss and fluctuates irregularly (such as the line loss is still high when the load decreases at night), and the metering difference between the beginning and end of the line is stable under the condition of excluding metering device errors.

[0050] Among them, the location of abnormal line loss areas caused by excessive reactive power loss is defined as follows: the actual line loss is greater than the theoretical line loss, and the power factor is low. Meanwhile, under normal three-phase balance, the area with excessive line current is the area of ​​abnormal line loss caused by excessive reactive power loss.

[0051] Under normal three-phase balance, a higher line current indicates increased resistance losses due to increased reactive current. The additional line loss caused by reactive current is calculated as: ΔP = 3I. q 2 R(I q (This refers to reactive current). If the additional line loss accounts for a high proportion of the actual line loss, this can be confirmed.

[0052] The high losses caused by overload, joint oxidation, and insufficient reactive power compensation can be quickly distinguished according to the following table:

[0053] By matching and verifying the above indicators, the specific causes of high-loss transformer areas / lines can be quickly identified, providing a basis for targeted rectification (namely, expanding conductor capacity, replacing connectors, and increasing capacity compensation devices).

[0054] (2) Load forecasting and situational awareness: Combining historical load data, real-time load fluctuations and external factors, the machine learning model LSTM is used to predict the load trend in the next 15 minutes to 2 hours; identify potential overload points (such as the load of a certain line is about to exceed the safety threshold) and three-phase imbalance critical points (such as the current deviation of a certain phase is about to exceed 15%), and provide early warnings.

[0055] First, collect data: historical load data (recorded in granularity such as 15 minutes and 30 minutes, including at least 6 months to 1 year of data, covering different seasons and electricity consumption patterns); real-time load data (high-frequency data from the last few hours, used to capture short-term fluctuations); external factor data: weather data (temperature, humidity, precipitation, wind speed, etc., which need to match the time of load data), holiday / workday tags (to distinguish differences in electricity consumption patterns), and special events (such as large-scale events, power outages for maintenance, etc.).

[0056] Then, data features are constructed: time features, extracting hours, minutes, days of the week, months, etc., to reflect periodic electricity consumption patterns; lag features, selecting load data from the past N time periods (such as the previous 1 hour, the previous 3 hours) as input to capture short-term load dependencies; rolling statistical features, calculating the average, maximum, and volatility of the load over a past period (such as 1 hour) to reflect load trends; and external feature encoding, converting holidays (0 / 1), weather types (such as sunny / rainy, using unique thermal encoding), etc., into numerical features that the model can recognize.

[0057] Next, construct the dataset: convert the data into input-output sequence pairs. For example, when predicting the load for the next 15 minutes, the input can include the load data of the past 2 hours plus the weather / time features of the corresponding time period, and the output is the load value for the next 15 minutes.

[0058] Next, construct the model: Input layer, with dimensions consistent with the number of features (e.g., the total dimension of lag features + weather + time features); LSTM layer, set 1-3 LSTM units, with the number of units per layer adjusted according to the data scale (e.g., 64, 128), and a Dropout layer can be added (to prevent overfitting, ratio 0.2-0.5); Output layer, fully connected layer, with the output dimension being the prediction duration (e.g., predicting the next 2 hours, outputting 8 values ​​at a 15-minute granularity).

[0059] Next, train the model: Divide the data into training set (70-80%), validation set (10-15%), and test set (10-15%) in chronological order to avoid a decrease in the model's generalization ability due to data leakage; use mean squared error (MSE) or mean absolute error (MAE) as the loss function to reflect the deviation between the predicted and the true values; use Adam (adaptive learning rate, high training efficiency) as the optimizer, with an initial learning rate of 0.001, which can be adjusted through a learning rate decay strategy; set the training parameters, including epochs (e.g., 50-200) and batch size (e.g., 32, 64), monitor the loss changes through the validation set, and use early stopping to prevent overfitting (stop training when the validation set loss does not decrease for several consecutive epochs).

[0060] Finally, predict the trend: input the latest real-time load data and weather data into the trained model, and output the load trend for the next 15 minutes to 2 hours.

[0061] (3) Rapid fault location: Based on the characteristics of sudden current drop, voltage loss and sudden temperature rise of the line collected by the sensor, combined with the topology, the fault type and precise location are located; based on whether the reclosing is successful, permanent faults (such as line breakage) and transient faults (such as lightning flashover) are distinguished, providing a basis for subsequent control.

[0062] (iv) Dynamic optimization and self-healing control: Based on the analysis results of the data layer, source-grid-load coordinated regulation is realized through IoT terminals to reduce line loss and ensure stable power supply.

[0063] (1) Dynamic load allocation reduces transmission loss:

[0064] To address three-phase imbalance, intelligent circuit breakers can be used to adjust the load distribution of each phase in real time, such as transferring an overloaded phase to a lightly loaded phase, so that the three-phase current deviation is ≤5%, thereby reducing unbalanced line losses.

[0065] For overloaded lines, the load of the overloaded line is automatically transferred to the parallel lightly loaded line through the tie switch to avoid the increase in resistance caused by overload.

[0066] To address reactive power loss, install intelligent reactive power compensation devices, such as SVG, in the transformer area / line. Based on the real-time power factor (target ≥ 0.95), automatically switch capacitors / reactors to reduce reactive current transmission losses.

[0067] (2) Fault self-healing improves power supply reliability:

[0068] For momentary faults, power supply can be quickly restored by reclosing triggered by IoT terminals to avoid unnecessary power outages;

[0069] For permanent faults, the platform automatically isolates the faulty section, such as disconnecting the switches on both sides of the fault point and supplying power to the non-faulty area through a backup line, reducing the power outage area to the smallest unit (such as a single household), and shortening the recovery time from the traditional hours to minutes.

[0070] For critical load users, such as hospitals and data centers, a priority power supply strategy is preset, and in the event of a fault, power is supplied first through energy storage power or backup lines to achieve zero power outages.

[0071] (3) Proactive maintenance to prevent line loss from worsening:

[0072] Based on long-term monitoring data such as line temperature and insulation resistance, assess the degree of line aging, arrange maintenance in advance, such as replacing aging cables, and avoid leakage losses caused by decreased insulation.

[0073] For high-loss users, such as those suspected of electricity theft or leakage, electricity consumption curves are monitored in real time through IoT terminals such as smart meters. When anomalies occur, an inspection and early warning are triggered to reduce management line losses.

[0074] (V) User interaction and global optimization: Through user-side IoT terminals, grid-user interaction is realized to reduce the pressure on the power system by peak shaving and valley filling.

[0075] (1) Guide off-peak electricity consumption: Before the peak load, push load warnings to high-energy-consuming users (such as factories) through smart meters or smart home devices, and reduce the load by using electricity price incentives (such as high electricity prices during peak hours) or automatic control (such as shutting down non-critical equipment).

[0076] (2) Distributed energy coordination: During peak load periods, user-side distributed energy sources, such as photovoltaics and energy storage, are connected and their reverse power supply is scheduled through the Internet of Things platform to reduce the pressure on the main grid power supply and reduce long-distance transmission line losses.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of the claims of the present invention.

Claims

1. A method for reducing line loss and improving power supply reliability based on the Internet of Things, characterized in that, Includes the following steps: (1) Full-dimensional load and line status monitoring: By deploying IoT sensors, an end-to-end monitoring network is built to realize the real-time collection of key parameters, providing a data foundation for subsequent analysis and control; (2) Construct a low-latency and wide-coverage data channel: Adopt a hierarchical communication architecture to achieve efficient data transmission in areas with different distances; (3) Real-time analysis and intelligent decision engine: Based on cloud and edge platforms, a three-dimensional data model of load-line-equipment is constructed to realize real-time line loss diagnosis, load prediction and situational awareness, and rapid fault location; (4) Dynamic optimization and self-healing control: Based on the analysis results of the data layer, source-grid-load coordinated regulation is realized through IoT terminals to reduce line loss and ensure stable power supply; (5) User interaction and global optimization: Through the user-side IoT terminal, the power grid-user interaction is realized, and peak shaving and valley filling are carried out to reduce the pressure on the power system.

2. The method for reducing line loss and improving power supply reliability based on the Internet of Things according to claim 1, characterized in that, The comprehensive load and line status monitoring includes the following steps: (1) Load node monitoring: Three-phase intelligent power transmitters are deployed at distribution transformers, branch lines and user incoming lines to collect current, voltage, active power, reactive power and power factor in real time and accurately capture load fluctuations; (2) Line status monitoring: Install temperature sensors, insulation monitors and micro-meteorological sensors at key locations to monitor line heating, insulation aging and icing / galloping status in real time, and identify abnormal sources of line loss. Key locations include line towers and cable joints. (3) Topology node monitoring: Install status sensors on key equipment to record the opening and closing positions and the number of actions, providing equipment status data for fault location and self-healing control.

3. The method for reducing line loss and improving power supply reliability based on the Internet of Things as described in claim 1, characterized in that, The construction of a low-latency and wide-coverage data channel specifically involves: (1) Within the transformer area, NB-IoT / LoRa narrowband Internet of Things technology is used to transmit sensor data; (2) Real-time control commands are transmitted via a 5G private network between lines and substations; (3) In the core network, local data is preprocessed by edge computing nodes and then uploaded to the cloud platform to reduce data transmission pressure.

4. The method for reducing line loss and improving power supply reliability based on the Internet of Things as described in claim 1, characterized in that, The real-time analysis and intelligent decision-making engine includes the following steps: (1) Real-time line loss diagnosis: Calculate the theoretical line loss and actual line loss of each line, locate abnormal line loss areas, including three-phase imbalance, leakage of electricity and excessive reactive power loss areas; automatically mark high loss transformer areas / lines, and analyze the triggering causes, including overload, joint oxidation and insufficient reactive power compensation; (2) Load forecasting and situational awareness: Combining historical load data, real-time load fluctuations and external factors, the machine learning model LSTM is used to predict the load trend for the next 15 minutes to 2 hours. Identify potential overload points and three-phase imbalance critical points, and provide early warnings; (3) Rapid fault location: Based on the characteristics of sudden current drop, voltage loss and sudden temperature rise of the line collected by the sensor, combined with the topology, the fault type and precise location are located; based on whether the reclosing is successful, permanent faults and transient faults are distinguished, providing a basis for subsequent control.

5. The method for reducing line loss and improving power supply reliability based on the Internet of Things according to claim 1, characterized in that, The dynamic optimization and self-healing control includes the following steps: (1) Dynamic load distribution to reduce transmission loss: For three-phase imbalance, the load distribution of each phase is adjusted in real time by intelligent circuit breakers to make the three-phase current deviation ≤5% and reduce the unbalanced line loss; For overloaded lines, the load of the overloaded line is transferred to the parallel light-load line through automatic switching of tie switches to avoid the increase in resistance caused by overload; For reactive power loss, intelligent reactive power compensation devices are installed in the transformer area / line, and the capacitor / reactor is automatically switched according to the real-time power factor, with a target of ≥0.95, to reduce reactive current transmission loss. (2) Fault self-healing to improve power supply reliability: For momentary faults, power supply is quickly restored through reclosing to avoid unnecessary power outages; for permanent faults, the platform automatically isolates the faulty section and provides backup lines to non-faulty areas, reducing the power outage area to the smallest unit and shortening the recovery time from the traditional hour level to the minute level. For critical load users, a priority power supply strategy is preset, and in the event of a fault, power is supplied first through energy storage power or backup lines to achieve zero power outage; (3) Proactive maintenance to prevent line loss deterioration: Based on long-term line monitoring data, assess the aging of the line, arrange maintenance in advance, and avoid leakage loss caused by insulation degradation. Based on high-loss users, the electricity consumption curve is monitored in real time through smart meters, and an audit warning is triggered when an anomaly occurs, thereby reducing management line losses.

6. The method for reducing line loss and improving power supply reliability based on the Internet of Things according to claim 1, characterized in that, The user interaction and global optimization include the following steps: (1) Guide off-peak electricity consumption: Before the peak load, push load warnings to high-energy-consuming users through smart meters or smart home devices, and reduce the load by using electricity price incentives or automatic control; (2) Distributed energy coordination: During peak load periods, user-side distributed energy is connected and its reverse power supply is scheduled through the Internet of Things platform to reduce the power supply pressure on the main grid and reduce long-distance transmission line loss.

Images