Intelligent power distribution network adaptive power-saving regulation and control method based on dynamic load prediction

Abstract

The invention discloses an intelligent power distribution network adaptive power-saving regulation and control method based on dynamic load prediction, and the method comprises the steps: 1, collecting the power load data of each user, the current and voltage data of a power distribution line, and local meteorological data in real time through a data collection device, and carrying out the data cleaning and preprocessing of the collected data; step 2, a dynamic load prediction model is constructed by using the processed data, and the dynamic load prediction model can accurately predict future electrical load changes according to current moment data input in real time; 3, according to a prediction result of the dynamic load prediction model, regulating and controlling the optimal power supply voltage and the power distribution proportion of each distribution line and the operation state of a transformer in combination with the real-time operation state of the power distribution network; and step 4, by configuring a sensor in the power distribution network, continuously collecting data parameters of each node and the power utilization state and load change condition of each power utilization device, and then performing comparative analysis with the data before regulation and control.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power saving methods, in particular to an intelligent power distribution network adaptive power saving regulation method based on dynamic load prediction. BACKGROUND

[0002] With the rapid development of social economy and the continuous growth of power demand, the efficient operation and energy saving of intelligent power distribution network have become important challenges faced by the power industry. Traditional power distribution network has certain limitations in load prediction and power supply strategy adjustment, which is difficult to accurately predict the change of electricity load in real time, resulting in that the power supply strategy cannot timely adapt to the dynamic fluctuation of load, thereby increasing the line loss and causing frequent redundant power supply.

[0003] Line loss not only wastes a large amount of electric energy resources, but also increases the operating cost of power enterprises. Redundant power supply means that the power supply exceeds the actual demand in some period or area, further aggravating the waste of energy. In addition, due to the lack of effective load prediction and adaptive regulation mechanism, when the electricity load changes suddenly, the power distribution network may not be able to respond in time, thereby affecting the stability and reliability of power supply and bringing bad electricity experience to users. Therefore, it has important practical significance to develop an intelligent power distribution network adaptive power saving regulation system and method which can accurately predict electricity load and adjust power supply strategy in real time according to load change. SUMMARY

[0004] In order to solve the above problems, the present application provides an intelligent power distribution network adaptive power saving regulation method based on dynamic load prediction, which comprises the following steps: step one, real-time collection of electricity load data of each user, current and voltage data of power distribution line and local weather data by data acquisition equipment, and then data cleaning and preprocessing of the collected data; removing noise and outliers in the data, and normalizing the data; step two, using the processed data to construct a dynamic load prediction model, which can accurately predict the change of electricity load in a period of time in the future according to the real-time input of current time data; step three, according to the prediction result of the dynamic load prediction model, combining the real-time running state of the power distribution network, regulating the best power supply voltage, power distribution ratio and operation state of the transformer of each power distribution line; step four, continuously collecting data parameters of each node and electricity state and load change of each electricity equipment by configuring sensors in the power distribution network, and then comparing and analyzing with the data before regulation.

[0005] Further, the data acquisition equipment includes smart meters, current sensors, voltage sensors and weather monitoring equipment.

[0006] Further, the data cleaning and preprocessing includes removing noise and outliers in the data, and normalizing the data.

[0007] Further, the dynamic load prediction model is trained by using a deep neural network, a long short-term memory network and a convolutional neural network.

[0008] Further, in the step three, a multi-objective optimization function is constructed by using a genetic algorithm to generate an adaptive power-saving control strategy, and the optimal solution is searched in the solution space by the genetic algorithm to control the optimal power supply voltage, power distribution ratio and operation state of the transformer of each distribution line.

[0009] Further, the step five is further included, after comparison and determination that the data parameters do not reach the expected target, feedback information is generated to re-input the dynamic load prediction model, the parameters of the optimization function are adjusted again, the control strategy is generated again, and the optimal power supply voltage, power distribution ratio and operation state of the transformer of each distribution line are controlled.

[0010] Further, in the step two, the dynamic load prediction model is constructed by using a long short-term memory network and an ensemble learning method.

[0011] Further, in the step three, a particle swarm optimization algorithm is used to generate an adaptive power-saving control strategy, and the optimal power supply strategy is searched by the particle swarm optimization algorithm to control the optimal power supply voltage, power distribution ratio and operation state of the transformer of each distribution line.

[0012] Compared with the prior art, the beneficial effects of the present application are: By using the accurate dynamic load prediction and the adaptive power-saving control strategy, the present application can optimize the power supply voltage, power distribution and other parameters of the power distribution network in real time, reduce the heat loss of current in the transmission process, effectively reduce the line loss, improve the power transmission efficiency, and further adjust the power supply in time according to the real-time change and prediction result of the power load, avoid the redundant power supply phenomenon that the power supply exceeds the actual demand, improve the energy utilization efficiency, reduce unnecessary power supply output in the load valley period, and finally track the change of the power load in real time and adjust the power supply strategy in time, so that the power distribution network can respond quickly when the load changes suddenly, maintain the stability of the voltage, frequency and other parameters, ensure the continuity and stability of the power supply, reduce the occurrence of power failure, and improve the power experience of users.

[0013] Additional aspects and advantages of the application will be given in the following description section, some of which will become apparent from the following description, or will be understood through practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description only represent some of the embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor under the premise of the drawings.

[0015] Figure 1 The overall flowchart of the intelligent power distribution network adaptive power saving regulation method based on dynamic load prediction of the present application is shown in the figure. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0017] The present application will be described in more detail. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application. It should be noted that when an element is described as "fixed to" another element, it can be directly on the other element or one or more intermediate elements can be present therebetween. When an element is described as "connected to" another element, it can be directly connected to the other element or one or more intermediate elements can be present therebetween.

[0018] In the description of the present application, it should be noted that the orientation words such as "front, rear, upper, lower, left, right", "transverse, vertical, perpendicular, horizontal" and "top, bottom" and the like indicate the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, and in the absence of the opposite description, these orientation words do not indicate and imply that the indicated device or element must have a specific orientation or be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the scope of protection of the present application; the orientation words "inner, outer" refer to the inner and outer of the contour of each component. In the description of the present application, it should be noted that the use of "first", "second" and the like to define parts is only for the convenience of distinguishing the corresponding parts, and unless otherwise stated, the above words have no special meaning, and therefore cannot be understood as a limitation on the scope of protection of the present application. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0019] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention.

[0020] Furthermore, the technical features involved in the different embodiments of this application described below can be combined with each other as long as they do not conflict with each other.

[0021] The preferred embodiments of the present invention will now be further described with reference to the accompanying drawings, such as... Figure 1 As shown, the adaptive power-saving control method for intelligent distribution networks based on dynamic load forecasting includes the following steps: Step 1: Real-time data collection of electricity load data from each user, current and voltage data from distribution lines, and local meteorological data are performed using data acquisition equipment. The collected data is then cleaned and preprocessed to remove noise and outliers, and the data is normalized. Step 2: A dynamic load forecasting model is constructed using the processed data. This model can accurately predict changes in electricity load over a future period based on real-time input data. Step 3: Based on the prediction results of the dynamic load forecasting model and the real-time operating status of the distribution network, the optimal supply voltage, power distribution ratio, and transformer operating status of each distribution line are adjusted. Step 4: Sensors are configured in the distribution network to continuously collect data parameters from each node, as well as the power consumption status and load changes of each electrical device. These data are then compared and analyzed with the data before adjustment.

[0022] This application, through precise dynamic load forecasting and adaptive energy-saving control strategies, can optimize parameters such as power supply voltage and power distribution in the distribution network in real time, reducing heat loss during current transmission and thus effectively reducing line losses and improving power transmission efficiency. Furthermore, it can adjust the power supply in a timely manner based on real-time changes and forecasts of electricity load, avoiding redundant power supply exceeding actual demand and improving energy utilization efficiency. During off-peak periods, unnecessary power output can be reduced. Finally, because it can track changes in electricity load in real time and adjust the power supply strategy promptly, the distribution network can respond quickly to sudden load changes, maintaining the stability of parameters such as voltage and frequency, ensuring the continuity and stability of power supply, reducing the occurrence of power outages, and improving the user's electricity experience.

[0023] Furthermore, based on the above embodiments, in step one, the data acquisition equipment includes smart meters, current sensors, voltage sensors, and meteorological monitoring equipment. These devices collect real-time data on the electricity load of each merchant, the current and voltage data of the power distribution lines, and local meteorological data (such as temperature, humidity, and light intensity).

[0024] Furthermore, based on the above embodiments, in step one, the data cleaning and preprocessing includes removing noise and outliers from the data, and normalizing the data. For example, for electricity load data, it is normalized to the [0, 1] interval to facilitate subsequent model training and processing.

[0025] Building upon the above embodiments, in step two, the dynamic load forecasting model is trained using deep neural networks, long short-term memory networks, and convolutional neural networks. During training, historical electricity load data, meteorological data, and date and time information are used as inputs to train the model. The model's parameters, such as the number of layers, nodes, and learning rate of the neural network, are continuously adjusted to improve the model's prediction accuracy. After training with a large amount of data, a high-precision dynamic load forecasting model is obtained. This model can accurately predict changes in electricity load over a future period (e.g., the next 1 hour, the next 4 hours, etc.) based on real-time input data. For example, on a weekday afternoon, based on current meteorological conditions (higher temperatures may lead to increased air conditioning load), time information (approaching the evening rush hour, some businesses may increase lighting and equipment operating time), and historical electricity consumption data for the same period, the model can predict these changes.

[0026] Building upon the above embodiments, in step three, a genetic algorithm is used to construct a multi-objective optimization function, generating an adaptive power-saving control strategy. The genetic algorithm searches for the optimal solution in the solution space to regulate the optimal supply voltage, power distribution ratio, and transformer operating status of each distribution line. For example, if it is predicted that the load will increase within the next hour, and the current in some lines is already close to full load, the control strategy decides to appropriately increase the transformer output voltage, transfer some load to other lines with lighter loads, and connect a set of reactive power compensation capacitors to improve the power factor in order to avoid line overload and reduce line losses. The intelligent distribution network execution module converts these control strategies into specific control commands and sends them to corresponding devices, such as intelligent switches, transformer tap changers, and reactive power compensation devices, to achieve real-time adjustment of the power supply strategy of the distribution network.

[0027] Furthermore, based on the above embodiments, it also includes step five: if the data parameters are determined to have not reached the expected target after comparison, feedback information is generated and re-input into the dynamic load prediction model, the parameters of the optimization function are readjusted, and the control strategy is generated again to control the optimal power supply voltage, power distribution ratio and transformer operating status of each distribution line.

[0028] Furthermore, this application also provides a second embodiment. Compared to the first embodiment, the second embodiment is suitable for use based on the characteristics of electricity load in residential communities. The difference between the second and first embodiments lies in that, in step two, the dynamic load prediction model is constructed using a Long Short-Term Memory (LSTM) network and an ensemble learning method. The LSTM network effectively captures the periodic and trend changes in residential electricity load. By learning from historical electricity data, the model can grasp the electricity consumption patterns of residents in different time periods, seasons, and weather conditions. The ensemble learning method integrates multiple LSTM network models with different structures. Each model focuses on different features and data patterns during training, and the prediction results of each model are ultimately combined to obtain a more accurate load prediction value. For example, when predicting electricity load on a weekend evening, the model predicts, based on historical weekend data and current temperature information, that the community's electricity load will reach its peak during that time period, and specifically predicts the magnitude and timing of the peak.

[0029] Building upon the above embodiments, in step three, an adaptive power-saving control strategy is generated using a particle swarm optimization algorithm. This algorithm searches for the optimal power supply strategy to regulate the best supply voltage, power distribution ratio, and transformer operating status for each distribution line. For example, if a peak electricity demand is predicted for a weekend evening, the control strategy adjusts the transformer tap changer in advance to increase the output voltage, thereby reducing copper and iron losses. Simultaneously, power is rationally allocated based on load forecasts for each branch line to prevent overload of some lines. The intelligent distribution network execution module converts these control strategies into control commands and sends them to transformer tap changers and intelligent switches, enabling real-time control of the distribution network.

[0030] The details of the exemplary embodiments described above are provided, and the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the invention.

Claims

1. A smart distribution network adaptive energy-saving control method based on dynamic load forecasting, characterized in that, The process includes the following steps: Step 1: Real-time data collection of electricity load data from each user, current and voltage data from distribution lines, and local meteorological data using data acquisition equipment. The collected data is then cleaned and preprocessed to remove noise and outliers, and normalized. Step 2: A dynamic load forecasting model is constructed using the processed data. This model accurately predicts future electricity load changes based on real-time input data. Step 3: Based on the prediction results of the dynamic load forecasting model and the real-time operating status of the distribution network, the optimal supply voltage and power distribution ratio of each distribution line, as well as the operating status of transformers, are adjusted. Step 4: Sensors are configured in the distribution network to continuously collect data parameters from each node, as well as the electricity status and load changes of each electrical device. These data are then compared and analyzed with the data before adjustment.

2. The adaptive power-saving control method for intelligent distribution networks based on dynamic load forecasting according to claim 1, characterized in that, The data acquisition equipment includes smart meters, current sensors, voltage sensors, and meteorological monitoring equipment.

3. The adaptive power-saving control method for intelligent distribution networks based on dynamic load forecasting according to claim 1, characterized in that, The data cleaning and preprocessing includes removing noise and outliers from the data, and normalizing the data.

4. The adaptive power-saving control method for intelligent distribution networks based on dynamic load forecasting according to claim 1, characterized in that, The dynamic load prediction model is trained using deep neural networks, long short-term memory networks, and convolutional neural networks.

5. The adaptive power-saving control method for intelligent distribution networks based on dynamic load forecasting according to claim 1, characterized in that, In step three, a multi-objective optimization function is constructed using a genetic algorithm to generate an adaptive power-saving control strategy. The genetic algorithm searches for the optimal solution in the solution space to regulate the optimal power supply voltage, power distribution ratio, and transformer operating status of each distribution line.

6. The adaptive power-saving control method for intelligent distribution networks based on dynamic load forecasting according to claim 5, characterized in that, It also includes step five, where, after comparison and determination, if the data parameters do not meet the expected target, feedback information is generated and re-input into the dynamic load prediction model, the parameters of the optimization function are readjusted, and a control strategy is generated again to control the optimal power supply voltage, power distribution ratio, and transformer operating status of each distribution line.

7. The adaptive power-saving control method for intelligent distribution networks based on dynamic load forecasting according to claim 1, characterized in that, In step two, the dynamic load prediction model is constructed using a long short-term memory network and an ensemble learning method.

8. The adaptive power-saving control method for intelligent distribution networks based on dynamic load forecasting according to claim 1, characterized in that, In step three, an adaptive power-saving control strategy is generated using a particle swarm optimization algorithm. The optimal power supply strategy is searched using the particle swarm optimization algorithm to control the optimal power supply voltage, power distribution ratio, and transformer operating status of each distribution line.

Images