Large-scale new energy power probability scheduling system for risk quantification

Abstract

The invention provides a risk quantitative large-scale new energy power probability scheduling system, which belongs to the technical field of power scheduling and comprises a risk quantitative scheduling module, and the risk quantitative scheduling module comprises a data acquisition and processing module, an intelligent prediction module, a risk quantitative evaluation module, a scheduling strategy generation module and an execution and monitoring module. The data acquisition and processing module is responsible for collecting data related to the new energy power system, the processed data is transmitted to the intelligent prediction module through the data transmission line, and the intelligent prediction module performs short-term and medium-and-long-term prediction on the new energy power generation amount. The generated new energy generating capacity prediction result is transmitted to a risk quantitative evaluation module, and the risk quantitative evaluation module transmits a calculated risk evaluation result to a scheduling strategy generation module by constructing a probability distribution model of new energy output and load; and the scheduling strategy generation module is responsible for generating a scheduling scheme according to the risk information and other related data.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power dispatching, and in particular to a large-scale new energy electric power probabilistic dispatching system with risk quantification. Background Art

[0002] As the world pays more and more attention to environmental protection and sustainable development, new energy accounts for an increasingly larger proportion in the power system. The development of new energy also provides the possibility of reducing the use of traditional fossil energy, reducing carbon emissions, and achieving energy transformation. In large-scale new energy power systems, risk quantification is crucial. Risk quantification can help dispatchers better understand the risks faced by the system, such as the risk of power shortage caused by insufficient output of new energy, the risk of power abandonment caused by excessive output of new energy, and the risk of equipment failure. By quantitatively evaluating these risks, corresponding risk response strategies can be formulated to improve the safety and reliability of the system. At the same time, risk quantification provides decision-making basis for participants in the power market and promotes the healthy development of the power market.

[0003] The traditional power dispatching system is mainly composed of power stations, transmission networks, distribution networks and dispatching centers. The dispatching system often adopts simplified models and algorithms. However, the power generation of new energy such as wind and solar energy is greatly affected by weather and seasons, which makes the power supply highly uncertain and volatile. The traditional dispatching system often finds it difficult to accurately predict these changes, resulting in low dispatching efficiency. Due to the lack of quantitative assessment of risks, it is difficult for traditional systems to assess and control the potential risks brought about by fluctuations in new energy. In response to the above problems, a large-scale new energy power probabilistic dispatching system with risk quantification is proposed. Summary of the invention

[0004] The present invention provides a large-scale renewable energy power probabilistic dispatching system with risk quantification, aiming to solve the problem that traditional dispatching systems in the prior art often adopt simplified models and algorithms, but the power generation of renewable energy such as wind power and solar power is greatly affected by weather and seasons, which makes the power supply highly uncertain and volatile.

[0005] The present invention is implemented as follows: comprising a risk quantification scheduling module, the risk quantification scheduling module comprising a data acquisition and processing module, an intelligent prediction module, a risk quantification assessment module, a scheduling strategy generation module and an execution and monitoring module;

[0006] The data acquisition and processing module is responsible for collecting data related to the new energy power system, and transmitting the processed data to the intelligent prediction module through the data transmission line. The intelligent prediction module is responsible for using the prediction algorithm to make short-term and medium-term predictions of the new energy power generation, and then transmitting the generated new energy power generation prediction results to the risk quantification assessment module through the data transmission line;

[0007] The risk quantification and assessment module constructs a probability distribution model of new energy output and load, analyzes its uncertainty, and then transmits the calculated risk indicators and risk assessment results to the scheduling strategy generation module through the data transmission line. The scheduling strategy generation module is responsible for generating a scheduling plan based on the risk information provided by the risk quantification and assessment module. The execution and monitoring module is responsible for converting the scheduling plan generated by the scheduling strategy generation module into operating instructions to control the operating status of the new energy power generation equipment in the power system.

[0008] As mentioned above, the data acquisition and processing module includes a load monitoring submodule, a meteorological data acquisition submodule, a seasonal feature identification submodule, an impact assessment submodule and a data preprocessing submodule. The load monitoring submodule uses sensors to monitor the load conditions of the power system. The meteorological data acquisition submodule is responsible for collecting meteorological data of wind speed, temperature and light intensity of renewable energy power generation. By installing anemometers, thermometers and light intensity sensors around renewable energy power plants, meteorological data is collected in real time. The seasonal feature identification submodule is responsible for determining the current season based on time series data and analyzing the impact on renewable energy power generation in different seasons. The impact assessment submodule is responsible for evaluating the impact of different meteorological conditions and seasons on renewable energy power generation. The data preprocessing submodule is responsible for processing the collected load data, meteorological data and seasonal feature data.

[0009] As mentioned above, the intelligent prediction module includes a short-term prediction submodule, a medium- and long-term prediction submodule and a dynamic correction submodule. The short-term prediction submodule is responsible for predicting the new energy power generation in the time range of several hours to several days in the future. The short-term prediction submodule uses short-term meteorological forecast data to make short-term predictions on the new energy power generation. The medium- and long-term prediction submodule is responsible for considering seasonal changes and making trend predictions on future new energy power generation. The medium- and long-term prediction submodule considers seasonal changes and long-term meteorological trends, analyzes historical meteorological data and new energy power generation data, and finds out the relationship between seasonal changes and new energy power generation. The dynamic correction submodule is responsible for making real-time corrections to the prediction results based on real-time updated meteorological data and actual power generation data.

[0010] As mentioned above, the risk quantification assessment module includes an uncertainty analysis submodule, a risk indicator calculation submodule and a risk visualization submodule. The uncertainty analysis submodule is responsible for constructing a probability distribution model of new energy output and load based on the collected data. The risk indicator calculation submodule is responsible for calculating the risk indicators of power shortage risk probability, power abandonment risk probability and voltage over-limit risk probability based on the probability distribution model. The risk visualization submodule is responsible for transmitting the calculated risk indicators in the form of charts to the mobile terminal of the dispatcher for display.

[0011] As mentioned above, the scheduling strategy generation module includes a risk assessment submodule, an emergency plan formulation submodule, an emergency execution submodule and a scheduling scheme generation submodule. The risk assessment submodule is responsible for assessing the power shortage risk and power abandonment risk caused by the uncertainty of new energy power generation. The emergency plan formulation submodule is responsible for formulating emergency plans based on risk assessment results. The emergency execution submodule is responsible for executing emergency plans when risks occur. The scheduling scheme generation submodule is responsible for simulating and verifying the results of the submodule.

[0012] As mentioned above, the execution and monitoring module includes an execution submodule, an instruction sending submodule, a device control submodule and a real-time monitoring submodule. The execution submodule is responsible for sending the scheduling plan to the control device of the power system and executing the scheduling operation. The instruction sending submodule is responsible for sending the scheduling instructions generated by the scheduling strategy generation module to various devices in the power system, including new energy power generation equipment, energy storage equipment, generator sets, transformers, circuit breakers and disconnectors, wherein the new energy power generation equipment includes wind turbines and solar panels, the energy storage equipment includes batteries and capacitors, and the generator sets include thermal generator sets and hydropower generator sets. The device control submodule is responsible for controlling the operating status of the new energy power generation equipment, energy storage equipment and generator sets according to the scheduling instructions. The real-time monitoring submodule monitors the system operating status in real time through sensors installed in the power system.

[0013] The risk-quantified large-scale renewable energy power probabilistic dispatching system provided by the present invention can more accurately evaluate the uncertainty of renewable energy output and the risks faced by the system by constructing a probability distribution model and calculating risk indicators, thereby providing a more scientific basis for dispatching decisions and improving the accuracy of dispatching. At the same time, risk quantification enables dispatchers to understand the risks that the system may face in advance and formulate corresponding emergency plans. When risks occur, they can implement emergency plans to ensure the stability of power supply and enhance the system's risk resistance. It also helps dispatchers to better understand the impact of different meteorological conditions and seasons on renewable energy power generation, thereby optimizing the resource allocation of renewable energy power generation equipment, energy storage equipment and generator sets, and improving the operating efficiency of the system. As the proportion of renewable energy in the power system continues to increase, its uncertainty and volatility have an increasingly greater impact on the system. The risk-quantified large-scale renewable energy power probabilistic dispatching system can better adapt to the development trend of renewable energy and improve the reliability and sustainability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this technical field, other drawings can be obtained based on these drawings without creative work. As shown in the accompanying drawings, the above and other purposes, features and advantages of the present invention will be clearer. The same reference numerals in all the drawings indicate the same parts. The drawings are not deliberately scaled to the actual size, and the focus is on illustrating the main purpose of the present invention.

[0015] Figure 1 It is a schematic diagram of the process structure of the large-scale renewable energy power probabilistic dispatching system for risk quantification provided by the present invention;

[0016] Figure 2 It is a schematic diagram of the structure of the execution and monitoring module of the risk quantified large-scale renewable energy power probabilistic dispatching system provided by the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0018] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the technical field without creative work are within the scope of protection of the present invention.

[0019] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0020] Furthermore, the terms “first”, “second”, etc. are merely used for distinguishing descriptions and should not be understood as indicating or implying relative importance.

[0021] For example, see Figure 1-2 .

[0022] This embodiment provides a large-scale new energy power probabilistic dispatching system with risk quantification, including a risk quantification dispatching module, which includes a data acquisition and processing module, an intelligent prediction module, a risk quantification assessment module, a dispatching strategy generation module, and an execution and monitoring module;

[0023] The data acquisition and processing module is responsible for collecting data related to the new energy power system, and transmitting the processed data to the intelligent prediction module through the data transmission line. The intelligent prediction module is responsible for using the prediction algorithm to make short-term and medium-term predictions of the new energy power generation, and then transmits the generated new energy power generation prediction results to the risk quantification assessment module through the data transmission line;

[0024] The risk quantification and assessment module constructs a probability distribution model of renewable energy output and load, analyzes its uncertainty, and then transmits the calculated risk indicators and risk assessment results to the scheduling strategy generation module through the data transmission line. The scheduling strategy generation module is responsible for generating a scheduling plan based on the risk information provided by the risk quantification and assessment module. When the simulation verification results show that the renewable energy power generation is low and the load demand is high in a specific time period, the output power of the generator set is increased, and the discharge power of the energy storage equipment is adjusted to meet the load demand, reduce the power supply of some non-critical loads, and give priority to the power supply of critical loads. After the scheduling strategy generation module determines the scheduling plan, it sends the scheduling instruction to the execution and monitoring module through the instruction transmission line. The execution and monitoring module is responsible for converting the scheduling plan generated by the scheduling strategy generation module into an operation instruction to control the operating status of the renewable energy power generation equipment in the power system.

[0025] The data acquisition and processing module includes a load monitoring submodule, a meteorological data acquisition submodule, a seasonal feature recognition submodule, an impact assessment submodule and a data preprocessing submodule. The load monitoring submodule uses sensors to monitor the load of the power system. Through the load sensor meter equipment installed at each node of the power system, the load data is collected in real time. The current and voltage parameters are measured through the meter, and the data is transmitted to the data processing center using the data transmission line. The meteorological data acquisition submodule is responsible for collecting meteorological data on wind speed, temperature and light intensity of renewable energy power generation. Meteorological data is collected by installing anemometers, thermometers and light intensity sensors around renewable energy power plants. These devices transmit data to the data processing center through data transmission lines. The seasonal feature recognition submodule is responsible for determining the current season based on time series data, using historical meteorological data and Time series analysis algorithm, establishes seasonal characteristic model, determines the current season by analyzing the similarity between the current time and historical seasonal data, analyzes the meteorological characteristics and new energy power generation data of different seasons, and summarizes the impact of different seasons on new energy power generation. The impact assessment submodule is responsible for evaluating the impact of different meteorological conditions and seasons on new energy power generation. It uses historical data and data analysis algorithms to quantify the impact of meteorological conditions and seasons on new energy power generation. By establishing a multivariate regression model, meteorological data and seasonal characteristics are used as input variables, and new energy power generation is used as output variables, the impact coefficient of meteorological conditions and seasons on new energy power generation is obtained. The data preprocessing submodule is responsible for processing the collected load data, meteorological data and seasonal characteristic data, and uses data cleaning algorithms to remove outliers and erroneous data and unify the data.

[0026] The intelligent prediction module includes a short-term prediction submodule, a medium- and long-term prediction submodule, and a dynamic correction submodule. The short-term prediction submodule is responsible for predicting the renewable energy power generation in the next few hours to a few days. First, short-term meteorological forecast data is collected, including meteorological information on wind speed and wind direction in a specific wind power generation area, and historical wind power generation data is obtained. Then, a machine learning algorithm is used for modeling, with meteorological data of wind speed and wind direction as input features and historical wind power generation data as output targets. A linear regression algorithm is used to establish a regression model. In the modeling process, the changing laws of renewable energy power generation under different meteorological conditions are analyzed, and the model is adjusted by training historical data. The parameters enable the model to reflect the relationship between wind speed, wind direction and wind power generation. The medium- and long-term prediction submodule is responsible for considering seasonal changes and making trend forecasts on future renewable energy power generation. By collecting historical meteorological data and renewable energy power generation data, the correlation between meteorological data of wind speed and light intensity in different seasons and wind and solar power generation is analyzed. The correlation coefficient between meteorological data and power generation in different seasons is calculated through statistical analysis methods. For solar power generation, the correlation coefficient between light intensity and solar power generation in different seasons is calculated, and a seasonal change model is established. For long-term meteorological trend forecasts, future changes in temperature and precipitation are predicted based on climate models. Trend. For solar power generation, temperature changes will affect the efficiency of solar panels, thereby affecting solar power generation, so as to predict future temperature change trends. At the turn of seasons, according to the medium- and long-term forecast results, equipment maintenance and resource allocation are arranged in advance. When it is predicted that the seasonal solar power generation will decrease, the maintenance of solar power generation equipment is arranged in advance to ensure that the equipment can operate normally in the high power generation season. At the same time, according to the forecast results, the resource allocation is adjusted and the spare capacity of the generator set is increased to cope with the changes in the power generation of new energy. The dynamic correction submodule is responsible for real-time correction of the forecast results according to the real-time updated meteorological data and actual power generation data. Sensors on the power generation equipment monitor the equipment's power generation, voltage and current operating parameters in real time. At the same time, meteorological monitoring equipment is used to obtain meteorological data such as wind speed, light intensity and temperature changes in real time. The real-time monitored operating parameters of the new energy power generation equipment and meteorological data are compared with the input characteristics of the prediction model. When a deviation is found between the actual data and the predicted data, a correction algorithm is used to adjust the prediction result according to the size of the deviation. When the actual wind speed is higher than the predicted wind speed, but the power generation does not reach the predicted value, it can be speculated that the equipment has failed or the power generation efficiency has been affected. At this time, the parameters of the prediction model are adjusted according to the prediction results, and the power generation prediction value is recalculated.

[0027] The risk quantification assessment module includes an uncertainty analysis submodule, a risk indicator calculation submodule and a risk visualization submodule. The uncertainty analysis submodule is responsible for constructing a probability distribution model of new energy output and load based on the collected data. First, the data of new energy output and load are collected. For new energy wind power generation, the output power data is collected by sensors installed on the wind power generation equipment, and the size and direction of wind speed are obtained by meteorological monitoring equipment. For new energy solar power generation, the output power data is collected by sensors installed on the solar power generation equipment, and the light intensity sensor and cloud monitoring equipment are used to obtain the light intensity and cloud coverage data. Then, the unified The statistical method is used to analyze the output and load data of renewable energy. For wind power generation, the wind power generation data under different wind speeds are analyzed, and the mean and variance of wind speed are calculated. For solar power generation, the solar power generation data under different light intensities and the power generation changes under cloud cover are analyzed, and the mean and variance parameters of light intensity are calculated. Finally, the parameters of the probability distribution model are determined according to the statistical analysis results. The risk indicator calculation submodule is responsible for calculating the risk indicators of power shortage risk probability, power abandonment risk probability and voltage over-limit risk probability according to the probability distribution model. First, the probability distribution of renewable energy output and load is analyzed, and the probability distribution model determined by the uncertainty analysis submodule is used to calculate the probability distribution of renewable energy output and load. The probability density of source output and load under different circumstances. When calculating the probability of power shortage risk, determine the probability that the output of renewable energy is less than the load demand in a specific time period. Use random sampling method to randomly generate scenarios. Each scenario includes random values ​​of renewable energy output and load. According to the probability distribution model, randomly extract the values ​​of renewable energy output and load. For each scenario, determine whether the output of renewable energy is less than the load demand. If it is confirmed to be, record it as a power shortage event. By counting the number of power shortage events, calculate the probability of power shortage risk. The probability of power shortage risk is equal to the number of power shortage events divided by the total number of scenarios. The risk visualization submodule is responsible for displaying the calculated risk indicators in the form of charts. It is transmitted to the mobile terminal of the dispatcher for display. First, the risk indicator data calculated by the risk indicator calculation submodule is received, including the power shortage risk probability, the power abandonment risk probability and the voltage over-limit risk probability. Then, a customized design is performed according to the needs of the dispatcher. The dispatcher chooses to display the risk indicator within a specific time period and selects the chart type (including bar charts, line charts and pie charts) required by the dispatcher to display the risk information. Finally, the risk indicator is transmitted to the dispatcher's mobile terminal in the form of a chart. The risk indicator data is converted into a chart using data visualization software, and the chart is sent to the dispatcher's mobile device (including mobile phones and computers) via a wireless network or data transmission line.

[0028] The dispatch strategy generation module includes a risk assessment submodule, an emergency plan formulation submodule, an emergency execution submodule and a dispatch plan generation submodule. The risk assessment submodule is responsible for assessing the power shortage risk and power abandonment risk caused by the uncertainty of renewable energy power generation. By collecting renewable energy output data, load data, meteorological data and historical risk event data, and then using the probability statistics data analysis algorithm, the renewable energy output data is analyzed to determine the probability distribution. By statistically analyzing the historical renewable energy output data, the parameters of its mean and variance are obtained, the load data is analyzed to understand the power demand in different time periods, the historical load data is analyzed in time series to determine the load change trend, and the impact of meteorological data on renewable energy power generation is analyzed. For solar power generation, the relationship between light intensity and power generation is analyzed. For wind power generation, the relationship between wind speed and power generation is analyzed. The impact of meteorological data on renewable energy power generation is quantified by establishing a regression model. Combined with historical risk event data, the probability and impact of risks under different circumstances are analyzed. The number and impact range of power shortage risks under different meteorological conditions in the past are counted. Taking the above factors into consideration, a risk assessment model is established. The output of renewable energy, load and meteorological factors are used as input variables, and the probability and impact of risks are used as output variables. The weights and impact relationships of various factors are determined through model training. The emergency plan formulation submodule is responsible for formulating emergency plans based on the risk assessment results, and the emergency execution submodule is responsible for When a risk occurs, the emergency plan is implemented. According to the risk assessment results obtained by the risk assessment submodule, the type and severity of the risk are determined. When the probability of power shortage risk is high and the impact is large, it is determined as a high-risk situation. Based on the risk assessment results and the actual situation of the power system, emergency plans of different levels are formulated. For the situation of starting the backup power supply, the capacity and timing of starting the backup power supply are determined according to the severity of the power shortage risk. When the power shortage risk occurs, the backup power supply is started. For the strategy of adjusting the load demand, according to the size of the power abandonment risk, the specific measures for adjusting the load demand are determined. When the power abandonment risk is high, priority is given to reducing the power supply of the interruptible load. Then, according to the forecast of the new energy power generation and the load demand, the storage and The use of energy storage equipment determines the charging and discharging strategy of energy storage equipment, charging when the renewable energy power generation is high, and discharging when the load is peak or the renewable energy power generation is insufficient. The emergency execution submodule monitors the renewable energy power generation, load demand and the operating status of the power system in real time. When the renewable energy power generation suddenly drops and causes the risk of power shortage, the emergency response mechanism is immediately triggered to determine the specific operation process of starting the backup power supply. First, a start signal is sent to the backup power supply, and the output power and voltage and other parameters of the backup power supply are adjusted to match the needs of the power system. At the same time, according to the emergency plan, the load demand is adjusted and the power supply of some non-critical loads is cut off to reduce the power demand. The scheduling plan generation submodule is responsible for generating a scheduling plan based on the results of the simulation verification submodule.When the simulation verification results show that the power generation of new energy is low and the load demand is high in a specific time period, the output power of the generator set is increased, and the discharge power of the energy storage equipment is adjusted to meet the load demand, and the power supply of some non-critical loads is reduced to give priority to the power supply of critical loads.

[0029] The execution and monitoring module includes an execution submodule, an instruction sending submodule, an equipment control submodule and a real-time monitoring submodule. The execution submodule is responsible for sending the dispatch plan to the control equipment of the power system. First, it receives the dispatch plan determined by the dispatch strategy generation module, establishes a data communication link, and converts the dispatch plan into a binary data format that conforms to a specific communication protocol to ensure that the format can be recognized and processed by the control equipment of the power system. At the same time, it adopts a combination of wired communication (Ethernet) and wireless communication (dedicated wireless network) for data transmission. When selecting the communication method, it makes a judgment based on the importance and real-time requirements of the data. For critical dispatch instructions, wired communication is used, and for some non-critical information that requires a quick response, wireless communication is used. The instruction sending submodule is responsible for sending the dispatch strategy to the control equipment of the power system. The dispatching instructions generated by the strategy generation module are sent to each device in the power system. This submodule receives the dispatching instructions generated by the dispatching strategy generation module and uses the distributed communication network to establish communication connections with each device. When the system is in normal operation and it is necessary to transmit regular dispatching instructions to the intelligent new energy power generation equipment, the IP protocol is used to send remote instructions. The instructions for adjusting the power generation are sent to the controller of the device through IP data packets. The distributed communication network is used to ensure that the instructions reach each new energy power generation equipment. When it is necessary to stop a new energy power generation equipment immediately to prevent the expansion of system failures, the TCP protocol is used to transmit instructions to ensure the accurate delivery of instructions. For the generator set, the industrial control bus type used by the generator set is Modbus bus and Prof i bus bus, using the distributed network to establish a connection with the controller of the generator set, and transmitting instructions through the industrial control bus. The instructions for adjusting the output power are sent to the controller of the generator set through the register write operation of the Modbus bus. For intelligent new energy power generation equipment, the instructions are encapsulated into data packets that comply with the network protocol. For the generator set, the instructions are converted into signals that comply with the industrial control bus data format. The equipment control submodule is responsible for controlling the operating status of the new energy power generation equipment, energy storage equipment and generator set according to the scheduling instructions. By receiving the scheduling instructions from the instruction sending submodule, the parameter range of the output power and voltage for the new energy power generation equipment is analyzed. According to the scheduling instructions, through Adjust the control parameters of the equipment to adjust the output power and voltage. For wind power generation equipment, adjust the angle and speed of the blades to control the output power. For solar power generation equipment, adjust the angle of the photovoltaic panel and the parameters of the inverter to control the output voltage. For energy storage equipment, analyze its charging and discharging status and power output constraints. According to the dispatch instructions, control the charging and discharging operations of the energy storage equipment to adjust its power output. For battery energy storage equipment, adjust the charging and discharging status and control the power output by controlling the charging current and discharging current. For generator sets, analyze the adjustment method of output power and operating status. According to the dispatch instructions, adjust the fuel supply and valve opening parameters of the generator set.In order to adjust the output power and operating status, the real-time monitoring submodule installs current sensors, voltage sensors and power sensors at key locations of the power system. These sensors collect the operating data of the power system current, voltage and power parameters in real time. The sensors transmit the collected data to the data processing center of the real-time monitoring submodule through a wireless network. Then, the data processing algorithm is used to analyze and process the monitoring data. The median filtering algorithm is first used to remove interference data. For a set of continuous current data points, these data points are sorted by size and the middle value is taken as the filtered result. Then, the statistical analysis algorithm is used to calculate the mean and variance parameters of the filtered data. For current data, all filtered currents are The values ​​are added and then divided by the number of data points to extract key information, which includes the current operating status of the power system, the working conditions of the equipment and the load demand. The current operating status of the power system is judged based on the mean and variance parameters of current, voltage and power. When the mean of current and voltage is within the normal range and the variance is small, it means that the power system is running stably. When the variance is large, it means that there is an abnormality in the system. For new energy power generation equipment, when the power output is close to its rated power, it means that the equipment is working normally. When the power output is significantly lower than the rated power, it means that there is a fault in the equipment. The load demand is judged by the size of current and power. When the current and power are large, it means that the load demand is high. When the current and power are small, it means that the load demand is low. ,

[0030] Working principle: When the system is in use, first, the load monitoring submodule uses sensors to monitor the load of the power system in real time and collect load demand data. At the same time, the meteorological data collection submodule collects meteorological data related to renewable energy power generation through meteorological monitoring equipment (anemometers, thermometers and light intensity sensors) installed around renewable energy power plants. Then, the seasonal feature recognition submodule determines the current season based on time series data and analyzes the typical impact of different seasons on renewable energy power generation. At the same time, the impact assessment submodule uses historical data and data analysis algorithms to quantify the specific impact of meteorological conditions and seasons on renewable energy power generation. Then, the data preprocessing submodule processes the collected load data, meteorological data and seasonal feature data to provide accurate data for subsequent modules.

[0031] The short-term prediction submodule uses short-term weather forecast data to make short-term predictions of renewable energy power generation in the next few hours to days, while the medium- and long-term prediction submodule considers seasonal changes and makes trend predictions of future renewable energy power generation. The dynamic correction submodule dynamically corrects the prediction results based on real-time updated weather data and actual power generation data.

[0032] The uncertainty analysis submodule builds a probability distribution model of renewable energy output and load based on the collected data and analyzes its uncertainty. Then, the risk indicator calculation submodule calculates the risk indicators of power shortage risk probability, power abandonment risk probability and voltage over-limit risk probability based on the probability distribution model. Then, the risk visualization submodule displays the calculated risk indicators to the dispatching personnel in the form of charts, so that the staff can better understand the system risk status. The risk assessment submodule assesses the power shortage risk and power abandonment risk caused by the uncertainty of renewable energy power generation, and quantifies the probability of occurrence and impact of the risk. The emergency plan formulation submodule formulates corresponding emergency plans based on the risk assessment results. When the risk occurs, the emergency execution submodule executes the emergency plan to ensure the stability of power supply. At the same time, the dispatch plan generation submodule generates a dispatch plan based on the simulation verification results.

[0033] Finally, the execution submodule sends the scheduling plan to the control device of the power system to perform the scheduling operation. The instruction sending submodule sends the scheduling instructions to various devices in the power system. The equipment control submodule controls the operating status of the new energy power generation equipment, energy storage equipment and generator sets according to the scheduling instructions. At the same time, the real-time monitoring submodule monitors the system operating status in real time through sensors installed in the power system so as to adjust the scheduling strategy in time.

[0034] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A large-scale new energy power probabilistic dispatching system with risk quantification, including a risk quantification dispatching module, characterized in that: The risk quantification scheduling module includes a data acquisition and processing module, an intelligent prediction module, a risk quantification assessment module, a scheduling strategy generation module and an execution and monitoring module; The data acquisition and processing module is responsible for collecting data related to the new energy power system, and transmitting the processed data to the intelligent prediction module through the data transmission line. The intelligent prediction module is responsible for using the prediction algorithm to make short-term and medium-term predictions of the new energy power generation, and then transmitting the generated new energy power generation prediction results to the risk quantification assessment module through the data transmission line; The risk quantification and assessment module constructs a probability distribution model of new energy output and load, analyzes its uncertainty, and then transmits the calculated risk indicators and risk assessment results to the scheduling strategy generation module through the data transmission line. The scheduling strategy generation module is responsible for generating a scheduling plan based on the risk information provided by the risk quantification and assessment module. The execution and monitoring module is responsible for converting the scheduling plan generated by the scheduling strategy generation module into operating instructions to control the operating status of the new energy power generation equipment in the power system.

2. The risk quantified large-scale renewable energy power probabilistic dispatching system according to claim 1 is characterized by: The data acquisition and processing module includes a load monitoring submodule, a meteorological data acquisition submodule, a seasonal feature identification submodule, an impact assessment submodule and a data preprocessing submodule. The load monitoring submodule uses sensors to monitor the load conditions of the power system. The meteorological data acquisition submodule is responsible for collecting meteorological data of wind speed, temperature and light intensity of renewable energy power generation. By installing anemometers, thermometers and light intensity sensors around renewable energy power plants, meteorological data is collected in real time. The seasonal feature identification submodule is responsible for determining the current season based on time series data and analyzing the impact on renewable energy power generation in different seasons. The impact assessment submodule is responsible for evaluating the impact of different meteorological conditions and seasons on renewable energy power generation. The data preprocessing submodule is responsible for processing the collected load data, meteorological data and seasonal feature data.

3. The risk quantified large-scale renewable energy power probabilistic dispatching system according to claim 1 is characterized by: The intelligent prediction module includes a short-term prediction submodule, a medium- and long-term prediction submodule and a dynamic correction submodule. The short-term prediction submodule is responsible for predicting the new energy power generation in the time range of several hours to several days in the future. The short-term prediction submodule uses short-term meteorological forecast data to make short-term predictions on the new energy power generation. The medium- and long-term prediction submodule is responsible for considering seasonal changes and making trend predictions on future new energy power generation. The medium- and long-term prediction submodule considers seasonal changes and long-term meteorological trends, analyzes historical meteorological data and new energy power generation data, and finds out the relationship between seasonal changes and new energy power generation. The dynamic correction submodule is responsible for making real-time corrections to the prediction results based on real-time updated meteorological data and actual power generation data.

4. The risk quantified large-scale renewable energy power probabilistic dispatching system according to claim 1 is characterized by: The risk quantification assessment module includes an uncertainty analysis submodule, a risk index calculation submodule and a risk visualization submodule. The uncertainty analysis submodule is responsible for constructing a probability distribution model of new energy output and load based on the collected data. The risk index calculation submodule is responsible for calculating the risk indicators of power shortage risk probability, power abandonment risk probability and voltage over-limit risk probability based on the probability distribution model. The risk visualization submodule is responsible for transmitting the calculated risk indicators in the form of charts to the mobile terminal of the dispatcher for display.

5. The risk quantified large-scale renewable energy power probabilistic dispatching system according to claim 1 is characterized by: The scheduling strategy generation module includes a risk assessment submodule, an emergency plan formulation submodule, an emergency execution submodule and a scheduling scheme generation submodule. The risk assessment submodule is responsible for assessing the power shortage risk and power abandonment risk caused by the uncertainty of new energy power generation. The emergency plan formulation submodule is responsible for formulating emergency plans based on risk assessment results. The emergency execution submodule is responsible for executing emergency plans when risks occur. The scheduling scheme generation submodule is responsible for simulating and verifying the results of the submodules.

6. The risk quantified large-scale renewable energy power probabilistic dispatching system according to claim 1 is characterized by: The execution and monitoring module includes an execution submodule, an instruction sending submodule, a device control submodule and a real-time monitoring submodule. The execution submodule is responsible for sending the scheduling plan to the control device of the power system and executing the scheduling operation. The instruction sending submodule is responsible for sending the scheduling instructions generated by the scheduling strategy generation module to various devices in the power system, including new energy power generation equipment, energy storage equipment, generator sets, transformers, circuit breakers and disconnectors. Among them, the new energy power generation equipment includes wind turbines and solar panels, the energy storage equipment includes batteries and capacitors, and the generator sets include thermal generator sets and hydropower generator sets. The device control submodule is responsible for controlling the operating status of the new energy power generation equipment, energy storage equipment and generator sets according to the scheduling instructions. The real-time monitoring submodule monitors the system operating status in real time through sensors installed in the power system.

Images