Power grid optimization control system and method based on artificial intelligence

Abstract

The invention relates to the technical field of intelligent power grid optimization, in particular to a power grid optimization control system and method based on artificial intelligence, and the system comprises a data collection module which is used for carrying out the real-time collection of power generation data; the data processing module is used for processing the power generation data; the data transmission module is used for transmitting the actual power generation data to a data control center; the control center intelligent decision module is used for evaluating and predicting the actual power generation data, monitoring the power load in real time and adjusting the output power of the power generation equipment according to the state of the power load; the intelligent optimization scheduling module is used for intelligently scheduling the power supply of the fault power plant according to the real-time monitoring data; and the decision execution module is used for performing decision execution on the intelligent scheduling plan. The operation efficiency and reliability of the power system are improved, so that continuous and stable power supply of the power grid is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grid optimization, and in particular to a grid optimization control system and method based on artificial intelligence. Background Art

[0002] As electricity demand continues to rise, the scale of the power grid continues to expand and its structure becomes complex. Traditional power grid operation and management mostly rely on manual experience combined with simple automation methods. Faced with massive amounts of operating data, the voltage, current and power information of each node are processed and analyzed slowly, and the real-time status of the power grid cannot be accurately grasped in a timely manner. At the same time, a large number of distributed energy sources are connected, including solar and wind power generation, whose output is intermittent and volatile, which brings huge challenges to the stable operation of the power grid. On the electricity consumption side, the electricity demand in different periods, different industries and user groups varies greatly, and the load peaks and valleys change significantly. Existing technologies have exposed many problems under this complex background. Generally speaking, traditional power grid optimization and control methods have poor flexibility and cannot adapt to the dynamic changes of the power grid. In the face of complex working conditions, they cannot make effective decisions quickly and cannot fully coordinate the power generation, transmission, distribution and power consumption links, resulting in low power grid operation efficiency and insufficient stability, thus failing to guarantee the quality of power.

[0003] Chinese Patent Publication No.: CN115378041A discloses a distribution network optimization method, system, distribution network, equipment and medium, the method includes injecting current source equivalent calculation on distributed energy and energy storage system in the distribution network, obtaining first operating parameters corresponding to the distributed energy and second operating parameters corresponding to the energy storage system; setting multiple optimization targets corresponding to the distribution network according to the first operating parameters and the second operating parameters, as well as the topological structure of the distribution network; setting objective functions and / or constraints corresponding to multiple optimization targets, solving the objective function according to the distribution network optimization algorithm to determine the distribution network optimization strategy, and adjusting the optimal configuration of the energy storage system according to the distribution network optimization strategy, wherein the distribution network optimization algorithm is used to solve the optimal solution of the objective function. The power grid optimization control method of the present invention has poor flexibility and cannot adapt to the dynamic changes of the power grid, resulting in low power grid operation efficiency and insufficient stability, thereby failing to ensure continuous and stable power supply to the power grid. Summary of the invention

[0004] To this end, the present invention provides an artificial intelligence-based power grid optimization control system and method to overcome the problem that the power grid optimization control method in the prior art has poor flexibility and cannot adapt to dynamic changes in the power grid, resulting in low power grid operation efficiency and insufficient stability, thereby being unable to ensure continuous and stable power supply to the power grid.

[0005] To achieve the above objectives, on the one hand, the present invention provides a power grid optimization control system based on artificial intelligence, the system comprising: Data acquisition module, used to collect power generation data in real time; A data processing module is used to process the power generation data to obtain actual power generation data, which includes the real-time status of the power generation equipment, the location coordinates of the data control center, the location coordinates of the power plant that has been shut down, the longitude and latitude of the locations of the two plants, the line impedance and the line capacity; A data transmission module, used to calculate the communication distance according to the location coordinates of the data control center and the location coordinates of the power plant with power outage, and to determine the data communication type according to the communication distance, and to transmit the actual power generation data to the data control center in the intelligent decision-making module of the control center according to the data communication type; The intelligent decision-making module of the control center is used to evaluate and predict the actual power generation data according to the energy resource evaluation model to obtain evaluation prediction data, which includes the evaluation prediction data accuracy, the total power supply and total power demand of each power plant, and is also used to monitor the power load in real time according to the evaluation prediction data to obtain the density of the power load, and adjust the output power of the power generation equipment according to the density of the power load, and is also used to adjust the power load according to the total power demand, and is also used to dispatch the power of the energy storage end according to the total power supply of each power plant; An intelligent optimization scheduling module is used to calculate the intelligent scheduling index according to the evaluation prediction data, and is also used to calculate the power supply optimization index of the power plant according to the intelligent scheduling index, and intelligently schedule the power supply of the faulty power plant according to the power supply optimization index of the power plant, and generate an intelligent scheduling strategy, and is also used to calculate the distance between the two plants according to the longitude and latitude of the locations of the two plants, and optimize the power supply optimization index of the power plant according to the distance between the two plants, and is also used to optimize the distance between the two plants according to the line impedance and the line capacity; The decision-making execution module is used to make decisions and execute the intelligent scheduling plan according to the real-time status of the power generation equipment and the intelligent scheduling strategy.

[0006] Furthermore, when the data transmission module transmits the actual power generation data, the data transmission module transmits the actual power generation data according to the position coordinates (x 2 ,y 2 ) and the location coordinates of the power plant that was out of power (x 1 ,y 1 ) Calculate the communication distance L and set , and compare the communication distance L with the preset communication distance L0, and judge the data communication type according to the comparison result, wherein: When L≤L0, the data communication type is determined to be short-distance communication, and the actual power generation data is transmitted to the data control center in the intelligent decision-making module of the control center according to the Ethernet data transmission method; When L>L0, the data communication type is determined to be long-distance communication, and the actual power generation data is transmitted to the data control center in the intelligent decision-making module of the control center according to the 4G / 5G wireless communication method.

[0007] Furthermore, when the intelligent decision-making module of the control center evaluates and predicts the actual power generation data, it evaluates and predicts the actual power generation data according to the energy resource evaluation and prediction model to obtain evaluation and prediction data, which includes the evaluation and prediction data accuracy rate N, the total power supply Qg and the total power demand Q of each power plant, and compares the evaluation and prediction data accuracy rate N in the evaluation and prediction data with the preset evaluation and prediction data accuracy rate N0, judges the accuracy of the evaluation and prediction data according to the comparison result, and optimizes the energy resource evaluation and prediction model according to the judgment result, wherein: When N≥N0, the prediction accuracy of the energy resource assessment prediction model is determined to be high precision, and the energy resource assessment prediction model is not optimized at this time; When N<N0, the prediction accuracy of the energy resource assessment prediction model is low. At this time, the energy resource assessment prediction model is optimized, and different energy resource assessment prediction models are used to predict the actual power generation data to obtain the predicted power generation power P1, P2 and P3. The weighted average power P is calculated based on the predicted power generation power P1, P2 and P3, and the setting , where ω1, ω2 and ω are the performance weight coefficients of the energy resource assessment prediction model on the validation set, and ω1+ω2+ω3=1.

[0008] Furthermore, the intelligent decision-making module of the control center obtains the power load state when monitoring the power load M in real time, calculates the power load M according to the time factor D, the seasonal factor S, the hour period H and the weather factor T, and sets , where β1, β2, β3 and β4 are the regression coefficients of each factor, and β1+β2+β3+β4=1, is the error term, the power load M is compared with the preset power load M0, the density of the power load is judged according to the comparison result, and the output power of the power generation equipment is adjusted according to the judgment result, where: When M≤M0, the power load is judged to be low load and the power supply load is sufficient. At this time, the surplus can enter the energy storage end for energy storage, and the output power of the power generation equipment is not adjusted; When M>M0, the power load is determined to be high load and the power supply load is insufficient. At this time, the surplus cannot enter the energy storage end for energy storage, and the output power of the power generation equipment is adjusted.

[0009] Furthermore, when the intelligent decision-making module of the control center adjusts the power load M, the average value of the power load is calculated based on the monitoring data. Calculate and set , where n is the time interval within [t0, tn], i is the time node, is the power load value at different time nodes, and the total power demand Q is calculated according to the average value of the power load, setting Q= × (tn-t0), compare the total power demand Q with the preset total power demand Q0, judge the controllable range of the total power demand Q according to the comparison result, and adjust the power load M according to the judgment result, where: When Q≤Q0, the control range of the total power demand Q is determined to be within the controllable range, and M is not adjusted at this time; When Q>Q0, it is determined that the control range of the total power demand Q is uncontrollable. At this time, the power load M is adjusted. After adjustment, the power load is M1, and M1=1.28×M is set.

[0010] Furthermore, when dispatching the energy storage end power, the intelligent decision module of the control center obtains the total power supply Qg of each power plant according to the evaluation prediction data, compares the total power supply Qg of each power plant with the total power demand Q, judges the total power demand Q according to the comparison result, and dispatches the energy storage end power according to the judgment result, wherein: When Qg≥Q, it is determined that the total power supply of the power plant meets the total power demand Q at this time, and the power at the energy storage end is not dispatched; When Qg<Q, it is determined that the total power supply of the power plant does not meet the total power demand Q at this time, and the power at the energy storage end is dispatched, and the power supply at the energy storage end is dispatched to Qg1, and Qg1=Q-Qg is set.

[0011] Furthermore, when the intelligent optimization scheduling module performs machine calculation on the intelligent scheduling index, it calculates the reliability index R according to the historical failure frequency F and the mean repair time MTTR of the power plant, and sets , calculate the total power generation cost index C according to the fuel cost Cf, operation and maintenance cost Cm and equipment depreciation cost Cd, set C=Cf+Cm+Cd, and calculate the flexibility index Fi according to the start time index Is, stop time index Ip and start success rate Ss, set Fi=0.3×Is+0.3×Ip+0.4×Ss, and output the reliability index R, total power generation cost index C and flexibility index Fi as intelligent scheduling indicators; When calculating the power supply optimization index Y of the power plant, the intelligent optimization scheduling module calculates the power supply priority index Y of the power plant according to the reliability index R, the power generation cost index C and the flexibility index Fi, sets Y=0.3×R+0.3×C+0.3×Fi-0.1, compares the power supply priority index Y of the power plant with the preset power supply optimal priority index Y0 of the power plant, judges the power supply priority of the power plant according to the comparison result, and intelligently schedules the power supply of the faulty power plant according to the judgment result, and generates an intelligent scheduling strategy, wherein: When Y>Y0, the power plant is determined to be a first-level priority power supply plant. When meeting the needs of the faulty power plant, the power plant will give priority to intelligently dispatching the power supply to the faulty power plant; When Y=Y0, the power plant is determined to be a second-level priority power plant. When the resources of the first-level priority power plant cannot meet the needs of the faulty power plant, the power plant intelligently dispatches the power supply to the faulty power plant. When Y<Y0, the power plant is determined to be a third-level priority power supply plant. When both the first-level and second-level priority power supply plants cannot meet the needs of the faulty power plant, the power plant intelligently dispatches the power supply to the faulty power plant.

[0012] Furthermore, when the intelligent optimization scheduling module optimizes the power supply optimization index Y of the power plant, it calculates the distance d between the two plants by the longitude and latitude of the two plants and sets , where R is the radius of the earth, φ1 and φ2 are longitudes, λ1 and λ2 are latitudes, and the distance d between the two plants is compared with the preset distance d0 between the two plants. The distance range between the two power plants is judged according to the comparison result, and the power supply priority index Y of the power plant is optimized according to the judgment result, where: When d≤d0, the distance range between the two power plants is determined to be a power supply range, and the power supply priority index Y of the power plant is not optimized at this time; When d>d0, the distance between the two power plants is determined to be a non-power supply range. At this time, the power supply priority index Y of the power plant is optimized. After optimization, the power supply priority index of the power plant is Yy, and Yy=0.3×R+0.3×C+0.3×Fi-0.1×d is set; When optimizing the distance d between the two plants, the intelligent optimization scheduling module compares the line impedance Z and the line capacity G with the preset line impedance Z0 and the preset line capacity G0, judges the line impedance range and the line capacity level according to the comparison result, and optimizes the distance d between the two plants according to the judgment result, wherein: When Z≤Z0 and G≥G0, it is determined that the line impedance range is small, the line capacity is high, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z≤Z0 and G<G0, it is determined that the line impedance range is small, the line capacity is low, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z>Z0 and G≥G0, it is determined that the line impedance range is large, the line capacity is high, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z>Z0 and G<G0, it is determined that the line impedance range is large, the line capacity is low, and the line transmission efficiency is not ideal. At this time, the distance d between the two plants is optimized. After optimization, the distance between the two plants is the line weighted distance ,set up , where k1 and k2 are weighting coefficients, and k1+k2=1.

[0013] Furthermore, when the decision-making execution module makes a decision to execute the intelligent dispatching plan, it generates an intelligent dispatching instruction through the real-time status of the power generation equipment and the intelligent dispatching strategy, feeds back the execution status of the intelligent dispatching instruction to the control center, obtains feedback information, judges the execution effect of the intelligent dispatching instruction according to the feedback information, and makes a decision according to the judgment result, wherein: When the execution of the intelligent scheduling instruction is consistent with the intelligent scheduling strategy, the execution effect is determined to be good, and the decision is executed according to the intelligent scheduling plan; When the execution of the intelligent scheduling instruction is inconsistent with the intelligent scheduling strategy, the execution effect is determined to be poor, and the decision is not executed according to the intelligent scheduling plan. The intelligent scheduling strategy is analyzed and adjusted through feedback information.

[0014] On the other hand, the present invention also provides a power grid optimization control method based on artificial intelligence, the method comprising: Step S1, real-time collection of power generation data; Step S2, processing the power generation data to obtain actual power generation data, which includes the real-time status of the power generation equipment, the location coordinates of the data control center, the location coordinates of the power plant that has been shut down, the longitude and latitude of the locations of the two plants, the line impedance and the line capacity; Step S3, calculating the communication distance according to the location coordinates of the data control center and the location coordinates of the power plant with power outage, judging the data communication type according to the communication distance, and transmitting the actual power generation data to the data control center in the intelligent decision-making module of the control center according to the data communication type; Step S4, evaluating and predicting the actual power generation data according to the energy resource evaluation model to obtain evaluation prediction data, which includes the evaluation prediction data accuracy, the total power supply and total power demand of each power plant; Step S5, monitoring the power load in real time according to the evaluation prediction data, obtaining the density of the power load, and adjusting the output power of the power generation equipment according to the density of the power load; Step S6, adjusting the power load according to the total power demand, and dispatching the power of the energy storage end according to the total power supply of each power plant; Step S7, calculating the intelligent scheduling index according to the evaluation prediction data; Step S8, calculate the power supply optimization index of the power plant according to the intelligent scheduling index, and intelligently schedule the power supply of the faulty power plant according to the power supply optimization index of the power plant to generate an intelligent scheduling strategy; Step S9, calculating the distance between the two plants according to the longitude and latitude of the two plants, optimizing the power supply optimization index of the power plant according to the distance between the two plants, and optimizing the distance between the two plants according to the line impedance and the line capacity; Step S10: making decisions and executing the intelligent dispatching plan according to the real-time status of the power generation equipment and the intelligent dispatching strategy.

[0015] Compared with the prior art, the beneficial effects of the present invention are that the system collects power generation data in real time through the data acquisition module to ensure the timeliness and accuracy of the data, the system processes the collected power generation data through the data processing module to extract the actual power generation data, so as to provide information support for subsequent data transmission and intelligent decision-making, the system intelligently selects the data communication type according to the communication distance through the data transmission module, optimizes the data transmission mode, so as to realize the accurate transmission of the actual power generation data to the data control center of the control center, thereby improving the efficiency and reliability of data transmission, the system evaluates and predicts the actual power generation data through the intelligent decision-making module of the control center, so as to facilitate the real-time monitoring of the power load and the adjustment of the output power of the power generation equipment, and adjusts the output of the power generation equipment in real time according to the power load status Power, ensure the stability and efficiency of power supply, adjust the power load according to the total power demand Q, optimize the allocation of power resources, and dispatch the power of the energy storage end according to the total power supply Qg of each power plant, so as to improve the flexibility and reliability of the power system. The system calculates the power supply optimization index according to the intelligent scheduling index through the intelligent optimization scheduling module to facilitate the intelligent scheduling of the faulty power plant, and optimizes the distance and line parameters between the two plants to improve the power supply optimization index of the power plant, and further improves the overall efficiency and stability of the power system. The system makes decisions and executes the intelligent scheduling plan according to the intelligent scheduling strategy through the decision-making execution module to ensure the smooth implementation of the scheduling plan, improve the operating efficiency and reliability of the power system, thereby ensuring the continuous and stable power supply of the power grid and reducing operating costs.

[0016] In particular, in the data acquisition module, when the power generation data is collected in real time, the power generation data is collected in real time through intelligent sensors, so as to achieve comprehensive and accurate acquisition of the power generation data, and real-time monitoring and early warning of the operating status of the power generation equipment, so as to improve the power generation efficiency and economic benefits.

[0017] In particular, in the data processing module, when processing power generation data, the data processing method and Z-score method are used to unify the scale and distribution characteristics of the data, enhance the applicability of the data, and improve the accuracy of data analysis and the optimization control effect of the power grid.

[0018] In particular, in the data transmission module, when the actual power generation data is transmitted, the data communication type is intelligently judged to achieve optimal selection of the data transmission method, thereby improving data transmission efficiency and reliability.

[0019] In particular, in the intelligent decision-making module of the control center, when processing and analyzing the actual power generation data, power load and power supply at the energy storage end, the application of the intelligent decision-making module of the control center can realize accurate prediction of power generation data, effective monitoring and regulation of power load, control of power demand and dispatch of power at the energy storage end, thereby improving the efficiency and accuracy of energy management and power dispatch.

[0020] In particular, in the intelligent optimization scheduling module, when optimizing the intelligent scheduling of the power plant, the intelligent scheduling of the power plant is optimized through the application of the intelligent optimization scheduling module, the flexibility and accuracy of power scheduling are improved, thereby improving the overall transmission efficiency and stability of the power plant.

[0021] In particular, in the decision-making execution module, when making decisions and executing the intelligent dispatching plan, the execution and management of power dispatching is realized through real-time response, strategy matching, execution effect evaluation and feedback, as well as adjustment and optimization, thereby improving the efficiency and reliability of power dispatching. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram of the structure of the power grid optimization control system based on artificial intelligence in this embodiment; Figure 2 Schematic diagram of the flow chart of the power grid optimization control method based on artificial intelligence in this embodiment. DETAILED DESCRIPTION

[0023] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0024] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0025] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention.

[0026] In addition, it should also be noted that in the description of the present invention, unless otherwise clearly specified and defined, the terms "installation", "connection", "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0027] Please refer to Figure 1 as shown, which is a schematic structural diagram of the power grid optimization control system based on artificial intelligence in this embodiment. The system includes: A data acquisition module for real-time acquisition of power generation data; A data processing module for processing the power generation data to obtain actual power generation data, which includes the real-time status of power generation equipment, the position coordinates of the data control center, the position coordinates of the power plants with power outages, the longitude and latitude of the positions of the two plants, the line impedance, and the line capacity. The data processing module is connected to the data acquisition module; A data transmission module for calculating the communication distance according to the position coordinates of the data control center and the position coordinates of the power plants with power outages, judging the data communication type according to the communication distance, and transmitting the actual power generation data to the data control center in the control center intelligent decision module according to the data communication type. The data transmission module is connected to the data processing module; The intelligent decision-making module of the control center is used to evaluate and predict the actual power generation data according to the energy resource evaluation model to obtain evaluation prediction data, which includes the accuracy of the evaluation prediction data, the total power supply and total power demand of each power plant, and is also used to monitor the power load in real time according to the evaluation prediction data to obtain the density of the power load, and adjust the output power of the power generation equipment according to the density of the power load, and is also used to adjust the power load according to the total power demand, and is also used to dispatch the power of the energy storage end according to the total power supply of each power plant. The intelligent decision-making module of the control center is connected to the data transmission module; An intelligent optimization scheduling module is used to calculate the intelligent scheduling index according to the evaluation prediction data, and is also used to calculate the power supply optimization index of the power plant according to the intelligent scheduling index, and intelligently schedule the power supply of the faulty power plant according to the power supply optimization index of the power plant, and generate an intelligent scheduling strategy, and is also used to calculate the distance between the two plants according to the longitude and latitude of the two plants, and optimize the power supply optimization index of the power plant according to the distance between the two plants, and is also used to optimize the distance between the two plants according to the line impedance and the line capacity. The intelligent optimization scheduling module is connected to the intelligent decision-making module of the control center; The decision-making execution module is used to make decisions and execute the intelligent scheduling plan according to the real-time status of the power generation equipment and the intelligent scheduling strategy. The decision-making execution module is connected with the intelligent optimization scheduling module and the intelligent decision-making module of the control center.

[0028] Specifically, the system is arranged in an artificial intelligence-based power grid optimization control terminal, which monitors and adjusts the power plant through changes in the power grid load, monitors the real-time data of the power plant in conjunction with the control center, and issues dispatch instructions for intelligent dispatching to ensure that the power grid frequency of each power plant is stable near the rated value, providing strong guarantee for the continuous and stable power supply of the power plant. Among them, the system collects power generation data in real time through the data acquisition module to ensure the timeliness and accuracy of the data. The system processes the collected power generation data through the data processing module to extract the actual power generation data to provide information support for subsequent data transmission and intelligent decision-making. The system intelligently selects the data communication type according to the communication distance through the data transmission module, and optimizes the data transmission method to facilitate the accurate transmission of the actual power generation data to the data control center of the control center, thereby improving the efficiency and reliability of data transmission. The system processes the actual power generation data through the intelligent decision-making module of the control center According to the evaluation and prediction, in order to facilitate the real-time monitoring of the power load and the adjustment of the output power of the power generation equipment, the output power of the power generation equipment is adjusted in real time according to the power load status to ensure the stability and efficiency of the power supply, the power load is adjusted according to the total power demand Q, the allocation of power resources is optimized, and the power of the energy storage end is dispatched according to the total power supply Qg of each power plant, so as to improve the flexibility and reliability of the power system. The system calculates the power supply optimization index according to the intelligent dispatching index through the intelligent optimization dispatching module to facilitate the intelligent dispatch of the faulty power plant, and optimizes the distance and line parameters between the two plants to improve the power supply optimization index of the power plant, and further improves the overall efficiency and stability of the power system. The system makes decisions and executes the intelligent dispatching plan according to the intelligent dispatching strategy through the decision-making execution module to ensure the smooth implementation of the dispatching plan, improve the operating efficiency and reliability of the power system, thereby ensuring the continuous and stable power supply of the power grid and reducing the operating cost.

[0029] Specifically, when the data acquisition module acquires the power generation data in real time, the data acquisition module acquires the power generation data in real time through the intelligent sensor.

[0030] Specifically, the smart sensor refers to a highly integrated multi-component device, including a power sensor, a temperature sensor, a pressure sensor, a flow sensor, a current sensor and a voltage sensor. The power sensor refers to a device used to measure power parameters in the power supply equipment of a power plant, the temperature sensor refers to a device used to measure the temperature in the equipment, the pressure sensor refers to a device used to measure the pressure of the liquid in the equipment, the flow sensor refers to a device used to measure the flow of fluid, the current sensor refers to a device used to measure the current in the power supply equipment, and the voltage sensor refers to a device used to measure the voltage in the power supply equipment. The power generation data refers to various information parameters related to the power production process of each power plant, including the power generation data of each power plant and the real-time status data of the power generation equipment. The power generation data of each power plant refers to the quantitative information of the electric power generated by each power plant within a specific time, and the real-time status data of the power generation equipment refers to the parameters and information used to describe the current operating status of the power generation equipment, such as temperature, hydraulic pressure, water flow, current, voltage, historical fault frequency F and mean repair time MTTR.

[0031] Specifically, in the data acquisition module, when the power generation data is collected in real time, the power generation data is collected in real time through intelligent sensors, so as to achieve comprehensive and accurate acquisition of the power generation data, and real-time monitoring and early warning of the operating status of the power generation equipment, so as to improve the power generation efficiency and economic benefits.

[0032] Specifically, when the data processing module processes the power generation data, it identifies and converts the power generation data through the data processing method to obtain the corresponding cleaned power generation data, and uses the Z-score method to standardize the cleaned power generation data to obtain the actual power generation data, which includes the real-time status of the power generation equipment, the location coordinates (x2, y2) of the data control center, the location coordinates (x1, y1) of the power plant that has been shut down, the longitude and latitude of the locations of the two plants, the line impedance Z and the line capacity G.

[0033] Specifically, the data processing method refers to the means of preliminary processing of the original power generation data, including outlier processing and missing value processing. The outlier processing refers to identifying and processing the data in the dataset that significantly deviates from other data points. The missing value processing refers to dealing with the data missing situation in the dataset. The cleaned power generation data refers to the power generation data after the data processing method. The Z - score method refers to the data standardization method, with the Chinese name of standard score method and the full name of Z - Standardization. The standardization process refers to the process of converting the cleaned power generation data into data with specific statistical characteristics through mathematical methods. The actual power generation data refers to the data obtained after the standardization process of the cleaned power generation data. The intelligent dispatching strategy refers to the rules and algorithms generated according to the intelligent dispatching plan of the power system. The position coordinates (x2, y2) of the data control center refer to the position used to locate the data control center on the earth. The position coordinates (x1, y1) of the power plant with power outage refer to the position used to locate the power plant with power outage on the earth. The longitude and latitude of the positions of the two plants refer to the two values used to determine any position on the earth. The longitude and latitude include longitude and latitude. The longitude refers to the position in the east - west direction, and the latitude refers to the position in the north - south direction. The line impedance Z refers to the hindrance effect of the power transmission line on the current. The line capacity G refers to the maximum power that the power transmission line can safely transmit.

[0034] Specifically, in the data processing module, when processing the power generation data, through the data processing method and the Z - score method, the scale and distribution characteristics of the data are unified, the applicability of the data is enhanced, and the accuracy of data analysis and the effect of power grid optimization control are improved.

[0035] Specifically, when the data transmission module transmits the actual power generation data, according to the position coordinates (x 2 , y 2 ) of the data control center and the position coordinates (x 1 , y 1 ) of the power plant with power outage, the communication distance L is calculated, set , and the communication distance L is compared with the preset communication distance L0. According to the comparison result, the data communication type is judged, where: When L ≤ L0, it is determined that the data communication type is short - distance communication, and the actual power generation data is transmitted to the data control center in the intelligent decision - making module of the control center according to the Ethernet data transmission method; When L > L0, it is determined that the data communication type is long - distance communication, and the actual power generation data is transmitted to the data control center in the intelligent decision - making module of the control center according to the 4G / 5G wireless communication method; Specifically, the communication distance L refers to the spatial distance between the power plant that has been shut down and the data control center. The preset communication distance L0 refers to the boundary used to divide short-distance communication and long-distance communication. The present embodiment does not limit the specific value of the preset communication distance L0. Relevant technical personnel in this field can freely set it according to actual conditions, as long as the requirements for judging the data communication type are met. For example, the specific value of the preset communication distance L0 can be set to 1000m. The data communication type refers to the communication category divided by the comparison result between the communication distance and the preset communication distance. The short-distance communication refers to the communication technology within a short distance range between the communicating parties. The long-distance communication refers to the communication technology within a long distance range between the communicating parties. The Ethernet data transmission method refers to a data transmission method based on Ethernet technology. The 4G / 5G wireless communication method refers to a wireless communication method based on the fourth and fifth generation mobile communication technologies.

[0036] Specifically, in the data transmission module, when the actual power generation data is transmitted, the data communication type is intelligently determined to achieve optimal selection of the data transmission method, thereby improving data transmission efficiency and reliability.

[0037] Specifically, when the intelligent decision-making module of the control center evaluates and predicts the actual power generation data, it evaluates and predicts the actual power generation data according to the energy resource evaluation and prediction model to obtain evaluation and prediction data, which includes the evaluation and prediction data accuracy rate N, the total power supply Qg and the total power demand Q of each power plant, and compares the evaluation and prediction data accuracy rate N in the evaluation and prediction data with the preset evaluation and prediction data accuracy rate N0, judges the accuracy of the evaluation and prediction data according to the comparison result, and optimizes the energy resource evaluation and prediction model according to the judgment result, wherein: When N≥N0, the prediction accuracy of the energy resource assessment prediction model is determined to be high accuracy, and the energy resource assessment prediction model is not optimized at this time; When N<N0, the prediction accuracy of the energy resource assessment prediction model is low. At this time, the energy resource assessment prediction model is optimized, and different energy resource assessment prediction models are used to predict the actual power generation data to obtain the predicted power generation power P1, P2 and P3. The weighted average power P is calculated based on the predicted power generation power P1, P2 and P3, and the setting , where ω1, ω2 and ω are the performance weight coefficients of the energy resource assessment prediction model on the validation set, and ω1+ω2+ω3=1; The intelligent decision-making module of the control center obtains the power load status when monitoring the power load M in real time, calculates the power load M according to the time factor D, the seasonal factor S, the hour period H and the weather factor T, and sets , where β1, β2, β3 and β4 are the regression coefficients of each factor, and β1+β2+β3+β4=1, is the error term, the power load M is compared with the preset power load M0, the density of the power load is judged according to the comparison result, and the output power of the power generation equipment is adjusted according to the judgment result, where: When M≤M0, the power load is judged to be low load and the power supply load is sufficient. At this time, the surplus can enter the energy storage end for energy storage, and the output power of the power generation equipment is not adjusted; When M>M0, the power load is judged to be high load and the power supply load is insufficient. At this time, the surplus cannot enter the energy storage end for energy storage, and the output power of the power generation equipment is adjusted; When the intelligent decision-making module of the control center adjusts the power load M, it calculates the average value of the power load according to the monitoring data. Calculate and set , where n is the time interval within [t0, tn], i is the time node, is the power load value at different time nodes, and the total power demand Q is calculated according to the average value of the power load, setting Q= × (tn-t0), compare the total power demand Q with the preset total power demand Q0, judge the controllable range of the total power demand Q according to the comparison result, and adjust the power load M according to the judgment result, where: When Q≤Q0, the control range of the total power demand Q is determined to be within the controllable range, and M is not adjusted at this time; When Q>Q0, it is determined that the control range of the total power demand Q is uncontrollable. At this time, the power load M is adjusted. After adjustment, the power load is M1, and M1=1.28×M is set; When dispatching the energy storage end power, the control center intelligent decision module obtains the total power supply Qg of each power plant according to the evaluation prediction data, compares the total power supply Qg of each power plant with the total power demand Q, judges the total power demand Q according to the comparison result, and dispatches the energy storage end power according to the judgment result, wherein: When Qg≥Q, it is determined that the total power supply of the power plant meets the total power demand Q at this time, and the power at the energy storage end is not dispatched; When Qg<Q, it is determined that the total power supply of the power plant does not meet the total power demand Q at this time, and the power at the energy storage end is dispatched, and the power supply at the energy storage end is dispatched to Qg1, and Qg1=Q-Qg is set.

[0038] Specifically, the energy resource evaluation and prediction model refers to a convolutional neural network model that obtains evaluation and prediction data after evaluating and predicting the actual power generation data. In this embodiment, the basic framework of the energy resource evaluation and prediction model is set as a convolutional neural network model, and the historical actual power generation data-historical evaluation and prediction data are used as the prediction model construction data set, 75% of the prediction model construction data set is used as the prediction model training set, and 25% of the prediction model construction data set is used as the prediction model verification set. The convolutional neural network model is trained according to the prediction model training set to obtain a trained convolutional neural network model, and the trained convolutional neural network model is verified according to the prediction model verification set. When the prediction accuracy reaches After reaching 97%, the trained convolutional neural network model is output as an energy resource evaluation prediction model. This embodiment does not specifically limit the construction parameters of the convolutional neural network model. Relevant technical personnel in this field can freely set them according to actual conditions, as long as the evaluation and prediction requirements are met. For example, the loss function of the convolutional neural network model can be set as a cross entropy function. The evaluation prediction data refers to the data obtained by processing the actual power generation data using the energy resource evaluation prediction model, such as fuel cost Cf, operation and maintenance cost Cm, equipment depreciation cost Cd, start time index Is, stop time index Ip and start success rate Ss. The evaluation prediction data accuracy N refers to the evaluation of the accuracy of the prediction data. The indicator between the predicted data and the actual power generation data, the total power supply Qg of each power plant refers to the sum of the power provided by all the power plants participating in the power supply, the total power demand Q refers to the total amount of power required in the time interval [t0, tn] calculated based on the average value of the power load, the preset evaluation prediction data accuracy N0 refers to the concept used to judge whether the accuracy of the evaluation prediction data reaches the expected level, the estimated prediction data accuracy accuracy refers to the concept used to evaluate the prediction performance of the energy resource evaluation prediction model, the predicted power generation refers to the result obtained after predicting the power generation using different energy resource evaluation prediction models, and the performance weight coefficient refers to the weighted average power P used to calculate The coefficient of, the power load M refers to the power demand borne by the power grid in a specific time period, the time factor D refers to the time variable that affects the power load, the seasonal factor S refers to the change in power load caused by seasonal changes, the hourly period H refers to the subdivision of 24 hours into hourly periods, the weather factor T refers to the weather conditions that affect the power load, the preset power load M0 refers to the power load reference value set according to historical data, this embodiment does not limit the specific value of the preset power load M0, and relevant technical personnel in this field can freely set it according to actual conditions, as long as it meets the requirements for comparison with the power load M, such as setting the specific value of the preset power load M0 to 400 megawatts, the density of the power load refers to the concentration of the power load per unit time,The output power of the power generation equipment refers to the actual output power of the power plant. This embodiment does not limit the method for adjusting the output power of the power generation equipment. Relevant technicians in this field can freely set it according to the actual situation. It only needs to meet the demand for adjusting the output power of the power generation equipment. For example, the method for adjusting the output power of the power generation equipment can be set to excitation adjustment. The power supply load refers to the power load actually provided by the power system to the user. The energy storage end refers to the equipment for storing electric energy. The monitoring data refers to the data for historical recording of the power load. The average value of the power load, It refers to the arithmetic mean of the power load values ​​of all time nodes within the time interval, and the time interval refers to a specific time period for calculating the average power load value. The time node refers to each specific time point within the time interval [t0, tn]. The preset total power demand Q0 refers to the expected power demand set in advance by the system. This embodiment does not limit the specific value of the preset total power demand Q0. Relevant technical personnel in this field can freely set it according to actual conditions, and only need to meet the requirements of comparison with the total power demand Q, such as it can be set to 350 megawatts. The control range refers to the control range of the total power demand Q. The scheduling refers to the process of controlling the power at the energy storage end. This embodiment does not limit the scheduling method. Relevant technical personnel in this field can freely set it according to actual conditions, and only need to meet the requirements of scheduling the power at the energy storage end, such as the scheduling method can be set to priority scheduling.

[0039] Specifically, in the intelligent decision-making module of the control center, when processing and analyzing the actual power generation data, power load and power supply at the energy storage end, the application of the intelligent decision-making module of the control center can realize accurate prediction of power generation data, effective monitoring and regulation of power load, control of power demand and dispatch of power at the energy storage end, thereby improving the efficiency and accuracy of energy management and power dispatch.

[0040] Specifically, when the intelligent optimization scheduling module calculates the intelligent scheduling index, it calculates the reliability index R according to the historical failure frequency F and the mean repair time MTTR of the power plant, and sets , calculate the total power generation cost index C according to the fuel cost Cf, operation and maintenance cost Cm and equipment depreciation cost Cd, set C=Cf+Cm+Cd, and calculate the flexibility index Fi according to the start time index Is, stop time index Ip and start success rate Ss, set Fi=0.3×Is+0.3×Ip+0.4×Ss, and output the reliability index R, total power generation cost index C and flexibility index Fi as intelligent scheduling indicators; When calculating the power supply optimization index Y of the power plant, the intelligent optimization scheduling module calculates the power supply priority index Y of the power plant according to the reliability index R, the power generation cost index C and the flexibility index Fi, sets Y=0.3×R+0.3×C+0.3×Fi-0.1, compares the power supply priority index Y of the power plant with the preset power supply optimal priority index Y0 of the power plant, judges the power supply priority of the power plant according to the comparison result, and intelligently schedules the power supply of the faulty power plant according to the judgment result, and generates an intelligent scheduling strategy, wherein: When Y>Y0, the power plant is determined to be a first-level priority power supply plant. When meeting the needs of the faulty power plant, the power plant will give priority to intelligently dispatching the power supply to the faulty power plant; When Y=Y0, the power plant is determined to be a second-level priority power plant. When the resources of the first-level priority power plant cannot meet the needs of the faulty power plant, the power plant intelligently dispatches the power supply to the faulty power plant. When Y<Y0, the power plant is determined to be a third-level priority power supply plant. When the first-level and second-level priority power supply plants cannot meet the needs of the faulty power plant, the power plant intelligently dispatches the power supply to the faulty power plant. When the intelligent optimization scheduling module optimizes the power supply optimization index Y of the power plant, it calculates the distance d between the two plants by the longitude and latitude of the two plants and sets , where R is the radius of the earth, φ1 and φ2 are longitudes, λ1 and λ2 are latitudes, and the distance d between the two plants is compared with the preset distance d0 between the two plants. The distance range between the two power plants is judged according to the comparison result, and the power supply priority index Y of the power plant is optimized according to the judgment result, where: When d≤d0, the distance range between the two power plants is determined to be a power supply range, and the power supply priority index Y of the power plant is not optimized at this time; When d>d0, the distance between the two power plants is determined to be a non-power supply range. At this time, the power supply priority index Y of the power plant is optimized. After optimization, the power supply priority index of the power plant is Yy, and Yy=0.3×R+0.3×C+0.3×Fi-0.1×d is set; When optimizing the distance d between the two plants, the intelligent optimization scheduling module compares the line impedance Z and the line capacity G with the preset line impedance Z0 and the preset line capacity G0, judges the line impedance range and the line capacity level according to the comparison result, and optimizes the distance d between the two plants according to the judgment result, wherein: When Z≤Z0 and G≥G0, it is determined that the line impedance range is small, the line capacity is high, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z ≤ Z0 and G < G0, it is determined that the line impedance range is small, the line capacity is at a low level, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z > Z0 and G ≥ G0, it is determined that the line impedance range is large, the line capacity is at a high level, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z > Z0 and G < G0, it is determined that the line impedance range is large, the line capacity is at a low level, and the line transmission efficiency is not in the ideal range. At this time, the distance d between the two plants is optimized, and the optimized distance between the two plants is the weighted distance of the line , set , where k1 and k2 are weighting coefficients, and k1 + k2 = 1.

[0041] Specifically, the intelligent scheduling index refers to the comprehensive index used to measure and optimize the performance in the power generation scheduling process. The historical failure frequency F refers to the average number of failures that occur in a power plant over a past period of time. The mean time to repair MTTR refers to the average time required to restore normal operation from the time of equipment failure. The reliability index refers to the index used to measure the operating ability of a power plant. The fuel cost Cf refers to the total cost of fuel consumed by a power plant for power generation. The operation and maintenance cost Cm refers to the expenses required for the daily operation and equipment maintenance of a power plant. The equipment depreciation cost Cd refers to the cost of value reduction due to equipment aging and wear. The start-up time index Is refers to the time required to measure the power plant from the shutdown state to the normal power generation state. Set , and 0 < Is < 1. The shortest start-up time in the power plant is Tmin, the longest is Tmax, and the start-up time of the power plant is Tstart. The shutdown time index Ip refers to the total time that the power plant stops generating electricity due to failures and maintenance. Set , and, 0 < Ip < 1. The shortest shutdown time in the power plant is T’min, the longest is T’max, and the shutdown time of the power plant is Tstop. The start-up success rate Ss refers to the probability of successful start-up when the power plant attempts to start. Set , Sc is the success rate of power generation equipment startup, Sq is the total number of power generation equipment startups, the flexibility index Fi refers to the ability of the power plant to adapt to changes in power grid demand, the power plant power supply optimization index Y refers to the power plant power supply performance and efficiency, the preset power plant power supply best priority index Y0 refers to a pre-set standard value, which is used to compare with the power plant power supply optimization index Y. This embodiment does not limit the value of the preset power plant power supply best priority index Y0. Relevant technicians in this field can freely set it according to actual conditions, and only need to meet the requirements of comparison with the power plant power supply optimization index Y. For example, the value of the preset power plant power supply best priority index Y0 can be set to 0.7. The power supply priority of the power plant refers to the division of the power supplied by the power plant. level, the power supply of the faulty power plant refers to the process of restoring power supply as soon as possible when a power plant fails, the intelligent scheduling refers to the use of information technology and algorithms to automatically and intelligently manage and schedule the power resources in the power grid, the faulty power plant refers to a power plant that cannot generate electricity normally due to an abnormal situation, the distance d between the two power plants refers to the straight-line distance between the two power plants, and the preset distance d0 between the two power plants refers to the distance used to determine whether the distance between the two power plants is within an acceptable range. This embodiment does not limit the range of the preset distance d0 between the two plants. Relevant technical personnel in this field can freely set it according to actual conditions, as long as it meets the need to determine whether the distance between the two power plants is within an acceptable range. For example, the range of the preset distance d0 between the two power plants can be set to 50km -200km, the distance range between the two power plants refers to the relative positional relationship between the two power plants, the preset line impedance Z0 refers to the value used to determine whether the actual line impedance Z is within an acceptable range, and the present embodiment does not limit the range of the preset line impedance Z0. Relevant technical personnel in this field can freely set it according to actual conditions, and only need to meet the need to determine whether the actual line impedance Z is within an acceptable range. For example, the range of the preset line impedance Z0 can be set to 50Ω-200Ω, and the preset line capacity G0 refers to the value used to determine whether the actual line capacity G meets the requirements. The present embodiment does not limit the level of the preset line capacity G0. Relevant technical personnel in this field can freely set it according to actual conditions, and only need to meet the need to determine whether the actual line capacity G meets the requirements. For example, the level of the preset line capacity G0 can be set to a high voltage level of 100MW -500MW, the line impedance range refers to the range of line impedance actually measured and calculated, the line capacity level refers to the power range that the line can safely transmit determined based on the physical characteristics of the line and the operating environment conditions, the line transmission efficiency refers to the ratio of the actual transmitted electric energy to the theoretical transmitted electric energy when electric energy is transmitted from one end to the other end, and the weighting coefficient refers to the coefficient for weighting the distance.

[0042] Specifically, in the intelligent optimization scheduling module, when optimizing the intelligent scheduling of the power plant, the intelligent scheduling of the power plant is optimized through the application of the intelligent optimization scheduling module, thereby improving the flexibility and accuracy of power scheduling, thereby improving the overall transmission efficiency and stability of the power plant.

[0043] Specifically, when the decision-making execution module makes a decision to execute the intelligent dispatch plan, it generates an intelligent dispatch instruction through the real-time status of the power generation equipment and the intelligent dispatch strategy, feeds back the execution status of the intelligent dispatch instruction to the control center, obtains feedback information, judges the execution effect of the intelligent dispatch instruction according to the feedback information, and makes a decision according to the judgment result, wherein: When the execution of the intelligent scheduling instruction is consistent with the intelligent scheduling strategy, the execution effect is determined to be good, and the decision is executed according to the intelligent scheduling plan; When the execution of the intelligent scheduling instruction is inconsistent with the intelligent scheduling strategy, the execution effect is determined to be poor, and the decision is not executed according to the intelligent scheduling plan. The intelligent scheduling strategy is analyzed and adjusted through feedback information.

[0044] Specifically, the intelligent dispatching plan refers to the power dispatching arrangement according to the power system, the decision execution refers to the process of executing the intelligent dispatching instructions by the intelligent dispatching plan, the real-time status of the power generation equipment refers to the operating status of the power generation equipment of the power plant at the current moment, the intelligent dispatching instructions refer to the power dispatching instructions generated according to the real-time status of the power system and the intelligent dispatching strategy, the feedback information refers to the execution results and status information obtained from the power plant, the execution effect refers to the actual execution result of the intelligent dispatching instructions in the power plant, the execution status of the dispatchable instructions refers to the actual execution status of the intelligent dispatching instructions in the power plant, and the analysis and adjustment refers to the process of continuously analyzing and improving the intelligent dispatching strategy. This embodiment does not limit the analysis and adjustment method. Relevant technical personnel in this field can freely set it according to actual conditions, as long as the needs for decision-making execution of the intelligent dispatching plan are met. For example, the analysis and adjustment method can be set to big data intelligent analysis and adjustment.

[0045] Specifically, in the decision-making execution module, when making decisions and executing the intelligent dispatching plan, the execution and management of power dispatching is realized through real-time response, strategy matching, execution effect evaluation and feedback, as well as adjustment and optimization, so as to improve the efficiency and reliability of power dispatching.

[0046] See also Figure 2 As shown, it is a flow chart of the power grid optimization control method based on artificial intelligence in this embodiment, and the method includes: Step S1, real-time collection of power generation data; Step S2, processing the power generation data to obtain actual power generation data, which includes the real-time status of the power generation equipment, the location coordinates of the data control center, the location coordinates of the power plant that has been shut down, the longitude and latitude of the locations of the two plants, the line impedance and the line capacity; Step S3, calculating the communication distance according to the location coordinates of the data control center and the location coordinates of the power plant with power outage, judging the data communication type according to the communication distance, and transmitting the actual power generation data to the data control center in the intelligent decision-making module of the control center according to the data communication type; Step S4, evaluating and predicting the actual power generation data according to the energy resource evaluation model to obtain evaluation prediction data, which includes the evaluation prediction data accuracy, the total power supply and total power demand of each power plant; Step S5, monitoring the power load in real time according to the evaluation prediction data, obtaining the density of the power load, and adjusting the output power of the power generation equipment according to the density of the power load; Step S6, adjusting the power load according to the total power demand, and dispatching the power of the energy storage end according to the total power supply of each power plant; Step S7, calculating the intelligent scheduling index according to the evaluation prediction data; Step S8, calculate the power supply optimization index of the power plant according to the intelligent scheduling index, and intelligently schedule the power supply of the faulty power plant according to the power supply optimization index of the power plant to generate an intelligent scheduling strategy; Step S9, calculating the distance between the two plants according to the longitude and latitude of the two plants, optimizing the power supply optimization index of the power plant according to the distance between the two plants, and optimizing the distance between the two plants according to the line impedance and the line capacity; Step S10: making decisions and executing the intelligent dispatching plan according to the real-time status of the power generation equipment and the intelligent dispatching strategy.

[0047] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A power grid optimization control system based on artificial intelligence, characterized in that: The system comprises: Data acquisition module, used to collect power generation data in real time; A data processing module is used to process the power generation data to obtain actual power generation data, which includes the real-time status of the power generation equipment, the location coordinates of the data control center, the location coordinates of the power plant that has been shut down, the longitude and latitude of the locations of the two plants, the line impedance and the line capacity; A data transmission module, used to calculate the communication distance according to the location coordinates of the data control center and the location coordinates of the power plant with power outage, and to determine the data communication type according to the communication distance, and to transmit the actual power generation data to the data control center in the intelligent decision-making module of the control center according to the data communication type; The intelligent decision-making module of the control center is used to evaluate and predict the actual power generation data according to the energy resource evaluation model to obtain evaluation prediction data, which includes the evaluation prediction data accuracy, the total power supply and total power demand of each power plant, and is also used to monitor the power load in real time according to the evaluation prediction data to obtain the density of the power load, and adjust the output power of the power generation equipment according to the density of the power load, and is also used to adjust the power load according to the total power demand, and is also used to dispatch the power of the energy storage end according to the total power supply of each power plant; An intelligent optimization scheduling module is used to calculate the intelligent scheduling index according to the evaluation prediction data, and is also used to calculate the power supply optimization index of the power plant according to the intelligent scheduling index, and intelligently schedule the power supply of the faulty power plant according to the power supply optimization index of the power plant, and generate an intelligent scheduling strategy, and is also used to calculate the distance between the two plants according to the longitude and latitude of the locations of the two plants, and optimize the power supply optimization index of the power plant according to the distance between the two plants, and is also used to optimize the distance between the two plants according to the line impedance and the line capacity; The decision-making execution module is used to make decisions and execute the intelligent scheduling plan according to the real-time status of the power generation equipment and the intelligent scheduling strategy.

2. The power grid optimization control system based on artificial intelligence according to claim 1 is characterized in that: When the data transmission module transmits the actual power generation data, it calculates the communication distance L according to the location coordinates (x2, y2) of the data control center and the location coordinates (x1, y1) of the power plant that has power outages, and sets , and compare the communication distance L with the preset communication distance L0, and judge the data communication type according to the comparison result, wherein: When L≤L0, the data communication type is determined to be short-distance communication, and the actual power generation data is transmitted to the data control center in the intelligent decision-making module of the control center according to the Ethernet data transmission method; When L>L0, the data communication type is determined to be long-distance communication, and the actual power generation data is transmitted to the data control center in the intelligent decision-making module of the control center according to the 4G / 5G wireless communication method.

3. The power grid optimization control system based on artificial intelligence according to claim 1 is characterized in that: When evaluating and predicting the actual power generation data, the intelligent decision-making module of the control center evaluates and predicts the actual power generation data according to the energy resource evaluation and prediction model to obtain evaluation and prediction data, which includes the evaluation and prediction data accuracy rate N, the total power supply Qg and the total power demand Q of each power plant, and compares the evaluation and prediction data accuracy rate N in the evaluation and prediction data with the preset evaluation and prediction data accuracy rate N0, judges the accuracy of the evaluation and prediction data according to the comparison result, and optimizes the energy resource evaluation and prediction model according to the judgment result, wherein: When N≥N0, the prediction accuracy of the energy resource assessment prediction model is determined to be high accuracy, and the energy resource assessment prediction model is not optimized at this time; When N<N0, the prediction accuracy of the energy resource assessment prediction model is low. At this time, the energy resource assessment prediction model is optimized, and different energy resource assessment prediction models are used to predict the actual power generation data to obtain the predicted power generation power P1, P2 and P3. The weighted average power P is calculated based on the predicted power generation power P1, P2 and P3, and the setting , where ω1, ω2 and ω are the performance weight coefficients of the energy resource assessment prediction model on the validation set, and ω1+ω2+ω3=1.

4. The power grid optimization control system based on artificial intelligence according to claim 3 is characterized in that: The intelligent decision-making module of the control center obtains the power load status when monitoring the power load M in real time, calculates the power load M according to the time factor D, the seasonal factor S, the hour period H and the weather factor T, and sets , where β1, β2, β3 and β4 are the regression coefficients of each factor, and β1+β2+β3+β4=1, is the error term, the power load M is compared with the preset power load M0, the density of the power load is judged according to the comparison result, and the output power of the power generation equipment is adjusted according to the judgment result, where: When M≤M0, the power load is judged to be low load and the power supply load is sufficient. At this time, the surplus can enter the energy storage end for energy storage, and the output power of the power generation equipment is not adjusted; When M>M0, the power load is determined to be high load and the power supply load is insufficient. At this time, the surplus cannot enter the energy storage end for energy storage, and the output power of the power generation equipment is adjusted.

5. The power grid optimization control system based on artificial intelligence according to claim 4 is characterized in that: When the intelligent decision-making module of the control center adjusts the power load M, it calculates the average value of the power load according to the monitoring data. Calculate and set , where n is the time interval within [t0, tn], i is the time node, is the power load value at different time nodes, and the total power demand Q is calculated according to the average value of the power load, setting Q= × (tn-t0), compare the total power demand Q with the preset total power demand Q0, judge the controllable range of the total power demand Q according to the comparison result, and adjust the power load M according to the judgment result, where: When Q≤Q0, the control range of the total power demand Q is determined to be within the controllable range, and M is not adjusted at this time; When Q>Q0, it is determined that the control range of the total power demand Q is uncontrollable. At this time, the power load M is adjusted. After adjustment, the power load is M1, and M1=1.28×M is set.

6. The power grid optimization control system based on artificial intelligence according to claim 5 is characterized in that: When dispatching the energy storage end power, the control center intelligent decision module obtains the total power supply Qg of each power plant according to the evaluation prediction data, compares the total power supply Qg of each power plant with the total power demand Q, judges the total power demand Q according to the comparison result, and dispatches the energy storage end power according to the judgment result, wherein: When Qg≥Q, it is determined that the total power supply of the power plant meets the total power demand Q at this time, and the power at the energy storage end is not dispatched; When Qg<Q, it is determined that the total power supply of the power plant does not meet the total power demand Q at this time, and the power at the energy storage end is dispatched, and the power supply at the energy storage end is dispatched to Qg1, and Qg1=Q-Qg is set.

7. The power grid optimization control system based on artificial intelligence according to claim 1 is characterized in that: When the intelligent optimization scheduling module performs machine calculation on the intelligent scheduling index, it calculates the reliability index R according to the historical failure frequency F and the mean repair time MTTR of the power plant, and sets , calculate the total power generation cost index C according to the fuel cost Cf, operation and maintenance cost Cm and equipment depreciation cost Cd, set C=Cf+Cm+Cd, and calculate the flexibility index Fi according to the start time index Is, stop time index Ip and start success rate Ss, set Fi=0.3×Is+0.3×Ip+0.4×Ss, and output the reliability index R, total power generation cost index C and flexibility index Fi as intelligent scheduling indicators; When calculating the power supply optimization index Y of the power plant, the intelligent optimization scheduling module calculates the power supply priority index Y of the power plant according to the reliability index R, the power generation cost index C and the flexibility index Fi, sets Y=0.3×R+0.3×C+0.3×Fi-0.1, compares the power supply priority index Y of the power plant with the preset power supply optimal priority index Y0 of the power plant, judges the power supply priority of the power plant according to the comparison result, and intelligently schedules the power supply of the faulty power plant according to the judgment result, and generates an intelligent scheduling strategy, wherein: When Y>Y0, the power plant is determined to be a first-level priority power supply plant. When meeting the needs of the faulty power plant, the power plant will give priority to intelligently dispatching the power supply to the faulty power plant; When Y=Y0, the power plant is determined to be a second-level priority power plant. When the resources of the first-level priority power plant cannot meet the needs of the faulty power plant, the power plant intelligently dispatches the power supply to the faulty power plant. When Y<Y0, the power plant is determined to be a third-level priority power supply plant. When both the first-level and second-level priority power supply plants cannot meet the needs of the faulty power plant, the power plant intelligently dispatches the power supply to the faulty power plant.

8. The power grid optimization control system based on artificial intelligence according to claim 7 is characterized in that: When the intelligent optimization scheduling module optimizes the power supply optimization index Y of the power plant, it calculates the distance d between the two plants by the longitude and latitude of the two plants and sets , where R is the radius of the earth, φ1 and φ2 are longitudes, λ1 and λ2 are latitudes, and the distance d between the two plants is compared with the preset distance d0 between the two plants. The distance range between the two power plants is judged according to the comparison result, and the power supply priority index Y of the power plant is optimized according to the judgment result, where: When d≤d0, the distance range between the two power plants is determined to be a power supply range, and the power supply priority index Y of the power plant is not optimized at this time; When d>d0, the distance between the two power plants is determined to be a non-power supply range. At this time, the power supply priority index Y of the power plant is optimized. After optimization, the power supply priority index of the power plant is Yy, and Yy=0.3×R+0.3×C+0.3×Fi-0.1×d is set; When optimizing the distance d between the two plants, the intelligent optimization scheduling module compares the line impedance Z and the line capacity G with the preset line impedance Z0 and the preset line capacity G0, judges the line impedance range and the line capacity level according to the comparison result, and optimizes the distance d between the two plants according to the judgment result, wherein: When Z≤Z0 and G≥G0, it is determined that the line impedance range is small, the line capacity is high, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z≤Z0 and G<G0, it is determined that the line impedance range is small, the line capacity is low, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z>Z0 and G≥G0, it is determined that the line impedance range is large, the line capacity is high, and the line transmission efficiency is in the ideal range. At this time, the distance d between the two plants is not optimized; When Z>Z0 and G<G0, it is determined that the line impedance range is large, the line capacity is low, and the line transmission efficiency is not ideal. At this time, the distance d between the two plants is optimized. After optimization, the distance between the two plants is the line weighted distance ,set up , where k1 and k2 are weighting coefficients, and k1+k2=1.

9. The power grid optimization control system based on artificial intelligence according to claim 1 is characterized in that: When the decision-making execution module makes a decision to execute the intelligent dispatch plan, it generates an intelligent dispatch instruction through the real-time status of the power generation equipment and the intelligent dispatch strategy, feeds back the execution status of the intelligent dispatch instruction to the control center, obtains feedback information, judges the execution effect of the intelligent dispatch instruction according to the feedback information, and makes a decision according to the judgment result, wherein: When the execution of the intelligent scheduling instruction is consistent with the intelligent scheduling strategy, the execution effect is determined to be good, and the decision is executed according to the intelligent scheduling plan; When the execution of the intelligent scheduling instruction is inconsistent with the intelligent scheduling strategy, the execution effect is determined to be poor, and the decision is not executed according to the intelligent scheduling plan. The intelligent scheduling strategy is analyzed and adjusted through feedback information.

10. An artificial intelligence-based power grid optimization control method applied to any one of claims 1 to 9, characterized in that: The method comprises: Step S1, real-time collection of power generation data; Step S2, processing the power generation data to obtain actual power generation data, which includes the real-time status of the power generation equipment, the location coordinates of the data control center, the location coordinates of the power plant that has been shut down, the longitude and latitude of the locations of the two plants, the line impedance and the line capacity; Step S3, calculating the communication distance according to the location coordinates of the data control center and the location coordinates of the power plant with power outage, judging the data communication type according to the communication distance, and transmitting the actual power generation data to the data control center in the intelligent decision-making module of the control center according to the data communication type; Step S4, evaluating and predicting the actual power generation data according to the energy resource evaluation model to obtain evaluation prediction data, which includes the evaluation prediction data accuracy, the total power supply and total power demand of each power plant; Step S5, monitoring the power load in real time according to the evaluation prediction data, obtaining the density of the power load, and adjusting the output power of the power generation equipment according to the density of the power load; Step S6, adjusting the power load according to the total power demand, and dispatching the power of the energy storage end according to the total power supply of each power plant; Step S7, calculating the intelligent scheduling index according to the evaluation prediction data; Step S8, calculate the power supply optimization index of the power plant according to the intelligent scheduling index, and intelligently schedule the power supply of the faulty power plant according to the power supply optimization index of the power plant to generate an intelligent scheduling strategy; Step S9, calculating the distance between the two plants according to the longitude and latitude of the two plants, optimizing the power supply optimization index of the power plant according to the distance between the two plants, and optimizing the distance between the two plants according to the line impedance and the line capacity; Step S10: making decisions and executing the intelligent dispatching plan according to the real-time status of the power generation equipment and the intelligent dispatching strategy.

Images