Intelligent thermal power generation dispatching method and system for self-adaptive load regulation

Abstract

The invention discloses an intelligent thermal power generation scheduling method and system for adaptive load regulation, and relates to the technical field related to power generation scheduling management, and the method comprises the steps: carrying out the dynamic sensing of a power supply demand, and building a sensing demand; dynamic modeling is conducted on the thermal power generation equipment, and a power generation fitting model is constructed; acquiring a real-time energy storage state of the energy storage equipment, generating real-time power generation data through the power generation fitting model, performing adaptive analysis of a sensing demand, and establishing an adaptive deviation; thermal power generation optimization scheduling is executed through the multi-target dynamic optimization scheduling network, and a thermal power generation optimization scheduling result is generated. The technical problems that in the prior art, complex and changeable power supply requirements are difficult to accurately adapt, real-time data of thermal power generation and energy storage equipment cannot be effectively utilized, and then power generation efficiency is reduced, power supply stability is poor and energy is wasted are solved, power supply and demand balance is achieved, and power generation efficiency is improved. The technical effects of improving the power supply stability, improving the power generation efficiency and reducing the energy waste are achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to power generation dispatching management, and specifically to an intelligent thermal power generation dispatching method and system with adaptive load regulation. Background Art

[0002] In today's power industry, power demand is showing a complex and changeable trend. Traditional thermal power generation scheduling methods are often difficult to accurately adapt to the complex and changeable power demand. The power consumption behavior of power users is diversified and dynamic, which leads to power demand fluctuations at any time. On the one hand, it is difficult to accurately and smoothly fit the short-term power demand, resulting in poor stability of power supply during peak and valley periods, frequent oversupply or shortage of power, which not only causes energy waste, but also may affect the reliable operation of the power grid; on the other hand, the lack of accuracy in the prediction of long-term total power supply makes it impossible for power generation companies to make reasonable arrangements when planning the investment and operation of power generation equipment, and it is difficult to adapt to the long-term supply and demand changes in the power market. At the same time, the performance of thermal power generation equipment will be affected by many factors during operation, such as fuel quality, equipment aging, etc. If these equipment cannot be dynamically modeled and the equipment data cannot be updated in real time, the real-time data of the equipment cannot be timely and comprehensively integrated into the power generation scheduling decision, resulting in the inability of power generation equipment to operate in the optimal state, low power generation efficiency, and increased equipment loss; in addition, the traditional thermal power generation scheduling mode fails to effectively utilize the real-time energy storage status information of energy storage equipment, so that the advantages of energy storage equipment cannot be fully utilized.

[0003] Therefore, at the current stage, relevant technologies have technical problems such as difficulty in accurately adapting to complex and changeable power supply demands and inability to effectively utilize real-time data of thermal power generation and energy storage equipment, which in turn leads to reduced power generation efficiency, poor power supply stability and energy waste. Summary of the invention

[0004] The present application solves the technical problems in the prior art that it is difficult to accurately adapt to complex and changeable power supply demands and cannot effectively utilize the real-time data of thermal power generation and energy storage equipment, which leads to reduced power generation efficiency, poor power supply stability and energy waste, by providing an intelligent thermal power generation scheduling method and system with adaptive load regulation. The application achieves a balance between power supply and demand and achieves the technical effects of improving the stability of power supply, increasing power generation efficiency and reducing energy waste.

[0005] The present application provides an intelligent thermal power generation scheduling method with adaptive load regulation, the method comprising: dynamically sensing power supply demand and establishing sensed demand, the sensed demand comprising a first sensed demand and a second sensed demand, the first sensed demand being a short-term stable fitting demand, the second sensed demand being a long-term total power supply forecast demand; dynamically modeling thermal power generation equipment, constructing a power generation fitting model, and sharing real-time equipment data of the thermal power generation equipment to the power generation fitting model; acquiring the real-time energy storage status of the energy storage equipment, generating real-time power generation data through the power generation fitting model, performing adaptation analysis of the sensed demand based on the real-time power generation data and the real-time energy storage status, and establishing an adaptation deviation; taking the adaptation deviation as the optimization target, executing thermal power generation optimal scheduling through a multi-objective dynamic optimization scheduling network, and generating a thermal power generation optimal scheduling result.

[0006] In a possible implementation, the intelligent thermal power generation scheduling method with adaptive load regulation also performs the following processing: obtaining a first perceived demand of the perceived demand, identifying real-time power generation data, the power supply deviation of the real-time energy storage state, and the timing response deviation based on the first perceived demand, and establishing a first adaptation deviation; after obtaining the second perceived demand of the perceived demand, reading the equipment task of the thermal power generation equipment, performing adaptation analysis of the long-term demand based on the equipment task, the real-time energy storage state, and the second perceived demand, establishing a second adaptation deviation, and establishing an adaptation deviation with the first adaptation deviation and the second adaptation deviation.

[0007] In a possible implementation, the intelligent thermal power generation scheduling method with adaptive load regulation also performs the following processing: performing a short-term stable fitting evaluation on the first perceived demand and establishing a fitting fluctuation coefficient; configuring a heating quality default penalty target using the fitting fluctuation coefficient; obtaining the node performance of the thermal power generation equipment and establishing a load balancing target based on the node performance; establishing an economic cost target and a carbon emission constraint target, and using the default penalty target, the load balancing target, the economic cost target and the carbon emission constraint target to construct the multi-objective dynamic optimization scheduling network to perform optimal scheduling of thermal power generation.

[0008] In a possible implementation, the intelligent thermal power generation scheduling method with adaptive load regulation further performs the following processing: the multi-objective dynamic optimization scheduling network is as follows: ; in, Characterize the multi-objective dynamic optimization function, Characterize the adaptation deviation of the regulation adaptation target, Characterize the default penalty target, ; is the penalty objective function for heat quality breach, representing The degree of penalty for breach of contract caused by the deviation of heat supply stability adaptation at all times, is the fitted volatility coefficient, Characterizes the first adaptation deviation, which is the deviation between the short-term heating system load supply and demand. Characterizes the allowable deviation threshold, Characterize the load balancing target, ; is the total number of nodes, Representing any node, Characterization The time of the node Actual power generation, Characterization The rated power generation capacity of each node, i.e., node performance, is the total power generation capacity of thermal power generation equipment, Characterizes the total rated capacity of all nodes, For the The node weight factor of the node, Characterize economic cost targets, ;in, For the Nodes at time The fuel cost, For the The start-up and stop costs of each node, Characterization Nodes at time Operation and maintenance costs, To meet carbon emission constraints, ; is the carbon emission penalty coefficient, For thermal power generation equipment at all times The actual total carbon dioxide emissions, is the maximum emission limit, , , , They are the balance weight coefficients of the default penalty target, load balancing target, economic cost target, and carbon emission constraint target respectively.

[0009] In a possible implementation, the intelligent thermal power generation scheduling method with adaptive load regulation also performs the following processing: performing a fault probability analysis on the thermal power generation equipment to generate a fault probability evaluation result; establishing a protection energy storage plan using the fault probability evaluation result; and compensating for the thermal power generation optimal scheduling result through the protection energy storage plan to perform control management of the thermal power generation equipment.

[0010] In a possible implementation, the intelligent thermal power generation scheduling method with adaptive load regulation also performs the following processing: establishing mapping power generation data with the thermal power generation optimal scheduling results; using the mapped power generation data to establish a timing warning database, and performing actual power generation abnormality warning of thermal power generation equipment based on the timing warning database.

[0011] In a possible implementation, the intelligent thermal power generation scheduling method with adaptive load regulation also performs the following processing: obtaining the load fluctuation rate, and establishing a first duration constraint based on the fluctuation rate; obtaining the energy storage state of the energy storage device, and establishing a second duration constraint based on the energy storage state; using the first duration constraint and the second duration constraint to construct a short-term window and a long-term window to establish perceived demand.

[0012] The present application also provides an intelligent thermal power generation scheduling system with adaptive load regulation, the system comprising: a perception demand establishment module, which is used to dynamically perceive the power supply demand and establish the perception demand, the perception demand comprising a first perception demand and a second perception demand, the first perception demand being a short-term stable fitting demand, and the second perception demand being a long-term total power supply forecast demand; a power generation fitting model construction module, which is used to dynamically model the thermal power generation equipment, construct a power generation fitting model, and share the real-time equipment data of the thermal power generation equipment to the power generation fitting model; an adaptation deviation establishment module, which is used to obtain the real-time energy storage status of the energy storage equipment, generate real-time power generation data through the power generation fitting model, perform adaptation analysis of the perception demand based on the real-time power generation data and the real-time energy storage status, and establish an adaptation deviation; a thermal power generation optimal scheduling module, which is used to use the adaptation deviation as the optimization target, perform thermal power generation optimal scheduling through a multi-objective dynamic optimization scheduling network, and generate a thermal power generation optimal scheduling result.

[0013] It is intended to dynamically sense the power demand and establish the sensed demand through the intelligent thermal power generation scheduling method and system with adaptive load regulation proposed in this application; dynamically model the thermal power generation equipment and build a power generation fitting model; obtain the real-time energy storage status of the energy storage equipment, generate real-time power generation data through the power generation fitting model, perform adaptation analysis of the sensed demand, and establish adaptation deviation; perform thermal power generation optimal scheduling through a multi-objective dynamic optimization scheduling network to generate thermal power generation optimal scheduling results. It solves the technical problems existing in the prior art that it is difficult to accurately adapt to complex and changeable power supply needs and cannot effectively utilize the real-time data of thermal power generation energy storage equipment, which leads to a decrease in power generation efficiency, poor power supply stability and energy waste, and achieves a balance between power supply and demand, and achieves the technical effects of improving the stability of power supply, improving power generation efficiency and reducing energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic flow chart of an intelligent thermal power generation scheduling method with adaptive load regulation provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of the structure of an intelligent thermal power generation scheduling system with adaptive load regulation provided in an embodiment of the present application.

[0017] Explanation of the reference numerals: demand perception establishing module 10 , power generation fitting model building module 20 , adaptation deviation establishing module 30 , thermal power generation optimal scheduling module 40 . DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The embodiment of the present application provides an intelligent thermal power generation scheduling method with adaptive load regulation, such as Figure 1 As shown, the method includes: Step S100, dynamically sense the power supply demand and establish the sensed demand, wherein the sensed demand includes a first sensed demand and a second sensed demand, wherein the first sensed demand is a short-term stable fitting demand, and the second sensed demand is a long-term total power supply forecast demand.

[0022] Preferably, during the operation of the power system, the power supply demand is constantly changing due to the influence of many factors such as user power consumption behavior, industrial production changes, weather factors, etc. Dynamic perception of power supply demand is to collect power grid data information related to power supply demand in real time through various monitoring equipment and data acquisition equipment, such as power consumption data in different regions and different time periods, power load changes in different industries, etc., in order to obtain power supply demand of the power grid. Specifically, user-side data collection is carried out, including the widespread installation of smart meters at various users. Smart meters in residential users' homes can record the power consumption at every moment, daily cumulative power consumption and other data in real time, such as the power changes when various household appliances are used intensively from 7 to 9 pm; in commercial places, such as shopping malls and office buildings, smart meters can collect power consumption data by area and floor to understand the peak power consumption in different areas during business hours; industrial users use special industrial power monitoring equipment to record in detail the start-up and shutdown time of large-scale production equipment, as well as the power consumption of different production processes, such as the high power consumption period during the blast furnace smelting process in steel plants. To monitor the operation data of the power grid, such as at the connection points of substations and transmission lines, various sensors are deployed. Among them, voltage sensors monitor the node voltage at all times to ensure that it is stable within a reasonable range to prevent excessively high or low voltage from affecting electrical equipment; current sensors accurately measure the current passing through the node to reflect the load conditions of power transmission; power sensors obtain active power and reactive power to provide a basis for analyzing the effective use and loss of electricity.

[0023] Preferably, based on the power grid data information obtained by dynamic perception, trend analysis is performed to determine the long-term change trend, and feature extraction is performed to determine the power supply demand characteristics and change patterns, and then the perceived demand is constructed, including the first perceived demand and the second perceived demand, wherein the first perceived demand is the short-term stable fitting demand, which is mainly the fluctuation of power supply demand in the short term (for example, different periods of a day, peak and trough periods of a week, etc.). Specifically, due to the users' daily routines and industrial production arrangements, the power demand will have large fluctuations in a short period of time, such as the peak period of residential electricity consumption in the morning and evening, the start and shutdown periods of factories, etc. The short-term stable fitting demand aims to predict and fit the power demand curve in a short period of time as accurately as possible through the analysis and processing of these short-term data, so that the power generation side can adjust the power generation in time according to the prediction results, maintain the stability of power supply, avoid oversupply or shortage of power supply, and ensure the stable operation of the power grid. The second perceived demand is the demand for long-term total power supply forecasting, which focuses on predicting the total power supply over a long period of time in the future (such as one month, one year or even several years). Specifically, it comprehensively considers the regional economic development trend, population growth, the construction and commissioning of new large-scale power consumption projects, etc. to make accurate long-term total power supply forecasts to adapt to the long-term supply and demand changes in the electricity market and avoid resource losses caused by insufficient or excess power generation capacity.

[0024] Furthermore, step S100 also includes step S110, obtaining the fluctuation rate of the load, and establishing a first duration constraint based on the fluctuation rate; step S120, obtaining the energy storage state of the energy storage device, and establishing a second duration constraint based on the energy storage state; step S130, using the first duration constraint and the second duration constraint to construct a short-term window and a long-term window to establish a perceived demand.

[0025] Preferably, by analyzing the real-time data collected by smart meters, sensors and other equipment in the power grid, the increase or decrease in the power load per unit time is calculated, and then the load fluctuation rate is determined, wherein the load fluctuation rate refers to the speed of change of the power load within a certain period of time. For example, within a certain period of time, the power load increases from 100 MW to 120 MW in 1 hour, and the load fluctuation rate is 20 MW / hour; then the first time constraint is determined according to the obtained load fluctuation rate, that is, if the load fluctuation rate is large, it means that the power demand changes rapidly. In order to ensure the stability and reliability of power supply, a shorter time is required to adjust the output of the power generation equipment to adapt to the change in load. For example, when the load fluctuation rate reaches a certain threshold, it may be required to complete the output adjustment of the power generation equipment within 15 minutes, and 15 minutes is the first time constraint; conversely, if the load fluctuation rate is small, the first time constraint can be relatively long.

[0026] Preferably, by monitoring parameters such as the power level and charging and discharging status of the energy storage device, the energy storage status of the energy storage device can be understood in real time. For example, the total capacity of the energy storage device is 1000 kWh, the current remaining power is 500 kWh, and it is in a charging state, which is an energy storage state of the energy storage device; then a second time constraint is established based on the energy storage state of the energy storage device, that is, if the energy storage device has sufficient power, then when responding to changes in power load, there is a relatively long time to make scheduling arrangements, wherein the energy storage device has sufficient capacity to balance power supply and demand within a certain period of time. For example, when the energy storage device has sufficient power, it may be allowed to decide whether to use the energy storage device for discharge or charging operations based on the power load within 1 hour, and 1 hour is the second time constraint. On the contrary, if the energy storage device has a low power level, in order to ensure that it can play a role at a critical time, the second time constraint will be shorter, and may require the relevant scheduling decision to be completed within 30 minutes.

[0027] Preferably, the short-term window is determined by comprehensively considering the first duration constraint and the second duration constraint, wherein the short-term window is mainly used to cope with short-term fluctuations in power load and ensure the stability of power supply. Specifically, the duration of the short-term window will be determined based on the comprehensive situation of the load fluctuation rate and the energy storage state of the energy storage device, that is, if the load fluctuation rate is large and the energy storage device has sufficient power, the short-term window may be relatively short, such as 30 minutes to 1 hour, so as to quickly respond to load changes and use the energy storage device for adjustment; if the load fluctuation rate is small and the energy storage device is not particularly sufficient, the short-term window may be appropriately extended to 1-2 hours. The long-term window is determined by comprehensively considering the first duration constraint and the second duration constraint, wherein the duration of the long-term window is usually in days, weeks or months. For example, if the load fluctuation rate shows a certain regularity over a long period of time and the energy storage state of the energy storage device is relatively stable, the long-term window may be set to one week. Within this time window, the power system can formulate power generation plans and arrange equipment maintenance based on the predicted load change trend and the available capacity of the energy storage device. At the same time, the long-term window will also consider the supply and demand changes in the power market to ensure the long-term stable operation of the power system, thereby achieving the optimal allocation of power resources. Using the first time constraint and the second time constraint to construct short-term windows and long-term windows can establish perceived demand in a more comprehensive and detailed manner, enabling the power system to flexibly adjust its operating strategy according to changes in demand at different time scales, thereby improving the stability and reliability of power supply.

[0028] Step S200 , dynamically modeling the thermal power generation equipment, constructing a power generation fitting model, and sharing the real-time equipment data of the thermal power generation equipment to the power generation fitting model.

[0029] Preferably, dynamic modeling is performed on thermal power generation equipment, wherein the thermal power generation equipment may include boilers, steam turbines, generators, etc. Dynamic modeling refers to establishing a mathematical model that can describe the dynamic behavior of thermal power generation equipment under different operating conditions. Specifically, the physical processes of the equipment (such as combustion, heat exchange, steam flow, and mechanical motion, etc.) are comprehensively considered. For example, a combustion model is established to describe the combustion of fuel in the boiler, including the combustion rate, heat release, etc.; a heat exchange model is established to calculate the heat absorption process of steam in the boiler and the heat release process in the steam turbine; a mechanical motion model is established to describe the rotation of the steam turbine rotor and the power generation process of the generator, etc., and various uncertain factors in the operation of the equipment are considered, such as changes in fuel quality, the influence of ambient temperature and humidity, etc., so that the model can more accurately reflect the actual operation of the equipment. Then, by analyzing and processing a large amount of historical operating data, a relationship model between power generation and various operating parameters is established. Specifically, the operating data of thermal power generation equipment under different operating conditions, including parameters such as fuel flow, steam pressure, temperature, speed and the corresponding power generation, are collected. Data fitting techniques, such as the least squares method and neural network algorithm, are used to find the best fitting function of various operating parameters and power generation, and then a power generation fitting model is established. The power generation can be quickly and accurately predicted based on the current operating parameters, so as to optimize the control and scheduling of the operation of thermal power generation equipment; finally, the real-time data of the thermal power generation equipment is transmitted to the power generation fitting model to reflect the operating status of the thermal power generation equipment. After receiving the real-time data, the power generation fitting model will update the parameters in the model according to these data, thereby adjusting the prediction results of the power generation in real time, so that the equipment is always in the best operating state, improving the power generation efficiency and the stability and reliability of the power grid operation.

[0030] Step S300, obtaining the real-time energy storage status of the energy storage device, generating real-time power generation data through the power generation fitting model, performing adaptation analysis of the perceived demand according to the real-time power generation data and the real-time energy storage status, and establishing an adaptation deviation.

[0031] Preferably, various sensors and monitoring devices installed on the energy storage device are used to collect relevant information of the energy storage device in real time, such as the current power level, charging and discharging status, battery health status, etc., so as to fully understand the actual energy storage situation of the energy storage device. For example, if the energy storage device is a lithium battery pack, the percentage of its remaining power, whether it is currently in the charging or discharging process, and the degree of battery aging, etc., are obtained to accurately reflect the real-time energy storage status of the energy storage device; the current real-time operating parameters of the thermal power generation equipment, such as fuel flow, steam temperature, pressure, etc., are input into the power generation fitting model, and the real-time power generation data such as the expected power generation power and power generation of the thermal power generation equipment at the current moment are calculated and output. For example, according to the real-time parameters such as the current steam pressure of 10MPa and the fuel flow of 50kg / h, the power generation fitting model calculates that the current power generation power is 500MW, that is, the real-time power generation data reflects the power generation of the thermal power generation equipment in the current state. The real-time power generation data and the real-time energy storage status are then compared with the established perceived needs for analysis, that is, to analyze whether the current power generation and energy storage conditions can meet the perceived needs and determine the degree of match between them, including whether the current real-time power generation can meet the power range specified in the short-term stable fitting needs, and whether the current energy storage status can cooperate with thermal power generation equipment to meet the long-term total power supply forecast needs in the future. For example, if the real-time power generation is 500MW, and the short-term stable fitting needs require that the power generation be stable between 450-550MW within the next hour, and the real-time energy storage status of the energy storage equipment shows that the power is sufficient and can provide certain power support when necessary to maintain the stability of the power generation, it is considered that the current situation meets the perceived needs to a certain extent. If the real-time power generation is too high or too low, or the power of the energy storage equipment is insufficient or excessive, it indicates a mismatch.

[0032] Preferably, the difference between the actual real-time power generation data and the real-time energy storage status and the perceived demand is then quantified to form an adaptation deviation, for example, the difference between the real-time power generation power and the power range specified in the short-term smooth fitting demand, or the difference between the power of the current energy storage device and the power required to meet the long-term total power supply forecast demand, etc., to intuitively reflect the gap between the actual operation of the current power supply system and the expected perceived demand, and then according to the size and direction of the adaptation deviation, corresponding measures can be taken, such as adjusting the operating parameters of the thermal power generation equipment to change the power generation power, or adjusting the charging and discharging strategy of the energy storage device to reduce the adaptation deviation, so that the power supply system can better meet the perceived demand, achieve stable supply and optimized configuration of electricity, and thus improve the stability and reliability of power supply.

[0033] Furthermore, step S300 also includes step S310, obtaining a first perceived demand of the perceived demand, identifying real-time power generation data, the power supply deviation of the real-time energy storage state, and the timing response deviation based on the first perceived demand, and establishing a first adaptation deviation; step S320, after obtaining the second perceived demand of the perceived demand, reading the equipment task of the thermal power generation equipment, performing adaptation analysis of the long-term demand based on the equipment task, the real-time energy storage state, and the second perceived demand, establishing a second adaptation deviation, and establishing an adaptation deviation with the first adaptation deviation and the second adaptation deviation.

[0034] Preferably, the first perceived demand (i.e., short-term stable fitting demand) of the perceived demand is obtained, and then the real-time power generation data (data such as the current actual power generation generated by the power generation fitting model) is compared with the corresponding power requirement in the first perceived demand. If the real-time power generation is higher than the power expected by the first perceived demand, there is a positive power supply deviation; conversely, if the real-time power generation is lower than the expected power, there is a negative power supply deviation; for example, the first perceived demand requires that the power generation be stable at 400MW in the next hour, and the real-time power generation data shows that the current power generation is 420MW, then the power supply deviation is +20MW. The first perceived demand also has requirements for the response time of the power generation and energy storage system. The real-time energy storage state reflects the available power, charging and discharging state, etc. of the energy storage device at the current moment. The changes in the real-time energy storage state and the real-time power generation data are compared and identified with the response time specified in the first perceived demand to obtain the timing response deviation. For example, when the power load suddenly increases, the first perceived demand may require the energy storage device to start discharging within 10 minutes to supplement the power gap. If the actual time for the energy storage device to start discharging exceeds 10 minutes, a timing response deviation is generated. A first adaptation deviation is established based on the power supply deviation and the timing response deviation. For example, different types of deviations are converted into a numerical value using weighted summation to represent the overall deviation degree between the current real-time power generation data and the real-time energy storage status and the first perceived demand.

[0035] Preferably, the second perceived demand (i.e., the long-term total power supply forecast demand) is obtained, and then the equipment tasks of the thermal power generation equipment are read, which may include the equipment maintenance plan, the scheduled power generation period, the power generation power limit in different periods, etc. These equipment tasks can affect the power generation capacity and operation status of the thermal power generation equipment in the long term. For example, a thermal power generation equipment is scheduled to undergo a 5-day maintenance next month, and it will not be able to generate electricity normally during these 5 days, which is part of the equipment task; then, an adaptation analysis of the long-term demand is performed based on the equipment tasks, the real-time energy storage status, and the second perceived demand. Specifically, the impact of the equipment tasks on the power generation capacity is considered, combined with The real-time energy storage status (such as the long-term energy storage trend of the energy storage equipment, the expected charging and discharging status, etc.) determines whether the current equipment operation and energy storage status can meet the long-term total power supply requirements in the second perceived demand. For example, if the second perceived demand predicts that 10 million kWh of electricity will be generated in the next month, and according to the equipment task and real-time energy storage status analysis, the thermal power generation equipment and energy storage system are expected to only generate 9 million kWh of electricity, there is a lack of demand; then the difference between the equipment task, the real-time energy storage status and the second perceived demand is quantified to form a second adaptation deviation, such as the difference in electricity quantity, the difference in power generation time, etc., to measure the gap between the current situation and the long-term demand. Finally, the first adaptation deviation and the second adaptation deviation are integrated to form an adaptation deviation to fully reflect the overall deviation between the current power system (including power generation equipment and energy storage equipment) and the perceived demand in the short and long term, which is helpful for the dynamic optimization scheduling of thermal power generation, so as to take measures to adjust the power generation and energy storage strategies, reduce the deviation, and enable the power system to better meet the actual needs.

[0036] Step S400, taking the adaptation deviation as the optimization target, executing thermal power generation optimization scheduling through a multi-objective dynamic optimization scheduling network, and generating a thermal power generation optimization scheduling result.

[0037] Preferably, the adaptation deviation is used as the optimization target, which means that the adaptation deviation should be reduced as much as possible by adjusting the operating parameters and scheduling strategies of the thermal power generation system, so that the output of the power generation system can better match the actual demand in multiple dimensions such as power and time; then the thermal power generation optimization scheduling is performed through the multi-objective dynamic optimization scheduling network, where the goals of thermal power generation optimization scheduling may include load balancing, reducing economic costs, controlling carbon emissions, and minimizing adaptation deviations. Specifically, a large amount of real-time data is first collected, including real-time operating data of thermal power generation equipment (such as power, temperature, pressure, etc.), real-time energy storage status of energy storage equipment (electricity, charging and discharging rate, etc.), real-time demand and forecast data of power load, equipment task information, etc., and input into the multi-objective dynamic optimization scheduling network, and then minimize the adaptation deviation as the core goal, while considering load balancing, reducing economic costs and controlling carbon emissions. Through continuous iteration and search, a set of optimal scheduling strategies are sought, such as determining the power generation of thermal power generation equipment at different times, the charging and discharging plan of energy storage equipment, etc., so that the thermal power generation system can minimize the adaptation deviation and optimize other goals under the premise of meeting various constraints (such as technical limitations of equipment, power balance requirements, etc.); and according to the optimal scheduling strategy obtained by optimization, the scheduling network generates specific scheduling instructions as the result of thermal power generation optimization scheduling, which is used to guide the operation of thermal power generation equipment and energy storage equipment, including the operation plan of each equipment in the thermal power generation system in the future (such as a few minutes or hours in the short term, a few days or weeks in the long term or even longer), such as the power generation set value of each thermal power generation equipment at different times, the charging and discharging schedule of energy storage equipment, the start and stop time of equipment, etc., so as to finally realize the efficient, stable and economical operation of the thermal power generation system.

[0038] Furthermore, step S400 also includes step S410, performing a short-term stable fitting evaluation on the first perceived demand and establishing a fitting fluctuation coefficient; step S420, configuring a heating quality default penalty target using the fitting fluctuation coefficient; step S430, acquiring the node performance of the thermal power generation equipment, and establishing a load balancing target based on the node performance; step S440, establishing an economic cost target and a carbon emission constraint target, and using the default penalty target, the load balancing target, the economic cost target and the carbon emission constraint target to construct the multi-objective dynamic optimization scheduling network to perform thermal power generation optimal scheduling.

[0039] Preferably, a short-term stable fitting evaluation is performed on the first perceived demand, that is, the matching degree between the actual first perceived demand data and a certain ideal stable demand pattern is analyzed. For example, a smooth curve that can best fit the demand data is found through the least square method to evaluate the fluctuation characteristics of the demand. The fitting fluctuation coefficient is an indicator used to quantify the degree of fluctuation of the demand data around the fitting curve, such as by calculating the statistics of the difference between the actual demand data and the fitting curve (such as standard deviation, variance, etc.). The larger the fitting fluctuation coefficient, the more violent the short-term fluctuation of the first perceived demand; conversely, the smaller the fluctuation coefficient, the more stable the demand. The fitting fluctuation coefficient is then used to configure the penalty target for the default of the heating quality, that is, the fluctuation coefficient is linked to the possible default cost or penalty. For example, when the fitting fluctuation coefficient exceeds a certain threshold, the corresponding penalty mechanism will be triggered to encourage the thermal power generation system to keep the heating quality stable as much as possible and reduce the heating quality problems caused by demand fluctuations. Among them, the heating quality usually requires a relatively stable temperature or heat supply within a certain period of time. If the first perceived demand fluctuates too much, it may cause the heating quality to be unstable and fail to meet the user's expectations for the heating quality.

[0040] Preferably, the node performance of thermal power generation equipment is obtained, including the equipment's power generation efficiency, power output capacity, reliability, maintenance cost, etc., to fully understand the operating status and capacity of each thermal power generation equipment, and establish a load balancing target based on the node performance, aiming to reasonably allocate power generation tasks so that the loads of various thermal power generation equipment are relatively balanced, avoiding excessive use of some equipment and underutilization of other equipment. For example, according to the equipment's power generation efficiency and power output capacity, the total power generation task is allocated to different equipment, so that they can operate in their respective optimal working ranges as much as possible while meeting the demand, so as to improve the operating efficiency and reliability of the entire system and reduce equipment wear and maintenance costs. Then establish economic cost targets and carbon emission constraint targets. Among them, the economic cost target mainly considers various cost factors in the thermal power generation process, such as fuel cost, equipment maintenance cost, etc., and minimizes the total of these costs by optimizing power generation scheduling to improve the economic benefits of the thermal power generation system; the thermal power generation system needs to control carbon emissions, and the carbon emission constraint target is to set a carbon emission target value. By adjusting the power generation method, optimizing fuel use and other measures, the carbon emissions in the thermal power generation process do not exceed this target value, such as using cleaner fuels, improving energy utilization efficiency, and increasing the proportion of renewable energy use to achieve energy conservation and emission reduction needs.

[0041] Preferably, the heat quality breach penalty target, load balancing target, economic cost target and carbon emission constraint target are integrated to construct a multi-objective dynamic optimization scheduling network, which can simultaneously consider the interrelationships and constraints between multiple targets, find the optimal scheduling plan, and balance each target; the multi-objective dynamic optimization scheduling network continuously adjusts and optimizes the scheduling plan based on the real-time operation data of thermal power generation equipment, first-perception demand data and other relevant information. For example, when the first-perception demand changes, the network will recalculate and adjust the power generation power and heating plan of each device to achieve load balancing, reduce economic costs and control carbon emissions while meeting the heat quality requirements. Through dynamic optimization scheduling, the thermal power generation system can adapt to different operating conditions and demand changes, achieve the optimization of overall performance, and thus achieve stable operation of the power system.

[0042] Furthermore, the multi-objective dynamic optimization scheduling network is as follows: ; in, Characterize the multi-objective dynamic optimization function, Characterize the adaptation deviation of the regulation adaptation target, Characterize the default penalty target, ; is the penalty objective function for heat quality breach, representing The degree of penalty for breach of contract caused by the deviation of heat supply stability adaptation at all times, is the fitted volatility coefficient, Characterizes the first adaptation deviation, which is the deviation between the short-term heating system load supply and demand. Characterizes the allowable deviation threshold, Characterize the load balancing target, ; is the total number of nodes, Representing any node, Characterization The time of the node Actual power generation, Characterization The rated power generation capacity of each node, i.e., node performance, is the total power generation capacity of thermal power generation equipment, Characterizes the total rated capacity of all nodes, For the The node weight factor of the node, Characterize economic cost targets, ;in, For the Nodes at time The fuel cost, For the The start-up and stop costs of each node, Characterization Nodes at time Operation and maintenance costs, To meet carbon emission constraints, ; is the carbon emission penalty coefficient, For thermal power generation equipment at all times The actual total carbon dioxide emissions, is the maximum emission limit, , , , They are the balance weight coefficients of the default penalty target, load balancing target, economic cost target, and carbon emission constraint target respectively.

[0043] Furthermore, step S400 also includes step S450, performing a fault probability analysis on the thermal power generation equipment to generate a fault probability evaluation result; step S460, establishing a protection energy storage plan using the fault probability evaluation result; and step S470, compensating for the thermal power generation optimal scheduling result through the protection energy storage plan to execute control management of the thermal power generation equipment.

[0044] Preferably, the failure probability analysis is performed on thermal power generation equipment (boilers, steam turbines, generators, etc.), that is, the historical operation data of the equipment is collected, including the operation time, maintenance records, time and cause of the failure, etc. of the equipment, and the failure probability of the equipment at different use stages is judged by using statistical methods and fault diagnosis techniques, such as reliability analysis and fault tree analysis. For example, the failure probability is judged according to the failure rate curve of the equipment (such as the bathtub curve). For equipment with a long operation time, the wear and aging of its components are considered to evaluate the increase in its failure probability; for new equipment, its potential failure risk is analyzed in combination with manufacturing quality, installation and commissioning, etc. At the same time, the influence of external environmental factors on the failure probability of the equipment is considered, such as temperature, humidity, fuel quality, etc. Through the failure probability analysis, the failure probability evaluation results are generated, including the failure probability of each thermal power generation equipment and key components, to reflect the failure possibility of the equipment under different operating conditions.

[0045] Preferably, according to the failure probability evaluation results, analyze the impact that different equipment failures may have on the thermal power generation system. For example, if a boiler fails, it may cause the entire power generation system to shut down and fail to supply power and heat normally; a turbine failure may affect power generation efficiency, resulting in a decrease in power generation; and consider the degree of interruption to power and heat supply when a failure occurs, as well as the time and cost required for recovery. Then, based on the failure impact analysis, determine the capacity, type, and configuration of the protective energy storage. The energy storage device can be a battery energy storage, a heat storage device, etc., and then formulate a charging and discharging strategy for the energy storage device. According to the failure probability and operating status of the equipment, reasonably arrange the charging time and charging amount of the energy storage device to ensure that the energy storage device has enough energy to compensate when the equipment fails. At the same time, consider the service life and maintenance cost of the energy storage device, optimize the charging and discharging strategy, extend the service life of the energy storage device, and finally obtain a protective energy storage solution.

[0046] Preferably, when a device failure occurs or it is predicted that the device has a high probability of failure, the energy storage device is used for compensation to perform optimal scheduling of thermal power generation. For example, if a certain power generation device stops due to a failure, the energy storage device can be discharged immediately to make up for the power generation gap and maintain the stability of power supply. Specifically, the optimal scheduling result is adjusted according to the actual state and failure of the energy storage device. If the power of the energy storage device is insufficient, the power generation plan of other devices may need to be readjusted to meet the power and heat demand; at the same time, the charging and discharging restrictions of the energy storage device are considered to avoid excessive use of the energy storage device and affect its performance and life. Through the implementation of the protection energy storage scheme and the compensation of the scheduling results, the control and management of thermal power generation equipment is realized, the operating status of the equipment and the status of the energy storage device are monitored in real time, and the operating parameters of the equipment and the charging and discharging operation of the energy storage device are adjusted in time according to the failure probability and scheduling results, and a failure warning mechanism is established. When the failure probability of the equipment reaches a certain threshold, measures are taken in advance, such as increasing the charging capacity of the energy storage device, adjusting the power generation plan, etc., to prevent the occurrence of failures, and finally realize the effective control and management of the thermal power generation system and improve the reliability and stability of the system.

[0047] Furthermore, step S400 also includes step S480, establishing mapping power generation data with the thermal power generation optimal scheduling result; step S490, using the mapped power generation data to establish a timing warning database, and performing actual power generation abnormality warning of thermal power generation equipment based on the timing warning database.

[0048] Preferably, the corresponding relationship between the optimal scheduling result of thermal power generation and the actual power generation data is clarified, and then the corresponding mapped power generation data is generated based on the determined mapping relationship, that is, these scheduling parameters are converted into a data form corresponding to the actual power generation process, that is, the mapped power generation data. For example, according to the relationship between the power generation power and time, the theoretical power generation at each time point is calculated to form a mapped power generation data set, which can reflect the power generation data that the thermal power generation equipment should generate at each moment according to the optimal scheduling result, or according to the power value that a certain generator should output in a specific time period in the scheduling result, the actual power data that the generator should generate in the time period is mapped, or the scheduled power generation time is converted into actual time series data. The mapped power generation data is organized and stored in time series to establish a time series warning database. In the database, each data point corresponds to a specific time point. For example, the mapped power generation data at each moment is recorded at time intervals of every minute or every hour, including the power, electricity and other information of each power generation equipment. Then, according to the performance parameters and operating experience of the thermal power generation equipment, a reasonable warning threshold is set for each power generation data. When the mapped power generation data exceeds this range, an early warning may be triggered. In addition to the mapped power generation data and the early warning threshold, the time series early warning database can also contain other relevant information, such as the equipment's operating status parameters (temperature, pressure, etc.), environmental parameters (weather conditions, grid load, etc.) and basic information of the equipment (model, rated capacity, etc.), which helps to more comprehensively analyze and judge the operation of thermal power generation equipment and improve the accuracy of abnormal early warning.

[0049] Preferably, during the actual operation of the thermal power generation equipment, the actual power generation data of the equipment is collected in real time and compared with the mapped power generation data in the timing warning database. For example, the actual power generation power, electricity volume and other data are collected once at regular intervals (such as every minute) through sensors and data acquisition systems installed on the equipment, and then compared with the mapped power generation data at the corresponding time in the database. When the actual power generation data exceeds the warning threshold range set in the timing warning database, it is judged that the equipment has an abnormal situation and a corresponding warning is triggered so that relevant personnel can promptly understand the abnormal situation of the equipment and take corresponding measures to ensure the stable operation of the thermal power generation system.

[0050] In the above, refer to Figure 1 The intelligent thermal power generation scheduling method according to the adaptive load regulation of the embodiment of the present invention is described in detail. Figure 2 An intelligent thermal power generation scheduling system with adaptive load regulation according to an embodiment of the present invention is described.

[0051] The intelligent thermal power generation dispatching system with adaptive load regulation according to the embodiment of the present invention is used to solve the technical problems existing in the prior art, such as the difficulty in accurately adapting to the complex and changing power supply demand and the inability to effectively utilize the real-time data of thermal power generation energy storage equipment, which leads to the decrease of power generation efficiency, poor power supply stability and energy waste, so as to achieve the balance of power supply and demand, and achieve the technical effects of improving the stability of power supply, improving power generation efficiency and reducing energy waste. Figure 2 As shown, the intelligent thermal power generation scheduling system with adaptive load regulation includes: a demand perception establishment module 10, a power generation fitting model construction module 20, an adaptation deviation establishment module 30, and a thermal power generation optimal scheduling module 40.

[0052] A perceived demand establishment module 10 is used to dynamically perceive the power supply demand and establish the perceived demand, wherein the perceived demand includes a first perceived demand and a second perceived demand, wherein the first perceived demand is a short-term stable fitting demand, and the second perceived demand is a long-term total power supply forecast demand; a power generation fitting model construction module 20 is used to dynamically model the thermal power generation equipment, construct a power generation fitting model, and share the real-time equipment data of the thermal power generation equipment to the power generation fitting model; an adaptation deviation establishment module 30 is used to obtain the real-time energy storage status of the energy storage equipment, generate real-time power generation data through the power generation fitting model, perform adaptation analysis of the perceived demand based on the real-time power generation data and the real-time energy storage status, and establish an adaptation deviation; a thermal power generation optimal scheduling module 40 is used to use the adaptation deviation as the optimization target, perform thermal power generation optimal scheduling through a multi-objective dynamic optimization scheduling network, and generate a thermal power generation optimal scheduling result.

[0053] The specific configuration of the adaptation deviation establishment module 30 will be described in detail below. The adaptation deviation establishment module 30 further includes: obtaining a first perceived demand of the perceived demand, performing real-time power generation data, power supply deviation of the real-time energy storage state, and timing response deviation identification according to the first perceived demand, and establishing a first adaptation deviation; after obtaining a second perceived demand of the perceived demand, reading the equipment task of the thermal power generation equipment, performing adaptation analysis of the long-term demand according to the equipment task, the real-time energy storage state, and the second perceived demand, establishing a second adaptation deviation, and establishing an adaptation deviation with the first adaptation deviation and the second adaptation deviation.

[0054] The specific configuration of the thermal power generation optimal scheduling module 40 will be described in detail below. The thermal power generation optimal scheduling module 40 further includes: performing a short-term stable fitting evaluation on the first perceived demand and establishing a fitting fluctuation coefficient; configuring a heat supply quality default penalty target using the fitting fluctuation coefficient; obtaining the node performance of the thermal power generation equipment and establishing a load balancing target based on the node performance; establishing an economic cost target and a carbon emission constraint target, and constructing the multi-objective dynamic optimization scheduling network using the default penalty target, the load balancing target, the economic cost target and the carbon emission constraint target to perform thermal power generation optimal scheduling.

[0055] The specific configuration of the thermal power generation optimal scheduling module 40 will be described in detail below. The thermal power generation optimal scheduling module 40 further includes: the multi-objective dynamic optimization scheduling network is as follows: ; in, Characterize the multi-objective dynamic optimization function, Characterize the adaptation deviation of the regulation adaptation target, Characterize the default penalty target, ; is the penalty objective function for heat quality breach, representing The degree of penalty for breach of contract caused by the deviation of heat supply stability adaptation at all times, is the fitted volatility coefficient, Characterizes the first adaptation deviation, which is the deviation between the short-term heating system load supply and demand. Characterizes the allowable deviation threshold, Characterize the load balancing target, ; is the total number of nodes, Representing any node, Characterization The time of the node Actual power generation, Characterization The rated power generation capacity of each node, i.e., node performance, is the total power generation capacity of thermal power generation equipment, Characterizes the total rated capacity of all nodes, For the The node weight factor of the node, Characterize economic cost targets, ;in, For the Nodes at time The fuel cost, For the The start-up and stop costs of each node, Characterization Nodes at time Operation and maintenance costs, To meet carbon emission constraints, ; is the carbon emission penalty coefficient, For thermal power generation equipment at all times The actual total carbon dioxide emissions, is the maximum emission limit, , , , They are the balance weight coefficients of the default penalty target, load balancing target, economic cost target, and carbon emission constraint target respectively.

[0056] The specific configuration of the thermal power generation optimal scheduling module 40 will be described in detail below. The thermal power generation optimal scheduling module 40 further includes: performing a fault probability analysis on the thermal power generation equipment to generate a fault probability evaluation result; establishing a protection energy storage scheme using the fault probability evaluation result; and compensating the thermal power generation optimal scheduling result through the protection energy storage scheme to perform control management of the thermal power generation equipment.

[0057] The specific configuration of the thermal power generation optimal dispatch module 40 will be described in detail below. The thermal power generation optimal dispatch module 40 further includes: establishing mapping power generation data with the thermal power generation optimal dispatch result; using the mapping power generation data to establish a time series warning database, and performing actual power generation abnormality warning of the thermal power generation equipment according to the time series warning database.

[0058] The specific configuration of the perceived demand establishment module 10 will be described in detail below. The perceived demand establishment module 10 further includes: obtaining the fluctuation rate of the load, and establishing a first duration constraint according to the fluctuation rate; obtaining the energy storage state of the energy storage device, and establishing a second duration constraint according to the energy storage state; and constructing a short-term window and a long-term window using the first duration constraint and the second duration constraint to establish the perceived demand.

[0059] The intelligent thermal power generation scheduling system with adaptive load regulation provided in the embodiment of the present invention can execute the intelligent thermal power generation scheduling method with adaptive load regulation provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0060] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0061] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. An intelligent thermal power generation scheduling method with adaptive load regulation, characterized in that: The method comprises: Dynamically sense the power supply demand and establish the sensed demand, wherein the sensed demand includes a first sensed demand and a second sensed demand, wherein the first sensed demand is a short-term stable fitting demand and the second sensed demand is a long-term total power supply forecast demand; Dynamically modeling the thermal power generation equipment, constructing a power generation fitting model, and sharing the real-time equipment data of the thermal power generation equipment to the power generation fitting model; Acquire the real-time energy storage status of the energy storage device, generate real-time power generation data through the power generation fitting model, perform adaptation analysis of the sensed demand according to the real-time power generation data and the real-time energy storage status, and establish an adaptation deviation; Taking the adaptation deviation as the optimization target, thermal power generation optimal scheduling is performed through a multi-objective dynamic optimization scheduling network to generate a thermal power generation optimal scheduling result.

2. The intelligent thermal power generation scheduling method with adaptive load regulation according to claim 1, characterized in that: The performing adaptation analysis of the perceived demand according to the real-time power generation data and the real-time energy storage state and establishing the adaptation deviation includes: Acquire a first sensed demand of the sensed demand, identify the real-time power generation data, the power supply deviation of the real-time energy storage state, and the timing response deviation according to the first sensed demand, and establish a first adaptation deviation; After obtaining the second perceived demand of the perceived demand, the equipment task of the thermal power generation equipment is read, and an adaptation analysis of the long-term demand is performed based on the equipment task, the real-time energy storage status, and the second perceived demand, and a second adaptation deviation is established, and an adaptation deviation is established with the first adaptation deviation and the second adaptation deviation.

3. The intelligent thermal power generation scheduling method with adaptive load regulation according to claim 2, characterized in that: The method of taking the adaptation deviation as the optimization target and performing thermal power generation optimization scheduling through a multi-objective dynamic optimization scheduling network includes: Performing a short-term stable fitting evaluation on the first perceived demand and establishing a fitting fluctuation coefficient; Using the fitted fluctuation coefficient, configuring a penalty target for heat quality breach; Obtaining node performance of thermal power generation equipment, and establishing a load balancing target according to the node performance; An economic cost target and a carbon emission constraint target are established, and the multi-objective dynamic optimization scheduling network is constructed using the breach penalty target, the load balancing target, the economic cost target and the carbon emission constraint target to perform optimal scheduling of thermal power generation.

4. The intelligent thermal power generation scheduling method with adaptive load regulation according to claim 1, characterized in that: The multi-objective dynamic optimization scheduling network is as follows: ； in, Characterize the multi-objective dynamic optimization function, Characterize the adaptation deviation of the regulation adaptation target, Characterize the default penalty target, ; is the penalty objective function for heat quality breach, representing The degree of penalty for breach of contract caused by the deviation of heat supply stability adaptation at all times, is the fitted volatility coefficient, Characterizes the first adaptation deviation, which is the deviation between the short-term heating system load supply and demand. Characterizes the allowable deviation threshold, Characterize the load balancing target, ; is the total number of nodes, Representing any node, Characterization The time of the node Actual power generation, Characterization The rated power generation capacity of each node, i.e., node performance, is the total power generation capacity of thermal power generation equipment, Characterizes the total rated capacity of all nodes, For the The node weight factor of the node, Characterize economic cost targets, ;in, For the Nodes at time The fuel cost, For the The start-up and stop costs of each node, Characterization Nodes at time Operation and maintenance costs, To meet carbon emission constraints, ; is the carbon emission penalty coefficient, For thermal power generation equipment at all times The actual total carbon dioxide emissions, is the maximum emission limit, , , , They are the balance weight coefficients of the default penalty target, load balancing target, economic cost target, and carbon emission constraint target respectively.

5. The intelligent thermal power generation scheduling method with adaptive load regulation according to claim 1, characterized in that: After generating the thermal power generation optimal dispatch result, the method includes: Performing a failure probability analysis on the thermal power generation equipment to generate a failure probability evaluation result; Establishing a protection energy storage scheme using the fault probability evaluation result; The protection energy storage scheme is used to compensate for the optimal dispatch result of thermal power generation to execute control management of thermal power generation equipment.

6. The intelligent thermal power generation scheduling method with adaptive load regulation according to claim 1, characterized in that: After generating the thermal power generation optimal dispatch result, the method further includes: Establishing power generation data mapped with thermal power generation optimal dispatch results; A time series warning database is established by using the mapped power generation data, and an actual power generation abnormality warning of the thermal power generation equipment is performed based on the time series warning database.

7. The intelligent thermal power generation scheduling method with adaptive load regulation according to claim 1, characterized in that: The dynamically sensing the power supply demand and establishing the sensing demand includes: Acquire a load fluctuation rate, and establish a first duration constraint according to the fluctuation rate; Acquire an energy storage state of the energy storage device, and establish a second duration constraint according to the energy storage state; The first duration constraint and the second duration constraint are used to construct a short-term window and a long-term window to establish a perception requirement.

8. Intelligent thermal power generation dispatching system with adaptive load regulation, characterized in that: The system is used to implement the intelligent thermal power generation scheduling method with adaptive load regulation according to any one of claims 1 to 7, and the system comprises: A sensing demand establishment module is used to dynamically sense the power supply demand and establish the sensing demand, wherein the sensing demand includes a first sensing demand and a second sensing demand, wherein the first sensing demand is a short-term stable fitting demand and the second sensing demand is a long-term total power supply forecast demand; A power generation fitting model building module is used to dynamically model the thermal power generation equipment, build a power generation fitting model, and share the real-time equipment data of the thermal power generation equipment to the power generation fitting model; An adaptation deviation establishment module is used to obtain the real-time energy storage state of the energy storage device, generate real-time power generation data through the power generation fitting model, perform adaptation analysis of the perceived demand according to the real-time power generation data and the real-time energy storage state, and establish an adaptation deviation; The thermal power generation optimal scheduling module is used to take the adaptation deviation as the optimization target, perform thermal power generation optimal scheduling through a multi-objective dynamic optimization scheduling network, and generate a thermal power generation optimal scheduling result.

Images