Real-time power supply fire coal cost calculation method and system suitable for warehouse-divided and time-divided coaling

Through data fusion and dynamic maintenance of coal-fired queue structure, combined with reinforcement learning and genetic algorithms, real-time coal-fired cost calculation of coal on warehouses and time periods is achieved, and the problems of lag and static in the existing technology are solved. More accurate and timely cost forecasts and feedback are provided to adapt to the bidding needs of the power market.

CN118941317AActive Publication Date: 2024-11-12LUCULENT SMART TECHNOLOGIES CO LTD

Patent Information

Application Number
CN202410979791.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-12
Estimated Expiration
2044-07-22

AI Technical Summary

Technical Problem

The existing coal-fired cost accounting methods have lag and static properties, which are difficult to provide reliable data support for bidding in the power market, and cannot reflect the changes in production strategies in the warehouse and time period in real time.

Method used

By obtaining coal data information from each coal mine for data fusion, the weighted prices of each coal unloading point every day are calculated, and a coal-fired queue structure is formed through the fuel control system, and dynamic maintenance is carried out in combination with real-time coal supply, considering the benchmark electricity price and deep adjustment of the Internet Compensate electricity prices, calculate the cost of power supply and power supply benefits, and optimize the coal-fired queue usage strategy using reinforcement learning and genetic algorithms.

Benefits of technology

Realize real-time calculation of power supply coal costs under the coal production strategy of warehouse and time period, provides reliable data support, avoids the lag of manual statistics and the staticity of experimental data, and improves the accuracy and time efficiency of statistical dimensions. to adapt to the short-term bidding needs of the spot power market.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941317A_ABST
    Figure CN118941317A_ABST
Patent Text Reader

Abstract

The invention discloses a real-time power supply fire coal cost calculation method and system suitable for warehouse-divided and time-divided coaling, and the method comprises the steps: obtaining coal coming data information of each coal mine, carrying out the data fusion, and calculating the weighted price of coal storage at each coal unloading point every day; the bunker adding amount and the bunker adding source of each raw coal bunker in each time period are obtained through a fuel management and control system, and a fire coal queue structure is formed; the fire coal queue structure and the real-time coal feeding amount of each coal feeder are compared, matched and calculated, dynamic maintenance of the queue is achieved, and the price of fire coal used by each coal feeder at the current moment is obtained; and considering the internet-surfing benchmark electricity price, deeply adjusting the compensation electricity price, and calculating the power supply fire coal cost and the power supply income. The method can adapt to real-time calculation of the power supply fire coal cost under the production strategies of warehouse-based coaling and time-based coaling of most of power plants at present. The data has real-time performance and dynamic performance, and the real-time production state is reflected. And the calculation result can flexibly set a load section to provide a statistical result according to user requirements, and the statistical dimension precision is higher.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of coal management, and in particular to a real-time power supply coal cost calculation method and system applicable to coal loading in different warehouses and time periods. Background Art

[0003] There are two main commonly used methods. One is to obtain the annual and monthly average power supply fuel cost of the plant through annual and monthly fuel costs and power supply statistics, and use the average power supply fuel cost instead of the real-time power supply fuel cost. The other is to obtain the power supply coal cost data of several typical operating points through field experiments. According to the data fitting curve of these operating points, the data of other operating points are inferred. This method is expensive and has a low frequency. The external environment data during the experiment replaces the environmental data for the whole year, the coal quality data during the experiment replaces the coal quality data for the whole year, and the coal loading, coal blending plan, and equipment wear during the experiment replace the data for the whole year.

[0004] As coal prices continue to rise, many power plants have started blending coal. Under the production strategy of loading coal in different warehouses and different time periods, the power generation cost accounting methods of the above two methods are obviously lagging and static. In order to obtain more accurate real-time data and provide data support for production decisions, it is urgent to adopt new statistical accounting methods and systems. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is that the existing statistical accounting method is difficult to provide reliable data support for power market bidding.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a real-time power supply coal cost calculation method applicable to coal loading in different warehouses and time periods, comprising:

[0008] Obtain the coal data information of each coal mine for data fusion, and calculate the weighted price of coal stored at each coal unloading point every day;

[0009] The fuel control system is used to obtain the amount of coal added to each raw coal bin and each time period, as well as the source of the added coal, to form a coal queue structure;

[0010] Compare and match the coal queue structure with the real-time coal supply of each coal feeder to achieve dynamic maintenance of the queue and obtain the coal price used by each coal feeder at the current moment;

[0011] Taking into account the benchmark on-grid electricity price and deep-adjustment compensation electricity price, calculate the coal-fired power supply cost and power supply revenue.

[0012] As a preferred solution of the real-time power supply and coal cost calculation method applicable to coal loading in different warehouses and time periods described in the present invention, the coal data information of each coal mine includes price, quantity, coal unloading, real-time coal supply, and power supply; data is extracted from the fuel control system, and the coal price of each coal mine is Coal quantity of each coal mine Coal unloading information, including the coal inventory at each unloading point and the daily unloading amount Unload i ; Record the weighted price of coal at each unloading point every day

[0013] Record the weighted price of coal at each coal unloading point on the previous day Record the amount of coal stored at each unloading point the day before

[0014] As a preferred solution of the real-time power supply coal cost calculation method applicable to coal loading in different warehouses and time periods described in the present invention, the calculation of the weighted price of coal stored at each coal unloading point every day includes calculating the daily weighted price, combining the price and quantity of the coal unloading point on the previous day, and calculating the weighted price of the day; if multiple types of coal are unloaded to the same coal unloading point on the same day, it is necessary to consider the quantity and price of each type of coal and calculate the total coal unloading quantity of each coal unloading point on the same day. and total price The formula is:

[0015]

[0016]

[0017] Calculate the weighted price of each coal unloading point on the day, the formula is expressed as:

[0018]

[0019] in, represents the weighted price of coal unloading point i today; represents the weighted price of coal unloading point i yesterday; It represents the total coal storage volume at coal unloading point i yesterday; It represents the weight of coal type m unloaded to coal unloading point i today; It represents the price of coal type m today; M represents the number of coal types unloaded today.

[0020] As a preferred solution of the real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods described in the present invention, the data fusion includes determining the location and type of the sensor and evaluating its measurement accuracy and coverage;

[0021] Install sensors at predetermined locations to ensure their stability and data transmission reliability; calibrate newly installed sensors and perform initial calibration to ensure the accuracy of sensor data; recalibrate regularly to integrate new sensor data into existing data acquisition systems:

[0022] Use data fusion algorithms to pre-process multi-source data, remove outliers and noise, and ensure data accuracy; use the fused data to optimize the calculation model of power supply coal costs;

[0023] The coal flow data integration formula is expressed as:

[0024]

[0025] in, represents the coal feed rate of the sth sensor at time t;

[0026] The coal bunker height data integration formula is expressed as:

[0027]

[0028] in, represents the height of the cth coal bunker at time t, and N is the number of sensors.

[0029] As a preferred solution of the real-time power supply coal cost calculation method applicable to coal loading in different warehouses and time periods described in the present invention, the forming of the coal queue structure includes obtaining the data of the added warehouse quantity and the added warehouse source of each raw coal warehouse and each time period through the fuel control system to construct an initial queue structure;

[0030] The coal queue structure can be represented as an ordered set of triples, where each triple contains the time t i 、Coal source S i and the amount of increase in position W i :

[0031] Queue={(t1, S1, W1), (t2, S2, W2),..., (t n , S n , W n )}

[0032] Dynamic maintenance of queue structure

[0033] Get the real-time coal supply. The real-time cumulative coal supply of the coal machine at time t is expressed as:

[0034]

[0035] in, Represents the instantaneous coal flow rate of coal feeder i at time t′.

[0036] As a preferred solution of the real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods described in the present invention, the dynamic maintenance of the queue includes: Update the queue structure:

[0037] Determine the coal batches to be consumed, initially starting with the first batch in the queue, and if all is consumed, move on to the next batch;

[0038] Update the batch remaining quantity, assuming that the real-time cumulative coal supply of coal feeder i at time t If it is greater than the remaining amount of the current batch W1, the formula for updating the queue structure is expressed as:

[0039]

[0040] like The coal-fired queue structure is expressed as:

[0041] Queue={(t2,S2,W2),...(t n S n ,W n )}

[0042] Otherwise, the amount of added positions is updated to:

[0043]

[0044] The update queue structure is represented as:

[0045]

[0046] in, represents the remaining amount of the updated i-th batch of coal; represents the remaining amount of the i-th batch of coal before updating; represents the real-time cumulative coal supply of coal feeder i at time t; It represents the remaining coal supply after the coal feeder i consumes the current batch of coal at time t;

[0047] Based on the real-time coal supply, determine the coal batch k currently consumed;

[0048]

[0049] in, represents the weighted average coal price of coal feeder i at time t; represents the price of the jth batch of coal in the queue; represents the amount of coal used by coal feeder i at time t in the jth batch;

[0050] Reinforcement learning optimization, defining states and actions, states s tIndicates the coal queue structure and coal supply at the current moment; action a t Indicates the coal batch selected for consumption;

[0051] The reward function formula is expressed as:

[0052] r t =-C fuel (t)+λ×Efficiency(t)-μ×I

[0053] The optimization objective formula is expressed as:

[0054]

[0055] Perform genetic algorithm optimization and define the fitness function

[0056] f(x)=-C fuel +λ×Ef-μ×EI

[0057] Among them, π represents the strategy; * represents the optimal strategy γ represents the discount factor, and its value range is [0,1]; C fuel (t) represents the coal cost at time t; Ef(t) represents the equipment operating efficiency at time t; EI(t) represents the environmental impact at time t; λ represents the weight coefficient of efficiency; μ: weight coefficient of environmental impact;

[0058] The initial population is randomly generated, and each individual represents a possible coal-fired queue usage strategy; the fitness of each individual is evaluated and calculated using the fitness function;

[0059] Based on the selection probability, select individuals from the current population for reproduction; select two parent individuals and perform crossover operation to generate offspring individuals; perform mutation operation on offspring individuals according to the mutation rate to generate new individuals; replace some or all parent individuals with offspring individuals to form a new population; repeat the iteration to reach the maximum number of iterations.

[0060] As a preferred solution of the real-time power supply coal cost calculation method applicable to coal loading in different warehouses and time periods described in the present invention, wherein: the calculation of power supply coal cost and power supply income includes that the coal cost calculation needs to consider the coal consumption and coal price of each coal feeder;

[0061]

[0062] Among them, C fuel (t) represents the coal cost in the current period; represents the cumulative coal supply of coal feeder i at time t; represents the coal price of coal feeder i at time t; Represents the cumulative power generation of generator set j at time t.

[0063] A real-time power supply and coal burning cost calculation system for coal loading in different warehouses and time periods, using any method described in the present invention, comprising:

[0064] The data collection module obtains the coal data information of each coal mine, performs data fusion, and calculates the weighted price of coal stored at each coal unloading point every day;

[0065] The coal-fired queue structure module obtains the amount and source of coal added in each raw coal bin and each time period through the fuel control system to form a coal-fired queue structure;

[0066] The dynamic maintenance module of the queue compares and matches the coal-fired queue structure with the real-time coal supply of each coal feeder to achieve dynamic maintenance of the queue;

[0067] The cost calculation module takes into account the benchmark electricity price and the deep adjustment compensation electricity price, and calculates the coal-fired power supply cost and power supply revenue.

[0068] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0069] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0070] The beneficial effects of the present invention are as follows: it can adapt to the real-time calculation of the cost of coal for power supply under the current production strategies of coal loading in separate warehouses and time periods in most power plants. It provides reliable data support for bidding in the electricity spot market. The data is real-time and dynamic, reflecting the real-time production status, avoiding the lag of manual statistics and the static nature of experimental data. The calculation results can be flexibly set according to user requirements to produce statistical results in load segments, and the statistical dimension has higher accuracy. Taking into account the short-cycle bidding characteristics of the electricity spot market, from the perspective of real-time demand for quotations, a method and system for real-time calculation of the cost of coal for power supply have been constructed, which breaks through the lagging status of cost management in terms of timeliness, transforms the traditional ex post mode of cost management into a new real-time model, and realizes cost forecasting and feedback more accurately and timely. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0072] Figure 1 An overall flow chart of a method for calculating the real-time power supply and coal burning cost applicable to coal loading in different warehouses and time periods provided in the first embodiment of the present invention;

[0073] Figure 2 A diagram of an on-site coal storage module for a method for calculating the real-time power supply and coal burning cost for loading coal in different warehouses and time periods provided in the first embodiment of the present invention;

[0074] Figure 3 A diagram of an actual warehouse data module for a real-time power supply coal cost calculation method applicable to warehouse-by-warehouse and time-by-time coal loading provided in the first embodiment of the present invention;

[0075] Figure 4 A profitability graph for each load segment of a real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0076] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0077] Example 1

[0078] Reference Figure 1 , which is an embodiment of the present invention, provides a real-time power supply coal cost calculation method applicable to coal loading in different warehouses and time periods, including:

[0079] S1: Obtain the coal data information of each coal mine for data fusion, calculate the weighted price of coal stored at each coal unloading point every day, and collect the platform parameters of the cloud service end.

[0080] Furthermore, the coal data information of each coal mine includes price, quantity, coal unloading, real-time coal supply, and power supply; data is extracted from the fuel control system, and the coal price of each coal mine Coal quantity of each coal mine Coal unloading information, including coal inventory at each unloading point and daily unloading volume Record the weighted price of coal at each unloading point every day

[0081] Furthermore, the weighted coal price of each coal unloading point on the previous day is recorded. Record the amount of coal stored at each unloading point the day before

[0082] Furthermore, increase the number and accuracy of sensors, evaluate the existing sensor network, and determine the specific locations and types of sensors that need to be added, such as adding coal bunker height sensors, coal feeder real-time flow sensors, etc. Purchase and install high-precision sensors to ensure that they can accurately measure the required data. Calibrate the newly installed sensors to ensure the accuracy and consistency of the data; integrate the new sensor data into the existing data acquisition system to ensure the synchronization of real-time data updates.

[0083] Furthermore, the formula says:

[0084]

[0085] in, represents the coal feed rate of the sth sensor at time t; represents the height of the cth coal bunker at time t, and N is the number of sensors.

[0086] Furthermore, Figure 2 As shown, the calculation of the weighted price of coal stored at each coal unloading point every day includes calculating the daily weighted price, combining the price and quantity of the coal unloading point on the previous day, and calculating the weighted price of the day; if multiple types of coal are unloaded to the same coal unloading point on the same day, it is necessary to consider the quantity and price of each type of coal and calculate the total coal unloading quantity of each coal unloading point on the day. and total price The formula is:

[0087]

[0088] Furthermore, the weighted price of each coal unloading point on the day is calculated, and the formula is expressed as:

[0089]

[0090] in, represents the weighted price of coal unloading point i today; represents the weighted price of coal unloading point i yesterday; It represents the total coal storage volume at coal unloading point i yesterday; It represents the weight of coal type m unloaded to coal unloading point i today; It represents the price of coal type m today; M represents the number of coal types unloaded today.

[0091] It should be noted that by counting the daily coal incoming and unloading conditions, obtaining the weighted price of each unloading coal, and matching the quantity and source of each raw coal bunker, the coal-fired queue structure of each raw coal bunker is obtained. Combined with the real-time collected coal supply of each coal feeder and the online power of the unit, the coal-fired cost of the unit power supply is calculated in real time. And the power supply income can be calculated by combining the online benchmark electricity price and deep adjustment compensation price.

[0092] S2: Obtain the amount of coal added to each raw coal bin and each time period, as well as the source of the added coal, through the fuel control system to form a coal queue structure.

[0093] Furthermore, the data fusion includes determining the location and type of sensors and evaluating their measurement accuracy and coverage.

[0094] Furthermore, the location and type of sensors that need to be added are determined to enhance the coal bunker height and coal feeder real-time flow.

[0095] Furthermore, install the sensor at the predetermined location to ensure its stability and reliability of data transmission; calibrate the newly installed sensor and perform initial calibration to ensure the accuracy of the sensor data; recalibrate regularly to ensure the accuracy and consistency of the sensor after long-term use; integrate the new sensor data into the existing data acquisition system.

[0096] Furthermore, the data sources that need to be integrated, such as meteorological data and coal quality data, are determined; data interfaces are established to ensure that data from different data sources can be transmitted and integrated in real time.

[0097] Furthermore, data fusion algorithms are used to pre-process multi-source data to remove outliers and noise to ensure data accuracy.

[0098] Furthermore, the fused data is used to optimize the calculation model of coal-fired power supply costs.

[0099] Furthermore, the coal flow rate data integration formula is expressed as:

[0100]

[0101] in, Represents the coal feed rate of the sth sensor at time t.

[0102] Furthermore, the coal bunker height data integration formula is expressed as:

[0103]

[0104] in, represents the height of the cth coal bunker at time t, and N is the number of sensors.

[0105] It should be noted that the raw coal bunker (multiple bunkers are set up for each unit) is the intermediate storage equipment before the coal enters the coal feeder. After the coal enters the raw coal bunker, it follows the first-in-first-out characteristics, and is naturally stratified to form a queue structure. Because the current coal price is high, most power plants are implementing a production strategy of loading coal in different bunkers and time periods according to the power generation plan, in order to reduce production costs. Therefore, the coal structure and price in different raw coal bunkers are different; the coal structure and price of the same coal bunker in different time periods are also different. The fuel control system is used to obtain the amount of coal added in each raw coal bunker and each time period, as well as the source of the added coal (which unloading point the coal comes from), to form a coal queue structure.

[0106] S3: Compare and match the coal queue structure with the real-time coal supply of each coal feeder to achieve dynamic maintenance of the queue and obtain the coal price used by each coal feeder at the current moment.

[0107] Furthermore, the formation of the coal-fired queue structure includes obtaining data on the amount of coal added to each raw coal bin and each time period and the source of coal added to each raw coal bin through the fuel control system, such as Figure 3 As shown, construct the initial queue structure.

[0108] Furthermore, the coal queue structure can be represented as an ordered set of triples, where each triple contains the time t i 、Coal source S i and the amount of increase in position W i .

[0109] Queue={(t1, S1, W1), (t2, S2, W2),..., (t n , S n , W n )}

[0110] Furthermore, the dynamic maintenance of the queue structure obtains the real-time coal supply. The real-time cumulative coal supply of the coal machine at time t is expressed as:

[0111]

[0112] in, Represents the instantaneous coal flow rate of coal feeder i at time t′.

[0113] Furthermore, the dynamic maintenance of the queue includes: Update the queue structure.

[0114] Furthermore, the coal batches to be consumed are determined, and consumption starts initially from the first batch in the queue, and if consumption is completed, it is transferred to the next batch.

[0115] Furthermore, to update the batch remaining quantity, let the real-time cumulative coal supply of coal feeder i at time t be If it is greater than the remaining amount of the current batch W1, the formula for updating the queue structure is expressed as:

[0116]

[0117] Furthermore, if The coal-fired queue structure is expressed as:

[0118] Queue={(t2,S2,W2),...,(t n ,S n ,W n )}

[0119] Furthermore, otherwise the amount of additional positions is updated to:

[0120]

[0121] Furthermore, the update queue structure is represented as:

[0122]

[0123] in, represents the remaining amount of the updated i-th batch of coal; represents the remaining amount of the i-th batch of coal before updating; represents the real-time cumulative coal supply of coal feeder i at time t; It represents the remaining coal supply after coal feeder i consumes the current batch of coal at time t;.

[0124] Furthermore, based on the real-time coal supply, the currently consumed coal batch k is determined.

[0125]

[0126] in, represents the weighted average coal price of coal feeder i at time t; represents the price of the jth batch of coal in the queue; It represents the amount of coal of the jth batch used by coal feeder i at time t.

[0127] Furthermore, reinforcement learning optimization defines states and actions, and states s t Indicates the coal queue structure and coal supply at the current moment; action a t Indicates the coal batch selected for consumption.

[0128] Furthermore, the reward function formula is expressed as:

[0129] r t =-C fuel (t)+λ×Efficiency(t)-u×I

[0130] Furthermore, the optimization objective formula is expressed as:

[0131]

[0132] Going further, perform genetic algorithm optimization and define the fitness function:

[0133] f(x)=-C fuel +λ×Ef-μ×El

[0134] Among them, π represents the strategy; * represents the optimal strategy γ represents the discount factor, and its value range is [0,1]; C fuel (t) represents the coal cost at time t; Ef(t) represents the equipment operating efficiency at time t; EI(t) represents the environmental impact at time t; λ represents the weight coefficient of efficiency; μ: the weight coefficient of environmental impact.

[0135] It should be noted that the initial population is randomly generated, and each individual represents a possible coal-fired queue usage strategy; the fitness of each individual is evaluated and calculated using the fitness function; based on the selection probability, individuals are selected from the current population for reproduction; two parent individuals are selected and a crossover operation is performed to generate offspring individuals; the offspring individuals are mutated according to the mutation rate to generate new individuals; some or all of the parent individuals are replaced with offspring individuals to form a new population; and iterations are repeated until the maximum number of iterations is reached.

[0136] S4: Considering the benchmark on-grid electricity price and deep adjustment compensation electricity price, calculate the coal-fired power supply cost and power supply revenue.

[0137] Furthermore, the calculation of the coal cost for power supply and the power supply revenue includes that the calculation of the coal cost needs to take into account the coal consumption and coal price of each coal feeder.

[0138]

[0139] Furthermore, C fuel (t) represents the coal cost in the current period; represents the cumulative coal supply of coal feeder i at time t; represents the coal price of coal feeder i at time t; Represents the cumulative power generation of generator set j at time t.

[0140] It should be noted that the system calculates the coal consumption of each coal feeder once a minute, and gradually deducts the coal consumption from the coal-fired queue structure until the consumption of this batch of raw coal is completed. After the consumption of this batch of raw coal is completed, the system will automatically switch to the price of the next batch of raw coal. This step is in line with the current production strategy of loading coal in different warehouses and time periods. It is obviously different from the model algorithm that assumes that all raw coal warehouses (coal feeders) use the same coal, and it is also obviously different from the model algorithm that assumes that a coal feeder uses the same type of coal all day. Because each coal feeder may start and stop at any time according to production scheduling. The queue structure must be dynamically matched through actual start and stop consumption.

[0141] On the other hand, this embodiment also provides a real-time power supply and coal cost calculation system applicable to coal loading in different warehouses and time periods, which includes:

[0142] The data collection module obtains the coal data information of each coal mine, performs data fusion, and calculates the weighted price of coal stored at each coal unloading point every day.

[0143] The coal-fired queue structure module obtains the added coal quantity and source of each raw coal bin and each time period through the fuel management and control system to form a coal-fired queue structure.

[0144] The dynamic maintenance module of the queue compares and matches the coal-fired queue structure with the real-time coal supply of each coal feeder to achieve dynamic maintenance of the queue.

[0145] The cost calculation module takes into account the benchmark electricity price and the deep adjustment compensation electricity price, and calculates the coal-fired power supply cost and power supply revenue.

[0146] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0147] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0148] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0149] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0150] Example 2, reference Figure 4 , which is an embodiment of the present invention, provides a real-time power supply and coal cost calculation method suitable for coal loading in different warehouses and time periods. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0151] Assuming that 100 tons of coal is added to coal bunker A at t1-t2, and 200 tons is added at t3-t4, and the coal level in coal bunker A is 11 meters at t1, it is estimated that the coal stored in coal bunker A at t1 is 110+(11-8)×50=260 tons (the estimation method provided by the owner is 110 tons below 8 meters of coal level and 50 tons for every 1 meter above 8 meters). According to the cumulative coal volume of the coal feeder, when coal feeder A consumes 260 tons of coal, the coal used at this time is the coal added at t1-t2.

[0152] Known conditions (provided by each factory based on their actual situation): benchmark electricity price 0.42 yuan / kWh, deep adjustment quotation_first tier 0.16 yuan / kWh, deep adjustment quotation_second tier 0.375 yuan / kWh, fixed cost of power generation yuan / kWh.

[0153] The coal cost for power generation in the current time period (yuan / MWh) has been calculated by the system in the previous step. Paid peak-shaving power refers to the ungenerated power generated when the average load rate of the thermal power plant in each paid peak-shaving grading interval is lower than the paid peak-shaving benchmark. At present, deep regulation is generally divided into two grades, 30%-40% rated load grade, 40%-50% load grade, and there is no deep regulation compensation for loads above 50%.

[0154] When the average load is ≥50% of the rated load, the profit = benchmark electricity price*1000-power generation coal cost-power generation fixed cost*1000

[0155] When 40% rated load ≤ average load < 50% rated load, revenue = (benchmark electricity price * 1000 * average load + (50% rated load - average load) * deep adjustment quotation_first gear * 1000) / average load - power generation coal cost - power generation fixed cost * 1000

[0156] When the average load is less than 40% of the rated load, the profit = (benchmark electricity price*1000*average load+(50% rated load-40% rated load)*deep adjustment quotation_first tier*1000+(40% rated load-average load)*deep adjustment quotation_second tier*1000) / average load-power generation coal cost-power generation fixed cost*1000

[0157] A certain plant has realized the real-time calculation of the coal cost for power supply by using the system of the present invention, and compared with the test and calculation data of the plant ( Figure 2), the two are close, and at the same time verify the economic feasibility of participating in deep regulation compensation, so that the quotation is more based on evidence (benchmark electricity price 400 yuan / MWh, standard coal unit price 844 yuan / MWh, first-tier deep regulation compensation price 300 yuan / MWh, second-tier deep regulation compensation price 650 yuan / MWh). The present invention calculates in real time, and there is no need to make assumptions about the ambient temperature, coal quality information, boiler efficiency, and turbine generator efficiency that remain stable. All changes in external factors are reflected in the calculation results and can be used throughout the year. Compared with experimental data, it avoids the disadvantage of using one experimental data to estimate the data for the whole year.

[0158] Table 1 Comparison of power plant experimental data and system calculation results

[0159]

[0160]

[0161] This set of test data was obtained by the plant through on-site tests at a well-known power and thermal engineering institute. This set of experimental data only selected a few characteristic load points, and based on the limited load point fitting curve, the performance of the unit under other loads was inferred. At the same time, the test data only expresses the unit efficiency under the equipment performance during the test. It can only be extended to the whole year under the assumption that the unit equipment has no wear, no maintenance, and the environmental factors remain unchanged. Considering the obvious difference between winter and summer operating conditions, as well as the inevitable wear and tear of equipment, this assumption will obviously cause obvious distortion of the data. If you want to use experimental data to guide the operation of the unit throughout the year, you will inevitably need to re-experiment regularly and increase the number of experiments under different loads, which is costly.

[0162] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A real-time power supply coal cost calculation method applicable to coal loading in different warehouses and time periods, characterized in that: include: Obtain the coal data information of each coal mine for data fusion, and calculate the weighted price of coal stored at each coal unloading point every day; The fuel control system is used to obtain the amount of coal added to each raw coal bin and each time period, as well as the source of the added coal, to form a coal queue structure; Compare and match the coal queue structure with the real-time coal supply of each coal feeder to achieve dynamic maintenance of the queue and obtain the coal price used by each coal feeder at the current moment; Taking into account the benchmark on-grid electricity price and deep-adjustment compensation electricity price, calculate the coal-fired power supply cost and power supply revenue.

2. The real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods as claimed in claim 1 is characterized by: The coal data information of each coal mine includes price, quantity, coal unloading, real-time coal supply, and power supply; data is extracted from the fuel management and control system, and the coal price of each coal mine is Coal quantity of each coal mine Coal unloading information, including the coal inventory at each unloading point and the daily unloading amount Unload i ; Record the weighted price of coal at each unloading point every day Record the weighted price of coal at each coal unloading point on the previous day Record the amount of coal stored at each unloading point the day before 3. The real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods as claimed in claim 2 is characterized by: The calculation of the weighted price of coal stored at each coal unloading point on a daily basis includes calculating the daily weighted price, combining the price and quantity of the coal unloading point on the previous day, and calculating the weighted price on the current day; If multiple types of coal are unloaded at the same unloading point on the same day, the total unloading volume of each unloading point on that day needs to be calculated by considering the quantity and price of each type of coal. and total price The formula is: Calculate the weighted price of each coal unloading point on the day, the formula is expressed as: in, represents the weighted price of coal unloading point i today; represents the weighted price of coal unloading point i yesterday; It represents the total coal storage volume at coal unloading point i yesterday; It represents the weight of coal type m unloaded to coal unloading point i today; It represents the price of coal type m today; M represents the number of coal types unloaded today.

4. The real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods as claimed in claim 3 is characterized by: The data fusion includes determining the location and type of sensors and evaluating the accuracy and coverage of their measurements; Install sensors at predetermined locations to ensure their stability and reliability of data transmission; calibrate newly installed sensors and perform initial calibration to ensure the accuracy of sensor data; Regular recalibration to integrate new sensor data into existing data acquisition systems: Use data fusion algorithms to pre-process multi-source data, remove outliers and noise, and ensure data accuracy; use the fused data to optimize the calculation model of power supply coal costs; The coal flow data integration formula is expressed as: in, represents the coal feed rate of the sth sensor at time t; The coal bunker height data integration formula is expressed as: in, represents the height of the cth coal bunker at time t, and N represents the number of sensors.

5. The real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods as claimed in claim 4 is characterized by: The forming of the coal-fired queue structure includes obtaining data on the amount of coal added to each raw coal bin and each time period and the source of coal added through the fuel control system, and constructing an initial queue structure; The coal queue structure can be represented as an ordered set of triples, where each triple contains the time t i 、Coal source S i and the amount of increase in position W i , the queue formula is expressed as: Queue={(t1,S1,W1),(t2,S2,W2),...,(t n ,S n ,W n )} The queue structure is dynamically maintained to obtain the real-time coal supply. The real-time cumulative coal supply of the coal machine at time t is expressed as: in, Represents the instantaneous coal flow rate of coal feeder i at time t.

6. The real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods as claimed in claim 5 is characterized by: The dynamic maintenance of the queue includes: Update the queue structure: Determine the coal batches to be consumed, initially starting with the first batch in the queue, and if all is consumed, move on to the next batch; Update the batch remaining quantity, assuming that the real-time cumulative coal supply of coal feeder f at time t If it is greater than the remaining amount of the current batch W1, the formula for updating the queue structure is expressed as: like The coal-fired queue structure is expressed as: Queue={(t2,S2,W2),...,(t n ,S n ,W n )) Otherwise, the amount of added positions is updated to: The update queue structure is represented as: in, represents the remaining amount of the updated i-th batch of coal; represents the remaining amount of the i-th batch of coal before updating; represents the real-time cumulative coal supply of coal feeder i at time t; It represents the remaining coal supply after the coal feeder i consumes the current batch of coal at time t; Based on the real-time coal supply, determine the coal batch k currently consumed; in, represents the weighted average coal price of coal feeder i at time t; represents the price of the jth batch of coal in the queue; represents the amount of coal used by coal feeder i at time t in the jth batch; Reinforcement learning optimization, defining states and actions, states s t Indicates the coal queue structure and coal supply at the current moment; action a t Indicates the coal batch selected for consumption; The reward function formula is expressed as: r t =-C fuel (t)+λ×Efficiency(t)-μ×I The optimization objective formula is expressed as: Perform genetic algorithm optimization and define the fitness function, which is expressed as follows: f(x)=-C fuel +λ×Ef-μ×EI Among them, π represents the strategy; * represents the optimal strategy γ represents the discount factor, and its value range is [0, 1]; C fuel (t) represents the coal cost at time t; Ef(t) represents the equipment operating efficiency at time t; EI(t) represents the environmental impact at time t; λ represents the weight coefficient of efficiency; μ represents the weight coefficient of environmental impact; The initial population is randomly generated, and each individual represents a possible coal-fired queue usage strategy; the fitness of each individual is evaluated and calculated using the fitness function; Based on the selection probability, select individuals from the current population for reproduction; select two parent individuals and perform crossover operation to generate offspring individuals; perform mutation operation on offspring individuals according to the mutation rate to generate new individuals; replace some or all parent individuals with offspring individuals to form a new population; repeat the iteration to reach the maximum number of iterations.

7. The real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods as claimed in claim 6 is characterized by: The calculation of the power supply coal cost and power supply income includes that the coal cost calculation needs to take into account the coal consumption and coal price of each coal feeder; Among them, C fuel (t) represents the coal cost in the current period; represents the cumulative coal supply of coal feeder i at time t; represents the coal price of coal feeder i at time t; Represents the cumulative power generation of generator set j at time t.

8. A real-time power supply and coal cost calculation system for coal loading in different warehouses and time periods, using the method as described in any one of claims 1 to 7, characterized in that: The data collection module obtains the coal data information of each coal mine, performs data fusion, and calculates the weighted price of coal stored at each coal unloading point every day; The coal-fired queue structure module obtains the amount and source of coal added in each raw coal bin and each time period through the fuel control system to form a coal-fired queue structure; The dynamic maintenance module of the queue compares and matches the coal-fired queue structure with the real-time coal supply of each coal feeder to achieve dynamic maintenance of the queue; The cost calculation module takes into account the benchmark electricity price and the deep adjustment compensation electricity price, and calculates the coal-fired power supply cost and power supply revenue.

9. A computer device comprising: Memory and processor; The memory stores a computer program, which is characterized in that when the processor executes the computer program, it implements the steps of a real-time power supply and coal cost calculation method applicable to coal loading in different warehouses and time periods.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the real-time power supply and coal burning cost calculation method applicable to coal loading in different warehouses and time periods are implemented.

Citation Information

Patent Citations

  • As-fired coal separate bin metering system of coal conveying system

    CN105203194A

  • Coal dispatching system and method for cluster type coal plant

    CN111506028A

  • Fire coal purchasing and power generation index prediction processing system suitable for power plant

    CN113159827A

  • Full-process tracking and efficient combustion control system and method for multi-condition coal quality

    CN115329563A

  • Plant monitoring system and plant monitoring method

    WO2017110359A1

Cited By

  • Power supply coal consumption dynamic recommendation method, system and device and storage medium

    CN119398472A