Scheduling method and system of coal-fired ammonia-doped unit, medium and electronic equipment

Abstract

The invention provides a coal-fired ammonia-doped unit scheduling method and system, a medium and electronic equipment, and relates to the technical field of energy transaction, and the method comprises the steps: obtaining the historical real electricity price and the historical real carbon price of a unit, and determining the predicted electricity price and the predicted carbon price in combination with a preset prediction model; obtaining a fuel cost model and an emission cost model, wherein the fuel cost model and the emission cost model are fuel cost and emission cost of the unit under different ammonia doping proportions and different power generation capacities; determining a preset constraint condition of the unit; determining a comprehensive income model by combining the fuel cost model, the emission cost model and the predicted electricity price; and based on a preset constraint condition and the comprehensive income model, determining a target power generation amount and a target ammonia doping proportion corresponding to the maximum income of the unit, so as to schedule the unit. The problem that the scheduling strategy of the existing unit is difficult to meet the dynamic optimization requirement under the dual-market environment is solved.

Description

Technical Field

[0001] The present disclosure relates to the field of energy trading technology, and in particular to a scheduling method, system, medium and electronic equipment for a coal-fired ammonia-blended unit. Background Art

[0002] As the global low-carbon transition continues, the power industry is shifting from traditional coal-fired power generation to a diversified and clean supply structure. The real-time trading mechanisms of the electricity spot market and the environmental constraints of the carbon market place higher demands on the flexibility, precision, and cost-effectiveness of power generation units. However, traditional coal-fired units face significant pressures on both economic and environmental performance in the face of fluctuating spot market electricity prices, volatile carbon market prices, and increasingly stringent environmental policies. This is especially true when attempting to incorporate low-carbon fuels such as ammonia to reduce carbon and pollutant emissions. Traditional single or static optimization scheduling strategies are unable to meet the dynamic optimization needs of this dual market environment. Summary of the Invention

[0003] In response to the deficiencies in the existing technology, the present disclosure provides a scheduling method, system, medium and electronic equipment for coal-fired ammonia-blended units, which solves the problem that the scheduling strategies of existing units are difficult to meet the dynamic optimization needs in a dual market environment.

[0004] At least one embodiment of the present disclosure provides a scheduling method for a coal-fired ammonia-blended unit, comprising:

[0005] Obtain the historical real electricity price and historical real carbon price of the unit in the historical preset time period;

[0006] Determine the predicted electricity price and predicted carbon price for a preset time period in the future based on a preset forecast model, historical actual electricity prices, and historical actual carbon prices;

[0007] Obtaining a fuel cost model and an emission cost model, wherein the fuel cost model is the fuel cost of the unit under different ammonia blending ratios and different power generation amounts, and the emission cost model is the emission cost of the unit under the predicted carbon price, the preset denitrification unit price, different ammonia blending ratios, and different power generation amounts;

[0008] Determining preset constraints of the unit, wherein the preset constraints include an ammonia blending ratio constraint and a power generation constraint;

[0009] Determine a comprehensive benefit model by combining the fuel cost model, the emission cost model, and the predicted electricity price, wherein the comprehensive benefit model is the benefit obtained by the unit under different ammonia blending ratios and different power generation amounts;

[0010] Based on the preset constraints and the comprehensive benefit model, the target power generation and target ammonia blending ratio corresponding to the unit when the benefit is maximized are determined, and the unit is dispatched based on the target power generation and the target ammonia blending ratio.

[0011] The technical solution provided by the present disclosure has at least the following beneficial effects:

[0012] Through the above scheme, we can establish a model that comprehensively considers the fuel cost, emission cost and preset constraints of coal and ammonia fuel in a preset time period in the future, targeting the characteristics of coal-fired ammonia-blended units. The cost curve of traditional coal-fired units can be expanded to a multi-dimensional model that can flexibly adjust the ammonia blending ratio and power generation, thereby accurately reflecting the comprehensive impact of changes in the ammonia blending ratio on the unit's fuel cost, emission cost and preset constraints.

[0013] By building a comprehensive revenue model for ammonia-blended units tailored to both the electricity spot market and the carbon market, we can continuously update future revenue forecasts based on the latest market price data. This model, combined with the current unit's operating status, optimizes decisions for subsequent periods, determining the target power generation and ammonia blending ratio for maximum revenue. This dynamic optimization approach is applicable to the current dual market environment, ensuring that the unit maintains improved overall economic and environmental benefits throughout its entire operating lifecycle.

[0014] In a scheduling method for a coal-fired ammonia-blended unit provided in one embodiment of the present disclosure, obtaining a fuel cost model includes:

[0015] Acquiring historical operating data of the unit, the historical operating data including historical fuel costs of the unit under multiple historical ammonia blending ratios and historical power generation;

[0016] Based on the historical operating data, respectively determine a coal fuel cost characteristic curve, an ammonia fuel cost characteristic curve, and an additional cost characteristic curve of the unit, wherein the coal fuel cost characteristic curve is a curve showing a relationship between the fuel cost and the power generation of the unit when the ammonia blending ratio is 0, the ammonia fuel cost characteristic curve is a curve showing a relationship between the fuel cost and the power generation of the unit when the ammonia blending ratio is 1, and the additional cost characteristic curve is a curve showing a relationship between the additional cost of the unit and the ammonia blending ratio;

[0017] A fuel cost model is determined based on the coal fuel cost characteristic curve, the ammonia fuel cost characteristic curve and the additional cost characteristic curve.

[0018] The technical solution provided by the present disclosure has at least the following beneficial effects:

[0019] By constructing a fuel cost model through the above scheme, we can comprehensively consider the corresponding coal fuel cost, ammonia fuel cost and additional cost under different required power generation and different ammonia blending ratios, so as to obtain a more accurate fuel cost model and improve the accuracy of subsequent profit predictions.

[0020] In a scheduling method for a coal-fired ammonia-blended unit provided in one embodiment of the present disclosure, obtaining an emission cost model includes:

[0021] Acquiring historical emission data of the unit, the historical emission data including historical carbon emissions and historical nitrogen oxide emissions generated by the unit under multiple historical ammonia blending ratios and historical power generation;

[0022] Based on the historical emission data, fitting and determining an emission characteristic curve of the unit, wherein the emission characteristic curve represents carbon emissions and nitrogen oxide emissions generated by the unit at different ammonia blending ratios and different power generation amounts;

[0023] An emission cost model is determined by combining the predicted carbon price, the preset denitrification unit price and the emission characteristic curve.

[0024] The technical solution provided by the present disclosure has at least the following beneficial effects:

[0025] The emission cost model constructed through the above scheme can accurately predict the corresponding carbon emission costs and nitrogen oxide denitrification costs under different ammonia blending ratios and different power generation based on the predicted carbon price and combined with historical emission data.

[0026] In a scheduling method for a coal-fired ammonia-blended unit provided in one embodiment of the present disclosure, the ammonia-blending ratio constraint includes:

[0027] The target ammonia blending ratio in the future preset time period is within a first preset range, and a difference between the target ammonia blending ratio in the future preset time period and the ammonia blending ratio in a time period before the future preset time period is lower than a first preset value.

[0028] The technical solution provided by the present disclosure has at least the following beneficial effects:

[0029] By controlling the target ammonia blending ratio within the first preset range, it can be ensured that the unit's carbon and nitrogen emission ratio can meet the corresponding environmental protection requirements. On this basis, by controlling the maximum fluctuation range of the ammonia blending ratio in adjacent time periods, it can be used to prevent boiler or combustion instability caused by excessive switching.

[0030] In a scheduling method for a coal-fired ammonia-blended unit provided in one embodiment of the present disclosure, the power generation constraint includes:

[0031] The target power generation in the future preset time period is within a second preset range, and a difference between the target power generation in the future preset time period and the power generation in a time period before the future preset time period is lower than a second preset value.

[0032] The technical solution provided by the present disclosure has at least the following beneficial effects:

[0033] By controlling the target power generation to be within the second preset range, it can be ensured that the power generation of the unit can meet the corresponding demand. On this basis, by controlling the maximum fluctuation range of power generation in adjacent time periods, boiler or combustion instability caused by excessively fast switching can be further prevented.

[0034] In a scheduling method for a coal-fired ammonia-blended unit provided in one embodiment of the present disclosure, determining, based on the preset constraints and the comprehensive benefit model, the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit includes:

[0035] Based on the preset constraints and the comprehensive benefit model, a target power generation and a target ammonia blending ratio corresponding to the maximum benefit of the unit are determined by a preset algorithm, wherein the preset algorithm includes mixed integer linear programming, mixed integer nonlinear programming, genetic algorithm or particle swarm algorithm.

[0036] In a scheduling method for a coal-fired ammonia-blended unit provided in one embodiment of the present disclosure, determining a predicted electricity price and a predicted carbon price for a preset future time period based on a preset forecast model, historical actual electricity prices, and historical actual carbon prices includes:

[0037] Determine the initial forecast electricity price and initial forecast carbon price for a preset time period in the future based on a preset forecast model, historical actual electricity prices, and historical actual carbon prices;

[0038] Fitting a first error distribution between historically predicted electricity prices and historically actual electricity prices within a preset historical time period, and a second error distribution between historically predicted carbon prices and historically actual carbon prices;

[0039] Sampling a first disturbance value from the first error proportion distribution, and superimposing the first disturbance value on the initial predicted electricity price to obtain a predicted electricity price, wherein the first disturbance value is a correction term for the initial predicted electricity price and is used to simulate the deviation between the actual electricity price and the initial predicted electricity price;

[0040] A second disturbance value is sampled from the second error proportion distribution, and the second disturbance value is superimposed on the initial predicted carbon price to obtain a predicted carbon price. The second disturbance value is a correction term for the initial predicted carbon price, which is used to simulate the deviation between the actual carbon price and the initial predicted carbon price.

[0041] The technical solution provided by the present disclosure has at least the following beneficial effects:

[0042] By introducing disturbance values ​​and superimposing them on the initial predicted electricity price and the initial predicted carbon price, it can be used to simulate and characterize an uncertain market environment, and improve the accuracy of the prediction of the unit's target power generation and target ammonia blending ratio at a preset time in the future.

[0043] At least one embodiment of the present disclosure further provides a scheduling system for a coal-fired ammonia-blended unit, comprising:

[0044] A data acquisition module is used to obtain the historical real electricity price and historical real carbon price of the unit in a historical preset time period;

[0045] A forecasting module is used to determine a forecast electricity price and a forecast carbon price for a preset time period in the future based on a preset forecasting model, historical actual electricity prices, and historical actual carbon prices;

[0046] a cost model generation module, configured to obtain a fuel cost model and an emission cost model, wherein the fuel cost model is the fuel cost of the unit at different ammonia blending ratios and different power generation amounts, and the emission cost model is the emission cost of the unit at different ammonia blending ratios and different power generation amounts under the predicted carbon price and the preset denitrification unit price;

[0047] A constraint module, configured to determine preset constraint conditions for the unit, wherein the preset constraint conditions include an ammonia blending ratio constraint and a power generation constraint;

[0048] a revenue model generating module, configured to determine a comprehensive revenue model by combining the fuel cost model, the emission cost model, and the predicted electricity price, wherein the comprehensive revenue model represents the revenue obtained by the unit under different ammonia blending ratios and different power generation amounts;

[0049] A scheduling module is used to determine the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit based on the preset constraints and the comprehensive benefit model, and to schedule the unit based on the target power generation and the target ammonia blending ratio.

[0050] The present disclosure also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes the scheduling method for a coal-fired ammonia-blended unit as described above.

[0051] The present disclosure also provides an electronic device, including a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, a scheduling method for a coal-fired ammonia-blended unit as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic flow chart of a method for dispatching a coal-fired ammonia-blended unit provided in the present disclosure;

[0053] Figure 2 This is a structural diagram of a dispatching system for a coal-fired ammonia-blended unit provided by the present disclosure;

[0054] Figure 3 A schematic diagram of the structure of an electronic device provided by the present disclosure.

[0055] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0056] 10. Electronic device, 11. Processor, 12. Read-only memory (ROM), 13. Random access memory (RAM), 14. Bus, 15. Input / output (I / O) interface, 16. Input unit, 17. Output unit, 18. Storage unit, 19. Communication unit. DETAILED DESCRIPTION

[0057] The principles and features of the present disclosure are described below. The examples given are only used to explain the present disclosure and are not used to limit the scope of the present disclosure.

[0058] The present disclosure provides a method for dispatching a coal-fired ammonia-blended unit. Figure 1 Shown, including:

[0059] Obtain the historical real electricity price and historical real carbon price of the unit in the historical preset time period;

[0060] Determine the predicted electricity price and predicted carbon price for a preset time period in the future based on a preset forecast model, historical actual electricity prices, and historical actual carbon prices;

[0061] Obtain a fuel cost model and an emission cost model. The fuel cost model is the fuel cost of the unit at different ammonia blending ratios and different power generation. The emission cost model is the emission cost of the unit at different ammonia blending ratios and different power generation under the predicted carbon price and the preset denitrification unit price.

[0062] Determine the preset constraints of the unit, which include ammonia blending ratio constraints and power generation constraints;

[0063] Combining the fuel cost model, emission cost model and predicted electricity price, a comprehensive profit model is determined. The comprehensive profit model is the profit obtained by the unit under different ammonia blending ratios and different power generation;

[0064] Based on the preset constraints and the comprehensive benefit model, the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit are determined, and the unit is dispatched based on the target power generation and target ammonia blending ratio.

[0065] Through the above scheme, we can establish a model that comprehensively considers the fuel cost, emission cost and preset constraints of coal and ammonia fuel in a preset time period in the future, targeting the characteristics of coal-fired ammonia-blended units. The cost curve of traditional coal-fired units can be expanded to a multi-dimensional model that can flexibly adjust the ammonia blending ratio and power generation, thereby accurately reflecting the comprehensive impact of changes in the ammonia blending ratio on the unit's fuel cost, emission cost and preset constraints.

[0066] By building a comprehensive revenue model for ammonia-blended units tailored to both the electricity spot market and the carbon market, we can continuously update future revenue forecasts based on the latest market price data. This model, combined with the current unit's operating status, optimizes decisions for subsequent periods, determining the target power generation and ammonia blending ratio for maximum revenue. This dynamic optimization approach is applicable to the current dual market environment, ensuring that the unit maintains improved overall economic and environmental benefits throughout its entire operating lifecycle.

[0067] Optionally, the obtaining of the historical real electricity price and historical real carbon price of the unit in the historical preset time period specifically includes:

[0068] Obtain historical real electricity and carbon price data for a preset time period from power trading platforms and carbon emission rights trading markets. This data should include historical clearing price records for the day-ahead, intraday, and real-time markets, as well as historical transaction price series for carbon emission rights.

[0069] It should be understood that the above-mentioned historical preset time period is not a fixed time period, but changes in real time. For example, the historical preset time period may be within one month or one week before the current time, and the above-mentioned preset conditions may also include emission limit constraints, quotation windows, result clearing requirements, etc.

[0070] The historical operating data of the unit is extracted from the power plant production database and fuel management system, including but not limited to: unit power generation records, start and stop times, ramp rate information, minimum and maximum technical power generation ranges, coal prices, ammonia prices, fuel blending ratios in different time periods, pollutant emissions and unit efficiency parameters.

[0071] The above historical data is cleaned, filtered, and standardized. This includes removing outliers, correcting missing data points using interpolation or smoothing methods, aligning data from different time scales to a unified time interval, and normalizing or standardizing multi-dimensional features such as price, output, and emissions.

[0072] Store the processed high-quality historical data in a database or data warehouse and create a retrieval index to facilitate quick access to the data in subsequent steps.

[0073] In an exemplary embodiment provided by the present disclosure, based on a preset forecasting model, historical actual electricity prices, and historical actual carbon prices, determining a forecast electricity price and a forecast carbon price for a preset time period in the future includes:

[0074] Determine the initial forecast electricity price and initial forecast carbon price for a preset time period in the future based on a preset forecast model, historical actual electricity prices, and historical actual carbon prices;

[0075] Among them, the preset prediction model training steps are:

[0076] Utilizing the above high-quality historical data, we can forecast future electricity and carbon prices, providing forward-looking information for unit optimization decisions.

[0077] The prediction model is trained based on the historical real electricity prices and carbon prices provided by the above-mentioned high-quality historical data, as well as related influencing factors (such as power system load, historical renewable energy output, carbon emissions, and fuel price trends). A preset prediction model is obtained by using deep learning models such as LSTM, GRU, or Transformer, leveraging the characteristics of historical time series data to fit and predict electricity and carbon price trends for a specific time period in the future (e.g., 24 hours before the previous day, 4 hours within a day, or 1 hour in real time).

[0078] Fit the first error distribution of the historical predicted electricity price and the historical actual electricity price within a preset historical time period, as well as the second error distribution of the historical predicted carbon price and the historical actual carbon price, wherein the above error distribution includes a normal distribution, a t distribution or a mixed Gaussian model, and the distribution parameters are dynamically adjusted over time. The dynamic adjustment method can use the GARCH model to estimate the time-varying volatility, so that the variance of the disturbance term changes with the volatility of the electricity price.

[0079] Sampling a first disturbance value from the first error proportional distribution, and superimposing the first disturbance value on the initial predicted electricity price to obtain a predicted electricity price, wherein the first disturbance value is a correction term for the initial predicted electricity price and is used to simulate the deviation between the actual electricity price and the initial predicted electricity price;

[0080] A second disturbance value is sampled from the second error proportion distribution, and the second disturbance value is superimposed on the initial predicted carbon price to obtain the predicted carbon price. The second disturbance value is a correction term for the initial predicted carbon price, which is used to simulate the deviation between the actual carbon price and the initial predicted carbon price.

[0081] By introducing disturbance values ​​and superimposing them on the initial predicted electricity price and the initial predicted carbon price, it can be used to simulate and characterize an uncertain market environment, and improve the accuracy of the prediction of the unit's target power generation and target ammonia blending ratio at a preset time in the future.

[0082] In an exemplary embodiment provided by the present disclosure, obtaining a fuel cost model includes:

[0083] Obtain historical operating data of the unit, including historical fuel costs of the unit under multiple historical ammonia blending ratios and historical power generation;

[0084] Based on historical operating data, the coal fuel cost characteristic curve, ammonia fuel cost characteristic curve and additional cost characteristic curve of the unit are determined respectively. Among them, the coal fuel cost characteristic curve is the relationship curve between the unit's fuel cost and power generation when the ammonia blending ratio is 0, the ammonia fuel cost characteristic curve is the relationship curve between the unit's fuel cost and power generation when the ammonia blending ratio is 1, and the additional cost characteristic curve is the relationship curve between the unit's additional cost and the ammonia blending ratio;

[0085] The fuel cost model is determined based on the coal fuel cost characteristic curve, the ammonia fuel cost characteristic curve and the additional cost characteristic curve.

[0086] The above fuel cost model can be expressed as:

[0087]

[0088] Among them, C fuel (P t ,x t ) is the preset time period t, the power generation of the unit is P t And the ammonia ratio is x t In the case of , the fuel cost of the unit;

[0089] C coal (P t ) means if the unit is generating power (i.e. power generation) P t The fuel cost when all fuel is coal is the coal fuel cost characteristic curve; If the unit generates power of P t The fuel cost when all the fuel is ammonia is the ammonia fuel cost characteristic curve;

[0090] Among them, x t ∈[0,1] is the heat proportion (or mass proportion, as defined) of ammonia in this period, and the coal proportion is (1-x t );β(x t ) is the possible additional cost characteristic curve, which depends on the ammonia blending ratio. For example, when the ammonia blending ratio is higher, more auxiliary equipment energy consumption (such as transportation, regulation, etc.) is required. Of course, it can also be set to 0 to indicate that it is ignored.

[0091] Considering the different power generation capacity P t Under these conditions, the fuel costs of coal and ammonia are significantly nonlinear, and it is necessary to convert the coal fuel cost characteristic curve C coal (P t ) and ammonia fuel cost characteristic curve The polynomial fit can be expressed as:

[0092] C coal (P t )=α c,0 +α c,1 ·P t +α c,2 ·P t 2 +...α c,n ·P t n

[0093]

[0094] Among them, α c,0 , α c,1 , α c,2 ...α c,n is the coefficient of the unit's coal fuel cost characteristics, α n,0 , α n,1 , α n,2 ...α n,n is the coefficient of the unit's ammonia fuel cost characteristics.

[0095] By constructing a fuel cost model through the above scheme, we can comprehensively consider the corresponding coal fuel cost, ammonia fuel cost and additional cost under different required power generation and different ammonia blending ratios, so as to obtain a more accurate fuel cost model and improve the accuracy of subsequent profit predictions.

[0096] In an exemplary embodiment provided by the present disclosure, obtaining an emission cost model includes:

[0097] Obtain historical emission data for the unit, including historical carbon emissions and historical nitrogen oxide emissions generated by the unit under multiple historical ammonia blending ratios and historical power generation;

[0098] Based on historical emission data, the emission characteristic curve of the unit is fitted and determined. The emission characteristic curve shows the carbon emissions and nitrogen oxide emissions generated by the unit at different ammonia blending ratios and different power generation;

[0099] The emission cost model is determined by combining the predicted carbon price, preset denitrification unit price and emission characteristic curve.

[0100] The above emission cost model can be expressed as:

[0101]

[0102] is the predicted carbon price in the carbon market, in yuan / ton; The power generation capacity of the unit is P t When and doping ratio is x t Carbon emissions per hour, in tons; The preset denitrification unit price per unit NOx, in yuan / ton; The power generation capacity of the unit is P t When and doping ratio is x t The NOx emissions of the unit are in tons.

[0103] The emission cost model constructed through the above scheme can accurately predict the corresponding carbon emission costs and nitrogen oxide denitrification costs under different ammonia blending ratios and different power generation based on the predicted carbon price and combined with historical emission data.

[0104] In an exemplary embodiment provided by the present disclosure, the ammonia blending ratio constraint includes:

[0105] The target ammonia blending ratio in the future preset time period is within the first preset range, and the difference between the target ammonia blending ratio in the future preset time period and the ammonia blending ratio in the time period before the future preset time period is lower than the first preset value.

[0106] The ammonia blending ratio constraint can be expressed as:

[0107]

[0108] |x t -x t-1 |≤Δx max

[0109] in, and are the minimum and maximum allowable ammonia blending ratios, i.e. the first preset range; Δx max It is the maximum variation range of the ammonia blending ratio in adjacent time periods, that is, the first preset value, which is used to prevent boiler or combustion instability caused by too fast switching.

[0110] In an exemplary embodiment provided by the present disclosure, the power generation constraint includes:

[0111] The target power generation in the future preset time period is within the second preset range, and the difference between the target power generation in the future preset time period and the power generation in the previous time period of the future preset time period is lower than the second preset value.

[0112] The power generation constraint can be expressed as:

[0113]

[0114] |P t -P t-1 |≤P ramp

[0115] in, and The minimum and maximum outputs allowed by the unit at the technical level, i.e. the second preset range; P ramp It is the maximum ramp rate of the unit between adjacent time periods, that is, the second preset value.

[0116] Based on the above expressions, the comprehensive benefit model provided in this embodiment can be expressed as:

[0117]

[0118] in, Expressed as the predicted electricity price.

[0119] In an exemplary embodiment provided by the present disclosure, based on preset constraints and a comprehensive benefit model, determining the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit includes:

[0120] Based on preset constraints and a comprehensive benefit model, the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit are determined through preset algorithms. The preset algorithms include mixed integer linear programming (MILP) and mixed integer nonlinear programming (MINLP). When high nonlinearity or high dimension occurs, genetic algorithm or particle swarm algorithm can be used.

[0121] If multi-scenario analysis is adopted, the optimization problem under each scenario is solved independently or in parallel, and the optimal robust quotation and output strategy is selected through weighted expectation or risk indicators (such as CVaR).

[0122] After the solution is completed, the optimal target ammonia blending ratio and unit target power generation plan for each period in a given future preset time period (such as the next 24 hours or shorter time granularity) are output for scheduling.

[0123] In actual operation, at fixed time intervals (such as 1 hour or shorter), the latest historical real electricity price data and historical real carbon price data are obtained again from the trading platform, and input into the preset prediction model to update the future price prediction results.

[0124] The new forecast results are input into the comprehensive benefit model to re-optimize and solve the unit operation decisions in subsequent periods and perform scheduling.

[0125] Dynamically output updated optimization strategies to ensure that unit decisions can promptly adapt to changes in electricity prices, carbon prices, loads, and other uncertain factors, thereby continuously improving comprehensive economic and environmental benefits throughout the entire operating cycle.

[0126] The present disclosure is also used to intuitively present the optimization scheduling results required to be performed to power plant operators.

[0127] The optimization scheduling results to be performed will be graphically displayed through the human-computer interaction interface (GUI), including the output in each period, ammonia blending ratio, expected benefits, emission indicators, and comparative analysis with other scenario results.

[0128] Decision makers can make appropriate adjustments to risk preferences, ammonia blending limits, carbon price transmission parameters, etc. based on the intuitive results, and obtain new strategic plans by calling different preset algorithms again.

[0129] This paper uses the historical operating data of the power plant (including unit output, fuel prices, pollutant emissions, etc.), electricity spot market prices and carbon market price forecast results to conduct a comprehensive analysis of the operating status of the coal-fired ammonia-blended unit and make real-time strategic adjustments, filling the gap in the existing technology for the lack of collaborative optimization decision-making methods for ammonia-blended units in the dual environment of electricity spot and carbon markets.

[0130] In summary, based on the characteristics and cost modeling of ammonia-blended coal-fired units (including fuel cost model, emission cost model and preset constraints), this paper proposes a collaborative optimization algorithm for the electricity spot and carbon markets. By dynamically adjusting the ammonia blending ratio and power generation plan, the corresponding operating parameters for maximizing the unit's profit are solved under the conditions of fluctuations in electricity spot market prices and carbon market prices, thereby improving the economic and environmental benefits of the unit.

[0131] The present disclosure can also graphically display the optimization results through a human-computer interaction interface, including multi-dimensional information such as output in each time period, ammonia blending ratio, expected benefits, emission indicators, etc., and support decision makers to adjust the plan according to risk preferences, ammonia blending upper limit, etc., thereby providing visual decision-making support for the operation optimization of ammonia-blending units in a dual market environment.

[0132] The present disclosure also provides a scheduling system for coal-fired ammonia-blended units. Figure 2 Shown, including:

[0133] A data acquisition module is used to obtain the historical real electricity price and historical real carbon price of the unit in a historical preset time period;

[0134] A forecasting module is used to determine a forecast electricity price and a forecast carbon price for a preset time period in the future based on a preset forecasting model, historical actual electricity prices, and historical actual carbon prices;

[0135] The cost model generation module is used to obtain the fuel cost model and the emission cost model. The fuel cost model is the fuel cost of the unit at different ammonia blending ratios and different power generation. The emission cost model is the emission cost of the unit at different ammonia blending ratios and different power generation under the predicted carbon price and the preset denitrification unit price.

[0136] A constraint module is used to determine preset constraints of the unit, including ammonia blending ratio constraints and power generation constraints;

[0137] The revenue model generation module is used to combine the fuel cost model, emission cost model and predicted electricity price to determine the comprehensive revenue model. The comprehensive revenue model is the revenue obtained by the unit under different ammonia blending ratios and different power generation;

[0138] The scheduling module is used to determine the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit based on preset constraints and the comprehensive benefit model, and to schedule the unit based on the target power generation and target ammonia blending ratio.

[0139] Furthermore, the cost model generation module specifically includes:

[0140] Obtain historical operating data of the unit, including historical fuel costs of the unit under multiple historical ammonia blending ratios and historical power generation;

[0141] Based on historical operating data, the coal fuel cost characteristic curve, ammonia fuel cost characteristic curve and additional cost characteristic curve of the unit are determined respectively. Among them, the coal fuel cost characteristic curve is the relationship curve between the unit's fuel cost and power generation when the ammonia blending ratio is 0, the ammonia fuel cost characteristic curve is the relationship curve between the unit's fuel cost and power generation when the ammonia blending ratio is 1, and the additional cost characteristic curve is the relationship curve between the unit's additional cost and the ammonia blending ratio;

[0142] The fuel cost model is determined based on the coal fuel cost characteristic curve, the ammonia fuel cost characteristic curve and the additional cost characteristic curve.

[0143] Furthermore, the cost model generation module specifically includes:

[0144] Obtain historical emission data for the unit, including historical carbon emissions and historical nitrogen oxide emissions generated by the unit under multiple historical ammonia blending ratios and historical power generation;

[0145] Based on historical emission data, the emission characteristic curve of the unit is fitted and determined. The emission characteristic curve shows the carbon emissions and nitrogen oxide emissions generated by the unit at different ammonia blending ratios and different power generation;

[0146] The emission cost model is determined by combining the predicted carbon price, preset denitrification unit price and emission characteristic curve.

[0147] Furthermore, the ammonia blending ratio constraints in the constraint module specifically include:

[0148] The target ammonia blending ratio in the future preset time period is within the first preset range, and the difference between the target ammonia blending ratio in the future preset time period and the ammonia blending ratio in the time period before the future preset time period is lower than the first preset value.

[0149] Furthermore, the power generation constraints in the constraint module specifically include:

[0150] The target power generation in the future preset time period is within the second preset range, and the difference between the target power generation in the future preset time period and the power generation in the previous time period of the future preset time period is lower than the second preset value.

[0151] Furthermore, the scheduling module specifically includes:

[0152] Based on preset constraints and a comprehensive benefit model, the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit are determined by a preset algorithm, which includes mixed integer linear programming, mixed integer nonlinear programming, genetic algorithm or particle swarm algorithm.

[0153] Furthermore, the prediction module specifically includes:

[0154] Determine the initial forecast electricity price and initial forecast carbon price for a preset time period in the future based on a preset forecast model, historical actual electricity prices, and historical actual carbon prices;

[0155] Fitting a first error distribution between historically predicted electricity prices and historically actual electricity prices within a preset historical time period, and a second error distribution between historically predicted carbon prices and historically actual carbon prices;

[0156] Sampling a first disturbance value from the first error proportional distribution, and superimposing the first disturbance value on the initial predicted electricity price to obtain a predicted electricity price, wherein the first disturbance value is a correction term for the initial predicted electricity price and is used to simulate the deviation between the actual electricity price and the initial predicted electricity price;

[0157] A second disturbance value is sampled from the second error proportion distribution, and the second disturbance value is superimposed on the initial predicted carbon price to obtain the predicted carbon price. The second disturbance value is a correction term for the initial predicted carbon price, which is used to simulate the deviation between the actual carbon price and the initial predicted carbon price.

[0158] The present disclosure also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes the scheduling method for a coal-fired ammonia-blended unit as described above.

[0159] The present disclosure also provides an electronic device, including a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, a scheduling method for a coal-fired ammonia-blended unit as described above is implemented.

[0160] Figure 3 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0161] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0162] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0163] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as a method for scheduling a coal-fired ammonia-blended unit.

[0164] In some embodiments, a method for scheduling a coal-fired ammonia-blended unit may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for scheduling a coal-fired ammonia-blended unit described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute a method for scheduling a coal-fired ammonia-blended unit in any other appropriate manner (e.g., by means of firmware).

[0165] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0166] Computer programs for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0167] In the context of the present disclosure, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0168] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or an LCD (liquid crystal display)) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0169] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0170] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0171] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0172] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and features of different embodiments or examples, unless they are mutually inconsistent.

[0173] Although the embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are illustrative and are not to be construed as limitations on the present disclosure. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present disclosure.

Claims

1. A method for dispatching a coal-fired ammonia-blended unit, characterized in that: include: Obtain the historical real electricity price and historical real carbon price of the unit in the historical preset time period; Determine the predicted electricity price and predicted carbon price for a preset time period in the future based on a preset forecast model, historical actual electricity prices, and historical actual carbon prices; Obtaining a fuel cost model and an emission cost model, wherein the fuel cost model is the fuel cost of the unit under different ammonia blending ratios and different power generation amounts, and the emission cost model is the emission cost of the unit under the predicted carbon price, the preset denitrification unit price, different ammonia blending ratios, and different power generation amounts; Determining preset constraints of the unit, wherein the preset constraints include an ammonia blending ratio constraint and a power generation constraint; Determine a comprehensive benefit model by combining the fuel cost model, the emission cost model, and the predicted electricity price, wherein the comprehensive benefit model is the benefit obtained by the unit under different ammonia blending ratios and different power generation amounts; Based on the preset constraints and the comprehensive benefit model, the target power generation and target ammonia blending ratio corresponding to the unit when the benefit is maximized are determined, and the unit is dispatched based on the target power generation and the target ammonia blending ratio.

2. The method for dispatching a coal-fired ammonia-blended unit according to claim 1, characterized in that: Obtaining a fuel cost model includes: Acquiring historical operating data of the unit, the historical operating data including historical fuel costs of the unit under multiple historical ammonia blending ratios and historical power generation; Based on the historical operating data, respectively determine a coal fuel cost characteristic curve, an ammonia fuel cost characteristic curve, and an additional cost characteristic curve of the unit, wherein the coal fuel cost characteristic curve is a curve showing a relationship between the fuel cost and the power generation of the unit when the ammonia blending ratio is 0, the ammonia fuel cost characteristic curve is a curve showing a relationship between the fuel cost and the power generation of the unit when the ammonia blending ratio is 1, and the additional cost characteristic curve is a curve showing a relationship between the additional cost of the unit and the ammonia blending ratio; A fuel cost model is determined based on the coal fuel cost characteristic curve, the ammonia fuel cost characteristic curve and the additional cost characteristic curve.

3. The method for dispatching a coal-fired ammonia-blended unit according to claim 1, characterized in that: Access emission cost models, including: Acquiring historical emission data of the unit, the historical emission data including historical carbon emissions and historical nitrogen oxide emissions generated by the unit under multiple historical ammonia blending ratios and historical power generation; Based on the historical emission data, fitting and determining an emission characteristic curve of the unit, wherein the emission characteristic curve represents carbon emissions and nitrogen oxide emissions generated by the unit at different ammonia blending ratios and different power generation amounts; An emission cost model is determined by combining the predicted carbon price, the preset denitrification unit price and the emission characteristic curve.

4. The method for dispatching a coal-fired ammonia-blended unit according to claim 1, characterized in that: The ammonia blending ratio constraints include: The target ammonia blending ratio in the future preset time period is within a first preset range, and a difference between the target ammonia blending ratio in the future preset time period and the ammonia blending ratio in a time period before the future preset time period is lower than a first preset value.

5. The method for dispatching a coal-fired ammonia-blended unit according to claim 1, characterized in that: The power generation constraints include: The target power generation in the future preset time period is within a second preset range, and a difference between the target power generation in the future preset time period and the power generation in a time period before the future preset time period is lower than a second preset value.

6. The method for dispatching a coal-fired ammonia-blended unit according to claim 1, characterized in that: The determining, based on the preset constraint conditions and the comprehensive benefit model, the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit includes: Based on the preset constraints and the comprehensive benefit model, a target power generation and a target ammonia blending ratio corresponding to the maximum benefit of the unit are determined by a preset algorithm, wherein the preset algorithm includes mixed integer linear programming, mixed integer nonlinear programming, genetic algorithm or particle swarm algorithm.

7. The method for dispatching a coal-fired ammonia-blended unit according to claim 1, characterized in that: The method of determining the predicted electricity price and the predicted carbon price for a preset time period in the future based on the preset prediction model, the historical actual electricity price, and the historical actual carbon price includes: Determine the initial forecast electricity price and initial forecast carbon price for a preset time period in the future based on a preset forecast model, historical actual electricity prices, and historical actual carbon prices; Fitting a first error distribution between historically predicted electricity prices and historically actual electricity prices within a preset historical time period, and a second error distribution between historically predicted carbon prices and historically actual carbon prices; Sampling a first disturbance value from the first error proportion distribution, and superimposing the first disturbance value on the initial predicted electricity price to obtain a predicted electricity price, wherein the first disturbance value is a correction term for the initial predicted electricity price and is used to simulate the deviation between the actual electricity price and the initial predicted electricity price; A second disturbance value is sampled from the second error proportion distribution, and the second disturbance value is superimposed on the initial predicted carbon price to obtain a predicted carbon price. The second disturbance value is a correction term for the initial predicted carbon price, which is used to simulate the deviation between the actual carbon price and the initial predicted carbon price.

8. A dispatching system for coal-fired ammonia-blended units, characterized in that: include: A data acquisition module is used to obtain the historical real electricity price and historical real carbon price of the unit in a historical preset time period; A forecasting module is used to determine a forecast electricity price and a forecast carbon price for a preset time period in the future based on a preset forecasting model, historical actual electricity prices, and historical actual carbon prices; a cost model generation module, configured to obtain a fuel cost model and an emission cost model, wherein the fuel cost model is the fuel cost of the unit at different ammonia blending ratios and different power generation amounts, and the emission cost model is the emission cost of the unit at different ammonia blending ratios and different power generation amounts under the predicted carbon price and the preset denitrification unit price; A constraint module, configured to determine preset constraint conditions for the unit, wherein the preset constraint conditions include an ammonia blending ratio constraint and a power generation constraint; a revenue model generating module, configured to determine a comprehensive revenue model by combining the fuel cost model, the emission cost model, and the predicted electricity price, wherein the comprehensive revenue model represents the revenue obtained by the unit under different ammonia blending ratios and different power generation amounts; A scheduling module is used to determine the target power generation and target ammonia blending ratio corresponding to the maximum benefit of the unit based on the preset constraints and the comprehensive benefit model, and to schedule the unit based on the target power generation and the target ammonia blending ratio.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes a scheduling method for a coal-fired ammonia-blended unit according to any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the scheduling method for a coal-fired ammonia-blended unit as described in any one of claims 1 to 7 is implemented.

Images