Thermal power plant scheduling method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to a thermal power plant scheduling method and device, electronic equipment, a storage medium and a program product, relates to the technical field of intelligent scheduling, and can dynamically respond to supply and demand changes and optimize a power supply and heat supply scheduling strategy. The method comprises the following steps: acquiring multi-source data of a thermal power plant, wherein the real-time multi-source data comprises power supply data, heat supply data and external data; a heat supply distribution weight is determined according to the external data, a power supply demand is obtained through prediction according to the power supply data, a heat supply demand is obtained through prediction according to the heat supply data, and a supply and demand satisfaction index of the thermal power plant is determined at least according to the heat supply distribution weight, the power supply demand and the heat supply demand; the supply and demand satisfaction index is substituted into a target function, the minimum supply and demand satisfaction index is taken as a target, the target function is solved according to preset constraint conditions, and a target scheduling strategy is generated; and scheduling power supply and heat supply of the thermal power plant according to the target scheduling strategy.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent scheduling technology, specifically to a scheduling method, apparatus, electronic device, storage medium, and program product for a thermal power plant. Background Technology

[0002] Traditional thermal power plant dispatching systems rely mainly on human experience and static models, making it difficult to cope with changing supply and demand relationships and complex operating environments. Summary of the Invention

[0003] To address the aforementioned technical problems, this disclosure provides a method, apparatus, electronic device, storage medium, and program product for dispatching thermal power plants.

[0004] To achieve the above objectives, in a first aspect, this disclosure provides a method for dispatching a thermal power plant, the method comprising: Acquire multi-source data from the thermal power plant, including real-time multi-source data such as power supply data, heating data, and external data; The heat supply allocation weight is determined based on the external data, and the power supply demand is predicted based on the power supply data. The heat supply demand is predicted based on the heat supply data. At least the supply and demand satisfaction index of the thermal power plant is determined based on the heat supply allocation weight, the power supply demand, and the heat supply demand. Substitute the supply and demand satisfaction index into the objective function, take minimizing the supply and demand satisfaction index as the objective, solve the objective function according to the preset constraints, and generate the target scheduling strategy; The power supply and heating supply of the thermal power plant are scheduled according to the target scheduling strategy.

[0005] Secondly, this disclosure provides a power plant dispatching device, the device comprising: The multi-source data acquisition unit is configured to acquire multi-source data from the thermal power plant, including real-time power supply data, heating data, and external data. The supply and demand analysis unit is configured to determine the heat allocation weight based on the external data, predict the power supply demand based on the power supply data, predict the heat supply demand based on the heat supply data, and determine the supply and demand satisfaction index of the thermal power plant based at least on the heat allocation weight, the power supply demand, and the heat supply demand. The scheduling strategy analysis unit is configured to input the supply and demand satisfaction index into the objective function, take the minimum supply and demand satisfaction index as the objective, solve the objective function according to preset constraints, and generate the target scheduling strategy. The scheduling unit is configured to schedule the power supply and heating supply of the thermal power plant according to the target scheduling strategy.

[0006] Thirdly, this disclosure provides an electronic device, including: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the method described in the first aspect.

[0007] Fourthly, this disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described in the first aspect.

[0008] Fifthly, this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0009] The above technical solution acquires power supply data, heating data, and external data from the combined heat and power (CHP) plant. Heating allocation weights are determined based on the external data, and power and heating demands are predicted using the power and heating data respectively. Then, a supply-demand satisfaction index is determined by combining the heating allocation weights, power and heating demands. Finally, the scheduling strategy is optimized based on the supply-demand satisfaction index. This solution solves the problems of insufficient data support, large prediction deviations, and delayed response in traditional systems, improves prediction accuracy, and enables the CHP plant's scheduling strategy to dynamically respond to changes in supply and demand, optimize energy allocation, enhance the synergy of CHP, and thus improve the efficiency of CHP plant scheduling.

[0010] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0011] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating a thermal power plant scheduling method according to an exemplary embodiment of the present disclosure.

[0012] Figure 2 This is a block diagram of a thermal power plant dispatching device according to an exemplary embodiment of the present disclosure.

[0013] Figure 3 This is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0014] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0015] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0016] As mentioned in the background section, the supply and demand forecasting models in traditional thermal power plant dispatching systems do not fully consider the dynamic impact of external environmental factors. They use a single historical data regression method to predict both power and heating demand, without dynamically correcting them based on key factors such as temperature changes and holidays. As a result, the predicted power and heating demand results deviate significantly. Secondly, the dispatching strategies of traditional thermal power plant dispatching systems rely on historical experience or fixed rules, which cannot respond to changes in supply and demand in real time, easily leading to energy waste or insufficient supply.

[0017] In view of this, the present disclosure provides a method, apparatus, electronic device, storage medium and program product for dispatching thermal power plants, which can dynamically respond to changes in supply and demand and optimize the dispatching strategy for power supply and heating.

[0018] Figure 1 This is a thermal power plant dispatching method illustrated according to an exemplary embodiment of the present disclosure, such as... Figure 1 As shown, the method may include the following steps: In step S11, multi-source data from the thermal power plant is acquired. The real-time multi-source data includes power supply data, heating data, and external data.

[0019] Among them, power supply data can be obtained through smart meters, heating data can be obtained through thermal sensors, and external data can be obtained through meteorological data interfaces. External data can include parameters such as environmental data, power grid load demand, and heating network load demand.

[0020] In step S12, the heat allocation weight is determined based on the external data, the power supply demand is predicted based on the power supply data, the heat supply demand is predicted based on the heat supply data, and the supply and demand satisfaction index of the thermal power plant is determined based at least on the heat allocation weight, the power supply demand, and the heat supply demand.

[0021] In step S13, the supply and demand satisfaction index is substituted into the objective function, and the objective function is solved according to the preset constraints to generate the target scheduling strategy, with the goal of minimizing the supply and demand satisfaction index.

[0022] In step S14, the power supply and heating supply of the thermal power plant are scheduled according to the target scheduling strategy.

[0023] In this embodiment, the heating allocation weight is determined based on external data, and the priority of heating is dynamically adjusted through the heating allocation weight. For example, the heating allocation weight is automatically increased when the temperature drops sharply. Compared with the traditional thermal power plant dispatching system that relies on fixed weights to allocate heating and power supply, this disclosure dynamically adjusts the priority of heating supply through the heating allocation weight, which can adapt to the impact of sudden temperature changes on the heating network load. In addition, at least the supply and demand satisfaction index of the thermal power plant is determined based on the heating allocation weight, power supply demand, and heating demand, providing a unified evaluation index. The supply and demand satisfaction index realizes the normalization processing of multi-source data, providing a basis for the optimization of dispatching strategies, thereby significantly improving the reliability of the target dispatching strategy.

[0024] In the above technical solution, power supply data, heating data, and external data from the combined heat and power (CHP) plant are acquired. Heating allocation weights are determined based on the external data, allowing for rapid response to the impact of temperature changes on the heating network load. For example, heating demand is prioritized during cold waves. Power supply and heating demand are predicted based on the power supply and heating data, respectively. Then, a supply-demand satisfaction index is determined by combining the heating allocation weights, power supply demand, and heating demand. Finally, the scheduling strategy is optimized based on the supply-demand satisfaction index, using it as a unified evaluation standard to provide a quantitative basis for optimizing the scheduling strategy. This achieves coordinated optimization of power supply and heating strategies, solving the problems of insufficient data support, large prediction deviations, and delayed response in traditional systems. It improves prediction accuracy, enabling the CHP plant's scheduling strategy to dynamically respond to changes in supply and demand, optimize energy allocation, enhance the synergy of CHP, and thus improve the efficiency of CHP plant scheduling.

[0025] To facilitate a better understanding of the thermal power plant dispatching method provided in this disclosure by those skilled in the art, the method is described in detail below.

[0026] In one feasible embodiment, the external data includes ambient temperature, power grid load demand, and heating network load demand; The step of determining the heating allocation weight based on the external data includes: Substituting the ambient temperature, the power grid load demand, and the heating network load demand into the following calculation formula, we obtain the heating allocation weights: , Among them, W h Characterizing the heating distribution weights, T represents the ambient temperature, T0 represents the reference temperature, and D... h Characterizing the heating network load demand, D e Characterizing grid load demand, k c The thermoelectric conversion coefficient is represented by α and γ, the weighting coefficients are represented by α+γ=1, and β represents the temperature sensitivity coefficient.

[0027] Among them, the heating priority is dynamically adjusted according to the ambient temperature and the power grid load demand to obtain the heating allocation weight. For example, the heating weight is increased in cold weather to give priority to meeting the heating network demand.

[0028] It is worth noting that ambient temperature T represents the real-time temperature data of the environment where the thermal power plant is located. This data can be collected through temperature sensors or meteorological data interfaces and is used to reflect the degree to which current heating demand is affected by temperature changes. Reference temperature T0 represents the temperature threshold corresponding to a pre-set baseline for heating demand. This threshold can be set through historical temperature data statistics or expert experience and serves as the calculation benchmark for temperature-sensitive parameters. The heating network load demand D... h The total amount of heat energy that a combined heat and power plant needs to supply can be obtained in real time through a heat network monitoring system, used to quantify the current heating demand pressure; grid load demand D e The total amount of electricity that a thermal power plant needs to supply can be obtained through the power grid dispatch system interface, used to quantify the current power demand pressure; the thermoelectric conversion coefficient k c The conversion coefficient characterizes the conversion of a unit of heat energy into electrical energy, serving as a unit for unifying the load demand of the power grid and the load demand of the heating network; the weighting coefficients α and γ can be set by empirical values ​​to balance the dynamic impact of temperature and load demand on the distribution of heating; the temperature sensitivity coefficient β characterizes the intensity of the influence of temperature changes on the weight of heating, and can be calibrated by regression analysis or trial and error, possessing the characteristic of adapting to the demand of different climatic regions, with the unit of temperature sensitivity coefficient β being ℃-1. It should be understood that, in this embodiment of the disclosure, a weighted formula comprising a temperature-sensitive term and a load demand ratio term is constructed to dynamically adjust the heating allocation weights; the temperature-sensitive term... A sigmoid function is used to map the difference between ambient temperature and reference temperature into a nonlinear weighting factor. When the actual temperature T is lower than the reference temperature T0, the function value increases rapidly as the temperature decreases, thereby increasing the heating weight to cope with the surge in heating demand. When the ambient temperature T is higher than the reference temperature T0, the function value tends to level off, which can avoid over-allocation of heating resources. (Load demand ratio) By using the ratio of heating network load demand to grid load demand, combined with the heat-to-power conversion coefficient, the resource competition relationship between power supply and heating in combined heat and power is quantified. When the heating network load demand is significantly higher than the grid load demand, this ratio is increased to prioritize the allocation of heating. The temperature-sensitive term and the load demand ratio term are weighted and summed using weighting coefficients. Under the constraint of ensuring that the total weight is constant, the coordinated response to temperature changes and load demand fluctuations is achieved, thereby dynamically optimizing the heating allocation strategy.

[0029] In this embodiment, by integrating external data including ambient temperature, power grid load demand and heating network load demand, a component is used to calculate the dynamic allocation ratio between heating and power supply through mathematical modeling. Specifically, a logistic regression model that includes temperature sensitivity coefficient and load demand ratio can be used to quantify the impact of external environmental changes on energy allocation and obtain the heating allocation weight.

[0030] Understandably, traditional methods typically adjust heat allocation using fixed weights or single factors, such as setting static weights based solely on historical heating data or adjusting the heating ratio only in response to temperature changes. Such methods cannot simultaneously capture the real-time competitive relationship between temperature surges and the grid / heat network load, leading to delayed heat allocation or supply-demand imbalances. However, this embodiment integrates temperature-sensitive terms and load demand ratios to establish a heat allocation analysis model. This model responds to the nonlinear effects of temperature changes while simultaneously balancing the differences in heat and power load demands in real time, significantly improving the accuracy and adaptability of heat allocation weight calculations. It effectively solves the problem of allocation deviations caused by the failure to dynamically consider changes in weather temperature and grid / heat network load demands in heat allocation weights, achieving real-time and accurate allocation of heating resources. Specifically, the temperature-sensitive term uses an S-shaped function to quickly respond to the impact of temperature surges on heating demand, avoiding insufficient or redundant heating under extreme temperatures. The load demand ratio term quantifies the competitive relationship between heat and power loads, preventing resource allocation imbalances caused by a surge in single load demand. The synergistic effect of these two factors allows for dynamic optimization of heat allocation weights under complex operating environments, improving the overall energy efficiency and supply-demand matching accuracy of the cogeneration system.

[0031] In one feasible embodiment, the power supply data includes historical power supply amount and power supply date; The step of predicting power demand based on the power supply data includes: Substituting the historical power supply and the power supply date into the following calculation formula, the power supply demand is obtained: , Among them, E pred (t) represents the power demand, y0 represents the baseline power supply, y1 represents the weighting coefficient of the historical power supply during the same period, and e t-i y1 represents the power supply at time lag i in the historical power supply data, y2 represents the weighting coefficient of the moving average, y1 + y2 = 1, j represents the sampled data of the historical power supply data, n represents the sampling sequence number, and e represents the weighting coefficient of the moving average. t-ni y3 represents the power supply at a time lag ni in the historical power supply data, and y3 represents the high-temperature correction amount. The high temperature characteristic function, T t Characterizing the predicted ambient temperature, T max Y4 represents the high temperature warning value, D represents the power supply correction amount for rest days, and Y4 represents the power supply correction amount for rest days. t D represents the date of power supply. off It represents a day off.

[0032] Among them, by analyzing the periodic patterns of historical power supply, and combining ambient temperature and calendar data, the predicted power demand is corrected. For example, when the predicted temperature (based on the expected temperature in the weather forecast) exceeds the warning value, the power supply correction amount is automatically increased.

[0033] It is worth noting that the baseline power supply y0 represents the basic power supply of the thermal power plant under normal operating conditions, ensuring the normal operation of the thermal power plant; the historical power supply e represents the power supply at time lag i. t-i This refers to selecting data from the historical power supply at time lag i; the weighting coefficient y1 of the historical power supply during the same period is dimensionless data. The moving average calculation of historical power supply over multiple periods can smooth data within a fixed time window, eliminating random fluctuations and reflecting periodic patterns; the weighting coefficient y2 of the moving average is dimensionless; high temperature indicator function. This represents the correction term triggered when the predicted temperature exceeds a preset threshold. Real-time ambient temperature can be obtained through temperature sensors or meteorological data interfaces to quantify the additional impact of extreme high temperatures on power demand. The unit of the high-temperature correction y3 is MW, which can be determined empirically, superimposed with the predicted impact of high-temperature weather on power demand. For example, in high-temperature weather, the usage rate of cooling appliances such as air conditioners and fans will further increase. (Rest day flag function) The logical judgment item for identifying whether the power supply date is a rest day can be implemented through a date type classifier or calendar database to distinguish the differences in power consumption patterns of different date types, such as classifying date types into weekdays and rest days; the unit of the rest day power supply correction y4 is MW, which can be determined based on experience, and the predicted amount of power supply demand on rest days is added. For example, on rest days (weekends or holidays), the use of entertainment facilities will further increase power consumption, thereby further increasing the power supply demand.

[0034] It should be understood that in this embodiment, a prediction benchmark is established using a baseline power supply quantity y0, and short-term fluctuation trends are captured by combining historical power supply quantities with lagged terms. A moving average term is used to smooth periodic changes, and a high-temperature indicator function and a rest day indicator function are introduced to dynamically respond to external environmental and date characteristics. For example, when the predicted temperature exceeds the high-temperature warning value, a high-temperature correction is automatically added to the predicted value to reflect changes in power demand caused by a surge in air conditioning load; when the power supply date is a rest day, a rest day correction adjusts the predicted value, adapting to scenarios of reduced industrial electricity consumption and increased residential electricity consumption. This embodiment integrates multi-source data, enabling the model to correct prediction biases in real time, thereby improving its adaptability to complex external conditions and historical dynamic patterns.

[0035] In this embodiment, periodic analysis is performed based on historical power supply and power supply dates. Combined with prediction tools such as high temperature indicator function and rest day correction, time series analysis and event-driven correction algorithm are used to capture the fluctuation impact of extreme weather and holidays on power supply demand and achieve power supply demand prediction.

[0036] Understandably, traditional power demand forecasting models typically rely solely on single historical data or static rules, failing to consider the dynamic impact of temperature fluctuations or date types on electricity consumption patterns, leading to forecast results that deviate from actual demand. However, this embodiment constructs a multi-factor dynamic forecasting model, incorporating historical data patterns, environmental temperature fluctuations, and date type differences into a unified calculation framework. This solves the problems of single-dimensionality and delayed response in traditional methods, significantly improving forecast accuracy and real-time performance. It effectively enhances the accuracy of power demand forecasting by dynamically fusing historical data, temperature changes, and date characteristics to precisely quantify the impact of extreme weather and rest days on power demand, providing a reliable forecasting basis for thermal power plant dispatching strategies and avoiding energy waste or supply shortages due to forecasting errors.

[0037] In one feasible embodiment, the heating data includes historical heating volume and heating dates; The step of predicting heating demand based on the heating data includes: Substituting the historical heating volume and the heating date into the following formula, the heating demand is obtained: , Among them, H pred (t) represents heating demand, r1 represents the weighting coefficient of historical heating supply for the same period, h t-i The heat supply at lag time i in the historical heat supply is represented by r1, r2 represents the weighting coefficient of the moving average, r1 + r2 = 1, k represents the number of historical heat supply samples, n represents the sampling sequence number, and h represents the heat supply at lag time i in the historical heat supply. t-ni r3 represents the heat supply at a lag of ni in the historical heat supply, and r3 represents the low-temperature correction factor. Characteristic function of low temperature, T t Characterizing the predicted temperature, T min Characterizes the low temperature warning value.

[0038] Among them, heating supply adjustments are triggered by combining historical weekly moving average data of heating supply with low temperature weather and calendar, such as adding a low temperature correction amount when the predicted temperature is lower than a set threshold.

[0039] It is worth noting that the heating supply h at time lag i in the historical heating data t-i Characterizes historical heating supply at an interval of i time units from the current time, for example, i could be 24 hours, capturing short-term heating supply fluctuations; moving average term The characterization involves summing the heat supply at the same point in time over the past k periods. For example, the period length of k could be 4 weeks to extract periodic characteristics; low temperature indicator function. Characterized when the predicted temperature is below the low temperature warning value Indicator functions that take a value of 1, such as T min The low-temperature correction mechanism can be triggered at -5℃; the unit of the low-temperature correction amount r3 is GJ / h, which can be determined empirically, and is superimposed with the predicted amount of heating demand due to low-temperature weather. For example, the increased use of heating equipment in low-temperature weather will further lead to an increase in heating demand.

[0040] It should be understood that the prediction in this embodiment is achieved by superimposing historical data items and environmental correction items; the historical heat supply h at time lag i. t-i Its weight r1 reflects short-term changes in heating demand; the moving average term identifies periodic patterns by accumulating the heating supply at the same time over multiple weeks and assigning it a weight r2; when the predicted temperature T... t Below the low temperature warning value T min At this time, the low temperature correction amount r3 can be set to a fixed increment or a dynamic value proportional to the temperature difference to compensate for the sudden increase in heating demand caused by low temperature.

[0041] In this embodiment, historical heating supply and heating dates are combined, and a prediction mechanism with low temperature indicator function and rest day correction is introduced. A moving average model and temperature threshold triggering mechanism are used to periodically analyze the real-time changes in heating demand caused by low temperature environment and rest days, so as to achieve the prediction of heating demand.

[0042] Understandably, traditional heating forecasting models rely solely on historical data time-series analysis, failing to incorporate low-temperature weather as an independent variable into the forecasting formula. The impact of low temperatures is typically modeled through a linear relationship between temperature and heating demand, but this model cannot accurately reflect the nonlinear demand changes during sudden temperature drops. The embodiments disclosed in this publication address the forecasting bias caused by sudden increases in heating demand during low-temperature weather. By dynamically identifying extreme weather conditions and applying corrections through a low-temperature flag function, the predicted values ​​more closely align with actual demand, achieving rapid response to dynamic environmental factors and improving the robustness of the forecasting model in complex scenarios. Furthermore, when forecasting heating demand, the embodiments of this publication can also introduce a date flag function, classifying dates into cold and warm seasons, thereby increasing the influence of date on the predicted heating demand.

[0043] In one feasible embodiment, determining the supply-demand satisfaction index of the thermal power plant based at least on the heat allocation weight, the power supply demand, and the heat supply demand includes: Obtain the current power supply and current heat supply of the thermal power plant; Determine a first ratio of the current heat supply to the heat demand, and a second ratio of the current power supply to the power demand; Substituting the first ratio, the heat allocation weight, and the second ratio into the following formula, the supply and demand satisfaction index of the thermal power plant is obtained: , Among them, SSI represents the supply and demand satisfaction index, w h H represents the weighting of heat allocation. act H represents the current heat supply. pred (t) represents heating demand, E act E represents the current power supply. pred (t) represents the power demand.

[0044] The predicted results of power supply demand and heating demand are integrated according to the heating allocation weight to obtain the supply and demand satisfaction index. For example, by weighted calculation of the current power supply relative to the power supply demand and the current heating supply relative to the heating demand, a comprehensive evaluation index (i.e., the supply and demand satisfaction index) is generated, and the scheduling strategy is optimized according to the supply and demand satisfaction index.

[0045] It is worth noting that the Supply-Demand Satisfaction Index (SSI) is a quantitative indicator that comprehensively reflects the supply-demand balance of a combined heat and power plant. It is calculated by weighting the ratio of actual operating data to predicted values ​​for heating and power supply, and is used to dynamically assess the synergy of combined heat and power generation. h Weighting coefficients, dynamically adjusted based on external environmental factors, are used to reflect changes in the priority of load demand between the heating network and the power grid; H act E represents the current heat supply. act The current power supply can be monitored and acquired in real time by corresponding sensors, and compared with its corresponding predicted value to correct for supply and demand discrepancies; H pred (t) represents heating demand, E pred (t) represents the power demand, which can be generated by combining historical data moving average, environmental factor correction term and date type flag function to provide dynamic benchmark reference.

[0046] It should be understood that by allocating heating weights w h With heating satisfaction Multiply, then add up the power supply satisfaction The weighted values ​​are used to generate a comprehensive supply and demand satisfaction index (SSI); heating satisfaction quantifies the degree of supply and demand matching on the heating side by the ratio of actual heating supply to predicted value, and power supply satisfaction quantifies the degree of matching on the power supply side in the same way; heating allocation weights w h It can be dynamically adjusted according to ambient temperature, heating demand, and power supply demand. For example, the heating weight can be increased in cold weather and decreased in hot weather; this can be achieved through real-time data collection of H...act and E act It can dynamically correct prediction deviations. For example, when the actual heating supply is lower than the predicted heating demand, the heating satisfaction rate decreases, thereby triggering an adjustment of the scheduling strategy.

[0047] In this embodiment, based on the heat allocation weight, the power supply demand and heat supply demand are dynamically integrated and evaluated to comprehensively assess the supply and demand balance of the cogeneration system and obtain the supply and demand satisfaction index.

[0048] Understandably, traditional technologies rely on fixed weights or single historical data for prediction, failing to consider the impact of temperature changes on heating priority and lacking feedback correction from real-time operational data. This disclosure addresses the problem of static models' inability to adapt to environmental changes through dynamic weight allocation and real-time data fusion. Furthermore, by quantitatively assessing the synergy between heating and power supply, it overcomes the lack of a basis for energy efficiency optimization in existing technologies. In addition, this disclosure improves the accuracy of supply and demand assessment for combined heat and power plants, adapting to external environmental changes through dynamic weight adjustments and reducing the impact of prediction bias on scheduling strategies. The combination of real-time data and prediction models enhances system response speed, avoids energy waste or supply shortages, and provides a basis for optimal allocation of combined heat and power through quantitative synergy assessment.

[0049] In this embodiment, a dynamic weight allocation and multi-factor correction mechanism is used to combine changes in the external environment with historical data to achieve real-time adjustment of power supply and heating demand. This avoids deviations between predicted and actual power supply and heating demand, improving the accuracy and reliability of the predicted values. By allocating heating weights, a dynamic correlation between power supply and heating demand is established, enabling coordinated optimization of power supply and heating, balancing the synergy of combined heat and power (CHP), optimizing energy allocation efficiency, reducing energy waste and supply shortage risks, thereby improving the overall energy efficiency of the CHP system. Furthermore, by generating a supply-demand satisfaction index in real time, a quantitative basis is provided for scheduling strategies, shortening response delays.

[0050] In one feasible embodiment, the constraint includes a preset threshold, and the step of solving the objective function based on the preset constraint to generate a target scheduling strategy, with the goal of minimizing the supply-demand satisfaction exponent, includes: If the supply and demand satisfaction index is greater than or equal to a preset threshold, the heating allocation weight is adjusted until the supply and demand satisfaction index, which is re-determined based on the power supply demand, the heating demand, and the adjusted heating allocation weight, is less than the preset threshold. The re-determined supply and demand satisfaction index is then substituted into the objective function to generate a target scheduling strategy. The objective function includes: X = min(SSI), Where X represents the target scheduling strategy, and SSI represents the supply and demand satisfaction index.

[0051] It is worth noting that the Supply and Demand Satisfaction Index (SSI) reflects the degree of matching between the current operating status of the thermal power plant and external demand. The target scheduling strategy X refers to a dynamic adjustment scheme that includes power supply strategy and heating strategy generated by optimization methods. It can be realized by the objective function minimization algorithm to balance the allocation of power supply and heating resources under the minimum constraint conditions.

[0052] It should be understood that the supply-demand satisfaction index is used as the objective function to find its minimum value, and the variables in the index calculation are dynamically updated through real-time collected power supply data, heating data, and external parameters. When changes in the external environment cause fluctuations in the load demand of the power grid or heating network, the supply-demand satisfaction index will change synchronously, triggering the optimization model to recalculate the optimal strategy. For example, when a sudden drop in temperature causes a surge in the load demand of the heating network, the heating allocation weights are adjusted accordingly, and the calculation of the supply-demand satisfaction index will prioritize ensuring heating demand. The optimization model automatically generates corresponding power supply and heating adjustment strategies by minimizing the index value. The entire process does not rely on preset rules or human experience, but achieves dynamic decision-making based on real-time data fusion and mathematical optimization.

[0053] Understandably, traditional scheduling strategies rely on fixed rules or historical experience, failing to respond in real time to dynamic parameter changes such as weather temperature and grid load, leading to supply-demand matching lags. However, this invention uses a supply-demand satisfaction index derived from multi-source data fusion as the optimization objective, employing mathematical methods to automatically solve for the optimal strategy, enabling scheduling decisions to adapt to external environmental fluctuations. For example, existing technologies for predicting power demand during high-temperature weather rely solely on historical data, neglecting the impact of real-time temperature on grid load. This invention, by dynamically adjusting the high-temperature correction, makes the predicted value more closely match actual demand. Furthermore, this invention enables real-time dynamic adjustment of power supply and heating strategies in cogeneration plants, solving the energy waste or insufficient supply problems caused by response lags in traditional methods. For instance, in scenarios of sudden increases in heating network load, the system can quickly adjust heating allocation weights and generate the optimal strategy, avoiding user complaints due to insufficient heating or energy waste caused by excessive heating. Moreover, by automatically balancing power supply and heating resource allocation through a mathematical optimization model, the overall operating efficiency of the cogeneration system is improved.

[0054] In a feasible embodiment, scheduling the power supply and heating supply of the thermal power plant according to the target scheduling strategy may include: The difference between the target scheduling strategy and the current scheduling strategy of the thermal power plant is determined, and the operating status of the thermal power plant for heating and power supply is dynamically adjusted based on the difference.

[0055] The difference is determined using the following formula: ΔX=X now -X, Where X represents the target scheduling strategy, X now ΔX represents the current scheduling strategy of the thermal power plant, and ΔX represents the difference between the current scheduling strategy and the target scheduling strategy.

[0056] It is worth noting that X now The strategy parameters characterizing the real-time operating status of the thermal power plant can be generated by using sensor networks and data processing modules to collect data on heat supply, power supply, and equipment operating status in real time. After processing, the current strategy parameters are generated to ensure that the adjustment instructions match the real-time operating conditions. X represents the target scheduling strategy generated based on the supply and demand satisfaction index. The optimal solution that satisfies the supply and demand balance target can be solved by a constraint optimization model. This model uses the thermal power plant's supply and demand satisfaction index as the objective function and combines it with equipment operating constraints to generate the optimal strategy parameters.

[0057] It should be understood that this disclosure involves real-time collection of the current heat and electricity supply and equipment operating parameters of the thermal power plant, which are then converted into the current strategy parameter X. now Based on the supply-demand satisfaction index of the thermal power plant output by the supply-demand relationship evaluation model, an optimization algorithm is used to generate the optimal strategy parameter X that satisfies the minimum constraint value. The difference ΔX between the two is used as a scheduling adjustment command to directly drive the thermal power plant to adjust its heating and power output. For example, when ΔX is positive, the current heating or power output is higher than the optimal target, and the corresponding output needs to be reduced; when ΔX is negative, the output needs to be increased. This difference ΔX calculation process is dynamically generated through a mathematical optimization model, avoiding the response lag problem caused by manual experience or fixed rules. At the same time, it transforms the complex multivariate optimization problem into a linear adjustment command, improving the real-time performance and operability of the scheduling system.

[0058] Understandably, traditional methods rely on human experience or static models to generate scheduling strategies, which cannot respond to changes in the external environment in real time, leading to energy waste or supply shortages. However, in this embodiment, the difference between the current strategy and the optimal strategy is dynamically calculated to directly generate real-time adjustment instructions, enabling the scheduling system to quickly match changes in supply and demand. For example, when a sudden drop in temperature causes a surge in the heating network load, traditional methods require waiting for manual adjustments or relying on historical data for recalculation, while this invention updates X in real time. now With X, incremental heating instructions can be generated immediately, significantly shortening the response time. On the other hand, existing technologies lack quantitative assessment of the synergy of combined heat and power (CHP). However, in this embodiment, by using the supply and demand satisfaction index as the optimization target, the allocation of heating and power supply is ensured to meet the optimal comprehensive energy efficiency, realizing real-time dynamic optimization of the CHP scheduling strategy. This solves the response lag problem caused by the reliance on historical data or human experience in traditional methods. Furthermore, by generating precise adjustment quantities through a mathematical optimization model, the efficiency of coordinated allocation of heating and power supply is improved, energy waste is reduced, and supply and demand balance is ensured.

[0059] Based on the same inventive concept, this disclosure also provides a thermal power plant dispatching device, the thermal power plant dispatching device 200 comprising: The multi-source data acquisition unit 201 is configured to acquire multi-source data from the thermal power plant, including real-time power supply data, heating data, and external data. The supply and demand analysis unit 202 is configured to determine the heat allocation weight based on the external data, predict the power supply demand based on the power supply data, predict the heat supply demand based on the heat supply data, and determine the supply and demand satisfaction index of the thermal power plant based at least on the heat allocation weight, the power supply demand, and the heat supply demand. The scheduling strategy analysis unit 203 is configured to input the supply and demand satisfaction index into the objective function, take the minimum supply and demand satisfaction index as the objective, solve the objective function according to preset constraints, and generate a target scheduling strategy. The scheduling unit 204 is configured to schedule the power supply and heating of the thermal power plant according to the target scheduling strategy.

[0060] In the above technical solution, power supply data, heating data, and external data from the combined heat and power (CHP) plant are acquired. Heating allocation weights are determined based on the external data, allowing for rapid response to the impact of temperature changes on the heating network load. For example, heating demand is prioritized during cold waves. Power supply and heating demand are predicted based on the power supply and heating data, respectively. Then, a supply-demand satisfaction index is determined by combining the heating allocation weights, power supply demand, and heating demand. Finally, the scheduling strategy is optimized based on the supply-demand satisfaction index, using it as a unified evaluation standard to provide a quantitative basis for optimizing the scheduling strategy. This achieves coordinated optimization of power supply and heating strategies, solving the problems of insufficient data support, large prediction deviations, and delayed response in traditional systems. It improves prediction accuracy, enabling the CHP plant's scheduling strategy to dynamically respond to changes in supply and demand, optimize energy allocation, enhance the synergy of CHP, and thus improve the efficiency of CHP plant scheduling.

[0061] Furthermore, when the constraints include a preset threshold, the scheduling strategy analysis unit 203 is configured to adjust the heating allocation weight when the supply-demand satisfaction index is greater than or equal to the preset threshold, until the supply-demand satisfaction index, which is re-determined based on the power supply demand, the heating demand, and the adjusted heating allocation weight, is less than the preset threshold. The re-determined supply-demand satisfaction index is then substituted into the objective function to generate a target scheduling strategy. The objective function includes: X = min(SSI), Where X represents the target scheduling strategy, and SSI represents the supply and demand satisfaction index.

[0062] Furthermore, the supply and demand analysis unit 202 is configured to obtain the current power supply and current heat supply of the thermal power plant; Determine a first ratio of the current heat supply to the heat demand, and a second ratio of the current power supply to the power demand; Substituting the first ratio, the heat allocation weight, and the second ratio into the following formula, the supply and demand satisfaction index of the thermal power plant is obtained: , Among them, SSI represents the supply and demand satisfaction index, w h H represents the weighting of heat allocation. act H represents the current heat supply. pred (t) represents heating demand, E act E represents the current power supply. pred (t) represents the power demand.

[0063] Furthermore, when the power supply data includes historical power supply volume and power supply date, the supply and demand analysis unit 202 is configured to substitute the historical power supply volume and the power supply date into the following calculation formula to obtain the power supply demand: , Among them, E pred (t) represents the power demand, y0 represents the baseline power supply, y1 represents the weighting coefficient of the historical power supply during the same period, and e t-i y1 represents the power supply at time lag i in the historical power supply data, y2 represents the weighting coefficient of the moving average, y1 + y2 = 1, j represents the sampled data of the historical power supply data, n represents the sampling sequence number, and e represents the weighting coefficient of the moving average. t-ni y3 represents the power supply at a time lag ni in the historical power supply data, and y3 represents the high-temperature correction amount. The high temperature characteristic function, T t Characterizing the predicted ambient temperature, T max Y4 represents the high temperature warning value, D represents the power supply correction amount for rest days, and Y4 represents the power supply correction amount for rest days. t D represents the date of power supply. off It represents a day off.

[0064] Furthermore, when the heating data includes historical heating volume and heating dates, the supply and demand analysis unit 202 is configured to substitute the historical heating volume and heating dates into the following calculation formula to obtain the heating demand: , Among them, H pred (t) represents heating demand, r1 represents the weighting coefficient of historical heating supply for the same period, h t-iThe heat supply at lag time i in the historical heat supply is represented by r1, r2 represents the weighting coefficient of the moving average, r1 + r2 = 1, k represents the number of historical heat supply samples, n represents the sampling sequence number, and h represents the heat supply at lag time i in the historical heat supply. t-ni r3 represents the heat supply at a lag of ni in the historical heat supply, and r3 represents the low-temperature correction factor. Characteristic function of low temperature, T t Characterizing the predicted ambient temperature, T min Characterizes the low temperature warning value.

[0065] Furthermore, when the external data includes ambient temperature, power grid load demand, and heating network load demand, the supply and demand analysis unit 202 is configured to substitute the ambient temperature, the power grid load demand, and the heating network load demand into the following calculation formula to obtain the heating allocation weight: , Among them, W h Characterizing the heating distribution weights, T represents the ambient temperature, T0 represents the reference temperature, and D... h Characterizing the heating network load demand, D e Characterizing grid load demand, k c The thermoelectric conversion coefficient is represented by α and γ, the weighting coefficients are represented by α+γ=1, and β represents the temperature sensitivity coefficient.

[0066] Regarding the thermal power plant dispatching device 200 in the above embodiments, the specific methods by which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0067] Based on the same inventive concept, this disclosure also provides an electronic device, comprising: A memory on which computer programs are stored; A processor is used to execute the computer program in the memory to implement the above-described thermal power plant scheduling method.

[0068] Figure 3 This is a block diagram illustrating an electronic device 300 according to an exemplary embodiment. Figure 3 As shown, the electronic device 300 may include a processor 301 and a memory 302. The electronic device 300 may also include one or more of a multimedia component 303, an input / output (I / O) interface 304, and a communication component 305.

[0069] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps in the aforementioned thermal power plant scheduling method. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data, such as power supply data, heating data, external data, heating allocation weights, power supply demand, heating demand, supply-demand satisfaction index, and target scheduling strategies, etc. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 302 or transmitted via the communication component 305. The audio component also includes at least one speaker for outputting audio signals. I / O interface 304 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 305 is used for wired or wireless communication between electronic device 300 and other devices. Wireless communication includes, for example, Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, and is not limited herein. Therefore, the corresponding communication component 305 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0070] In an exemplary embodiment, the electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described thermal power plant scheduling method.

[0071] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the thermal power plant scheduling method described above. For example, the computer-readable storage medium may be the memory 302 including program instructions described above, which may be executed by the processor 301 of the electronic device 300 to complete the thermal power plant scheduling method described above.

[0072] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0073] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0074] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for dispatching a thermal power plant, characterized in that, The method includes: Acquire multi-source data from the thermal power plant, including real-time multi-source data such as power supply data, heating data, and external data; The heat supply allocation weight is determined based on the external data, and the power supply demand is predicted based on the power supply data. The heat supply demand is predicted based on the heat supply data. At least the supply and demand satisfaction index of the thermal power plant is determined based on the heat supply allocation weight, the power supply demand, and the heat supply demand. Substitute the supply and demand satisfaction index into the objective function, take minimizing the supply and demand satisfaction index as the objective, solve the objective function according to the preset constraints, and generate the target scheduling strategy; The power supply and heating supply of the thermal power plant are scheduled according to the target scheduling strategy.

2. The thermal power plant dispatching method according to claim 1, characterized in that, The constraints include preset thresholds. The objective function, which aims to minimize the supply-demand satisfaction exponent, is solved based on the preset constraints to generate a target scheduling strategy, including: If the supply and demand satisfaction index is greater than or equal to a preset threshold, the heating allocation weight is adjusted until the supply and demand satisfaction index, which is re-determined based on the power supply demand, the heating demand, and the adjusted heating allocation weight, is less than the preset threshold. The re-determined supply and demand satisfaction index is then substituted into the objective function to generate a target scheduling strategy. The objective function includes: X = min(SSI), Where X represents the target scheduling strategy, and SSI represents the supply and demand satisfaction index.

3. The thermal power plant dispatching method according to claim 1, characterized in that, The determination of the supply-demand satisfaction index of the thermal power plant based at least on the heat allocation weight, the power supply demand, and the heat supply demand includes: Obtain the current power supply and current heat supply of the thermal power plant; Determine a first ratio of the current heat supply to the heat demand, and a second ratio of the current power supply to the power demand; Substituting the first ratio, the heat allocation weight, and the second ratio into the following formula, the supply and demand satisfaction index of the thermal power plant is obtained: ， Among them, SSI represents the supply and demand satisfaction index, w h H represents the weighting of heat allocation. act H represents the current heat supply. pred (t) represents heating demand, E act E represents the current power supply. pred (t) represents the power demand.

4. The thermal power plant dispatching method according to claim 1, characterized in that, The power supply data includes historical power supply volume and power supply dates; The step of predicting power demand based on the power supply data includes: Substituting the historical power supply and the power supply date into the following calculation formula, the predicted power demand is obtained: ， Among them, E pred (t) represents the power demand, y0 represents the baseline power supply, y1 represents the weighting coefficient of the historical power supply during the same period, and e t-i y1 represents the power supply at time lag i in the historical power supply data, y2 represents the weighting coefficient of the moving average, y1 + y2 = 1, j represents the sampled data of the historical power supply data, n represents the sampling sequence number, and e represents the weighting coefficient of the moving average. t-ni y3 represents the power supply at a time lag ni in the historical power supply data, and y3 represents the high-temperature correction amount. The high temperature characteristic function, T t Characterizing the predicted ambient temperature, T max Y4 represents the high temperature warning value, D represents the power supply correction amount for rest days, and Y4 represents the power supply correction amount for rest days. t D represents the date of power supply. off It represents a day off.

5. The thermal power plant dispatching method according to claim 1, characterized in that, The heating data includes historical heating volume and heating dates; The step of predicting heating demand based on the heating data includes: Substituting the historical heating volume and the heating date into the following formula, the heating demand is obtained: ， Among them, H pred (t) represents heating demand, r1 represents the weighting coefficient of historical heating supply for the same period, h t-i The heat supply at lag time i in the historical heat supply is represented by r1, r2 represents the weighting coefficient of the moving average, r1 + r2 = 1, k represents the number of historical heat supply samples, n represents the sampling sequence number, and h represents the heat supply at lag time i in the historical heat supply. t-ni r3 represents the heat supply at a lag of ni in the historical heat supply, and r3 represents the low-temperature correction factor. Characteristic function of low temperature, T t Characterizing the predicted ambient temperature, T min Characterizes the low temperature warning value.

6. The thermal power plant dispatching method according to claim 1, characterized in that, The external data includes ambient temperature, power grid load demand, and heating network load demand. The step of determining the heating allocation weight based on the external data includes: Substituting the ambient temperature, the power grid load demand, and the heating network load demand into the following calculation formula, we obtain the heating allocation weights: ， Among them, W h Characterizing the heating distribution weights, T represents the ambient temperature, T0 represents the reference temperature, and D... h Characterizing the heating network load demand, D e Characterizing grid load demand, k c The thermoelectric conversion coefficient is represented by α and γ, the weighting coefficients are represented by α+γ=1, and β represents the temperature sensitivity coefficient.

7. A power plant dispatching device, characterized in that, The device includes: The multi-source data acquisition unit is configured to acquire multi-source data from the thermal power plant, including real-time power supply data, heating data, and external data. The supply and demand analysis unit is configured to determine the heat allocation weight based on the external data, predict the power supply demand based on the power supply data, predict the heat supply demand based on the heat supply data, and determine the supply and demand satisfaction index of the thermal power plant based at least on the heat allocation weight, the power supply demand, and the heat supply demand. The scheduling strategy analysis unit is configured to input the supply and demand satisfaction index into the objective function, take the minimum supply and demand satisfaction index as the objective, solve the objective function according to preset constraints, and generate the target scheduling strategy. The scheduling unit is configured to schedule the power supply and heating of the thermal power plant according to the target scheduling strategy.

8. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1-6.

Images