Optimized scheduling method and device based on energy system and computer equipment

Abstract

The invention relates to an optimal scheduling method and device based on an energy system and computer equipment. The method comprises the steps that an optimal scheduling model set for an energy system is obtained, and decision variables of the optimal scheduling model comprise unit generation power, heat supply power, the carbon capture amount of a carbon capture device and the heat storage load of a fused salt heat storage loop; obtaining input data of the optimal scheduling model, wherein the input data comprises operation state data of the energy system at the current moment, and a power load prediction value, a thermal load prediction value and a renewable energy output prediction value of a future preset scheduling period; taking the sum of the minimum power generation cost and the carbon emission cost as a target function, and optimizing the optimal scheduling model based on the input data; and controlling a cogeneration unit, a carbon capture device and a fused salt heat storage loop of the energy system according to decision variables in the optimized preset optimization scheduling model. By adopting the method, the system operation efficiency and the low-carbon target can be considered.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an optimal scheduling method, apparatus and computer equipment based on energy systems. Background Technology

[0002] In the context of energy transition, the thermoelectric decoupling technology of combined heat and power (CHP) units has become a key to improving the flexibility of the power system.

[0003] Existing technologies often focus solely on optimizing power generation costs or carbon emissions, making it difficult to achieve a real-time balance between economic efficiency and low carbon emissions. Furthermore, the dispatching system does not fully integrate the synergistic characteristics of carbon capture devices and thermal inertial components (heating pipelines, thermal storage devices, etc.), resulting in a delayed response to renewable energy output, weak absorption capacity, and a tendency to curtail wind and solar power, making it difficult to achieve both system operating efficiency and low carbon targets. Summary of the Invention

[0004] Therefore, it is necessary to provide an energy system-based optimization scheduling method, device, computer equipment, computer-readable storage medium, and computer program product that can balance system operating efficiency and low-carbon goals, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides an optimal scheduling method based on an energy system, including:

[0006] An optimized scheduling model for the energy system is obtained, wherein the decision variables of the preset optimized scheduling model include the unit's power generation, heating power, carbon capture amount of the carbon capture device, and thermal storage load of the molten salt thermal storage circuit.

[0007] The carbon capture device is used to capture carbon dioxide generated during the operation of the cogeneration unit of the energy system, and to introduce the waste heat of the capture process into the molten salt heat storage circuit through the molten salt heat exchanger.

[0008] The input data of the optimized scheduling model is obtained, including the current operating status data of the energy system, the predicted power load, the predicted heat load, and the predicted output of renewable energy for the future preset scheduling period.

[0009] The optimal scheduling model is optimized based on the input data, with the objective function being to minimize the sum of power generation cost and carbon emission cost.

[0010] Based on the decision variables in the optimized preset scheduling model, the cogeneration unit, carbon capture device, and molten salt thermal storage circuit of the energy system are controlled.

[0011] In one embodiment, optimizing the optimized scheduling model includes:

[0012] The optimization scheduling model is optimized under the premise of meeting the equipment operation constraints, which include power load balance constraints and thermal load balance constraints.

[0013] Among them, the power load balance constraint is jointly determined by the power load forecast, the renewable energy output forecast, and the power load within the plant.

[0014] The thermal load balance constraint is dynamically determined by the predicted thermal load, the thermal inertia model, and the operating status of the molten salt thermal storage circuit. The thermal inertia model is used to characterize the thermal dynamic characteristics of the heating network.

[0015] In one embodiment, the parameters of the optimized scheduling model include: energy price, carbon emission cost coefficient, equipment efficiency parameters, and maximum and minimum operating power; the equipment operation constraints also include: minimum / maximum unit output constraints, upper and lower limits of carbon capture constraints, and molten salt thermal storage capacity constraints.

[0016] In one embodiment, optimizing the optimized scheduling model includes:

[0017] A global search is performed across the entire solution space to obtain a preliminary solution set;

[0018] A local fine-grained search is performed on the preliminary solution set to obtain the optimal values ​​of the decision variables of the optimized scheduling model.

[0019] In one embodiment, the step of performing a global search across the entire solution space to obtain a preliminary solution set includes:

[0020] An initial population is constructed, in which each individual represents a potential operating scheme of the cogeneration unit, carbon capture device and molten salt thermal storage circuit;

[0021] Based on the non-dominated ranking principle of multi-objective optimization, the initial population is divided into multiple frontier levels to distinguish the superiority or inferiority of different operating schemes in terms of the objectives of power generation cost and carbon emission cost.

[0022] Calculate the crowding distance for individuals within the same frontier level;

[0023] Based on the aforementioned frontier level and crowding distance, genetic operations are performed on individuals in the population to iteratively generate a new population, thereby searching the preliminary solution set globally.

[0024] In one embodiment, the method further includes:

[0025] The sensor network deployed in the carbon capture device, molten salt circuit and ejector system collects operating parameters such as temperature, pressure and flow rate in real time.

[0026] Based on the aforementioned operating parameters, predictive maintenance strategies and anomaly warnings are generated by utilizing big data analysis and combining ultrasonic testing and infrared thermal imaging technologies.

[0027] Secondly, this application also provides an energy system-based optimized scheduling device, comprising:

[0028] The model acquisition module is used to acquire an optimized scheduling model set for the energy system. The decision variables of the preset optimized scheduling model include the unit's power generation, heating power, carbon capture amount of the carbon capture device, and the heat storage load of the molten salt heat storage circuit. The carbon capture device is used to capture carbon dioxide generated during the operation of the cogeneration unit of the energy system and to introduce the waste heat of the capture process into the molten salt heat storage circuit through the molten salt heat exchanger.

[0029] The operation status data acquisition module is used to acquire the input data of the optimized scheduling model. The input data includes the current operation status data of the energy system, the predicted power load, the predicted heat load, and the predicted output of renewable energy for the future preset scheduling period.

[0030] The model optimization module is used to optimize the optimized scheduling model based on the input data, with the objective function of minimizing the sum of power generation cost and carbon emission cost.

[0031] The control module is used to control the cogeneration unit, carbon capture device and molten salt thermal storage circuit of the energy system according to the decision variables in the optimized preset scheduling model.

[0032] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described energy system-based optimized scheduling method.

[0033] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described energy system-based optimized scheduling method.

[0034] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described energy system-based optimized scheduling method.

[0035] The aforementioned energy system-based optimization scheduling method, apparatus, computer equipment, computer-readable storage medium, and computer program product acquire an optimization scheduling model set for the energy system. The decision variables of the preset optimization scheduling model include unit power generation, heating power, carbon capture capacity of the carbon capture device, and heat storage load of the molten salt thermal storage circuit. The carbon capture device is used to capture carbon dioxide generated during the operation of the cogeneration unit of the energy system and introduces the waste heat from the capture process into the molten salt thermal storage circuit through a molten salt heat exchanger. The input data of the optimization scheduling model is acquired, including the current operating status data of the energy system, the predicted power load, the predicted heat load, and the predicted renewable energy output for a future preset scheduling period, in order to minimize... Using the sum of power generation cost and carbon emission cost as the objective function, the optimized scheduling model is optimized based on the input data. According to the decision variables in the optimized preset optimized scheduling model, the cogeneration units, carbon capture devices, and molten salt thermal storage loops of the energy system are controlled. Since an optimized scheduling model can be obtained, and the unit's power generation, heating power, carbon capture capacity of the carbon capture device, and thermal storage load of the molten salt thermal storage loop are used as decision variables for this model, optimization is performed with the objective function of minimizing the sum of power generation cost and carbon emission cost. This achieves coordinated optimization of unit output, heating power, carbon capture capacity, and molten salt thermal storage load, significantly improving the absorption capacity of renewable energy sources such as wind power and the dynamic matching accuracy of cogeneration, thereby improving the operating efficiency of the energy system while achieving low-carbon goals. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is an application environment diagram of an energy system-based optimization scheduling method in one embodiment;

[0038] Figure 2 This is a flowchart illustrating an energy system-based optimization scheduling method in one embodiment.

[0039] Figure 3 This is a flowchart illustrating the steps involved in optimizing a scheduling model in one embodiment.

[0040] Figure 4 This is a flowchart illustrating the steps of performing a global search across the entire solution space in another embodiment;

[0041] Figure 5 This is a structural block diagram of an energy system-based optimized scheduling device in one embodiment;

[0042] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0044] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0045] The energy system-based optimization scheduling method provided in this application can be applied to, for example... Figure 1 In the application environment shown, the computer device 102, acting as a dispatch center, communicates with the energy system device 104 via a network. The energy system device 104 includes a combined heat and power unit, a carbon capture device, and a molten salt thermal storage circuit. The computer device 102 can be a terminal or a server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart vehicle devices, projection equipment, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0046] Specifically, the computer equipment can acquire an optimized scheduling model set for the energy system. The decision variables of the preset optimized scheduling model include the generating power of the units, the heating power, the carbon capture amount of the carbon capture device, and the thermal storage load of the molten salt thermal storage circuit. The computer equipment can also acquire the input data of the optimized scheduling model, which includes the current operating status data of the energy system, the predicted values ​​of the power load, the predicted values ​​of the heat load, and the predicted values ​​of the renewable energy output for the future preset scheduling period. With the objective function of minimizing the sum of the power generation cost and the carbon emission cost, the computer equipment optimizes the optimized scheduling model based on the input data. Based on the decision variables in the optimized preset optimized scheduling model, the computer equipment controls the cogeneration units, carbon capture devices, and molten salt thermal storage circuits of the energy system.

[0047] In one exemplary embodiment, such as Figure 2 As shown, an optimal scheduling method based on an energy system is provided, which can be applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0048] Step 202: Obtain the optimized scheduling model for the energy system. The decision variables of the preset optimized scheduling model include the unit's power generation, heating power, carbon capture amount of the carbon capture device, and thermal storage load of the molten salt thermal storage circuit.

[0049] The energy system is equipped with a carbon capture device, which is used to capture carbon dioxide generated during the operation of the cogeneration unit in the energy system, and to introduce the waste heat from the capture process into the molten salt heat storage circuit of the energy system through a molten salt heat exchanger.

[0050] Specifically, the computer equipment can acquire an optimized scheduling model for the energy system. The decision variables of the preset optimized scheduling model include the generating power of the unit, the heating power, the carbon capture amount of the carbon capture device, and the thermal storage load of the molten salt thermal storage circuit.

[0051] For example, a carbon capture device can be installed in the flue of a cogeneration unit to capture carbon dioxide using a chemical absorption method, and the waste heat from the capture process can be introduced into a molten salt heat storage circuit through a molten salt heat exchanger.

[0052] For example, in the energy system of this application embodiment, carbon capture technology is combined with the thermoelectric decoupling process. During power generation, mature carbon capture technologies, such as chemical absorption and physical adsorption, are used to capture the generated carbon dioxide. By installing corresponding carbon capture equipment in locations such as the flue of the cogeneration unit, the captured carbon dioxide is compressed, transported, and stored. This not only reduces carbon emissions but also indirectly affects the operating conditions of the cogeneration unit by adjusting the operating parameters of the carbon capture equipment, such as the capture rate and capture volume, thereby providing more degrees of control over thermoelectric decoupling.

[0053] For example, the connection between the carbon capture device and the molten salt heat storage circuit is as follows: the high-temperature steam outlet of the regeneration tower of the carbon capture system is connected to the molten salt heat exchanger through a plate heat exchanger, and the working temperature of the molten salt is controlled at 380-420℃.

[0054] Step 204: Obtain the input data for the optimized scheduling model. The input data includes the current operating status data of the energy system, the predicted power load, the predicted heat load, and the predicted output of renewable energy for the future preset scheduling cycle.

[0055] The preset scheduling period can be set to a specific duration as needed, such as the next 24 hours.

[0056] For example, the current operating status data of the energy system may include: real-time power generation, heating power, and main steam parameters of the cogeneration unit; operating load and solvent circulation rate of the carbon capture unit; liquid level, temperature, and pump / valve status of the high / low temperature tanks in the molten salt thermal storage circuit; and pressure, temperature, and flow rate of key nodes in the heating network. In specific applications, this data can be collected in real time by temperature, pressure, flow rate, and liquid level sensors pre-installed in the cogeneration unit, carbon capture unit, molten salt circuit, and heating network. The data collected by these sensors can be transmitted to computer equipment.

[0057] For example, computer equipment can obtain officially released power load forecast data from the power grid dispatch center in its region through a secure data exchange interface. Alternatively, computer equipment can also use historical load data, weather forecasts (temperature, humidity, etc.), date type (weekday / holiday), and other information to perform load forecasting using time series analysis (such as the ARIMA model) or machine learning algorithms (such as LSTM networks) to obtain power load forecast values ​​for future preset dispatch periods.

[0058] For example, heat load forecasts can be obtained by combining historical data, real-time monitoring, and predictions based on external environmental factors. In specific applications, firstly, a historical database is constructed to store heat load data recorded in time series, along with corresponding outdoor meteorological data such as temperature, humidity, wind speed, and solar radiation intensity, as well as social activity pattern data such as weekdays / holidays. Based on this, a prediction model is built using a machine learning algorithm with a Long Short-Term Memory (LSTM) network as its core. This model uses refined weather forecast data for a specific future time period and the future date type as its main input features, and outputs hourly heat load forecasts for the corresponding time period through trained network weights. For example, an online correction mechanism can also be introduced: the latest actual heat load measurements are compared with the model predictions in real time. When the deviation exceeds a set threshold, the model's parameters are automatically fine-tuned, or algorithms such as Kalman filtering are used to dynamically correct subsequent prediction results. This effectively addresses uncertainties such as sudden weather changes, ensures prediction accuracy, and provides a reliable forward-looking decision-making basis for the aforementioned optimized scheduling based on the thermal inertia model.

[0059] Renewable energy output forecasts are numerical estimates of the electrical power (i.e., "output") that renewable energy facilities such as wind farms and photovoltaic power plants can generate within a specific future time period. For example, computer equipment can acquire numerical weather prediction (NWP) data, and based on the NWP data and historical output data, train specialized prediction models (such as Support Vector Machines (SVR), Random Forests, or deep learning models) to predict renewable energy output forecasts.

[0060] Step 206: Using the goal of minimizing the sum of power generation cost and carbon emission cost, optimize the scheduling model based on the input data.

[0061] Specifically, computer equipment can optimize the optimal scheduling model based on input data, with the objective function of minimizing the sum of power generation cost and carbon emission cost, to obtain the decision variables in the optimized preset optimal scheduling model, which is the globally optimal scheduling scheme.

[0062] For example, computer equipment can use a hybrid NSGA II-MOPSO algorithm to solve the model and output the Pareto optimal scheduling scheme to achieve dynamic matching between the consumption of renewable energy such as wind power and thermal power load.

[0063] Step 208: Control the cogeneration unit, carbon capture device and molten salt thermal storage circuit of the energy system according to the decision variables in the optimized preset scheduling model.

[0064] Specifically, the computer equipment can generate scheduling instructions based on the decision variables in the optimized preset scheduling model, and send the scheduling instructions to the cogeneration units, carbon capture devices and molten salt thermal storage circuits of the energy system, thereby controlling the cogeneration units, carbon capture devices and molten salt thermal storage circuits of the energy system.

[0065] For example, the globally optimal scheduling scheme determined by the computer equipment includes the setpoints for the power generation and heating power of each cogeneration unit in each time period within a future scheduling cycle, the carbon capture amount of the carbon capture system or the corresponding solvent regeneration energy consumption setpoint, and the heat storage or release power setpoint of the molten salt thermal storage system. These power and load setpoints are parsed and generated into control commands that can be directly recognized and executed by the underlying actuators. The generated control commands are sent in real time to their respective PLCs, DCSs, or dedicated controllers, which drive the final actuators such as frequency converters, electric regulating valves, pumps, and compressors to complete the actual regulation of energy and material flow.

[0066] The aforementioned energy system-based optimal scheduling method obtains an optimal scheduling model for the energy system. The decision variables of the preset optimal scheduling model include unit power generation, heating power, carbon capture capacity of the carbon capture device, and the thermal storage load of the molten salt thermal storage loop. The carbon capture device is used to capture carbon dioxide generated during the operation of the cogeneration units in the energy system, and the waste heat from the capture process is introduced into the molten salt thermal storage loop through a molten salt heat exchanger. The input data for the optimal scheduling model includes the current operating status data of the energy system, the predicted power load, predicted heating load, and predicted renewable energy output for the future preset scheduling period, with the objective of minimizing the sum of power generation costs and carbon emission costs. This function optimizes the scheduling model based on input data. According to the decision variables in the optimized scheduling model, it controls the cogeneration units, carbon capture devices, and molten salt thermal storage loops of the energy system. Since the optimized scheduling model can be obtained, and the unit's power generation, heating power, carbon capture capacity of the carbon capture device, and thermal storage load of the molten salt thermal storage loop are used as decision variables, the objective function is to minimize the sum of power generation cost and carbon emission cost. This allows for the coordinated optimization of unit output, heating power, carbon capture capacity, and molten salt thermal storage load, significantly improving the absorption capacity of renewable energy sources such as wind power and the accuracy of dynamic matching between cogeneration and power. While achieving low-carbon goals, it also improves the operating efficiency of the energy system.

[0067] In an exemplary embodiment, optimizing the optimal scheduling model includes: optimizing the optimal scheduling model under the premise of satisfying equipment operation constraints, the equipment operation constraints including power load balance constraints and thermal load balance constraints; wherein, the power load balance constraints are jointly determined by the predicted power load, the predicted renewable energy output, and the plant's internal power load; the thermal load balance constraints are jointly and dynamically determined by the predicted thermal load, the thermal inertia model, and the operating status of the molten salt thermal storage circuit, the thermal inertia model being used to characterize the thermal dynamic characteristics of the heating network.

[0068] Among them, equipment operation constraints refer to the limiting conditions set to ensure the safe and economical operation of various equipment in the energy system (cogeneration units, carbon capture devices, molten salt thermal storage circuits, etc.), including power load balance constraints and thermal load balance constraints.

[0069] The power load balance constraint refers to the requirement that the total power supply of the energy system should be balanced with the total power demand. The power supply consists of the power generation of combined heat and power units and the output of renewable energy, while the power demand consists of the power load forecast and the power load of the plant.

[0070] The heat load balance constraint refers to the requirement that the total heat supply of the energy system should be balanced with the total heat demand. The heat supply consists of the heating power of the cogeneration unit, the heat released by the molten salt thermal storage circuit, and the heat released by thermal inertial components (heating pipelines, building envelope, etc.). The heat demand is determined by the predicted heat load.

[0071] The thermal inertia model is a mathematical model used to quantify the thermal dynamic characteristics of heating networks (such as heat storage capacity, release rate, and heat loss patterns).

[0072] In this embodiment, the timing of cogeneration production can be optimized by establishing an accurate thermal inertia model and combining it with system heat load prediction. For example, if an increase in heat load is predicted in the future, thermal inertia can be utilized in advance to appropriately increase the energy input of heating equipment during periods of relatively low electricity load and cost. Excess heat is stored in thermally inertial components such as pipes, heat storage devices, and building envelopes within the heating system. When heat load demand increases, this stored heat can be gradually released, reducing reliance on immediate power generation and heating from the cogeneration unit, thereby achieving heat and electricity decoupling and improving energy efficiency.

[0073] The thermal inertia model is a lumped-parameter or distributed-parameter mathematical model characterizing the dynamic characteristics of heat storage and release in the entire heating system (including the heating pipe network, heat storage devices, and building envelope). It treats the heating system as a thermodynamic system with specific heat capacity and thermal resistance, describing the thermal dynamics by establishing differential equations showing the time-varying internal temperature field. First, temperature data from key nodes in the system is collected in real time using an array of temperature sensors deployed on the surface of the heating pipes, the walls of the storage tanks, and inside the building. Simultaneously, flow meters monitor the flow velocity of the circulating medium in the heating pipe network. Based on this real-time data and the system's physical parameters, such as the heat capacity of the pipe material, the thermal resistance of the insulation layer, and the equivalent heat capacity of the building, a system identification method is used. By fitting the actual temperature drop curve with the theoretical heat transfer equation, key parameters in the model, such as the total equivalent heat capacity C and the total thermal resistance R, are calibrated online to construct a transfer function model that accurately reflects the system's actual heat storage and release capacity.

[0074] In this embodiment, the thermal inertia model acts as a virtual energy storage unit in system scheduling, providing a physical basis and adjustment freedom for the timing optimization of cogeneration production. Based on this model, the scheduling center can quantitatively determine how much heat the system can store or release under current operating conditions, and the approximate time constant required to complete this process. This allows the system to proactively utilize thermal inertia as a buffer: during periods of low electricity load and low electricity prices, the cogeneration unit or electric boiler is instructed to moderately increase its output, temporarily storing excess heat exceeding the instantaneous heat load demand in the thermal inertia of the entire heating system, resulting in a slow rise in the overall system temperature; conversely, during periods of high electricity load or a surge in heat load demand, the heat source is instructed to reduce its output, relying on the heat stored in the system's thermal inertia to maintain heating, resulting in a slow decrease in system temperature. Through proactive peak-shaving and valley-filling management, the operating constraint of cogeneration units being determined by heat demand is broken, achieving decoupling of heat and electricity.

[0075] For example, thermal inertia monitoring modules can be deployed in heating pipelines, thermal storage devices, and building envelopes to establish thermal inertia models and regulate the rhythm of heat storage and release based on load prediction.

[0076] For example, a dual-tank system with high-temperature and low-temperature storage can be constructed with a molten salt energy storage system as the core. During the operation of the thermal power unit, when excess heat occurs, it is stored in the molten salt tank; when heat is needed, the stored heat is released for heating or to participate in the power generation process.

[0077] For example, the two ways of storing heat inertia—storing it in "pipelines, building components, etc." and storing it in "molten salt tanks"—are two different levels of complementary heat storage mechanisms. The method of storing heat in heating pipes, heat storage devices, and building envelopes can be called "distributed" or "passive" heat inertia utilization. It relies on the heat capacity of the materials of existing system components. When the temperature of the heating medium is higher than the ambient temperature, the heat will be naturally absorbed by these structural materials; when the medium temperature drops, the stored heat will be slowly released. This method essentially exploits and utilizes the inherent physical properties of the system. The method of storing heat in molten salt tanks is "centralized" or "active" heat storage. It involves constructing a dedicated, large-capacity high-temperature molten salt thermal storage system, typically a dual-tank system. By actively controlling the heat exchange process between the molten salt and heat sources, such as carbon capture waste heat, steam extraction from cogeneration units, or cold sources, it achieves directional and large-scale energy storage and release. It is a new and powerful energy storage unit with a thermal storage capacity far greater than that of distributed thermal inertia and a high operating temperature, such as 380-420℃.

[0078] For example, computer equipment can ensure the balance of power supply and demand by calculating the equation between total power supply and total power demand. Specifically: Generating capacity + Renewable energy output forecast = Power load forecast + Plant power load.

[0079] For example, computer equipment can dynamically quantify the heat storage and release characteristics of a heating network through a thermal inertia model, and calculate the equation between the total heat supply and the total heat demand by combining the operating status of the molten salt thermal storage circuit. Specifically: Unit heating power + heat released by the molten salt thermal storage circuit + heat released by the thermal inertia components (calculated by the thermal inertia model) = predicted heat load.

[0080] In the above embodiments, by strictly adhering to the constraints of power load balance and heat load balance, on the one hand, it can ensure real-time supply and demand matching of power and heat systems, avoiding power shortages or insufficient heat; on the other hand, the power side can fully absorb renewable energy such as wind power, and the heat side can reduce the dependence on immediate heat supply of cogeneration units through the synergistic storage and release of heat by thermal inertial components and molten salt thermal storage, ultimately achieving the technical effects of decoupling of heat and power, high absorption of renewable energy, and dynamic balance between economy and low carbon emissions.

[0081] In an exemplary embodiment, the parameters of the optimized scheduling model include: energy price, carbon emission cost coefficient, equipment efficiency parameters, and maximum and minimum operating power; the equipment operation constraints also include: minimum / maximum unit output constraints, upper and lower limits of carbon capture constraints, and molten salt thermal storage capacity constraints.

[0082] In one embodiment, optimizing the scheduling model includes: performing a global search across the entire solution space to obtain a preliminary solution set; and performing a local fine-grained search on the preliminary solution set to obtain the optimal values ​​of the decision variables of the scheduling model.

[0083] For example, the optimization scheduling model of this application is a mathematical model that comprehensively considers multiple factors such as electricity load demand, heat load demand, power generation cost, carbon emission cost, and equipment operation constraints. The variables in the model include the power generation, heat supply, and carbon capture of each cogeneration unit; the parameters cover energy prices, carbon emission cost coefficients, equipment efficiency parameters, and maximum and minimum operating power. The objective function is set to minimize the sum of power generation cost and carbon emission cost while meeting electricity and heat load demands. The model constraints include: electricity load balance constraints, heat load balance constraints, minimum / maximum unit output constraints, upper and lower limits for carbon capture, and molten salt thermal storage capacity constraints, and a coupling coefficient between carbon capture and unit power generation is set.

[0084] In one embodiment, such as Figure 3 As shown, the optimization of the scheduling model includes:

[0085] Step 302: Perform a global search across the entire solution space to obtain a preliminary solution set.

[0086] Step 304: Perform a local fine search on the preliminary solution set to obtain the optimal values ​​of the decision variables of the optimized scheduling model.

[0087] For example, a computer device can first use the NSGA II algorithm to perform a global search of the entire solution space to obtain a preliminary solution set, and then use the MOPSO algorithm to perform a local fine search of the preliminary solution set to obtain the optimal values ​​of the decision variables of the optimization scheduling model.

[0088] In the above embodiments, the advantages of the two algorithms are effectively combined by adopting a serial hybrid mode of "global first, local later" to overcome the limitations that may exist in a single algorithm, thereby improving the accuracy of the optimal solution.

[0089] In one embodiment, such as Figure 4 As shown, a global search is performed across the entire solution space to obtain a preliminary solution set, including:

[0090] Step 402: Construct an initial population. In the initial population, each individual represents a potential operating scheme for a combined heat and power unit, a carbon capture device, and a molten salt thermal storage circuit.

[0091] Step 404: Based on the non-dominated ranking principle of multi-objective optimization, the initial population is divided into multiple frontier levels.

[0092] Step 406: Calculate the crowding distance between individuals within the same frontier level.

[0093] Step 408: Based on the frontier level and crowding distance, perform genetic operations on the individuals in the population to iteratively generate a new population in order to search for an initial solution set globally.

[0094] Specifically, the computer equipment can construct an initial population, where each individual in the population represents a potential operating scheme of a combined heat and power unit, a carbon capture device, and a molten salt thermal storage loop. Based on the non-dominated ranking principle of multi-objective optimization, the population is divided into multiple frontier levels to distinguish the advantages and disadvantages of different operating schemes in terms of power generation cost and carbon emission cost objectives. The crowding distance of individuals within the same frontier level is calculated to maintain the diversity of operating schemes during the optimization process and avoid the search from getting trapped in local optima too early. Based on the frontier level and the crowding distance, selection, crossover, and mutation genetic operations are performed on the individuals in the population to iteratively generate a new population, thereby searching for an initial solution set globally.

[0095] In the above embodiments, by constructing an initial population, based on the non-dominated sorting principle of multi-objective optimization, the initial population is divided into multiple frontier levels, the crowding distance of individuals within the same frontier level is calculated, and genetic operations are performed on the individuals in the population according to the frontier level and the crowding distance to iteratively generate a new population. This can better traverse the entire solution space, thereby quickly searching for a preliminary solution set in the global scope.

[0096] In one embodiment, the energy system-based optimization scheduling method of this application further includes: acquiring real-time collected operating parameters, which are collected through a sensor network deployed in the carbon capture device, molten salt circuit and ejector system; and generating predictive maintenance strategies and anomaly warnings based on the operating parameters by using big data analysis and combining ultrasonic detection and infrared thermal imaging technologies.

[0097] Specifically, temperature, pressure, and flow operating parameters can be collected in real time through a sensor network deployed in carbon capture devices, molten salt circuits, and ejector systems. These operating parameters are then input into a remote diagnostic module. Using big data analysis combined with ultrasonic detection and infrared thermal imaging technology, predictive maintenance strategies or anomaly warnings can be generated. The intelligent monitoring system can then drive the ELCV valve to execute on-demand heating commands based on the predictive maintenance strategies or anomaly warnings.

[0098] In practice, the response time of the ELCV valve from receiving the command to completing the execution is no more than 5 seconds.

[0099] In practical implementation, the system pressure can be monitored in real time, and when the pressure exceeds the safety threshold, the interlocking logic of the pressure relief valve action and the audible and visual alarm will be automatically triggered, and the fault point location accuracy provided by the system is no more than 1 meter.

[0100] In the above embodiments, since real-time operating parameters can be acquired, and based on these parameters, big data analysis combined with ultrasonic detection and infrared thermal imaging technologies can be used to generate predictive maintenance strategies or anomaly warnings, intelligent monitoring and safety warnings can be achieved, ensuring the reliability of the new energy system.

[0101] In one specific embodiment, an energy system-based optimization scheduling method is provided, comprising the following steps:

[0102] 1. Obtain the optimized scheduling model for the energy system. The decision variables of the optimized scheduling model include the unit's power generation, heating power, carbon capture amount of the carbon capture device, and heat storage load of the molten salt heat storage circuit. The carbon capture device is used to capture carbon dioxide generated during the operation of the cogeneration unit of the energy system and introduces the waste heat of the capture process into the molten salt heat storage circuit through the molten salt heat exchanger.

[0103] 2. Obtain the input data for the optimized scheduling model. The input data includes the current operating status data of the energy system, the predicted power load, the predicted heat load, and the predicted output of renewable energy for the future preset scheduling period.

[0104] 3. Using the minimization of the sum of power generation cost and carbon emission cost as the objective function, the optimal scheduling model is optimized based on the input data.

[0105] The parameters of the optimized scheduling model include: energy price, carbon emission cost coefficient, equipment efficiency parameters, and maximum and minimum operating power; the equipment operation constraints also include: minimum / maximum unit output constraints, upper and lower limits of carbon capture constraints, and molten salt thermal storage capacity constraints.

[0106] Specifically, the optimization of the scheduling model includes: optimizing the scheduling model under the premise of meeting equipment operation constraints, which include power load balance constraints and thermal load balance constraints; wherein, the power load balance constraints are jointly determined by the predicted power load, the predicted renewable energy output, and the power load within the plant; the thermal load balance constraints are jointly and dynamically determined by the predicted thermal load, the thermal inertia model, and the operating status of the molten salt thermal storage circuit, and the thermal inertia model is used to characterize the thermal dynamic characteristics of the heating network.

[0107] The optimization of the scheduling model includes: constructing an initial population, where each individual represents a potential operating scheme for a cogeneration unit, a carbon capture device, and a molten salt thermal storage loop; dividing the initial population into multiple frontier levels based on the non-dominated ranking principle of multi-objective optimization; calculating the crowding distance between individuals within the same frontier level; performing genetic operations on the individuals based on the frontier level and the crowding distance to iteratively generate a new population, thereby searching for a preliminary solution set globally; and performing a local fine-grained search on the preliminary solution set to obtain the optimal values ​​of the decision variables of the scheduling model.

[0108] 4. Based on the decision variables in the optimized preset scheduling model, control the cogeneration units, carbon capture devices, and molten salt thermal storage circuits of the energy system.

[0109] 5. Acquire real-time operating parameters, which are collected through a sensor network deployed in the carbon capture device, molten salt circuit, and ejector system; based on the operating parameters, generate predictive maintenance strategies or anomaly warnings by using big data analysis combined with ultrasonic detection and infrared thermal imaging technology.

[0110] By deeply coupling the carbon capture process with a molten salt thermal storage loop, carbon dioxide is captured from flue gas using chemical absorption, and waste heat from the capture process is recovered through a molten salt heat exchanger. This reduces carbon emissions and improves energy efficiency, achieving low-carbon and high-efficiency operation of the integrated energy system. Simultaneously, by accurately modeling the thermal inertia of the heating network, thermal storage devices, and building envelope, and combining load forecasting with dynamic control of heat storage and release, a multi-objective optimization model is established with power generation costs and carbon emission costs as objectives. This model utilizes NSGA. The II and MOPSO hybrid intelligent algorithm solves the problem, achieving coordinated optimization of unit output, heating power, carbon capture, and molten salt thermal storage load, significantly improving the absorption capacity of renewable energy such as wind power and the accuracy of dynamic heat and power matching. Through real-time sensor networks, big data analysis, and infrared ultrasonic detection technology, the safe operation of carbon capture devices, molten salt circuits, and heating networks is ensured. ELCV valves enable precise heating regulation, and pressure relief protection and fault location functions further ensure system reliability, timely detection of equipment faults, and extension of equipment life. This solution, through multi-dimensional coordination of energy flow, carbon flow, and information flow, significantly improves energy utilization efficiency and renewable energy acceptance capacity while reducing power generation costs and carbon emission costs.

[0111] In a specific embodiment, this application proposes and constructs an integrated energy system optimization scheduling scheme based on carbon capture and thermal inertia coordinated regulation. The core of this scheme lies in deploying a chemical absorption carbon capture device in the flue of a combined heat and power (CHP) unit, and efficiently recovering the waste heat from its regeneration process to a molten salt thermal storage loop via a molten salt heat exchanger, achieving deep coupling between carbon emission reduction and waste heat utilization. Simultaneously, the thermal inertia characteristics of heating pipelines, thermal storage devices, and building envelopes are accurately modeled and utilized, combined with load forecasting to dynamically regulate the rhythm of heat storage and release, effectively decoupling the rigid constraints of CHP production. Based on this, a mathematical model is established with the objective of minimizing power generation costs and carbon emission costs, covering key variables such as unit power generation / heating capacity, carbon capture amount, and molten salt thermal storage load. A hybrid NSGA II-MOPSO intelligent algorithm is used to efficiently solve this multi-objective optimization problem, outputting a Pareto optimal scheduling scheme, significantly improving the absorption capacity of renewable energy sources such as wind power and the accuracy of dynamic matching of CHP loads. The integrated intelligent monitoring and safety early warning system collects data in real time through a sensor network distributed across key nodes, utilizes big data analysis to optimize operational strategies, and integrates ultrasonic detection and infrared thermal imaging technologies for anomaly prevention. ELCV valves enable precise on-demand heating adjustment within seconds, while pressure relief protection and high-precision fault location mechanisms ensure safe and reliable system operation. This solution achieves comprehensive optimization of the system's low-carbon, economical, efficient, and safe operation through deep synergy of energy flow, carbon flow, and information flow.

[0112] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0113] Based on the same inventive concept, this application also provides an energy system optimization scheduling apparatus for implementing the energy system optimization scheduling method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more energy system optimization scheduling apparatus embodiments provided below can be found in the limitations of the energy system optimization scheduling method described above, and will not be repeated here.

[0114] In one exemplary embodiment, such as Figure 5 As shown, an energy system-based optimized scheduling device 500 is provided, comprising:

[0115] The model acquisition module 502 is used to acquire the optimized scheduling model set for the energy system. The decision variables of the preset optimized scheduling model include the unit power generation, heating power, carbon capture amount of the carbon capture device, and heat storage load of the molten salt heat storage circuit. The carbon capture device is used to capture carbon dioxide generated during the operation of the cogeneration unit of the energy system and introduce the waste heat of the capture process into the molten salt heat storage circuit through the molten salt heat exchanger.

[0116] The operation status data acquisition module 504 is used to acquire the input data of the optimized scheduling model. The input data includes the current operation status data of the energy system, the predicted power load, the predicted heat load, and the predicted output of renewable energy for the future preset scheduling cycle.

[0117] The model optimization module 506 is used to optimize the optimal scheduling model based on the input data, with the objective function of minimizing the sum of power generation cost and carbon emission cost.

[0118] The control module 508 is used to control the cogeneration unit, carbon capture device and molten salt thermal storage circuit of the energy system according to the decision variables in the optimized preset scheduling model.

[0119] In an exemplary embodiment, the model optimization module is further configured to: optimize the optimization scheduling model under the premise of satisfying equipment operation constraints, the equipment operation constraints including power load balance constraints and thermal load balance constraints; wherein, the power load balance constraints are jointly determined by the predicted power load, the predicted renewable energy output, and the power load within the plant; the thermal load balance constraints are jointly and dynamically determined by the predicted thermal load, the thermal inertia model, and the operating status of the molten salt thermal storage circuit, the thermal inertia model being used to characterize the thermal dynamic characteristics of the heating network.

[0120] In an exemplary embodiment, the parameters of the optimized scheduling model include: energy price, carbon emission cost coefficient, equipment efficiency parameters, and maximum and minimum operating power; the equipment operation constraints also include: minimum / maximum unit output constraints, upper and lower limits of carbon capture constraints, and molten salt thermal storage capacity constraints.

[0121] In an exemplary embodiment, the model optimization module is further configured to perform a global search across the entire solution space to obtain a preliminary solution set; and to perform a local fine-grained search on the preliminary solution set to obtain the optimal values ​​of the decision variables for optimizing the scheduling model.

[0122] In an exemplary embodiment, the model optimization module is further configured to: construct an initial population, wherein each individual in the initial population represents a potential operating scheme of a cogeneration unit, a carbon capture device, and a molten salt thermal storage circuit; divide the initial population into multiple frontier levels based on the non-dominated sorting principle of multi-objective optimization; calculate the crowding distance between individuals within the same frontier level; and perform genetic operations on the individuals in the population based on the frontier level and the crowding distance to iteratively generate a new population in order to search for a preliminary solution set globally.

[0123] In an exemplary embodiment, the above-mentioned energy system-based optimized scheduling device further includes: an early warning module, used to acquire real-time collected operating parameters, which are collected by a sensor network deployed in the carbon capture device, molten salt circuit and ejector system; based on the operating parameters, using big data analysis and combining ultrasonic detection and infrared thermal imaging technology, to generate predictive maintenance strategies or anomaly warnings.

[0124] The modules in the aforementioned energy system-based optimized scheduling device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0125] In one exemplary embodiment, a computer device is provided, the internal structure of which can be as shown in the figure. Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an optimized scheduling method based on an energy system.

[0126] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0127] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the energy system-based optimization scheduling method in any of the above embodiments.

[0128] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the energy system-based optimization scheduling method in any of the above embodiments.

[0129] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the energy system-based optimized scheduling method in any of the above embodiments.

[0130] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0131] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0132] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0133] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An optimal scheduling method based on an energy system, characterized in that, The method includes: An optimized scheduling model for the energy system is obtained, wherein the decision variables of the optimized scheduling model include the unit's power generation, heating power, carbon capture capacity of the carbon capture device, and thermal storage load of the molten salt thermal storage circuit; The carbon capture device is used to capture carbon dioxide generated during the operation of the cogeneration unit of the energy system, and to introduce the waste heat of the capture process into the molten salt heat storage circuit through the molten salt heat exchanger. The input data of the optimized scheduling model is obtained, including the current operating status data of the energy system, the predicted power load, the predicted heat load, and the predicted output of renewable energy for the future preset scheduling period. The optimal scheduling model is optimized based on the input data, with the objective function being to minimize the sum of power generation cost and carbon emission cost. Based on the decision variables in the optimized preset scheduling model, the cogeneration unit, carbon capture device, and molten salt thermal storage circuit of the energy system are controlled.

2. The method according to claim 1, characterized in that, Optimizing the aforementioned scheduling model includes: The optimization scheduling model is optimized under the premise of meeting the equipment operation constraints, which include power load balance constraints and thermal load balance constraints. Among them, the power load balance constraint is jointly determined by the power load forecast, the renewable energy output forecast, and the plant's internal power load; The thermal load balance constraint is dynamically determined by the predicted thermal load, the thermal inertia model, and the operating status of the molten salt thermal storage circuit. The thermal inertia model is used to characterize the thermal dynamic characteristics of the heating network.

3. The method according to claim 2, characterized in that, The parameters of the optimized scheduling model include: energy price, carbon emission cost coefficient, equipment efficiency parameters, and maximum and minimum operating power; the equipment operation constraints also include: minimum unit output constraint, maximum unit output constraint, upper and lower limits of carbon capture capacity constraint, and molten salt thermal storage capacity constraint.

4. The method according to claim 1, characterized in that, Optimizing the aforementioned scheduling model includes: A global search is performed across the entire solution space to obtain an initial solution set; A local fine-grained search is performed on the preliminary solution set to obtain the optimal values ​​of the decision variables of the optimized scheduling model.

5. The method according to claim 4, characterized in that, The step of performing a global search across the entire solution space to obtain a preliminary solution set includes: An initial population is constructed, in which each individual represents a potential operating scheme of the cogeneration unit, carbon capture device and molten salt thermal storage circuit; Based on the non-dominated ranking principle of multi-objective optimization, the initial population is divided into multiple frontier levels; Calculate the crowding distance for individuals within the same frontier level; Based on the aforementioned frontier level and crowding distance, genetic operations are performed on individuals in the population to iteratively generate a new population, thereby searching the preliminary solution set globally.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Real-time operational parameters are acquired through a sensor network deployed in the carbon capture device, molten salt circuit, and ejector system. Based on the aforementioned operating parameters, predictive maintenance strategies or anomaly warnings are generated by utilizing big data analysis and combining ultrasonic testing and infrared thermal imaging technologies.

7. An optimized scheduling device based on an energy system, characterized in that, The device includes: The model acquisition module is used to acquire an optimized scheduling model for the energy system. The decision variables of the optimized scheduling model include the unit's power generation, heating power, carbon capture amount of the carbon capture device, and the thermal storage load of the molten salt thermal storage circuit. The carbon capture device is used to capture carbon dioxide generated during the operation of the cogeneration unit of the energy system and to introduce the waste heat of the capture process into the molten salt thermal storage circuit through the molten salt heat exchanger. The operation status data acquisition module is used to acquire the input data of the optimized scheduling model. The input data includes the current operation status data of the energy system, the predicted power load, the predicted heat load, and the predicted output of renewable energy for the future preset scheduling period. The model optimization module is used to optimize the optimized scheduling model based on the input data, with the objective function of minimizing the sum of power generation cost and carbon emission cost. The control module is used to control the cogeneration unit, carbon capture device and molten salt thermal storage circuit of the energy system according to the decision variables in the optimized preset scheduling model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A 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 steps of the method according to any one of claims 1 to 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 steps of the method according to any one of claims 1 to 6.

Images