Dual-optimization park-level integrated energy system scheduling method and system

Abstract

The invention discloses a dual-optimization park-level integrated energy system scheduling method and system. The method comprises the steps of collecting park data, adjusting a scheduling period and constructing an optimization scheduling model. And importing wind power and photovoltaic power generation optimal output data, and constructing an intra-day optimization scheduling model. And outputting an intra-day optimization result to complete a scheduling process. According to the mechanism provided by the invention, through real-time rolling optimization scheduling and load prediction error correction, the flexibility and stability of the integrated energy system are remarkably improved. Load, market price and weather changes are efficiently handled, emergencies are quickly responded, and stable energy supply is ensured. The carbon emission cost is brought into a scheduling target, the balance between economic benefits and an environmental protection target is realized, and the construction of a low-carbon park is assisted. Key problems of multi-time scale balance, demand response, economical efficiency optimization and the like of the park energy system are effectively solved, and technical guarantee is provided for a low-carbon and intelligent comprehensive energy system.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a dual-optimization park-level integrated energy system scheduling method and system. Background Art

[0002] Global climate change and carbon emission control have become the focus of global attention. As the main energy consumption and carbon emission source, the construction industry, especially industrial parks, plays a key role in achieving energy conservation and emission reduction.

[0003] The low-carbon park uses clean energy such as photovoltaic (PV), wind power and ground source heat pumps, as well as diversified energy storage methods including battery energy storage and phase change heat / cold energy storage, to build a park-level integrated energy system (IES). Optimizing this system can not only improve energy efficiency and reduce carbon emissions, but also promote the development of surrounding industries and the harmonious coexistence of the environment and human activities. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: At the optimization level, the park faces the following technical challenges:

[0006] The first is how to integrate multiple energy systems including electricity, cooling, heating and gas to achieve coordinated operation and optimization of the system. Secondly, it is necessary to consider weather changes that may affect the output of renewable energy on the day, as well as unexpected human behaviors that may affect the load of the park. This requires the intelligent management of the park's integrated energy system in combination with predictive control strategies. Therefore, studying the scheduling method of the integrated energy system combined with load forecasting will become one of the keys to achieving intelligent management of the park's energy system. The scheduling model must not only consider the random conditions of the day, but also consider immutable conditions such as power purchase plans and planned human activities to achieve efficient operation and optimization of the park's energy system.

[0007] Since scheduling needs to balance variable and immutable conditions, this paper adopts multi-time scale day-ahead and intraday optimization algorithms to optimize the scheduling of the integrated energy system of low-carbon parks. At present, some studies have tried to use day-ahead and intraday optimization algorithms and adopt methods such as demand response and energy storage facility scheduling to balance the fluctuations of renewable energy and achieve dynamic energy supply and demand balance. These studies focus on how to formulate reasonable energy distribution and equipment operation plans based on predicted load and weather conditions to achieve an economical and environmentally friendly energy system. Although day-ahead and intraday optimization scheduling are widely used in the field of power systems, there are relatively few studies on the overall hybrid energy system of low-carbon parks.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a dual-optimization park-level integrated energy system scheduling method, comprising: collecting park data, adjusting the scheduling cycle, and constructing an optimized scheduling model.

[0009] Import the optimal output data of wind power and photovoltaic power generation and build an intraday optimization scheduling model.

[0010] Output the intraday optimization results and complete the scheduling process.

[0011] As a preferred scheme of the dual-optimization park-level integrated energy system scheduling method described in the present invention, the collection of park data and adjustment of the scheduling cycle include collecting distribution network and gas distribution network data, and constructing an optimized scheduling model with 24 hours as a scheduling cycle and one hour as a time step under the constraints of the distribution network, gas distribution network and related coupling equipment.

[0012] As a preferred scheme of the dual-optimization park-level integrated energy system scheduling method described in the present invention, the importing of the optimal output data of wind power and photovoltaic power generation includes, after obtaining the preliminary day-ahead scheduling optimization results, further importing the optimal output data of wind power and photovoltaic power generation, and setting the start time of intraday scheduling to t=1.

[0013] The forecast period is 15 minutes × 3, and the intraday scheduling cycle is set to 15 minutes × 4.

[0014] In each scheduling cycle, the system updates the actual output data of wind power and photovoltaics in real time. By analyzing the historical data of wind power and photovoltaics at the current moment, the system uses the long short-term memory network (LSTM) to predict the output situation in future time periods.

[0015] As a preferred solution of the dual-optimization park-level integrated energy system scheduling method described in the present invention, the construction of the intra-day optimization scheduling model includes first performing a prediction calculation, and the load prediction is expressed as:

[0016] P d (t) = f(W t ,H t ,T t )

[0017] Among them, P d (t) represents the predicted load at time t. t Represents the weather conditions at time t. t Represents the historical load data at time t. t Represents the time characteristics of time t.

[0018] The price prediction is expressed as:

[0019] P e(t) = g(M h ,D m )

[0020] Among them, P e (t) represents the predicted electricity price at time t. h Represents historical market price data. m Represents market demand forecast.

[0021] After clarifying the load and price forecast results, the next step is to optimize the start and stop plan of the unit. The start and stop of the generator set not only affects the economic benefits of the system, but also the physical characteristics and operating life of the unit. Therefore, under the premise of meeting the load demand, the start and stop time of the unit should be reasonably arranged to reduce the power generation cost and carbon emission cost.

[0022] As a preferred solution of the dual-optimization park-level integrated energy system scheduling method described in the present invention, wherein: the construction of the intra-day optimization scheduling model also includes, the objective function is expressed as:

[0023]

[0024] Among them, C gen (t) represents the power generation cost at time t, including fuel cost and startup cost. emission (t) represents the carbon emission cost at time t.

[0025] The constraints are expressed as:

[0026]

[0027] Among them, P gen,i (t) represents the power generation of unit i at time t.

[0028] As a preferred solution of the dual-optimization park-level integrated energy system scheduling method described in the present invention, the construction of the intraday optimization scheduling model also includes that the goal of energy storage management optimization is to maximize the economic benefits of energy storage equipment, which is expressed as:

[0029]

[0030] Among them, P dis (t) represents the discharge power of the energy storage device at time t. ch (t) represents the charging power of the energy storage device at time t. e (t) represents the electricity price at time t.

[0031] The constraints are as follows:

[0032] The power limit of energy storage equipment is expressed as:

[0033] 0≤Pch (t)≤P ch,max

[0034] 0≤P dis (t)≤P dis,max

[0035] The energy balance of energy storage equipment is expressed as:

[0036]

[0037] Where E(t) represents the remaining energy of the energy storage device at time t, η ch represents the charging power, η dis Indicates the discharge power.

[0038] The objective function of the electricity and gas purchasing strategy is expressed as:

[0039]

[0040] The constraints are expressed as:

[0041] Q e (t)+P gen (t)+P dis (t) = P d (t)

[0042] Q g (t) = Q gen (t)

[0043] Among them, Q e (t) represents the amount of electricity purchased at time t. g (t) represents the gas purchase volume at time t. e (t) and P g (t) denote the prices of electricity and natural gas, respectively.

[0044] As a preferred scheme of the dual-optimization park-level integrated energy system scheduling method described in the present invention, the output of intraday optimization results includes intraday scheduling using a rolling optimization method, scheduling is performed every 15 minutes, the rolling optimization time window is 4 hours, and only the scheduling plan for the last 15 minutes is executed.

[0045] Real-time load tracking is expressed as:

[0046]

[0047] in, is the actual load at time t. ΔP d (t) is the load forecast error correction.

[0048] The objective function of the fast adjustment strategy is the same as that of the day-ahead scheduling, but with an additional adjustment cost term:

[0049]

[0050] Among them, C adjust (t) is the adjustment cost at time t, reflecting the cost caused by plan deviation.

[0051] Output the intraday optimization results and complete the scheduling process.

[0052] A dynamic load capacity management system for oil-immersed power transformers, characterized in that it includes:

[0053] Build model modules, collect park data, adjust the dispatch cycle, and build an optimized dispatch model. Import the optimal output data of wind power and photovoltaic power generation to build an intraday optimized dispatch model.

[0054] The output result module outputs the intraday optimization results and completes the scheduling process.

[0055] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0056] A computer-readable storage medium stores a computer program, which implements the steps of the method described above when executed by a processor.

[0057] Beneficial effects of the present invention: The proposed mechanism significantly improves the flexibility and stability of the integrated energy system through real-time rolling optimization scheduling and load forecast error correction. Through the day-ahead and intraday rolling optimization algorithms, combined with real-time data feedback, the operation strategy is dynamically adjusted, which not only effectively responds to changes in load, market prices and weather, but also quickly responds to emergencies to ensure stable energy supply. The load forecast error correction mechanism dynamically corrects the forecast deviation, minimizes the impact of uncertainty, and enhances the system's responsiveness. The collaborative optimization strategy of unit start-stop and energy storage management effectively smooths load demand, reduces operating costs, and improves the system's ability to cope with fluctuations in renewable energy. The optimization of multi-energy electricity and gas purchase strategies reduces procurement costs and improves energy supply stability through dynamic market price decisions. In addition, the carbon emission cost is included in the scheduling target to achieve a balance between economic benefits and environmental protection goals, and to help build a low-carbon park. This series of innovative technologies effectively solves key issues such as multi-time scale balance, demand response, and economic optimization of the park energy system, providing technical support for a low-carbon, intelligent integrated energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0059] Figure 1 A dual-optimized park-level integrated energy system scheduling method and overall flow chart of the system is provided for the first embodiment of the present invention.

[0060] Figure 2 A dual-optimization park-level integrated energy system scheduling method and a system energy consumption comparison chart are provided for the second embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0062] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a dual-optimization park-level integrated energy system scheduling method, comprising:

[0063] S1: Collect park data, adjust the scheduling cycle, and build an optimized scheduling model.

[0064] In the design of the integrated energy system of the low-carbon park, the core goal is to achieve efficient and coordinated operation of electricity, heat and cold energy, improve overall energy utilization efficiency, and promote sustainable development. The system integrates a variety of energy production and storage equipment to achieve energy complementarity and conversion and optimize energy management.

[0065] Specifically, the integrated energy system design of a low-carbon park can include the following main components: photovoltaic power generation system, absorption chiller, geothermal heat pump and various energy storage solutions such as batteries, energy storage tanks, etc. The system also includes a photovoltaic cogeneration system for the simultaneous production of electricity and heat energy, thereby enhancing the system's adaptability and flexibility to energy demand. These components not only support the balance of energy supply and demand within the park, but also provide the ability to respond to external energy fluctuations.

[0066] This scheduling scheme is based on day-ahead and intraday scheduling strategies, combined with load forecasting, energy market price forecasting and energy storage management, and uses a real-time rolling optimization method to dynamically schedule the system to achieve stable system operation, minimized costs and optimized control of carbon emissions. The overall optimization scheduling architecture of the park is designed based on a multi-time scale integrated energy system scheduling method, aiming to achieve the goals of low-carbon, economical and efficient operation through refined time management and strategy adjustment. Multiple time scales are divided into short time scales for identifying instantaneous load fluctuations and real-time response capabilities, medium time scales for daily scheduling and energy efficiency optimization, and long time scales for specifying seasonal regulation and long-term optimization.

[0067] This scheduling framework is mainly divided into two parts: day-ahead scheduling and intraday scheduling, in order to adapt to the dynamic changes in energy demand and optimize resource use. In the day-ahead scheduling stage, the scheduling plan is formulated in units of one hour and is usually calculated 24 hours in advance. The main goal of this stage is to minimize daily operating costs and carbon emission costs while maximizing comprehensive energy efficiency.

[0068] Specific scheduling strategies include:

[0069] Unit start and stop scheduling: Optimize the start and stop times of generators and other energy equipment based on predicted energy demand and prices.

[0070] Energy storage management: Rationally arrange the charging and discharging plans of energy storage equipment to cope with energy price fluctuations and demand peaks and valleys.

[0071] Electricity and gas purchasing strategies: Based on market conditions and forecast results, decide when and how much electricity and natural gas to purchase to reduce costs and ensure stability of energy supply.

[0072] Intraday scheduling is based on real-time optimization of the day-ahead plan. The scheduling period is 15 minutes. Each calculation covers the demand for the next 4 hours, but only the plan for the most recent period is executed. The goal of this stage is to further reduce operating costs, carbon emission costs, and adjustment costs, while reducing the impact of uncertainty. The key tasks of intraday scheduling include:

[0073] Real-time load tracking: Monitor energy usage and power market dynamics in real time, and adjust power generation and energy usage plans to respond to actual demand and price changes.

[0074] Rapidly adjust strategies: Make necessary adjustments to the initial plan to respond to unexpected events or forecast errors to ensure stable system operation and maximize efficiency benefits.

[0075] The intraday optimization scheduling is based on the day-ahead scheduling plan, with the goal of minimizing the total cost of the park's comprehensive energy system within the next 4 hours. The total cost includes operating cost, carbon emission cost, and adjustment cost. Since the day-ahead optimization model no longer contains fractional terms after processing, the constructed day-ahead-intraday optimization model can be solved by a linear solver. However, linearizing the comprehensive energy efficiency optimization problem may affect the expression of the target cost, making the programming solution complicated. Although the commonly used linear weighted method can assign weight coefficients according to the importance and dimensional differences of the target, in most cases, it is difficult to reasonably select the weight value. Therefore, in the day-ahead multi-objective optimization, we use the main objective function method to find the optimal solution. The main objective function method is a commonly used method in multi-objective optimization problems to determine a set of optimal solutions. When a system has multiple objectives to be optimized (such as cost, carbon emission, energy efficiency, etc.), this method helps decision makers select a primary objective as the core of optimization and treat other objectives as constraints or secondary objectives. In an energy scheduling problem, it may be necessary to minimize both operating costs and carbon emissions. However, these objectives may not be optimal at the same time, because reducing carbon emissions may increase operating costs. The core idea of ​​the main objective function method is to select the most important goal as the "main objective function" and treat other goals as secondary goals or constraints. With the highest comprehensive energy efficiency as the goal, the cost is converted into constraints for optimization. By gradually adjusting the cost upper limit constraint, the solution is traversed to obtain the Pareto optimal frontier. The Pareto optimal solution refers to a solution that cannot make another goal better without making at least one goal worse. If there is a solution that cannot further reduce carbon emissions without increasing costs, and cannot further reduce costs without increasing carbon emissions, this solution is considered to be Pareto optimal. The Pareto optimal frontier is the set of all Pareto optimal solutions in the objective space. It depicts the optimal trade-off between different goals and represents the trade-off relationship between multiple optimization goals. This means that this method can be used to find a scheduling plan with the lowest carbon emissions within a certain cost range, and to find a solution that minimizes the total operating cost while ensuring the stability of energy supply. Finally, the parameters of the integrated energy distribution network system (such as power-to-gas, gas turbines, carbon capture and other equipment) are loaded, and the active output of wind power and photovoltaic power on the day before is predicted based on data such as wind speed and light.

[0076] S2: Import the optimal output data of wind power and photovoltaic power generation and build an intraday optimization scheduling model.

[0077] In the optimization and dispatching of the integrated energy system of the low-carbon park, an optimization and dispatching model is first constructed under the constraints of the distribution network, gas distribution network and related coupling equipment, with a dispatching cycle of 24 hours and a time step of one hour. The design objectives of this model are to reduce the comprehensive operating cost of the distribution network system, reduce carbon emissions, maximize the use of renewable energy such as wind power and photovoltaic power generation, and minimize network energy loss. In this process, the optimal output state and energy flow path of various renewable energy power generation units and energy storage devices in the distribution network and gas distribution network are determined. After obtaining the preliminary day-ahead dispatching optimization results, the optimal output data of wind power and photovoltaic power generation are further imported, and the start time of intraday dispatching is set to t=1. At this time, the predicted time period is 15 minutes × 3, and the intraday dispatching cycle is set to 15 minutes × 4. In each dispatching cycle, the system will update the actual output data of wind power and photovoltaic power generation in real time to ensure the accuracy of the optimization process. By analyzing the historical data of wind power and photovoltaic power generation at the current moment, the system uses a long short-term memory network (LSTM) to predict the output of future time periods. On this basis, an intraday optimization scheduling model is constructed, and the previous optimal output is used as the benchmark value, so as to minimize the deviation between the actual output and the benchmark value during the day as the optimization goal. In order to ensure the dynamic optimization of scheduling, the system needs to determine whether the current moment is still within the rolling optimization scheduling cycle. If so, the system replaces the wind power and photovoltaic output data at the beginning of the next cycle with the actual output value at the end of the previous cycle, and updates the predicted value at each moment to correct the initial conditions and re-enter the optimization process. If not, the final intraday optimization result is output to complete the scheduling process.

[0078] The steps of the day-ahead scheduling strategy are as follows:

[0079] Load forecasting is the first step in energy system scheduling and the basis for ensuring the rationality of the scheduling plan. In order to accurately predict the load demand for the next day, multiple influencing factors need to be considered. Common influencing factors include historical load data, weather conditions (such as temperature, humidity, wind speed, etc.), and time characteristics (such as daytime, nighttime, weekdays or holidays, etc.). At this stage, a deep learning model (LSTM) is used to improve the prediction accuracy.

[0080] P d (t) = f(W t ,H t ,T t )

[0081] Among them, P d (t) represents the predicted load at time t. t Indicates the weather conditions (temperature, humidity, etc.) at time t. t Represents the historical load data at time t. tRepresents the time characteristics of time t (different time periods, whether it is a holiday).

[0082] The forecast of electricity and natural gas prices is crucial for decision-making on electricity and gas purchasing strategies. Similar to load forecasting, price forecasting also requires historical market price data and market demand forecasts as input data. By analyzing past market price and demand changes, a forecasting model is constructed to estimate price fluctuations at different time periods in the future day.

[0083] P e (t) = g(M h ,D m )

[0084] Among them, P e (t) represents the predicted electricity price at time t. h Represents historical market price data. m Represents market demand forecast.

[0085] After clarifying the load and price forecast results, the next step is to optimize the start and stop plan of the unit. The start and stop of the generator set not only affects the economic benefits of the system, but also the physical characteristics and operating life of the unit. Therefore, it is necessary to reasonably arrange the start and stop time of the unit on the premise of meeting the load demand to minimize the power generation cost and carbon emission cost.

[0086] Objective function:

[0087]

[0088] Where: C gen (t) represents the power generation cost at time t, including fuel cost, startup cost, etc.

[0089] C emission (t) represents the carbon emission cost at time t

[0090] Constraints:

[0091] The power generation balance constraint ensures that the total power generation must meet the load demand, and the unit start and stop time constraint ensures that the start and stop time of each unit must comply with the minimum start and stop time limit of the unit to avoid frequent start and stop causing damage to the unit.

[0092]

[0093] Among them, P gen,i (t) is the power generation capacity of unit i at time t.

[0094] The management of energy storage systems plays an important role in scheduling optimization. By charging when electricity prices are low and discharging when electricity prices are high, it helps smooth load and price fluctuations, thereby improving the economic benefits of the system. In energy storage management optimization, the goal is to maximize the economic benefits of energy storage equipment. The specific optimization objective function is:

[0095]

[0096] Among them, P dis (t) represents the discharge power of the energy storage device at time t. ch (t) represents the charging power of the energy storage device at time t. e (t) represents the electricity price at time t.

[0097] Constraints:

[0098] Energy storage equipment power limit:

[0099] 0≤P ch (t)≤P ch,max

[0100] 0≤P dis (t)≤P dis,max

[0101] Energy balance of energy storage equipment:

[0102]

[0103] Where: E(t) represents the remaining energy of the energy storage device at time t, η ch and η dis are the charging and discharging powers respectively.

[0104] Based on the load and price forecasts, the goal of the electricity and gas purchasing strategy is to purchase the required electricity and natural gas in the best way to minimize costs and ensure the stability of energy supply. In this step, it is necessary to decide the amount of electricity and gas to be purchased at each moment.

[0105] Objective function:

[0106]

[0107] Among them, Q e (t) represents the amount of electricity purchased at time t. g (t) represents the gas purchase volume at time t. e (t) and P g (t) denote the prices of electricity and natural gas, respectively.

[0108] Constraints:

[0109] The purchase of electricity and gas must meet the needs, namely:

[0110] Q e (t)+P gen (t)+P dis (t) = P d (t)

[0111] Q g (t) = Q gen (t)

[0112] The intraday scheduling adopts the rolling optimization method, with scheduling performed every 15 minutes. The rolling optimization time window is 4 hours, but only the scheduling plan for the last 15 minutes is executed.

[0113] Intraday scheduling can dynamically adjust the actual load demand when the system is running in real time. In each period, the real-time monitoring system records the current load and combines the real-time market price to timely correct the initial load forecast. This process can effectively deal with load deviations caused by weather changes, user behavior or other unforeseen events.

[0114]

[0115] in, is the actual load at time t. ΔP d (t) is the load forecast error correction.

[0116] Based on real-time load and market price changes, quickly adjust power generation, energy storage, electricity purchase and gas purchase plans. Recalculate unit start and stop and energy storage operations according to current market conditions and emergencies. The objective function is the same as day-ahead scheduling, but with an additional adjustment cost term:

[0117]

[0118] Among them, C adjust (t) is the adjustment cost at time t, reflecting the cost caused by plan deviation.

[0119] S3: Output the intraday optimization results and complete the scheduling process.

[0120] Solve the model in Matlab and get the intraday optimization results.

[0121] The above embodiments also include a dual-optimized park-level integrated energy system dispatching system, specifically:

[0122] Build model modules, collect park data, adjust the dispatch cycle, and build an optimized dispatch model. Import the optimal output data of wind power and photovoltaic power generation to build an intraday optimized dispatch model.

[0123] The output result module outputs the intraday optimization results and completes the scheduling process.

[0124] The computer device may be a server. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data cluster data of the power monitoring system. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a dual-optimization park-level integrated energy system scheduling method is implemented.

[0125] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may 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 may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0126] Example 2, reference Figure 2 , which is an embodiment of the present invention, provides a dual-optimization park-level integrated energy system scheduling method and system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0127] The present invention uses actual data from a specific park to test the optimization method for day-ahead and intraday scheduling. Figure 2, is a comparison of three situations: the day-ahead stage, the intraday stage, and the no-optimization stage. The blue line segment represents the day-ahead stage, the orange line segment represents the intraday stage, and the gray line segment represents the no-optimization stage. The effectiveness of these optimization algorithms in achieving low-carbon optimization goals indicates their applicability in a park environment. Compared with no optimization, the day-ahead optimization reduces energy consumption by an average of about 2.91%, while the intraday optimization reduces it by an average of about 0.89%. This shows that while both optimization methods significantly improve energy consumption, the day-ahead optimization is more effective.

[0128] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A dual-optimization park-level integrated energy system scheduling method, characterized in that: include: Collect park data, adjust scheduling cycles, and build optimized scheduling models; Import the optimal output data of wind power and photovoltaic power generation to build an intraday optimization scheduling model; Output the intraday optimization results and complete the scheduling process.

2. The dual-optimization park-level integrated energy system scheduling method according to claim 1, characterized in that: The collecting of park data and adjusting of the dispatching cycle include collecting data of the distribution network and the gas distribution network, and constructing an optimized dispatching model with 24 hours as a dispatching cycle and one hour as a time step under the constraints of the distribution network, the gas distribution network and related coupling equipment.

3. The dual-optimization park-level integrated energy system scheduling method according to claim 2, characterized in that: The importing of the optimal output data of wind power and photovoltaic power generation includes, after obtaining a preliminary day-ahead dispatch optimization result, further importing the optimal output data of wind power and photovoltaic power generation, and setting the start time of intraday dispatch as t=1; The forecast period is 15 minutes × 3, and the intraday scheduling period is set to 15 minutes × 4; In each scheduling cycle, the system updates the actual output data of wind power and photovoltaics in real time. By analyzing the historical data of wind power and photovoltaics at the current moment, the system uses the long short-term memory network (LSTM) to predict the output situation in future time periods.

4. The dual-optimization park-level integrated energy system scheduling method according to claim 3, characterized in that: The construction of the intraday optimization dispatching model includes first performing a forecast calculation, and the load forecast is expressed as: P d (t)=f(W t ,H t ,T t ) Among them, P d (t) represents the predicted load at time t; W t Indicates the weather conditions at time t; H t Represents the historical load data at time t; T t represents the time characteristics of time t; The price prediction is expressed as: P e (t)=g(M h ,D m ) Among them, P e (t) represents the predicted electricity price at time t; M h Represents historical market price data; D m represents the market demand forecast; After clarifying the load and price forecast results, the next step is to optimize the start and stop plans of the units; the start and stop of the generating units not only affect the economic benefits of the system, but also the physical characteristics and operating life of the units; therefore, on the premise of meeting the load demand, the start and stop time of the units should be reasonably arranged to reduce the power generation cost and carbon emission cost.

5. The dual-optimization park-level integrated energy system scheduling method according to claim 4, characterized in that: The construction of the intraday optimization scheduling model also includes that the objective function is expressed as: Among them, C gen (t) represents the power generation cost at time t, including fuel cost and startup cost; C emission (t) represents the carbon emission cost at time t; The constraints are expressed as: Among them, P gen，i (t) represents the power generation of unit i at time t.

6. The dual-optimization park-level integrated energy system scheduling method according to claim 5, characterized in that: The construction of the intraday optimization scheduling model also includes that the goal of energy storage management optimization is to maximize the economic benefits of energy storage equipment, which is expressed as: Among them, P dis (t) represents the discharge power of the energy storage device at time t; P ch (t) represents the charging power of the energy storage device at time t; P e (t) represents the electricity price at time t; The constraints are as follows: The power limit of energy storage equipment is expressed as: 0≤P ch (t)≤P ch，max 0≤P dis (t)≤P dis，max The energy balance of energy storage equipment is expressed as: Where E(t) represents the remaining energy of the energy storage device at time t, η ch represents the charging power, η dis Indicates discharge power; The objective function of the electricity and gas purchasing strategy is expressed as: The constraints are expressed as: Q e (t)+P gen (t)+P dis (t)=P d (t) Q g (t)=Q gen (t) Among them, Q e (t) represents the amount of electricity purchased at time t; Q g (t) represents the gas purchase volume at time t; P e (t) and P g (t) denote the prices of electricity and natural gas, respectively.

7. The dual-optimization park-level integrated energy system scheduling method according to claim 6, characterized in that: The output of intraday optimization results includes that intraday scheduling adopts a rolling optimization method, scheduling is performed every 15 minutes, the rolling optimization time window is 4 hours, and only the scheduling plan of the last 15 minutes is executed; Real-time load tracking is expressed as: in, is the actual load at time t; ΔP d (t) is the load forecast error correction; The objective function of the fast adjustment strategy is the same as that of the day-ahead scheduling, but with an additional adjustment cost term: Among them, C adiust (t) is the adjustment cost at time t, reflecting the cost of plan deviation; Output the intraday optimization results and complete the scheduling process.

8. A dual-optimization park-level integrated energy system dispatching system using the method according to any one of claims 1 to 7, characterized in that: Build model modules, collect park data, adjust the dispatch cycle, and build an optimized dispatch model; import the optimal output data of wind power and photovoltaic power generation, and build an intraday optimized dispatch model; The output result module outputs the intraday optimization results and completes the scheduling process.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images