Multi-cycle load curve optimization decomposition method and system based on power market

Abstract

The invention discloses a multi-cycle load curve optimization decomposition method and system based on an electric power market, and relates to the technical field of electric power system optimization and dispatch, and the method comprises the steps: collecting various data related to the electric power market, and processing the collected various data; establishing a plurality of typical scenes based on the processed data; aiming at each generated typical scene, carrying out optimization decomposition on a load curve by utilizing a multi-objective optimization algorithm; the typical scene model is updated in real time by receiving real-time data in the electricity market in real time, and the current load decomposition strategy is automatically adjusted based on market changes. Through real-time data processing and a multi-objective optimization algorithm, the consumption proportion of new energy can be maximized, dependence on conventional energy is reduced, and the environmental protection property of a power grid is improved. And secondly, the smoothness of a load curve is optimized, and the stability of power grid operation is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization and dispatching, and in particular to a method and system for optimizing and decomposing a multi-period load curve based on a power market. Background Art

[0002] In recent years, with the increasing global attention to renewable energy, the proportion of renewable energy generation in the power market has gradually increased. Renewable energy such as photovoltaic power generation and wind power generation has become an important part of the power system due to its environmental protection characteristics and improved technical maturity. However, due to the volatility and intermittent characteristics of these renewable energy power generation methods, traditional power grid dispatching technology faces many challenges. Traditional power system dispatching usually relies on a load curve model based on prediction, and power plants output power according to load demand and electricity price fluctuations. This method has high accuracy and operability in the era when conventional fossil energy power generation is dominant, but in the current environment where the proportion of new energy is gradually increasing, it cannot effectively respond to changes in the real-time power market. With the reform of the power market and the introduction of the spot market mechanism, power dispatching technology is gradually developing in a more flexible and intelligent direction. The ability to collect and analyze real-time data, the ability to decompose and allocate complex loads, and the efficient management of renewable energy generation have become the key to power system dispatching.

[0003] However, the existing power dispatching technology still has obvious shortcomings when dealing with the uncertainty and volatility of renewable energy generation. First, the decomposition and dispatching of load curves rely on relatively static historical data and simple prediction models, and cannot be dynamically adjusted according to real-time market data (such as electricity prices, load demand, weather conditions, etc.), resulting in low system operation efficiency. Secondly, the existing load decomposition strategy is usually unable to fully absorb renewable energy generation resources, especially when wind power generation and photovoltaic power generation fluctuate greatly, conventional power sources still account for a large proportion, resulting in high carbon emissions and costs in power grid operation. In addition, the load dispatching system lacks the ability to respond to market price fluctuations in real time, and it is difficult to effectively optimize the user's electricity cost. In view of these shortcomings, how to achieve the optimal decomposition of load curves and automatically adjust the allocation of different power generation resources through multi-objective optimization algorithms combined with real-time data processing has become an important research topic in the current field of power dispatching technology. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

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

[0006] Therefore, the technical problem solved by the present invention is that the existing power system load decomposition technology cannot effectively cope with the volatility and real-time market changes of renewable energy power generation, resulting in insufficient new energy consumption, rigid load scheduling, and insufficient optimization of user electricity costs.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a multi-period load curve optimization decomposition method based on the power market, which comprises:

[0009] Collect various data related to the electricity market and process the collected data;

[0010] Establish multiple typical scenarios based on processed data;

[0011] For each typical scenario generated, the load curve is optimized and decomposed using a multi-objective optimization algorithm;

[0012] By receiving real-time data from the power market in real time, the typical scenario model is updated in real time, and the current load decomposition strategy is automatically adjusted based on market changes.

[0013] 3. As a preferred scheme of the multi-period load curve optimization decomposition method based on the electricity market described in the present invention, wherein: the multiple data include intraday electricity price data, electricity price fluctuation range and frequency, regional load demand curve, historical demand trend data, photovoltaic power generation, light intensity, wind power generation, wind speed, new energy policy support intensity, market access rules and restrictions data, temperature, meteorological warning, long-term climate trend data, green electricity contract data, spot market transaction volume and electricity delivery data, power generation equipment status monitoring data, power grid equipment carrying capacity data, power generation plan and actual power generation comparison data and power grid spare capacity data.

[0014] As a preferred solution of the multi-period load curve optimization decomposition method based on the power market described in the present invention, the processing of the collected various data includes preprocessing of various data, analysis of the electricity price fluctuation range, extraction of typical forms of load curves and analysis of fluctuations in new energy power generation;

[0015] Various data preprocessing including data cleaning, time alignment and synchronization, and denoising;

[0016] The analysis of electricity price fluctuation range includes using time series analysis methods to extract the fluctuation range of electricity prices and analyze the peak and trough periods of electricity prices;

[0017] The typical form extraction of load curve includes: using K-means to classify historical load curves according to their forms and extract the typical forms of load curves; using pattern recognition technology to automatically detect the regular forms in load curves and normalize the load curve data of different regions or industries;

[0018] The fluctuation analysis of renewable energy power generation includes using meteorological data to analyze the changing trends of power generation for wind power and photovoltaic power generation, especially the fluctuation range of power generation under different weather conditions; analyzing the correlation between meteorological conditions and renewable energy power generation through time series prediction models, and extracting the typical fluctuation patterns of power generation; and analyzing the distribution of prediction errors by comparing actual power generation with predicted power generation.

[0019] As a preferred solution of the multi-period load curve optimization decomposition method based on the power market described in the present invention, the typical scenarios include electricity price fluctuation scenarios, policy change scenarios, weather condition scenarios and load demand scenarios.

[0020] As a preferred solution of the multi-period load curve optimization decomposition method based on the power market of the present invention, wherein: the electricity price fluctuation scenario includes simulating the peak and valley conditions of electricity prices in different time periods to understand the impact of electricity price fluctuations on load and power generation;

[0021] The policy change scenarios include simulating scenarios of policy support or tightening to analyze the impact of policy changes on the power market and new energy;

[0022] The weather condition scenarios include simulating the impact of different weather conditions on renewable energy power generation and analyzing the volatility of the renewable energy power generation curve due to weather changes;

[0023] The load demand scenario includes simulating the load curve changes under different electricity demand conditions and analyzing the impact of high load and low load periods on the power system.

[0024] As a preferred solution of the multi-period load curve optimization decomposition method based on the power market of the present invention, the objectives of the optimization algorithm include: improving the smoothness of the load curve;

[0025] Maximize the proportion of new energy consumption;

[0026] Minimize the user's electricity costs;

[0027] The integration based on weighted smoothing function is used to improve the smoothness of the load curve. The formula is expressed as:

[0028]

[0029] Where, L(t) represents the load curve, S smoothrepresents the smoothness measure; α1 represents the weight associated with load smoothness, t0 and t1 are the starting and ending points of the optimization time period;

[0030] The new energy consumption rate is used, which is expressed as the maximum proportion of new energy consumption in the power generation curve. The formula is:

[0031]

[0032] Among them, E renewable Represents the amount of renewable energy consumed, P renewable (t) represents the amount of electricity generated by renewable energy, P total (t) represents the total power generation, t0 and t1 are the starting point and end point of the optimization time period; α2 represents the weight related to the proportion of new energy consumption;

[0033] The formula for expressing the user's electricity cost using the time-weighted electricity price curve is:

[0034]

[0035] Among them, C cost represents the electricity cost, λ(t) represents the electricity price at time t, L(t) represents the load curve at time t, t0 and t1 are the starting point and end point of the optimization time period; α3 represents the weight related to the user's electricity cost;

[0036] Combining these three objectives together forms a multi-objective optimization problem, which is expressed as:

[0037] In the optimization process, these three objectives are combined to form a multi-objective optimization problem. By reducing load fluctuations, the stability and reliability of the power system are improved, and the frequency of large-scale dispatch is reduced. At the same time, priority is given to the consumption of new energy, the proportion of new energy in total power generation is optimized, and the use of renewable energy is promoted. In addition, by optimizing user electricity consumption in different time periods, especially reducing unnecessary electricity consumption during peak electricity price periods, the user's electricity cost is effectively reduced and the overall economic benefits are improved.

[0038] The formula is:

[0039] min(S smooth +E renewable +C cost )

[0040] Among them, S smooth represents the smoothness measure, E renewable Represents the amount of renewable energy consumed, C cost Indicates the cost of electricity.

[0041] 8. As a preferred solution of the multi-period load curve optimization decomposition method based on the power market described in the present invention, wherein: the automatic adjustment of the current load decomposition strategy includes load distribution optimization, load peak adjustment and new energy priority consumption;

[0042] The load distribution optimization includes giving priority to the use of new energy, reducing dependence on conventional fossil fuel power generation, and reducing carbon emissions;

[0043] The load peak adjustment includes that the system actively adjusts the load peak according to the fluctuation of electricity price and the demand of users, so as to optimize the operation cost of the power grid and users;

[0044] The priority consumption of new energy includes that the system dynamically adjusts the load distribution of different power generation resources by analyzing weather forecast data and real-time meteorological information.

[0045] In a second aspect, the present invention provides a multi-period load curve optimization decomposition system based on the power market, which comprises:

[0046] The data module collects various data related to the power market and processes the collected data;

[0047] The scenario building module builds multiple typical scenarios based on the processed data;

[0048] The optimization module uses a multi-objective optimization algorithm to optimize and decompose the load curve for each typical scenario generated;

[0049] The adjustment module receives real-time data from the power market in real time, updates the typical scenario model in real time, and automatically adjusts the current load decomposition strategy based on market changes.

[0050] In a third aspect, the present invention provides 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 a multi-period load curve optimization decomposition method based on the electricity market are implemented.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of a method for optimizing decomposition of a multi-period load curve based on an electricity market are implemented.

[0052] Compared with the prior art, the beneficial effect of the present invention is that through real-time data processing and multi-objective optimization algorithms, the proportion of new energy consumption can be maximized, the dependence on conventional energy can be reduced, and the environmental protection of the power grid can be improved. Secondly, the smoothness of the load curve is optimized, ensuring the stability of the power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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.

[0054] Figure 1 A flowchart of a method and system for optimizing and decomposing a multi-period load curve based on an electricity market is provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned purposes, features and advantages of the present invention more understandable, 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 them. 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.

[0056] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0059] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides a multi-period load curve optimization decomposition method based on the electricity market.

[0060] A method flow chart of a multi-period load curve optimization decomposition method and system based on the power market, comprising:

[0061] S1: Collect various data related to the electricity market and process the collected data. The various data include intraday electricity price data, electricity price fluctuation range and frequency, regional load demand curve, historical demand trend data, photovoltaic power generation, light intensity, wind power generation, wind speed, new energy policy support intensity, market access rules and restrictions, temperature, meteorological warning, long-term climate trend data, green power contract data, spot market transaction volume and power delivery data, power generation equipment status monitoring data, power grid equipment carrying capacity data, power generation plan and actual power generation comparison data and power grid spare capacity data.

[0062] The processing of various collected data includes various data preprocessing, analysis of electricity price fluctuation range, extraction of typical forms of load curves and analysis of fluctuations in new energy power generation.

[0063] Various data preprocessing includes data cleaning, time alignment and synchronization, and denoising.

[0064] The analysis of electricity price fluctuation range includes using time series analysis methods to extract the fluctuation range of electricity prices and analyze the peak and trough periods of electricity prices.

[0065] The typical form extraction of load curve includes: using K-means to classify historical load curves according to their forms and extract the typical forms of load curves; using pattern recognition technology to automatically detect the regular forms in load curves and normalize the load curve data of different regions or industries.

[0066] The fluctuation analysis of renewable energy power generation includes using meteorological data to analyze the changing trends of power generation for wind power and photovoltaic power generation, especially the fluctuation range of power generation under different weather conditions; analyzing the correlation between meteorological conditions and renewable energy power generation through time series prediction models, and extracting the typical fluctuation patterns of power generation; and analyzing the distribution of prediction errors by comparing actual power generation with predicted power generation.

[0067] Furthermore, by systematically collecting various data related to the power market, a solid data foundation is provided for subsequent optimization analysis. Data processing includes steps such as cleaning, time alignment, and denoising to ensure the accuracy and consistency of the data.

[0068] S2: Establish multiple typical scenarios based on the processed data.

[0069] Typical scenarios include electricity price fluctuation scenarios, policy change scenarios, weather condition scenarios and load demand scenarios.

[0070] The electricity price fluctuation scenario includes simulating the peak and trough conditions of electricity prices at different time periods to understand the impact of electricity price fluctuations on load and power generation.

[0071] The electricity price fluctuation scenario requires modeling the changes in electricity prices, especially simulating the fluctuations in electricity prices over time series.

[0072] The ARIMA model is used to predict future electricity price fluctuations. The formula is expressed as:

[0073]

[0074] Where: P(t) represents the electricity price at time t; μ represents the constant term; φ i represents the autoregressive coefficient; θ j represents the moving average coefficient; ∈(t) represents the error term.

[0075] By using historical electricity price data, scenarios of future electricity price fluctuations can be generated to analyze the impact of electricity price peaks and troughs on the load curve.

[0076] The policy change scenarios include simulating scenarios of policy support or tightening to analyze the impact of policy changes on the electricity market and new energy.

[0077] Policy change impact model:

[0078] I policy =W subsidy ·P subsidy +W limit ·P limit

[0079] Where: I policy represents the overall impact of policy changes; W subsidy is the weight of policy support;

[0080] P subsidy represents the intensity of policy support, W limit is the weight of the policy restriction, P limit It is the intensity of policy restrictions.

[0081] The weather condition scenario includes simulating the impact of different weather conditions on renewable energy power generation and analyzing the volatility of the renewable energy power generation curve due to weather changes.

[0082] Weather condition scenarios require predictions of fluctuations in renewable energy generation, especially the impact of meteorological conditions such as light intensity and wind speed on power generation.

[0083] Wind power generation formula:

[0084]

[0085] Among them, P wind represents wind power generation, ρ represents air density, A represents the swept area of ​​the wind wheel, v represents wind speed, and η represents the efficiency of the wind turbine.

[0086] Photovoltaic power generation formula:

[0087] P solar =G t ·A·η

[0088] Among them, P solar Represents photovoltaic power generation; G t It represents the solar radiation intensity per unit area; A represents the area of ​​the photovoltaic panel; η represents the efficiency of the photovoltaic cell.

[0089] The load demand scenario includes simulating the load curve changes under different electricity demand conditions and analyzing the impact of high load and low load periods on the power system.

[0090] The load forecasting formula is expressed as: L(t) = β0 + β1T(t) + β2P(t) + β3H(t) + ∈

[0091] Among them, L(t) represents the load demand at time t, T(t) represents the temperature at time t, P(t) represents the electricity price at time t, H(t) is the humidity at time t, β0, β1, β2, β3 represent regression coefficients, and ∈ is the error term.

[0092] Furthermore, by conducting scenario analysis on the processed data, several typical scenarios were established, including electricity price fluctuations, policy changes, weather conditions, and load demand. Through scenario modeling, the system can simulate the performance of the power system under different market conditions, providing a basis for multi-objective optimization.

[0093] S3: For each typical scenario generated, the load curve is optimized and decomposed using a multi-objective optimization algorithm.

[0094] The goals of the optimization algorithm include: improving the smoothness of the load curve.

[0095] Maximize the consumption ratio of new energy.

[0096] Minimize the user's electricity costs.

[0097] The integration based on weighted smoothing function is used to improve the smoothness of the load curve. The formula is expressed as:

[0098]

[0099] Where, L(t) represents the load curve, S smooth represents the smoothness measure; α1 represents the weight related to load smoothness, and t0 and t1 are the starting and ending points of the optimization time period.

[0100] The new energy consumption rate is used, which is expressed as the maximum proportion of new energy consumption in the power generation curve. The formula is:

[0101]

[0102] Among them, E renewable Represents the amount of renewable energy consumed, P renewable (t) represents the amount of electricity generated by renewable energy, P total (t) represents the total power generation, t0 and t1 are the starting point and end point of the optimization time period; α2 represents the weight related to the proportion of new energy consumption.

[0103] The formula for expressing the user's electricity cost using the time-weighted electricity price curve is:

[0104]

[0105] Among them, C cost represents the electricity cost, λ(t) represents the electricity price at time t, L(t) represents the load curve at time t, t0 and t1 are the starting point and end point of the optimization time period; α3 represents the weight related to the user's electricity cost.

[0106] Combining these three objectives together forms a multi-objective optimization problem, which is expressed as:

[0107] During the optimization process, these three objectives are combined to form a multi-objective optimization problem. By reducing load fluctuations, the stability and reliability of the power system can be improved and the frequency of large-scale dispatching can be reduced. At the same time, priority is given to the consumption of new energy, the proportion of new energy in total power generation is optimized, and the use of renewable energy is promoted. In addition, by optimizing user electricity consumption in different time periods, especially reducing unnecessary electricity consumption during peak electricity price periods, the user's electricity cost can be effectively reduced and the overall economic benefits can be improved.

[0108] The formula is:

[0109] min(S smooth +E renewable +C cost )

[0110] Among them, S smooth represents the smoothness measure, E renewable Represents the amount of renewable energy consumed, C cost Indicates the cost of electricity.

[0111] Furthermore, the load curves of each typical scenario are optimized and decomposed through a multi-objective optimization algorithm. This not only improves the smoothness of the load curve, but also maximizes the proportion of new energy consumption and minimizes the user's electricity cost. The introduction of multi-objective optimization enables the system to achieve a balance between different objectives.

[0112] S4: By receiving real-time data in the power market in real time, the typical scenario model is updated in real time, and the current load decomposition strategy is automatically adjusted based on market changes.

[0113] Automatically adjust the current load decomposition strategy, including load distribution optimization, load peak adjustment and new energy priority consumption;

[0114] The load distribution optimization includes giving priority to the use of new energy, reducing dependence on conventional fossil fuel power generation, and reducing carbon emissions;

[0115] The load peak adjustment includes that the system actively adjusts the load peak according to the fluctuation of electricity price and the demand of users, so as to optimize the operation cost of the power grid and users;

[0116] The priority consumption of new energy includes that the system dynamically adjusts the load distribution of different power generation resources by analyzing weather forecast data and real-time meteorological information.

[0117] Furthermore, the system can receive real-time data from the power market, such as electricity prices, load demand, weather changes, etc., automatically update the scenario model, and adjust the load decomposition strategy according to market changes. This real-time update and dynamic adjustment ensures the flexibility of the system.

[0118] Embodiment 2 is an embodiment of the present invention, which provides a multi-period load curve optimization decomposition system based on the power market, including:

[0119] The data module collects various data related to the electricity market and processes the collected data.

[0120] The scenario establishment module establishes multiple typical scenarios based on the processed data.

[0121] The optimization module uses a multi-objective optimization algorithm to optimize and decompose the load curve for each typical scenario generated.

[0122] The adjustment module receives real-time data from the power market in real time, updates the typical scenario model in real time, and automatically adjusts the current load decomposition strategy based on market changes.

[0123] The detection module inputs the fused features into the fully connected layer, processes them and outputs the detection results.

[0124] Embodiment 3, an embodiment of the present invention, is different from the first two embodiments in that:

[0125] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0126] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0127] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0128] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0129] Example 4, a detailed analysis is performed based on a variety of data in the actual electricity market. The test content includes important parameters such as electricity price fluctuations, load demand, weather conditions and renewable energy power generation. By collecting data related to the electricity market, including photovoltaic power generation, wind power generation, conventional power generation, real-time electricity prices, user load demand and other data, the processed data is cleaned, normalized, denoised and other operations to ensure the accuracy and consistency of the data. On this basis, the system has carried out detailed modeling for typical scenarios in different time periods (such as peak electricity prices, increased wind speed, increased light, etc.).

[0130] In the process of scenario establishment, the system generated multiple representative scenarios: for example, the peak period of photovoltaic power generation, the period of wind power fluctuation, the period of conventional power load increase, etc. By using a multi-objective optimization algorithm, the system mainly considered three goals in load decomposition: first, to improve the smoothness of the load curve and ensure the stability of the grid operation; second, to maximize the proportion of new energy consumption to reduce dependence on traditional fossil energy; third, to minimize the user's electricity cost and optimize the overall economic benefits.

[0131] For these typical scenarios, the system can dynamically adjust the decomposition strategy using real-time market data (such as weather data, electricity price fluctuations, changes in load demand, etc.). The optimization algorithm receives market update data every 10 minutes and recalculates the load decomposition plan based on the latest data. In the specific implementation process, the optimization algorithm not only takes into account the volatility of renewable energy generation, but also minimizes the volatility of the power dispatching system through comprehensive trade-offs under multiple scenarios. The specific strategies used by the algorithm include genetic algorithms combined with linear programming algorithms to achieve efficient solutions.

[0132] The results of load decomposition are compared with the conventional static decomposition scheme to verify the advantages of real-time data update and automatic adjustment strategy. All experimental data are recorded in a table and displayed in Excel format. The experimental table shows the load decomposition effect of the test object under different scenarios, including initial load, adjusted load, total power generation and the proportion of new energy use. The experimental data are shown in Table 1.

[0133] Table 1 Experimental data table

[0134]

[0135] It can be seen from the experimental data table that the optimized load adjustment significantly reduces the peak load of the power grid, especially in scenarios 1, 2 and 5, where the load after load decomposition is significantly lower than the initial load. This reduction is mainly achieved by maximizing the proportion of renewable energy generation. Specifically, the proportion of renewable energy consumption in scenarios 2 and 6 increased by about 10%, respectively, effectively reducing the use of conventional power generation. In addition, in multiple scenarios, the user's electricity cost has been significantly reduced through the load decomposition of the optimization algorithm. For example, in scenarios 3 and 6 where electricity prices are higher, through real-time optimization and adjustment, the system reduces the user's electricity consumption during peak electricity price periods, thereby reducing the total cost.

[0136] Compared with the existing load decomposition technology, the traditional static method can only perform simple load forecasting and allocation based on historical data, and cannot dynamically respond to market changes, resulting in low resource utilization and insufficient consumption of new energy. The present invention significantly improves the dynamic response capability of the system by real-time collection and processing of market data and combining multi-objective optimization algorithms. In actual experiments, the system successfully increased the consumption ratio of new energy such as photovoltaic power generation and wind power generation by 20%-30% through scenario prediction and real-time adjustment, while greatly reducing dependence on conventional energy, with significant economic and environmental benefits.

[0137] In addition, the multi-objective optimization algorithm used in the invention can strike a balance between multiple objectives. For example, between improving load smoothness and maximizing new energy consumption, the system achieves an effective combination of new energy consumption ratio and grid stability through the algorithm. Moreover, by applying real-time data updates, the system can quickly respond to electricity prices, demand changes and weather fluctuations to achieve more intelligent and flexible load distribution. Compared with traditional static algorithms, the dynamic optimization of the present invention significantly improves dispatching efficiency and provides technical support for the intelligent regulation of future power grids.

[0138] 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 multi-period load curve optimization decomposition method based on the power market, characterized by: include, Collect various data related to the electricity market and process the collected data; Establish multiple typical scenarios based on processed data; For each typical scenario generated, the load curve is optimized and decomposed using a multi-objective optimization algorithm; By receiving real-time data from the power market in real time, the typical scenario model is updated in real time, and the current load decomposition strategy is automatically adjusted based on market changes.

2. The multi-period load curve optimization decomposition method based on the power market according to claim 1, characterized in that: The various data include intraday electricity price data, electricity price fluctuation range and frequency, regional load demand curve, historical demand trend data, photovoltaic power generation, light intensity, wind power generation, wind speed, new energy policy support intensity, market access rules and restrictions, temperature, meteorological warnings, long-term climate trend data, green electricity contract data, spot market transaction volume and electricity delivery data, power generation equipment status monitoring data, power grid equipment carrying capacity data, power generation plan and actual power generation comparison data and power grid backup capacity data.

3. The multi-period load curve optimization decomposition method based on the power market according to claim 2, characterized in that: Processing of various collected data includes preprocessing of various data, analysis of electricity price fluctuation range, extraction of typical forms of load curves and analysis of fluctuations in new energy power generation; Various data preprocessing including data cleaning, time alignment and synchronization, and denoising; The analysis of electricity price fluctuation range includes using time series analysis methods to extract the fluctuation range of electricity prices and analyze the peak and trough periods of electricity prices; The typical form extraction of the load curve includes, using K-means, classifying the historical load curve according to the form, and extracting the typical form of the load curve; Through pattern recognition technology, regular patterns in load curves are automatically detected, and load curve data from different regions or industries are normalized; The analysis of fluctuations in renewable energy power generation includes using meteorological data to analyze the changing trends of wind power and photovoltaic power generation, especially the fluctuation range of power generation under different weather conditions; using time series prediction models to analyze the correlation between meteorological conditions and renewable energy power generation, and extracting typical fluctuation patterns of power generation; By comparing the actual power generation with the predicted power generation, the distribution of the prediction error is analyzed.

4. The multi-period load curve optimization decomposition method based on the power market according to claim 3, characterized in that: The typical scenarios include electricity price fluctuation scenarios, policy change scenarios, weather condition scenarios and load demand scenarios.

5. The multi-period load curve optimization decomposition method based on the power market according to claim 4, characterized in that: The electricity price fluctuation scenario includes simulating the peak and valley conditions of electricity prices at different time periods to understand the impact of electricity price fluctuations on load and power generation; The policy change scenarios include simulating scenarios of policy support or tightening to analyze the impact of policy changes on the power market and new energy; The weather condition scenarios include simulating the impact of different weather conditions on renewable energy power generation and analyzing the volatility of the renewable energy power generation curve due to weather changes; The load demand scenario includes simulating the load curve changes under different electricity demand conditions and analyzing the impact of high load and low load periods on the power system.

6. The multi-period load curve optimization decomposition method based on the power market according to claim 5, characterized in that: The objectives of the optimization algorithm include: improving the smoothness of the load curve; Maximize the proportion of new energy consumption; Minimize the user's electricity costs; The integration based on weighted smoothing function is used to improve the smoothness of the load curve. The formula is expressed as: Where, L(t) represents the load curve, S smooth represents the smoothness measure; α1 represents the weight related to load smoothness, t0 and t1 are the starting and ending points of the optimization time period; The new energy consumption rate is used, which is expressed as the maximum proportion of new energy consumption in the power generation curve. The formula is: Among them, E renewable Represents the amount of renewable energy consumed, P renewable (t) represents the amount of electricity generated by renewable energy, P total (t) represents the total power generation, t0 and t1 are the starting point and end point of the optimization time period; α2 represents the weight related to the proportion of new energy consumption; The formula for expressing the user's electricity cost using the time-weighted electricity price curve is: Among them, C cost represents the electricity cost, λ(t) represents the electricity price at time t, L(t) represents the load curve at time t, t0 and t1 are the starting point and end point of the optimization time period; α3 represents the weight related to the user's electricity cost; Combining these three objectives together forms a multi-objective optimization problem, which is expressed as: In the optimization process, these three objectives are combined to form a multi-objective optimization problem. By reducing load fluctuations, the stability and reliability of the power system are improved, and the frequency of large-scale dispatch is reduced. At the same time, priority is given to the consumption of new energy, the proportion of new energy in total power generation is optimized, and the use of renewable energy is promoted. In addition, by optimizing user electricity consumption in different time periods, especially reducing unnecessary electricity consumption during peak electricity price periods, the user's electricity cost is effectively reduced and the overall economic benefits are improved. The formula is: my(S smooth +E renewable +C cost ) Among them, S smooth represents the smoothness measure, E renewable Represents the amount of renewable energy consumed, C cost Indicates the cost of electricity.

7. The multi-period load curve optimization decomposition method based on the power market according to claim 6, characterized in that: The automatic adjustment of the current load decomposition strategy includes load distribution optimization, load peak adjustment and new energy priority consumption; The load distribution optimization includes giving priority to the use of new energy, reducing dependence on conventional fossil fuel power generation, and reducing carbon emissions; The load peak adjustment includes that the system actively adjusts the load peak according to the fluctuation of electricity price and the demand of users, so as to optimize the operation cost of the power grid and users; The priority consumption of new energy includes that the system dynamically adjusts the load distribution of different power generation resources by analyzing weather forecast data and real-time meteorological information.

8. A multi-period load curve optimization decomposition system based on the power market, based on the multi-period load curve optimization decomposition method based on the power market according to any one of claims 1 to 7, characterized in that: The data module collects various data related to the power market and processes the collected data; The scenario building module builds multiple typical scenarios based on the processed data; The optimization module uses a multi-objective optimization algorithm to optimize and decompose the load curve for each typical scenario generated; The adjustment module receives real-time data from the power market in real time, updates the typical scenario model in real time, and automatically adjusts the current load decomposition strategy based on market changes.

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 multi-period load curve optimization decomposition method based on the power market 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 multi-period load curve optimization decomposition method based on the power market according to any one of claims 1 to 7 are implemented.

Images