Optimized scheduling method and device for power system

Abstract

The invention relates to the technical field of clean energy market optimization, and particularly provides an optimal scheduling method and device for a power system, and the method comprises the steps: obtaining a policy factor adjustment vector of the power system through a pre-trained Markov chain prediction model based on a policy factor vector of a current power system; adjusting the policy factor vector of the current power system by using the policy factor adjustment vector of the power system; wherein the policy factor comprises at least one of the following: carbon quota demand, carbon emission reduction and green evidence obligation consumption. According to the technical scheme, the market mechanism can be optimized, development of renewable energy sources can be promoted, the electric power structure can be optimized, and the aim of carbon emission reduction can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of clean energy market optimization, and in particular to an optimization scheduling method and device for an electric power system. Background Art

[0002] As global climate change and environmental issues become increasingly severe, regions around the world are actively promoting energy structure transformation to reduce greenhouse gas emissions and promote sustainable development. Against this backdrop, electricity markets, green certificate markets, and carbon markets have garnered widespread attention as key mechanisms for promoting renewable energy development and carbon emission reduction. These markets, through economic incentives and policy guidance, encourage businesses and consumers to adopt clean energy and reduce fossil fuel use.

[0003] However, achieving coordination between these market prices faces numerous challenges. First, the interactions and impacts between market prices are complex, requiring in-depth analysis and understanding. Second, the impact of new policy changes on market operations requires scientific assessment. Furthermore, market participants require effective decision-making support tools to address market dynamics.

[0004] Among existing technologies, the paper "Optimal Dispatch of Wind-Inclusive Power Systems Considering a Green Certificate-Carbon Trading Mechanism" proposes an optimal dispatch model for power systems that incorporate wind power. This model comprehensively considers the Green Certificate Trading (TGC) mechanism and the Carbon Trading (CT) mechanism. This study first models the Green Certificate Trading mechanism and incorporates a carbon offset mechanism into the traditional carbon trading model. In the economic objective function, the researchers introduce the TGC cost based on the wind power ratio and the CT cost affected by TGC, thereby constructing a Green Certificate-Carbon Trading Cost (TCC) model. The paper "Key Blockchain Technologies for Collaborative Operation of Electricity-Carbon-Green Certificate Markets in New Power Systems" focuses on the collaborative operation of electricity-carbon-green certificate markets and proposes key technologies to achieve this goal using blockchain technology. This study first outlines the architecture for the collaborative operation of electricity-carbon-green certificate markets and analyzes the collaborative operation of these markets from the perspectives of products, entities, and policies. On this basis, the researchers constructed a market operation system based on blockchain technology, including: establishing a unified points certification mechanism to connect the transaction objects between the electricity-carbon-green certificate markets; utilizing the smart contract function of the blockchain to ensure the transparency and reliability of transactions; combining consensus mechanism and points certification, and applying it to collaborative markets to ensure consistency and coordination among participants; by tracking the source and destination of electricity, an electricity-carbon-green certificate traceability model was constructed to ensure the accuracy of electricity data.

[0005] However, while each of these approaches has its own strengths, they also have certain drawbacks. Potential drawbacks when applying optimization scheduling models include the models' potential to rely on simplified assumptions that may not fully capture the complex interactions and dynamics between markets; the high data dependency of optimization results, meaning any bias or incompleteness in input data can lead to inaccurate results; and the models' potential to overlook external factors such as policy changes, technological advancements, and market demand fluctuations, which significantly impact the actual effectiveness of market synergy. While blockchain technology can enhance data transparency and transaction security in research on electricity-green certificate-carbon market synergy, its application in the energy sector is still in its early stages. Lack of technological maturity may lead to unforeseen implementation issues. Furthermore, networks using the Proof of Work (PoW) consensus mechanism may consume significant amounts of energy, which is inconsistent with sustainable development goals. Summary of the Invention

[0006] In order to overcome the above-mentioned defects, the present invention proposes an optimization scheduling method and device for a power system.

[0007] In a first aspect, a method for optimizing and dispatching a power system is provided, the method comprising:

[0008] Based on the current power system policy factor vector, a pre-trained Markov chain prediction model is used to obtain the power system policy factor adjustment vector;

[0009] adjusting the policy factor vector of the current power system using the policy factor adjustment vector of the power system;

[0010] Among them, the policy factors include at least one of the following: carbon quota demand, carbon emission reduction and green certificate obligation absorption.

[0011] Preferably, during the training process of the pre-trained Markov chain prediction model, a pre-built power simulation system is used as a training environment.

[0012] Furthermore, the construction process of the pre-built power simulation system includes:

[0013] Combining the mathematical models of the electricity trading market, the green certificate trading market, and the carbon trading market to construct a comprehensive system dynamics model;

[0014] The comprehensive system dynamics model is simulated to obtain an electric power simulation system.

[0015] Furthermore, the mathematical model of the power trading market is as follows:

[0016]

[0017] RV es =(RV fe +RV ne )(1-τ)

[0018] RV ep =IF THEN ELSE(SMOOTH3I(SV ep ,3,0.38)>0.75,0.75,

[0019] IF THEN ELSE(SMOOTH3I(SV ep ,3,0.38)<0.3,0.3,

[0020] SMOOTH3I(SV ep , 3, 0.38)))

[0021] SV ep =I ep +RV eed

[0022] SV ed =I ed +I ed ×R eg

[0023] In the above formula, RV eed For excess electricity demand, RV ep For electricity prices, RV cp is the carbon price, RV gp is the green certificate price, SV ed For power needs, RV es For power supply, RV fe is the electricity generated by fossil energy, RV ne is the amount of electricity generated by renewable energy, τ is the transmission loss of electricity in the power grid, SV ep is the change of electricity price, SMOOTH3I is the smoothing function, I ep is the initial value of electricity price, I ed is the initial value of power demand, R eg is the electricity growth rate.

[0024] Furthermore, the mathematical model of the green certificate trading market is as follows:

[0025]

[0026] RV gt =IF THEN ELSE(MIN(RV gb , RV gs )<0,0,MIN(RV gb , RVgs ))

[0027]

[0028] RV gp =IF THEN ELSE(SMOOTH3I(SV gp ,1,20)>25,25,

[0029] IF THEN ELSE(SMOOTH3I(SV gp ,1,20)<15,15,

[0030] SMOOTH3I(SV gp , 1, 20)))

[0031] RV ne =SV neic ×C neut

[0032]

[0033] RV nep =(RV ep +RV gp )×RV gs

[0034] SV gp =I gp +RV ged

[0035] SV sgh =I sgh +RV gs -RV gt

[0036] SV dgh =RV gt -RV oc

[0037] In the above formula, RV ged Due to the excess demand for green certificates, RV gb Estimated purchase volume of green certificates, RV gs Estimated sales volume of green certificates, RV ne is the supply of green certificates, RV gt is the green certificate trading volume, RV oc is the mandatory consumption volume, SV ed is the power demand, R q is the quota ratio, RV gp is the green certificate price, SV gp is the price change of green certificate, SMOOTH3I is the smoothing function, SV neicis the installed capacity of new energy, C neut is the average utilization time of new energy equipment, I neic is the initial value of new energy installed capacity, RV nep For the profit margin of new energy installation, RV ep is the electricity price, I gp is the initial value of the green certificate price, SV sgh is the green certificate holdings of the supply-side enterprise, I sgh is the initial value of the green certificate holdings of the supply-side enterprise, SV dgh The green certificate holdings of demand-side enterprises.

[0038] Furthermore, the mathematical model of the carbon trading market is as follows:

[0039]

[0040]

[0041] RV ct =IF THEN ELSE(MIN(RV cb , RV cs )<0,0,MIN(RV cb , RV cs ))

[0042]

[0043] RV cp =IF THEN ELSE(SMOOTH3I(SV cp ,1,40)>300,300,

[0044] IF THEN ELSE(SMOOTH3I(SV cp ,1,40)<10,10,

[0045] SMOOTH3I(SV cp , 1, 40)))

[0046] RV fe =SV feic ×C feut

[0047]

[0048] RV fep =(RV ep +RV cp )×RV cs

[0049] SV GDP =I GDP×(1+R GDP )

[0050] SV cp =I cp +RV ced

[0051] SV sch =I sch +RV cs -RV ct

[0052] SV dch =RV ct -RV cd

[0053] In the above formula, RV ced For excess carbon demand, RV cb Estimated purchase amount of carbon quotas, RV cs Estimated sales volume of carbon quotas, RV cd is the carbon quota demand, RV fe is the electricity generated by fossil energy, C cf is the carbon emission factor, RV ct is the carbon quota trading volume, RV cs is the carbon quota supply, SV GDP Indicates GDP, RV cp is the carbon price, SV cp is the change of carbon price, SMOOTH3I is the smoothing function, SV feic is the installed capacity of fossil energy, C feut is the average utilization time of fossil energy equipment, I feic is the initial value of fossil energy installed capacity, RV fep To increase the profit margin of fossil energy installation, RV ep is the electricity price, I GDP is the initial value of GDP, R GDP is the GDP growth rate, I cp is the initial value of carbon price, SV sch is the carbon quota holdings of the supply-side enterprise, I sch is the initial value of the carbon quota held by the supply-side enterprise, SV dch It refers to the carbon quota holdings of demand-side enterprises.

[0054] Preferably, the state space of the pre-trained Markov chain prediction model consists of the policy factor vector of the power system, the action space consists of the policy factor adjustment vector of the power system, and the reward function consists of the electricity price optimization function, the carbon emission reduction optimization function and the green consumption optimization function.

[0055] Furthermore, the electricity price optimization function is as follows:

[0056] min[|SV ep -ε·I ep |]

[0057] The carbon emission reduction optimization function is as follows:

[0058]

[0059] The green consumption optimization function is as follows:

[0060] max[RV oc +RV gt ]

[0061] In the above formula, SV ep is the change in electricity price, I ep is the initial value of electricity price, ε is the time-varying price deviation weight, RV cd is the carbon quota demand, Em n Direct carbon dioxide emissions from thermal power generation, E n is the total power generation, E trade For the new energy electricity of market-based transactions, RV oc is the mandatory consumption volume, RV gt Green certificate trading volume.

[0062] In a second aspect, a power system optimization and scheduling device is provided, the power system optimization and scheduling device comprising:

[0063] An analysis module is used to obtain a policy factor adjustment vector of the power system based on the current power system policy factor vector using a pre-trained Markov chain prediction model;

[0064] an adjustment module, configured to adjust the policy factor vector of the current power system using the policy factor adjustment vector of the power system;

[0065] Among them, the policy factors include at least one of the following: carbon quota demand, carbon emission reduction and green certificate obligation absorption.

[0066] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0067] The present invention provides a method and apparatus for optimizing power system scheduling, comprising: obtaining a power system policy factor adjustment vector based on the current power system's policy factor vector using a pre-trained Markov chain prediction model; and adjusting the current power system's policy factor vector using the power system policy factor adjustment vector. The policy factors include at least one of the following: carbon quota demand, carbon emission reduction, and green certificate obligation absorption. The technical solution provided by the present invention not only helps optimize market mechanisms but also promotes the development of renewable energy, optimizes the power structure, and achieves carbon emission reduction targets. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 1 is a flow chart showing the main steps of the method for optimizing scheduling of a power system according to an embodiment of the present invention;

[0069] Figure 2 This is an example diagram of electricity, green certificate, and carbon price trends in an embodiment of the present invention;

[0070] Figure 3 This is an example diagram of the transmission relationship between electricity price and carbon price in an embodiment of the present invention;

[0071] Figure 4 This is an example diagram of the transmission relationship between electricity price and green certificate price in an embodiment of the present invention;

[0072] Figure 5 This is an example diagram of simulation of electricity price changes under different scenarios in an embodiment of the present invention;

[0073] Figure 6 This is an example diagram of the simulation of the change of green certificate prices under different scenarios in the embodiment of the present invention;

[0074] Figure 7 This is an example diagram of the simulation of carbon price changes under different scenarios in an embodiment of the present invention. DETAILED DESCRIPTION

[0075] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0076] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0077] Example 1

[0078] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart showing the main steps of the method for optimizing the dispatching of a power system according to an embodiment of the present invention. Figure 1 As shown, the optimization scheduling method of the power system in the embodiment of the present invention mainly includes the following steps:

[0079] Step S101: Based on the current power system policy factor vector, a pre-trained Markov chain prediction model is used to obtain a power system policy factor adjustment vector;

[0080] Step S102: adjusting the policy factor vector of the current power system using the policy factor adjustment vector of the power system;

[0081] Among them, the policy factors include at least one of the following: carbon quota demand, carbon emission reduction and green certificate obligation absorption.

[0082] In this embodiment, during the training process of the pre-trained Markov chain prediction model, a pre-built power simulation system is used as a training environment.

[0083] In one embodiment, the construction process of the pre-built power simulation system includes:

[0084] Combining the mathematical models of the electricity trading market, the green certificate trading market, and the carbon trading market to construct a comprehensive system dynamics model;

[0085] The comprehensive system dynamics model is simulated to obtain an electric power simulation system.

[0086] In this embodiment, the comprehensive system dynamics model includes five types of variable parameters, which are represented as follows.

[0087] State variables: Also known as accumulated variables, they represent the stock in the system, which accumulates over time. The current value of a state variable is equal to its past value plus the change in that value over time.

[0088] Rate variables: These variables directly affect the rate of change of the state variables, reflecting the speed at which the state variables are input or output. Rate variables are usually no different from auxiliary variables.

[0089] Auxiliary variables: Auxiliary variables are calculated from other variables in the system. Their current values are independent of their historical values. Auxiliary variables are used to simplify decision functions and make complex decision processes easier to understand.

[0090] Constants: Constants have values that do not change over time; they represent fixed parameters or conditions in a model.

[0091] Exogenous variables: In system dynamics, these variables exist outside the model and are determined by factors external to the model. These variables are not caused by other variables within the model, but rather by external factors. Exogenous variables are typically deterministic or random variables with specific probability distributions, whose parameters are not elements of the model system. Exogenous variables influence the system but are not themselves affected by it. They can include economic variables, policy variables, and so on.

[0092] The electricity market is a market-based platform for trading electricity, aiming to optimize the allocation and utilization of electricity resources through market mechanisms. According to relevant policies, market participants, including power generation companies, power supply companies, electricity retailers, and end users, meet their respective electricity demand and supply through electricity trading. This process not only ensures energy security and stable supply but also promotes market efficiency and resource optimization.

[0093] Through the electricity market, power generation companies can determine the amount and price of electricity generated based on their own costs and market signals, while users can choose to purchase electricity based on electricity prices and demand. This mechanism not only promotes the efficient allocation of power resources, but also encourages power generation companies to improve power generation efficiency and reduce costs through competition, thereby promoting the healthy development of the entire power market. This market-oriented operation mode not only helps to achieve the energy policy goals set by the government, but also provides flexible trading options and economic incentives for all participants, thereby promoting energy efficiency and sustainable economic development. Through analysis of the electricity market, in one embodiment, the mathematical model of the electricity trading market is as follows:

[0094]

[0095] RV es =(RV fe +RV ne )(1-τ)

[0096] RV ep =IF THEN ELSE(SMOOTH3I(SV ep ,3,0.38)>0.75,0.75,

[0097] IF THEN ELSE(SMOOTH3I(SV ep ,3,0.38)<0.3,0.3,

[0098] SMOOTH3I(SV ep , 3, 0.38)))

[0099] SV ep =I ep +RV eed

[0100] SV ed =I ed +I ed ×R eg

[0101] In the above formula, RV eed For excess electricity demand, RV ep For electricity prices, RV cp is the carbon price, RV gp is the green certificate price, SV ed For power needs, RV es For power supply, RV fe is the electricity generated by fossil energy, RV ne is the amount of electricity generated by renewable energy, τ is the transmission loss of electricity in the power grid, SV ep is the change of electricity price, SMOOTH3I is the smoothing function, I ep is the initial value of electricity price, I ed is the initial value of power demand, R eg is the electricity growth rate.

[0102] The Green Certificate market is a market-based mechanism established to promote the consumption of renewable energy. It aims to promote the adoption and consumption of green electricity through economic incentives. According to relevant policies, responsible entities, including power companies and end users, must fulfill their renewable energy consumption obligations by purchasing Green Certificates. Fulfilling this obligation not only supports the country's energy transition but also reflects environmental responsibility.

[0103] This mechanism not only promotes the consumption of renewable energy but also increases green electricity production capacity through market-based means, thereby promoting the healthy development of the entire renewable energy market. This market-based approach not only helps achieve renewable energy targets set by the government, but also provides flexible trading options and economic incentives for all participants, thereby promoting the goal of sustainable development.

[0104] Through analysis of the green certificate trading market, in one embodiment, the mathematical model of the green certificate trading market is as follows:

[0105]

[0106] RV gt =IF THEN ELSE(MIN(RV gb , RV gs )<0,0,MIN(RV gb , RV gs ))

[0107]

[0108] RV gp =IF THEN ELSE(SMOOTH3I(SV gp ,1,20)>25,25,

[0109] IF THEN ELSE(SMOOTH3I(SV gp ,1,20)<15,15,

[0110] SMOOTH3I(SV gp , 1, 20)))

[0111] RV ne =SV neic ×C neut

[0112]

[0113] RV nep =(RV ep +RV gp )×RV gs

[0114] SV gp =I gp +RV ged

[0115] SV sgh =I sgh +RV gs -RV gt

[0116] SV dgh =RV gt -RV oc

[0117] In the above formula, RV ged Due to the excess demand for green certificates, RV gb Estimated purchase volume of green certificates, RV gs Estimated sales volume of green certificates, RV ne is the supply of green certificates, RV gt is the green certificate trading volume, RV oc is the mandatory consumption volume, SV ed is the power demand, R q is the quota ratio, RV gp is the green certificate price, SV gp is the price change of green certificate, SMOOTH3I is the smoothing function, SV neic is the installed capacity of new energy, C neut is the average utilization time of new energy equipment, I neicis the initial value of new energy installed capacity, RV nep For the profit margin of new energy installation, RV ep is the electricity price, I gp is the initial value of the green certificate price, SV sgh is the green certificate holdings of the supply-side enterprise, I sgh is the initial value of the green certificate holdings of the supply-side enterprise, SV dgh The green certificate holdings of demand-side enterprises.

[0118] In the primary carbon emissions trading market, the government allocates carbon allowances to businesses based on established emission reduction targets. In the fossil fuel power generation sector, higher-emission power generation facilities often need to purchase additional carbon allowances from lower-emission facilities to meet their emissions needs. These lower-emission facilities, thanks to their advanced technology and strong emission reduction capabilities, often still have excess carbon allowances even after achieving their established reduction targets.

[0119] These surplus carbon allowances can be traded on the secondary market, realizing their economic value. For low-carbon emission facilities, selling these excess allowances can generate additional financial benefits; for high-carbon emission facilities, purchasing these allowances is a key means of ensuring compliance with government-mandated emission reduction standards. This mechanism not only promotes effective carbon emissions management but also incentivizes companies to reduce carbon emissions through technological innovation and efficiency improvements, thereby driving the entire industry towards more sustainable development.

[0120] Through analysis of the carbon trading market, in one embodiment, the mathematical model of the carbon trading market is as follows:

[0121]

[0122] RV ct =IF THEN ELSE(MIN(RV cb , RV cs )<0,0,MIN(RV cb , RV cs ))

[0123]

[0124] RV cp =IF THEN ELSE(SMOOTH3I(SV cp ,1,40)>300,300,

[0125] IF THEN ELSE(SMOOTH3I(SV cp ,1,40)<10,10,

[0126] SMOOTH3I(SV cp , 1, 40)))

[0127] RV fe =SV feic ×C feut

[0128]

[0129] RV fep =(RV ep +RV cp )×RV cs

[0130] SV GDP =I GDP ×(1+R GDP )

[0131] SV cp =I cp +RV ced

[0132] SV sch =I sch +RV cs -RV ct

[0133] SV dch =RV ct -RV cd

[0134] In the above formula, RV ced For excess carbon demand, RV cb Estimated purchase amount of carbon quotas, RV cs Estimated sales volume of carbon quotas, RV cd is the carbon quota demand, RV fe is the electricity generated by fossil energy, C cf is the carbon emission factor, RV ct is the carbon quota trading volume, RV cs is the carbon quota supply, SV GDP Indicates GDP, RV cp is the carbon price, SV cp is the change of carbon price, SMOOTH3I is the smoothing function, SV feic is the installed capacity of fossil energy, C feut is the average utilization time of fossil energy equipment, I feic is the initial value of fossil energy installed capacity, RV fep To increase the profit margin of fossil energy installation, RV ep is the electricity price, I GDP is the initial value of GDP, R GDPis the GDP growth rate, I cp is the initial value of carbon price, SV sch is the carbon quota holdings of the supply-side enterprise, I sch is the initial value of the carbon quota held by the supply-side enterprise, SV dch It refers to the carbon quota holdings of demand-side enterprises.

[0135] Based on data from platforms such as the Carbon Emissions Trading Network, the Energy Conservation Industry Network, the Energy Statistics Yearbook, and relevant analysis reports from power grid companies, we can set initial variable values and some constants for the system dynamics models of the three markets. The values of the main variables are shown in Table 1 below.

[0136] Table 1

[0137] variable name Value Initial value of electricity price 0.38 yuan / kWh Initial value of green certificate price 20 yuan / ticket Initial carbon price 40 yuan / t Fossil energy installed capacity <![CDATA[4.2866×10 12 kWh]]> New energy installed capacity <![CDATA[2.255×10 11 kWh]]> Average utilization time of fossil energy equipment 4354h Average utilization time of new energy equipment 1163h GDP <![CDATA[4.4712×10 12 Yuan]]> GDP growth rate 6.9％ Electricity growth rate 7％

[0138] See Figure 2 , Figure 2 This chart shows the trends in carbon prices, green certificate prices, and electricity prices from 2020 to 2040, driven by the coupling of three markets: carbon trading, green certificate trading, and electricity trading. Carbon prices have been rising due to increasing market demand for carbon allowances. However, after around 2030, the rise in carbon prices will slow. With the coordinated development of the electricity, certificate, and carbon markets, higher carbon prices will incentivize companies to increase their carbon emission reduction efforts. Green certificate prices will decline in the short term as carbon emissions gradually decrease, the proportion of fossil energy use decreases, and the proportion of green electricity increases. However, in the long term, as existing green certificates expire and market volume stabilizes, the supply and demand of green certificates will reach equilibrium, and prices will converge with actual market demand. In the long term, green certificate prices will slowly rise and align with international standards. Electricity prices will also show a steady upward trend, primarily driven by the deepening of electricity market reforms, the implementation of coal-fired power capacity pricing strategies, and the accelerated marketization of new energy transactions. As carbon quotas gradually shrink and thermal power generation costs increase, the proportion of thermal power generation decreases, while the proportion of green power generation gradually increases to meet growing national electricity demand and environmental protection requirements. These changes have jointly promoted the sustainable development of the power industry. At the same time, strategic guidance and the improvement of market mechanisms have ensured the steady growth of electricity prices, reflecting the actual cost of power generation and the relationship between market supply and demand.

[0139] This embodiment analyzes the collected simulation data to explore how fluctuations in green certificate prices and carbon prices affect electricity prices, and deeply analyzes how this impact is transmitted through green certificate prices and carbon prices.

[0140] The fitted function images of carbon price and electricity price are as follows: Figure 3As shown in the figure. The relationship between carbon prices and electricity prices can be viewed as approximately exponential. An exponential function is a mathematical model used to simulate the rapid change of a variable as another variable increases or decreases. In this model, the role of the exponential function is to adjust the impact of changes in carbon prices on electricity prices, so that the change in electricity prices does not rise in a straight line, but accelerates as the carbon price increases. Through the function expression and the conduction relationship diagram, it can be observed that as the carbon price rises, the electricity price also increases, and the growth rate gradually accelerates. This shows that although the impact of small changes in carbon prices on electricity prices is not significant at first, as carbon prices continue to rise, their impact on electricity prices will become increasingly obvious.

[0141] The fitting function image of green certificate price and electricity price is as follows: Figure 4 As shown. The transmission relationship between green certificate prices and electricity prices is approximately linear, and the linear function shows that each unit change in green certificate prices has the same effect on electricity prices. As green certificate prices decrease, electricity prices will increase, and the extent of the increase depends on the size of the change in green certificate prices. This reflects the importance of green certificate prices to the electricity market because a reduction in green certificate prices may result in carbon costs not being effectively transmitted to the electricity market, resulting in increased costs for thermal power companies, affecting their enthusiasm for power generation, and potentially driving up electricity prices. The above relationship also shows that electricity prices are negatively correlated with green certificate prices, that is, changes in green certificate prices have a negative impact on electricity prices.

[0142] In one embodiment, this embodiment analyzes important new policies for the coordinated development of the electricity-green certificate-carbon market. The purpose of conducting a scenario analysis of important new policies for the coordinated development of the electricity-green certificate-carbon market is to evaluate the impact of different new policies on the coordinated operation of these three markets. Through this analysis, it is possible to predict the potential impact of policy changes on the behavior of market players and how these changes affect the process of low-carbon transformation of the entire energy system. It helps to identify the most effective policy combination to promote the development of renewable energy, optimize the power structure, and achieve carbon reduction targets. In addition, it can also help decision makers understand the dynamic response of the market under different policy scenarios, so as to formulate more scientific and reasonable policies to support energy transformation and sustainable development.

[0143] Different policy variables are set for different scenarios, including:

[0144] Average carbon emission factor of electricity, residual carbon emission factor and proportion of green electricity consumption in the industry.

[0145] Average electricity carbon emission factor: In the carbon trading market, the average electricity carbon emission factor is a key parameter for determining carbon quota demand and trading prices. It helps market participants understand the cost of carbon emissions and promotes investment and application of low-carbon technologies.

[0146] Residual carbon emission factor: The average carbon emission factor of electricity causes the problem of double calculation of environmental rights and interests when offsetting carbon from green electricity consumption. Using the residual carbon emission factor after removing green electricity to calculate the total carbon emission reduction of green electricity consumption can effectively avoid the problem of repeated calculation of environmental value, achieve a balance between the total calculated value of carbon emissions from electricity consumption and the total emissions on the power generation side, take into account the environmental value of green electricity, more accurately calculate the emission reduction effect of green electricity, and be more conducive to the development of green electricity.

[0147] Industry green electricity consumption ratio: Studying the industry's green electricity consumption ratio will help promote the industry's transition to low-carbon production methods, reduce dependence on fossil fuels, and reduce the overall carbon footprint.

[0148] In this embodiment, the overall multi-scenario basic settings are shown in Table 2 below. The values under each scenario can be subjected to a certain range of sensitivity analysis during simulation analysis.

[0149] Table 2

[0150] Program Objectives Scenario 1 Scenario 2 Scenario 3 Average carbon emission factor of electricity 0.5568 0.5 0.45 Residual carbon emission factor 0.5942 0.55 0.5 Proportion of green electricity consumption by industry 0.3 0.4 0.5

[0151] By analyzing the simulation data under different scenarios, we can get the impact of various new policy factors on the electricity-green certificate-carbon market prices, such as Figures 5 to 7 shown.

[0152] Simulation results show that electricity prices and carbon prices follow similar trends across scenarios, while green certificate prices exhibit significantly different trends in one scenario compared to the others. First, electricity prices are analyzed. Across all three scenarios, electricity prices generally show an upward trend. However, in scenario three, electricity prices increase slightly in the later stages compared to the other two scenarios, though the increase is modest. Lowering the average carbon emission factor and the residual carbon emission factor increases the appeal of low-carbon electricity, potentially incentivizing more clean energy generation and thus impacting the price structure of the electricity market. Increasing the proportion of green electricity consumption in the industry leads to increased demand for green electricity, which could drive up prices within the supply-demand equation, especially given the relatively tight supply of green electricity. With the deepening implementation of low-carbon policies, the transition costs for the power industry are likely to rise further, potentially leading to further increases in electricity prices, particularly in the later stages, where the upward trend becomes steeper. Despite various policy adjustments and market changes, the overall trend in electricity prices remains relatively stable, likely due to the power market's regulatory mechanisms and the ability to balance supply and demand. These diverse factors, acting together, contribute to an upward trend in electricity prices, but with similar magnitudes.

[0153] Next, we analyze the price of Green Certificates. In Scenarios 1 and 2, Green Certificate prices first declined and then rose. However, in Scenario 2, Green Certificate prices were generally higher than in Scenario 1. However, in Scenario 3, the price showed an overall upward trend, with occasional dips, but the fluctuations were relatively small. The reductions in the average and residual carbon emission factors for electricity generation suggest an increase in demand for low-carbon electricity in the power industry, which in turn increases demand for Green Certificates, as Green Certificates serve as environmental certification of renewable energy generation. The increase in the proportion of green electricity consumption in the industry also suggests an increase in demand for green electricity. As the electrolytic aluminum industry is energy-intensive, its increased demand for green electricity could significantly impact the demand side of the Green Certificate market. This increased demand could drive up Green Certificate prices, as Green Certificate prices are influenced by supply and demand. When supply exceeds demand, Green Certificate prices fall; conversely, when supply exceeds demand, Green Certificate prices rise.

[0154] Finally, we analyze carbon prices. Across all three scenarios, carbon prices show an overall upward trend, but Scenario 1 shows higher overall carbon prices than Scenario 2, which in turn is higher than Scenario 3. Currently, the power industry is being encouraged to reduce carbon emissions, which has led to an increase in demand for carbon allowances, and thus, an increase in carbon prices. The power industry is achieving energy conservation and emissions reductions through improved energy efficiency and the adoption of clean energy. This is likely to increase investment in low-carbon technologies, which in turn may increase carbon prices as companies seek to reduce carbon emissions to avoid future carbon costs. The reductions in the average and residual carbon emission factors for electricity, as well as the increase in the proportion of green electricity consumption within the industry, are intended to reduce demand for carbon allowances within the power industry to a certain extent. Therefore, in the scenario analysis, the upward trend in carbon prices in Scenario 3 is smaller than in Scenario 2, which in turn is smaller than in Scenario 1.

[0155] In this embodiment, the state space of the pre-trained Markov chain prediction model is composed of the policy factor vector of the power system, the action space is composed of the policy factor adjustment vector of the power system, and the reward function is composed of the electricity price optimization function, the carbon emission reduction optimization function and the green consumption optimization function.

[0156] Furthermore, the electricity price optimization function is as follows:

[0157] min[|SV ep -ε·I ep |]

[0158] The carbon emission reduction optimization function is as follows:

[0159]

[0160] The green consumption optimization function is as follows:

[0161] max[RV oc +RV gt]

[0162] In the above formula, SV ep is the change in electricity price, I ep is the initial value of electricity price, ε is the time-varying price deviation weight, RV cd is the carbon quota demand, Em n Direct carbon dioxide emissions from thermal power generation, E n is the total power generation, E trade For the new energy electricity of market-based transactions, RV oc is the mandatory consumption volume, RV gt Green certificate trading volume.

[0163] This example combines system dynamics models with reinforcement learning to address the complexities of the price transmission mechanism in the electricity, green certificate, and carbon markets. First, by constructing a comprehensive system dynamics model, it enables in-depth analysis of the interactions and impacts between electricity, green certificate, and carbon market prices, revealing the complex causal chains between these variables. This model improves understanding and forecasting of market price dynamics, providing more accurate decision-making support for market participants. Second, by using Markov decision making and reinforcement learning to identify the optimal policy mix, policymakers can assess market responses to different policy changes, enhancing the adaptability and foresight of new policies. This approach not only helps optimize market mechanisms but also promotes the development of renewable energy, optimizes the power mix, and achieves carbon reduction targets. It also analyzes potential changes in market player behavior and how these changes impact the overall energy system's transition to a low-carbon economy. This provides decision makers with a scientific and rational basis for policymaking.

[0164] Example 2

[0165] Based on the same inventive concept, the present invention further provides an optimized dispatching device for a power system, the optimized dispatching device for a power system comprising:

[0166] An analysis module is used to obtain a policy factor adjustment vector of the power system based on the current power system policy factor vector using a pre-trained Markov chain prediction model;

[0167] an adjustment module, configured to adjust the policy factor vector of the current power system using the policy factor adjustment vector of the power system;

[0168] Among them, the policy factors include at least one of the following: carbon quota demand, carbon emission reduction and green certificate obligation absorption.

[0169] Preferably, during the training process of the pre-trained Markov chain prediction model, a pre-built power simulation system is used as a training environment.

[0170] Furthermore, the construction process of the pre-built power simulation system includes:

[0171] Combining the mathematical models of the electricity trading market, the green certificate trading market, and the carbon trading market to construct a comprehensive system dynamics model;

[0172] The comprehensive system dynamics model is simulated to obtain an electric power simulation system.

[0173] Furthermore, the mathematical model of the power trading market is as follows:

[0174]

[0175] RV es =(RV fe +RV ne )(1-τ)

[0176] RV ep =IF THEN ELSE(SMOOTH3I(SV ep ,3,0.38)>0.75,0.75,

[0177] IF THEN ELSE(SMOOTH3I(SV ep ,3,0.38)<0.3,0.3,

[0178] SMOOTH3I(SV ep , 3, 0.38)))

[0179] SV ep =I ep +RV eed

[0180] SV ed =I ed +I ed ×R eg

[0181] In the above formula, RV eed For excess electricity demand, RV ep For electricity prices, RV cp is the carbon price, RV gp is the green certificate price, SV ed For power needs, RV es For power supply, RV fe is the electricity generated by fossil energy, RV neis the amount of electricity generated by renewable energy, τ is the transmission loss of electricity in the power grid, SV ep is the change of electricity price, SMOOTH3I is the smoothing function, I ep is the initial value of electricity price, I ed is the initial value of power demand, R eg is the electricity growth rate.

[0182] Furthermore, the mathematical model of the green certificate trading market is as follows:

[0183]

[0184] RV gt =IF THEN ELSE(MIN(RV gb , RV gs )<0,0,MIN(RV gb , RV gs ))

[0185]

[0186] RV gp =IF THEN ELSE(SMOOTH3I(SV gp ,1,20)>25,25,

[0187] IF THEN ELSE(SMOOTH3I(SV gp ,1,20)<15,15,

[0188] SMOOTH3I(SV gp , 1, 20)))

[0189] RV ne =SV neic ×C neut

[0190]

[0191] RV nep =(RV ep +RV gp )×RV gs

[0192] SV gp =I gp +RV ged

[0193] SV sgh =I sgh +RV gs -RV gt

[0194] SVdgh =RV gt -RV oc

[0195] In the above formula, RV ged Due to the excess demand for green certificates, RV gb Estimated purchase volume of green certificates, RV gs Estimated sales volume of green certificates, RV ne is the supply of green certificates, RV gt is the green certificate trading volume, RV oc is the mandatory consumption volume, SV ed is the power demand, R q is the quota ratio, RV gp is the green certificate price, SV gp is the price change of green certificate, SMOOTH3I is the smoothing function, SV neic is the installed capacity of new energy, C neut is the average utilization time of new energy equipment, I neic is the initial value of new energy installed capacity, RV nep For the profit margin of new energy installation, RV ep is the electricity price, I gp is the initial value of the green certificate price, SV sgh is the green certificate holdings of the supply-side enterprise, I sgh is the initial value of the green certificate holdings of the supply-side enterprise, SV dgh The green certificate holdings of demand-side enterprises.

[0196] Furthermore, the mathematical model of the carbon trading market is as follows:

[0197]

[0198] RV ct =IF THEN ELSE(MIN(RV cb , RV cs )<0,0,MIN(RV cb , RV cs ))

[0199]

[0200] RV cp =IF THEN ELSE(SMOOTH3I(SV cp ,1,40)>300,300,

[0201] IF THEN ELSE(SMOOTH3I(SV cp ,1,40)<10,10,

[0202] SMOOTH3I(SV cp , 1, 40)))

[0203] RV fe =SV feic ×C feut

[0204]

[0205] RV fep =(RV ep +RV cp )×RV cs

[0206] SV GDP =I GDP ×(1+R GDP )

[0207] SV cp =I cp +RV ced

[0208] SV sch =I sch +RV cs -RV ct

[0209] SV dch =RV ct -RV cd

[0210] In the above formula, RV ced For excess carbon demand, RV cb Estimated purchase amount of carbon quotas, RV cs Estimated sales volume of carbon quotas, RV cd is the carbon quota demand, RV fe is the electricity generated by fossil energy, C cf is the carbon emission factor, RV ct is the carbon quota trading volume, RV cs is the carbon quota supply, SV GDP Indicates GDP, RV cp is the carbon price, SV cp is the change of carbon price, SMOOTH3I is the smoothing function, SV feic is the installed capacity of fossil energy, C feut is the average utilization time of fossil energy equipment, I feic is the initial value of fossil energy installed capacity, RV fep To increase the profit margin of fossil energy installation, RV ep is the electricity price, I GDP is the initial value of GDP, R GDPis the GDP growth rate, I cp is the initial value of carbon price, SV sch is the carbon quota holdings of the supply-side enterprise, I sch is the initial value of the carbon quota held by the supply-side enterprise, SV dch It refers to the carbon quota holdings of demand-side enterprises.

[0211] Preferably, the state space of the pre-trained Markov chain prediction model consists of the policy factor vector of the power system, the action space consists of the policy factor adjustment vector of the power system, and the reward function consists of the electricity price optimization function, the carbon emission reduction optimization function and the green consumption optimization function.

[0212] Furthermore, the electricity price optimization function is as follows:

[0213] min[|SV ep -ε·I ep |]

[0214] The carbon emission reduction optimization function is as follows:

[0215]

[0216] The green consumption optimization function is as follows:

[0217] max[RV oc +RV gt ]

[0218] In the above formula, SV ep is the change in electricity price, I ep is the initial value of electricity price, ε is the time-varying price deviation weight, RV cd is the carbon quota demand, Em n Direct carbon dioxide emissions from thermal power generation, E n is the total power generation, E trade For the new energy electricity of market-based transactions, RV oc is the mandatory consumption volume, RV gt Green certificate trading volume.

[0219] Example 3

[0220] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of the power system optimization scheduling method in the above embodiment.

[0221] Example 4

[0222] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the optimization scheduling method of an electric power system in the above embodiment.

[0223] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0224] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0225] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0226] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0227] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for optimizing the dispatching of a power system, characterized in that: The method comprises: Based on the current power system policy factor vector, a pre-trained Markov chain prediction model is used to obtain the power system policy factor adjustment vector; adjusting the policy factor vector of the current power system using the policy factor adjustment vector of the power system; Among them, the policy factors include at least one of the following: carbon quota demand, carbon emission reduction and green certificate obligation absorption.

2. The method according to claim 1, wherein During the training process of the pre-trained Markov chain prediction model, a pre-built power simulation system is used as a training environment.

3. The method according to claim 2, wherein The construction process of the pre-built power simulation system includes: Combining the mathematical models of the electricity trading market, the green certificate trading market, and the carbon trading market to construct a comprehensive system dynamics model; The comprehensive system dynamics model is simulated to obtain an electric power simulation system.

4. The method according to claim 3, wherein The mathematical model of the electricity trading market is as follows: RV es =(RV fe +RV ne )(1-τ) RV ep =IFTHENELSE(SMOOTH3I(SV ep ,3,0.38)>0.75,0.75, IFTHENELSE(SMOOTH3I(SV ep ,3,0.38)<0.3,0.3, SMOOTH3I(SV ep ,3,0.38))) SV ep =I ep +RV eed SV ed =I ed +I ed ×R eg In the above formula, RV eed For excess electricity demand, RV ep For electricity prices, RV cp is the carbon price, RV gp is the green certificate price, SV ed For power needs, RV es For power supply, RV fe is the electricity generated by fossil energy, RV ne is the amount of electricity generated by renewable energy, τ is the transmission loss of electricity in the power grid, SV ep is the change of electricity price, SMOOTH3I is the smoothing function, I ep is the initial value of electricity price, I ed is the initial value of power demand, R eg is the electricity growth rate.

5. The method according to claim 3, wherein The mathematical model of the green certificate trading market is as follows: RV gt =IFTHENELSE(MIN(RV gb ,RV gs )<0,0,MIN(RV gb ,RV gs )) RV gp =IFTHENELSE(SMOOTH3I(SV gp ,1,20)>25,25, IFTHENELSE(SMOOTH3I(SV gp ,1,20)<15,15, SMOOTH3I(SV gp ,1,20))) RV ne =SV neic ×C neut RV nep =(RV ep +RV gp )×RV gs SV gp =I gp +RV ged SV sgh =I sgh +RV gs -RV gt SV dgh =RV gt -RV oc In the above formula, RV ged Due to the excess demand for green certificates, RV gb Estimated purchase volume of green certificates, RV gs Estimated sales volume of green certificates, RV ne is the supply of green certificates, RV gt is the green certificate trading volume, RV oc is the mandatory consumption volume, SV ed is the power demand, R q is the quota ratio, RV gp is the green certificate price, SV gp is the price change of green certificate, SMOOTH3I is the smoothing function, SV neic is the installed capacity of new energy, C neut is the average utilization time of new energy equipment, I neic is the initial value of new energy installed capacity, RV nep For the profit margin of new energy installation, RV ep is the electricity price, I gp is the initial value of the green certificate price, SV sgh is the green certificate holdings of the supply-side enterprise, I sgh is the initial value of the green certificate holdings of the supply-side enterprise, SV dgh The green certificate holdings of demand-side enterprises.

6. The method according to claim 3, wherein The mathematical model of the carbon trading market is as follows: RV ct =IFTHENELSE(MIN(RV cb ,RV cs )<0,0,MIN(RV cb ,RV cs )) RV cp =IFTHENELSE(SMOOTH3I(SV cp ,1,40)>300,300, IFTHENELSE(SMOOTH3I(SV cp ,1,40)<10,10, SMOOTH3I(SV cp ,1,40))) RV fe =SV feic ×C feut RV fep =(RV ep +RV cp )×RV cs SV GDP =I GDP ×(1+R GDP ) SV cp =I cp +RV ced SV sch =I sch +RV cs -RV ct SV dch =RV ct -RV cd In the above formula, RV ced For excess carbon demand, RV cb Estimated purchase amount of carbon quotas, RV cs Estimated sales volume of carbon quotas, RV cd is the carbon quota demand, RV fe is the electricity generated by fossil energy, C cf is the carbon emission factor, RV ct is the carbon quota trading volume, RV cs is the carbon quota supply, SV GDP Indicates GDP, RV cp is the carbon price, SV cp is the change of carbon price, SMOOTH3I is the smoothing function, SV feic is the installed capacity of fossil energy, C feut is the average utilization time of fossil energy equipment, I feic is the initial value of fossil energy installed capacity, RV fep To increase the profit margin of fossil energy installation, RV ep is the electricity price, I GDP is the initial value of GDP, R GDP is the GDP growth rate, I cp is the initial value of carbon price, SV sch is the carbon quota holdings of the supply-side enterprise, I sch is the initial value of the carbon quota held by the supply-side enterprise, SV dch It refers to the carbon quota holdings of demand-side enterprises.

7. The method according to claim 1, wherein The state space of the pre-trained Markov chain prediction model consists of the policy factor vector of the power system, the action space consists of the policy factor adjustment vector of the power system, and the reward function consists of the electricity price optimization function, the carbon emission reduction optimization function and the green consumption optimization function.

8. The method according to claim 7, wherein The electricity price optimization function is as follows: min[|SV ep -ε·I ep |] The carbon emission reduction optimization function is as follows: The green consumption optimization function is as follows: max[RV oc +RV gt ] In the above formula, SV ep is the change in electricity price, I ep is the initial value of electricity price, ε is the time-varying price deviation weight, RV cd is the carbon quota demand, Em n Direct carbon dioxide emissions from thermal power generation, E n is the total power generation, E trade For the new energy electricity of market-based transactions, RV oc is the mandatory consumption volume, RV gt Green certificate trading volume.

9. A device based on the power system optimization scheduling method according to any one of claims 1 to 8, characterized in that: The device comprises: An analysis module is used to obtain a policy factor adjustment vector of the power system based on the current power system policy factor vector using a pre-trained Markov chain prediction model; an adjustment module, configured to adjust the policy factor vector of the current power system using the policy factor adjustment vector of the power system; Among them, the policy factors include at least one of the following: carbon quota demand, carbon emission reduction and green certificate obligation absorption.

Images