A multi-energy complementary comprehensive energy scheduling optimization method

Abstract

The present application relates to a kind of multi-energy complementary comprehensive energy scheduling optimization method, belong to new energy scheduling technical field.The present application method includes: based on the power generation of each thermal power unit of multi-energy complementary comprehensive energy base, the operating state of each thermal power unit is constructed the day-ahead scheduling cost model of the energy base thermal power unit;Based on wind power output, photovoltaic output, the power generation of each thermal power unit and the outgoing dc power demand of the energy base is constructed the power generation profit model of the energy base;Based on day-ahead scheduling cost model and power generation profit model with the maximum comprehensive income of the energy base as target constructs objective function;Based on various constraint conditions to solve objective function, obtain optimal day-ahead scheduling plan, including wind power output, photovoltaic output, the power generation of each thermal power unit and the operating state of each thermal power unit.The present application method can improve the energy utilization of multi-energy complementary comprehensive energy base, improve the economic benefit of multi-energy complementary comprehensive energy base.

Description

Technical Field

[0001] The present invention belongs to the technical field of new energy dispatching, and particularly relates to a multi-energy complementary integrated energy dispatching optimization method. Background Art

[0002] By preferentially using clean energy resources, giving full play to the regulating performance of thermal power and hydropower, appropriately configuring energy storage facilities, and mobilizing the enthusiasm of flexible response on the demand side, the multi-energy complementary integrated energy base is conducive to giving play to the advantages of areas rich in new energy resources, facilitating the large-scale consumption of clean electricity, optimizing the energy structure, breaking through the constraints of resources and environment. Building a multi-energy complementary integrated energy base is a key measure to realize the transformation and upgrading of the power system. However, the system of the multi-energy complementary integrated energy base is complex and the coordination and optimization are difficult, resulting in problems such as low comprehensive efficiency of the power system, insufficient coordination among links such as the power grid, load, and generation, low utilization rate of various energy sources, and weak complementary and mutual assistance capabilities among various energy sources. Summary of the Invention

[0003] In view of the above analysis, the present invention aims to provide a multi-energy complementary integrated energy dispatching optimization method to improve the utilization rate of various energy sources in the multi-energy complementary integrated energy base and enhance the complementary and mutual assistance capabilities among various energy sources. The method of the present invention specifically includes the following steps:

[0004] Construct a day-ahead dispatching cost model of the thermal power units in the energy base based on the power generation power and operating status of each thermal power unit in the multi-energy complementary integrated energy base; construct a power generation profit model of the energy base based on wind power output, photovoltaic power output, power generation power of each thermal power unit, and the DC power transmission demand of the energy base;

[0005] Construct an objective function with the maximum comprehensive income of the energy base as the goal based on the day-ahead dispatching cost model and the power generation profit model;

[0006] Solve the objective function based on the constraints of the total thermal power output of the power grid on the energy base, the power balance constraint of the energy base, the wind power output constraint, the photovoltaic power output constraint, the output constraint of each thermal power unit, the thermal power unit ramping constraint, and the energy storage capacity constraint, and obtain the optimal day-ahead dispatching plan of the energy base, including wind power output, photovoltaic power output, power generation power of each thermal power unit, and the operating status of each thermal power unit.

[0007] Further, the constraint of the total thermal power output of the energy base includes:

[0008]

[0009] Wherein, represents the power generation power of the i-th thermal power unit at time t; T represents the total number of thermal power units; p net,t represents the net power generation power of the energy base; PDCline,t P represents the external DC power demand at time t; limit This indicates the limit on the amount of electricity that the power grid can sell to the energy base; This represents the minimum output of the i-th thermal power unit.

[0010] Furthermore, the construction of the power generation profitability model for the energy base based on the power generation capacity of each thermal power unit, wind power output, photovoltaic power output, and the external DC power demand of the energy base includes:

[0011] The net on-grid power generation calculation model is determined based on the power generation capacity, wind power output, photovoltaic power output, and the DC power transmission demand of the energy base of each thermal power unit.

[0012] Based on the net on-grid power generation calculation model, the grid electricity sales time-of-use price and the power generation on-grid time-of-use price, the total price calculation model for net on-grid power generation is determined;

[0013] Based on the power generation, wind power output, photovoltaic output, and p of each thermal power unit c A power generation profitability model for the energy base is constructed to calculate the total price of contracted electricity price and net on-grid power generation for the energy base and the power grid.

[0014] Furthermore, the power generation profit model of the energy base is expressed as follows:

[0015]

[0016] Where F1 represents the power generation profit of the energy base; t represents time; N represents the number of time points; p c The contracted electricity price between the energy base and the power grid; P represents the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units; pv,t and P pw,t F represents the wind power output and photovoltaic power output at time t, respectively; net This represents the total price of the net on-grid power generation. The calculation model for the total price of the net on-grid power generation is as follows: p b,t and p s,t These are the time-of-use tariffs for electricity sold to the grid and the time-of-use tariffs for electricity generated and fed into the grid; the calculation model for net on-grid power generation is as follows:

[0017] Furthermore, based on historical data of multiple indicators affecting electricity prices, the time-of-use electricity price for grid sales and the time-of-use electricity price for generation are predicted, including:

[0018] The entropy weight method is used to determine multiple indicators affecting electricity prices, including similar daily electricity prices, the electricity price one day before the forecast date, electricity price volatility, the ratio of available installed capacity to load, load volatility, and forecast load.

[0019] Based on the historical data of the aforementioned multiple indicators and the corresponding time-of-use electricity prices for power grid sales and power generation on the corresponding dates, a training set is constructed to train the LSTM model and obtain the trained LTSTM model.

[0020] Using a trained LTSTM model, based on historical data of the multiple indicators corresponding to the day-ahead scheduling plan, the time-of-use electricity price for grid sales and the time-of-use electricity price for generation are predicted.

[0021] Furthermore, the multiple indicators affecting electricity prices determined based on the entropy weight method include:

[0022] Based on historical electricity price factors, climate and environmental factors, compliance factors, economic factors, market factors, and power grid stability factors, multiple indicators that may affect electricity prices are identified.

[0023] The historical data of each indicator are normalized to obtain the normalized historical data of each indicator;

[0024] The weight of each indicator in each category of factors is calculated based on the normalized historical data of each indicator.

[0025] Multiple indicators affecting electricity prices are determined based on the weight of each indicator among various factors.

[0026] Furthermore, the day-ahead dispatch cost model for thermal power units, constructed based on the power generation capacity and operating status of each thermal power unit in a multi-energy complementary integrated energy base, is expressed as follows:

[0027]

[0028] Where F2 represents the day-ahead scheduling cost; t represents the time; and N represents the number of time points. and These represent coal-fired cost, ramp-up cost, and start-up / shutdown cost, respectively.

[0029]

[0030] Let represent the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units; a, b, and c are the cost coefficients of thermal power units; and γ is the ramp-up cost factor of thermal power units. Let u be the startup cost of the i-th thermal power unit; i,t-1 The operating state of the i-th thermal power unit at time t-1; u i,t This represents the operating status of the i-th thermal power unit at time t.

[0031] Furthermore, when solving the objective function, if The calculation expressions for wind power output and photovoltaic power output are as follows:

[0032]

[0033] Among them, P pv,t and P pw,t These represent the wind power output and photovoltaic power output at time t, respectively.

[0034] Furthermore, the power balance constraint is expressed as:

[0035]

[0036] in, P represents the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units; pv,t and P pw,t Let λ represent the wind power output and photovoltaic power output at time t, respectively; pv and λ pw These represent the transmission rates of wind power and solar power after considering grid losses, respectively; Δe j N represents the output of the j-th energy storage unit at time t; s Indicates the number of energy storage units; P DCline,t This represents the external DC power demand at time t.

[0037] Furthermore, the output constraints of each thermal power unit are expressed as follows:

[0038]

[0039] in, P represents the power generation of the i-th thermal power unit at time t; i,min P i,max λ represents the minimum and maximum output of the i-th thermal power unit at time t, respectively; T This indicates the percentage of power output that the unit can provide to entities other than the power plant.

[0040] The present invention can achieve at least one of the following beneficial effects:

[0041] By considering the minimum day-ahead dispatch cost of thermal power units and the maximum power generation profit of the energy base, this paper solves the optimal day-ahead dispatch plan of the energy base based on the power transmission demand of the multi-energy complementary integrated energy base and the power curtailment constraints of the grid. This plan rationally coordinates the power supply of various energy sources, improves the utilization rate of wind power and photovoltaic power, reduces energy waste caused by wind and solar curtailment, lowers the dispatch and operation costs of thermal power units, enhances the complementary and mutually supportive capabilities of various energy sources, and optimizes the economic benefits of the energy base.

[0042] When constructing the power generation profitability model of the energy base, the time-of-use electricity price of the power grid and the time-of-use electricity price of the power generation are predicted based on historical data of multiple indicators affecting electricity prices, thereby further improving the accuracy of solving the objective function aimed at maximizing the comprehensive benefits of the energy base.

[0043] When predicting the time-of-use electricity price for both grid sales and generation, the entropy weight method was used to determine multiple indicators affecting electricity prices, identifying the most critical indicators influencing changes in electricity prices in energy bases. By selecting historical data from these most critical indicators to predict electricity prices, the problem of significant discrepancies between predicted and actual electricity prices, stemming from a lack of reasonable historical data selection in existing electricity price prediction methods, was resolved.

[0044] Other features and advantages of the invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained from what is particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0045] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0046] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0047] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0048] A specific embodiment of the present invention discloses a multi-energy complementary integrated energy dispatch optimization method, which specifically includes steps S01 to S03.

[0049] Step S01: Construct a day-ahead dispatch cost model for the thermal power units of the energy base based on the power generation capacity and operating status of each thermal power unit in the multi-energy complementary integrated energy base; construct a power generation profit model for the energy base based on wind power output, photovoltaic power output, power generation capacity of each thermal power unit and the external DC power demand of the energy base.

[0050] A multi-energy complementary integrated energy base is a new energy development model that integrates various energy resources and technologies to achieve complementary advantages of different energy forms, improve energy utilization efficiency, reduce costs, and support sustainable regional economic development. In this invention, the energy base includes wind power generation, photovoltaic power generation, and thermal power generation.

[0051] The operating status of a thermal power unit refers to whether the thermal power unit is in operation or stopped.

[0052] Specifically, based on the power generation capacity and operating status of each thermal power unit in the multi-energy complementary integrated energy base, a day-ahead dispatch cost model for the thermal power units of the energy base is constructed, expressed as:

[0053]

[0054] Where F2 represents the day-ahead scheduling cost; t represents the time; and N represents the number of time points. and These represent coal-fired cost, ramp-up cost, and start-up / shutdown cost, respectively.

[0055]

[0056] denoted as t, where represents the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units; a, b, and c are the cost coefficients of the thermal power units, obtained by fitting the analysis of the unit operation data; γ is the ramp-up cost factor of the thermal power units. Let u be the startup cost of the i-th thermal power unit; i,t-1 u represents the operating state value of the i-th thermal power unit at time t-1. i,t Let t be the operating status value of the i-th thermal power unit at time t. The value is 1 when the unit is in the operating state and 0 when it is in the stopped state.

[0057] Specifically, a power generation profitability model for the energy base is constructed based on wind power output, photovoltaic power output, the power generation capacity of each thermal power unit, and the DC power transmission demand of the energy base, including:

[0058] The net on-grid power generation calculation model is determined based on the power generation capacity, wind power output, photovoltaic power output, and the DC power transmission demand of the energy base. The net on-grid power generation calculation model is expressed as follows: Where, p net,t P represents the net on-grid power generation of the energy base; DCline,t This represents the external DC power demand at time t; P represents the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units; pv,t and P pw,t These represent the wind power output and photovoltaic power output at time t, respectively.

[0059] The total price calculation model for net on-grid power generation, based on the net on-grid power generation calculation model, the grid electricity sales time-of-use price, and the power generation on-grid time-of-use price, is expressed as follows: p b,t and p s,tThese are the time-of-use electricity prices for grid sales and generation and grid connection, respectively; F net This represents the total price of the net on-grid power generation;

[0060] Based on the total price calculation model of the power generation capacity of each thermal power unit, wind power output, photovoltaic power output, contract electricity price between the energy base and the grid, and net on-grid power generation capacity, a power generation profitability model for the energy base is constructed, which is expressed as: F1 represents the power generation profit of the energy base; N represents the number of time points, which is 24 in day-ahead scheduling; p c This refers to the contracted electricity price between the energy base and the power grid.

[0061] It should be noted that the time-of-use electricity price for grid sales and the time-of-use electricity price for generation occur during real-time grid transactions. Therefore, when constructing the day-ahead dispatch cost model and the generation profitability model, it is necessary to predict the time-of-use electricity price for grid sales and the time-of-use electricity price for generation.

[0062] Furthermore, based on historical data of multiple indicators affecting electricity prices, the time-of-use electricity price for grid sales and the time-of-use electricity price for generation are predicted, including:

[0063] The entropy weight method is used to determine multiple indicators affecting electricity prices. These indicators include the electricity price on similar days, the electricity price the day before the forecast date, electricity price volatility, the ratio of available installed capacity to load, load volatility, and forecast load. Among these, the similar day refers to the historical day that is closest to the forecast load on the dispatch day.

[0064] Based on the historical data of the aforementioned multiple indicators and the corresponding time-of-use electricity prices for power grid sales and power generation on the corresponding dates, a training set is constructed to train the LSTM model and obtain the trained LTSTM model.

[0065] Using a trained LTSTM model, based on historical data of the multiple indicators corresponding to the day-ahead scheduling plan, the time-of-use electricity price for grid sales and the time-of-use electricity price for generation are predicted.

[0066] Furthermore, the time-of-use electricity price for grid sales and the time-of-use electricity price for generation are expressed as follows:

[0067]

[0068] Among them, on-peak refers to peak electricity consumption periods, off-peak refers to off-peak electricity consumption periods, and mid-peak refers to peak electricity consumption periods.

[0069] Furthermore, the entropy weight method is used to determine several indicators affecting electricity prices, including:

[0070] Based on historical electricity price factors, climate and environmental factors, load factors, economic factors, market factors, and power grid stability factors, multiple indicators that may affect electricity prices are identified.

[0071] The historical data of each indicator are normalized to obtain the normalized historical data of each indicator;

[0072] The weight of each indicator in each category of factors is calculated based on the normalized historical data of each indicator.

[0073] Multiple indicators affecting electricity prices are determined based on the weight of each indicator among various factors.

[0074] Furthermore, historical electricity price factors include the electricity price at time t on similar days (yuan / kWh), the electricity price at time t-1 on similar days (yuan / kWh), the electricity price at time t+1 on similar days (yuan / kWh), and the electricity price the day before the forecast date (yuan / kWh).

[0075] Climate environmental factors include temperature (°C), precipitation (mm), and daily evaporation (mm);

[0076] Load factors include the load-available installed capacity ratio (%), load fluctuation (%), forecast load (kW), and load gap rate (%).

[0077] Economic factors include regional GDP (in RMB 100 million), equipment operation and maintenance costs (in RMB 10,000), user price sensitivity (%), and inflation (%).

[0078] Market factors include renewable energy capacity (MW), renewable energy generation (kWh), energy storage market size and demand (MW), electricity supply and demand (%), user electricity demand (MW), market competition index (%), and electricity price volatility (%).

[0079] Power grid stability factors include line congestion (MW), transmission line inductance (H), power plant equipment failure rate (%), system network constraints (MW / min), and automation system recovery time (min).

[0080] Furthermore, the historical data for each indicator are normalized to obtain normalized historical data for each indicator. For historical data of indicators where larger values ​​are better (e.g., regional GDP) or indicators where smaller values ​​are better (e.g., power plant equipment failure rate), the normalization formulas are as follows:

[0081]

[0082] Where, r ijThis represents the data of the j-th indicator among all indicators in the i-th historical data sample (each historical data sample includes one historical data point from each of the above indicators); r j,min and r j,max These represent the minimum and maximum values ​​of the data corresponding to the j-th indicator, respectively; a ij This represents the normalized historical data for the j-th indicator.

[0083] Furthermore, based on the normalized historical data of each indicator, the weights of each indicator in each category of factors are calculated, including:

[0084] A judgment matrix A is constructed based on normalized historical data. ij ={a ij} m×n , where m is the number of historical data samples and n is the total number of indicators;

[0085] Based on judgment matrix A ij Construct the initial decision matrix B ij ={p ij} m×n ,in

[0086] Based on the initial decision matrix B ij Calculate the entropy value of each indicator to obtain the entropy value of each indicator. Where k = lnm;

[0087] The weights of each indicator are obtained based on their entropy values.

[0088] Furthermore, by selecting historical data over many years, and based on the weights of various indicators among different factors, several indicators affecting electricity prices were determined as follows: similar daily electricity price, electricity price one day before the forecast date, electricity price volatility, load-available installed capacity ratio, load volatility, and forecast load.

[0089] Step S02: Based on the day-ahead scheduling cost model and the power generation profit model, construct an objective function with the goal of maximizing the comprehensive benefits of the energy base.

[0090] Specifically, the objective function is expressed as F = max(F1 - F2).

[0091] Step S03: Based on the constraints of the power grid on the total thermal power output of the energy base, the power balance constraints of the energy base, the wind power output constraints, the photovoltaic output constraints, the output constraints of each thermal power unit, the ramp-up constraints of the thermal power unit, and the energy storage capacity constraints, solve the objective function to obtain the optimal day-ahead scheduling plan of the energy base, including wind power output, photovoltaic output, power generation of each thermal power unit, and the operating status of each thermal power unit.

[0092] Specifically, the total output constraint of thermal power plants is expressed as follows:

[0093]

[0094] in, p represents the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units; net,t P represents the net on-grid power generation of the energy base; DCline,t P represents the external DC power demand at time t; limit This indicates the limit on the amount of electricity that the power grid can sell to the energy base; This represents the minimum output of the i-th thermal power unit.

[0095] Specifically, the power balance constraints of the energy base are expressed as follows:

[0096]

[0097] in, P represents the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units; pv,t and P pw,t Let λ represent the wind power output and photovoltaic power output at time t, respectively; pv and λ pw These represent the transmission rates of wind power and solar power after considering grid losses, respectively; Δe j N represents the output of the j-th energy storage unit at time t; s Indicates the number of energy storage units; P DCline,t This represents the external DC power demand at time t.

[0098] Specifically, the wind power output constraint is expressed as follows: in, This represents the maximum wind power output at time t.

[0099] Specifically, the photovoltaic output constraint is expressed as follows: in, This represents the maximum photovoltaic output at time t.

[0100] Specifically, the output constraints of each thermal power unit are expressed as follows:

[0101]

[0102] in, P represents the power generation of the i-th thermal power unit at time t; i,min P i,max λ represents the minimum and maximum output of the i-th thermal power unit at time t, respectively; T This indicates the percentage of power output that the unit can provide to entities other than the power plant.

[0103] Specifically, the ramping constraint for thermal power units is expressed as follows:

[0104] -R i,down ·Δt≤P i,t+1 -P i,t ≤R i,up ·Δt

[0105] Among them, P i,t+1 P i,t R represents the output of the i-th thermal power unit at time t+1 and time t; i,down R i,up Δt represents the maximum downward and upward ramp rates of the i-th thermal power unit per unit time; Δt represents the time interval.

[0106] Specifically, the energy storage capacity constraint is expressed as: E j,min ≤E j,t ≤E j,max Where E j,min E j,max These are the minimum and maximum capacities of the j-th energy storage unit, respectively.

[0107] Specifically, in step SO3, the objective function is solved using a particle swarm optimization algorithm based on the constraints of total thermal power output, power balance of the energy base, wind power output, photovoltaic power output, output of each thermal power unit, thermal power unit ramping constraints, and energy storage capacity.

[0108] Furthermore, based on the energy base's day-ahead scheduling plan for the first N days, the values ​​of wind power output, photovoltaic power output, power generation of each thermal power unit, operating status of each thermal power unit, and output of each energy storage unit at time t each day represent the initial positions of N particles. All N particles constitute a particle group, and the optimal particle is solved using the objective function as the fitness function.

[0109] Specifically, the position and velocity updates for each particle in a single iteration are as follows:

[0110] x n,i =x i +v n,i ;

[0111] v n,i =wv i +c1r1(p b,i -x i )+c2r2(g b,i -x i );

[0112] Among them, v i x i v represents the velocity and position of the i-th particle, respectively; n,i x n,iLet p represent the velocity and position of the i-th particle after a single iteration update; b,i g b,i , respectively, represent the individual best particle and the global best particle for the i-th particle to date; w is the inertia coefficient; c1 and c2 are learning factors; r1 and r2 are uniform random numbers in the range [0,1], which increases the randomness of particle flight.

[0113] Furthermore, when the maximum number of iterations is reached, the position of the globally optimal particle corresponds to the optimal solution of the objective function, i.e., the optimal day-ahead scheduling plan of the energy base, including wind power output, photovoltaic power output, power generation of each thermal power unit, and the operating status of each thermal power unit.

[0114] This embodiment discloses a multi-energy complementary integrated energy dispatch optimization method. By considering the minimum day-ahead dispatch cost of thermal power units and the maximum power generation profit of the energy base, the optimal day-ahead dispatch plan of the energy base is solved based on the power transmission demand of the multi-energy complementary integrated energy base and the power curtailment constraints of the grid. This method rationally coordinates the power supply of various energy sources, improves the utilization rate of wind power and photovoltaic power, reduces energy waste caused by wind and solar curtailment, reduces the dispatch and operation costs of thermal power units, enhances the complementary and mutual support capabilities of various energy sources, and optimizes the economic benefits of the energy base.

[0115] When constructing a power generation profitability model for an energy base, the time-of-use (TOU) electricity price for grid sales and generation is predicted based on historical data of multiple indicators affecting electricity prices. This further improves the accuracy of solving the objective function aimed at maximizing the overall revenue of the energy base. In predicting the TOU electricity price for grid sales and generation, the entropy weight method is used to determine multiple indicators affecting electricity prices, identifying the most critical indicators influencing electricity price changes in the energy base. By selecting historical data of these most critical indicators for price prediction, the problem of significant deviations between predicted and actual electricity prices caused by a lack of reasonable historical data selection in existing electricity price prediction methods is solved.

[0116] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A multi-energy complementary integrated energy dispatch optimization method, characterized in that, Includes the following steps: Based on the power generation capacity and operating status of each thermal power unit in the multi-energy complementary integrated energy base, a day-ahead dispatch cost model for the thermal power units of the energy base is constructed; based on wind power output, photovoltaic power output, power generation capacity of each thermal power unit, and the external DC power demand of the energy base, a power generation profit model for the energy base is constructed. Based on the day-ahead scheduling cost model and the power generation profitability model, an objective function is constructed with the goal of maximizing the comprehensive benefits of the energy base. Based on the constraints of the power grid on the total thermal power output of the energy base, the power balance constraints of the energy base, the wind power output constraints, the photovoltaic output constraints, the output constraints of each thermal power unit, the ramp-up constraints of the thermal power unit, and the energy storage capacity constraints, the objective function is solved to obtain the optimal day-ahead scheduling plan of the energy base, including wind power output, photovoltaic output, power generation of each thermal power unit, and the operating status of each thermal power unit; The total thermal power output constraints of the energy base include: ； in, Let represent the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units. This indicates the net on-grid power generation capacity of the energy base; This represents the external DC power demand at time t; This indicates the limit on the amount of electricity that the power grid can sell to the energy base; This represents the minimum output of the i-th thermal power unit.

2. The multi-energy complementary integrated energy dispatch optimization method according to claim 1, characterized in that, The power generation profitability model for the energy base, constructed based on the power generation capacity of each thermal power unit, wind power output, photovoltaic power output, and the external DC power demand of the energy base, includes: A calculation model for net on-grid power generation is determined based on the power generation capacity, wind power output, photovoltaic power output, and the DC power demand of the energy base for each thermal power unit. Based on the net on-grid power generation calculation model, the grid electricity sales time-of-use price and the power generation on-grid time-of-use price, the total price calculation model for net on-grid power generation is determined; A power generation profitability model for the energy base is constructed based on the total price calculation model of the power generation capacity of each thermal power unit, wind power output, photovoltaic power output, contract electricity price between the energy base and the power grid, and net on-grid power generation capacity.

3. The multi-energy complementary integrated energy dispatch optimization method according to claim 2, characterized in that, The power generation profitability model of the energy base is expressed as follows: ； in, This indicates the profitability of power generation at the energy base; t represents time; N represents the number of time points; The contracted electricity price between the energy base and the power grid; Let represent the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units. and These represent the photovoltaic power output and wind power output at time t, respectively. This represents the total price of the net on-grid power generation. The calculation model for the total price of the net on-grid power generation is as follows: ; and These are the time-of-use tariffs for electricity sold to the grid and the time-of-use tariffs for electricity generated and fed into the grid; the calculation model for net on-grid power generation is as follows: .

4. The multi-energy complementary integrated energy dispatch optimization method according to claim 3, characterized in that, Based on historical data of multiple indicators affecting electricity prices, predict the time-of-use electricity price for grid sales and the time-of-use electricity price for generation, including: The entropy weight method is used to determine multiple indicators affecting electricity prices, including similar daily electricity prices, the electricity price one day before the forecast date, electricity price volatility, the ratio of available installed capacity to load, load volatility, and forecast load. Based on the historical data of the aforementioned multiple indicators and the corresponding time-of-use electricity prices for power grid sales and power generation on the corresponding dates, a training set is constructed to train the LSTM model and obtain the trained LTSTM model. Using a trained LTSTM model, based on historical data of the multiple indicators corresponding to the day-ahead scheduling plan, the time-of-use electricity price for grid sales and the time-of-use electricity price for generation are predicted.

5. The multi-energy complementary integrated energy dispatch optimization method according to claim 4, characterized in that, The multiple indicators affecting electricity prices determined based on the entropy weight method include: Based on historical electricity price factors, climate and environmental factors, load factors, economic factors, market factors, and power grid stability factors, multiple indicators that may affect electricity prices are identified. The historical data of each indicator are normalized to obtain the normalized historical data of each indicator; The weight of each indicator in each category of factors is calculated based on the normalized historical data of each indicator. Multiple indicators affecting electricity prices are determined based on the weight of each indicator among various factors.

6. The multi-energy complementary integrated energy dispatch optimization method according to any one of claims 2-5, characterized in that, The day-ahead dispatch cost model for thermal power units, constructed based on the power generation capacity and operating status of each thermal power unit in a multi-energy complementary integrated energy base, is expressed as follows: ； in, Represents the day-ahead scheduling cost; t represents time; N represents the number of time points; , and These represent coal-fired cost, ramp-up cost, and start-up / shutdown cost, respectively. ； ； ； Let represent the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units; a, b, and c are the cost coefficients of the thermal power units. This is the cost factor for the ramp-up of thermal power units; Let i be the startup cost of the i-th thermal power unit; The operating state of the i-th thermal power unit at time t-1; This represents the operating status of the i-th thermal power unit at time t.

7. The multi-energy complementary integrated energy dispatch optimization method according to claim 6, characterized in that, When solving the objective function, if The calculation expressions for wind power output and photovoltaic power output are as follows: ； ； in, and Let t represent the photovoltaic power output and wind power output at time t, respectively.

8. The multi-energy complementary integrated energy dispatch optimization method according to any one of claims 1-5 and 7, characterized in that, The power balance constraint is expressed as: ； in, Let represent the power generation of the i-th thermal power unit at time t; T represents the total number of thermal power units. and These represent the photovoltaic power output and wind power output at time t, respectively. and These represent the transmission rates of photovoltaic and wind power after considering grid losses, respectively. This represents the output of the j-th energy storage unit at time t; Indicates the number of energy storage units; This represents the external DC power demand at time t.

9. The multi-energy complementary integrated energy dispatch optimization method according to claim 8, characterized in that, The output constraints of each thermal power unit are expressed as follows: ； in, This represents the power generation of the i-th thermal power unit at time t; , These are the minimum and maximum outputs of the i-th thermal power unit at time t, respectively; This indicates the percentage of power output that the unit can provide to entities other than the power plant.

Images