Renewable energy scheduling method and device based on risk perception, terminal and medium

Abstract

This invention discloses a renewable energy dispatching method, device, terminal, and medium based on risk perception. The method predicts photovoltaic (PV) power generation using confidence level, environmental data, and a PV power generation prediction model; constructs a two-layer optimization model to coordinate aggregator costs and building user costs during demand response; and obtains building flexible participation capacity and demand response incentive price by solving the two-layer optimization model. Based on confidence level, PV power generation, building flexible participation capacity, and demand response incentive price, it constructs an aggregator day-ahead bidding profit optimization model and supply and demand constraints, respectively. Based on the aggregator day-ahead bidding profit optimization model and supply and demand constraints, it optimizes the energy storage system's charging and discharging strategy and energy trading strategy. This solves the problem of existing technologies failing to consider the uncertainty of power generation, user participation costs in demand response, and willingness to respond, making it difficult to effectively balance the risks of power shortages and trading benefits, and achieving power dispatch optimization under uncertain conditions.

Description

Technical Field

[0001] This invention relates to the field of energy dispatching, and more particularly to a method, apparatus, terminal, and medium for dispatching renewable energy based on risk perception. Background Technology

[0002] With the advancement of global energy transition and carbon neutrality goals, the proportion of renewable energy in the power system is continuously increasing. However, the intermittency and uncertainty of renewable energy generation pose significant challenges to the safe and stable operation of the power grid. Against this backdrop, resource aggregators are gradually becoming important players in the electricity market, integrating distributed energy resources (such as photovoltaic power generation, energy storage, and flexible loads) to achieve efficient utilization of flexible resources.

[0003] Currently, most existing dispatching methods are based on deterministic predictions of renewable energy. While this approach is simple and intuitive, it neglects the uncertainty of power generation, which can easily lead to deviations in dispatching results from reality. Furthermore, existing building energy demand response mechanisms are all flexible dispatching models based on market electricity prices or predetermined incentives, failing to consider the costs of building users participating in demand response and their willingness to respond under different incentive conditions, making it difficult to fully tap into the energy flexibility of demand-side users. When formulating energy storage system charging and discharging strategies and energy trading strategies based on the above-mentioned methods, it is difficult to effectively balance the risks of power shortages with trading benefits, and to achieve power dispatching optimization under uncertain conditions.

[0004] Therefore, existing technologies still need improvement and development. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a renewable energy dispatching method, device, terminal and medium based on risk perception, in order to address the above-mentioned deficiencies of the prior art. The aim is to solve the problem that the prior art does not consider the uncertainty of power generation, the cost of user participation in demand response and the willingness to respond, and it is difficult to effectively balance the risk of power shortage and the benefits of trading, so as to achieve power dispatching optimization under uncertain conditions.

[0006] The technical solution adopted by this invention to solve the problem is as follows:

[0007] In a first aspect, embodiments of the present invention provide a renewable energy dispatching method based on risk perception, wherein the method includes:

[0008] Acquire confidence level, environmental data, and photovoltaic power generation prediction model; determine photovoltaic power generation based on the confidence level, environmental data, and photovoltaic power generation prediction model.

[0009] A two-layer optimization model is constructed to optimize the aggregator cost and the building user cost during the user demand response period;

[0010] Solve the two-layer optimization model to determine the building's flexible participation capacity and demand response incentive price;

[0011] A day-ahead bid profit optimization model for aggregators is constructed based on the building flexible participation capacity, the demand response incentive price, and the energy trading strategy.

[0012] Supply and demand constraints are constructed based on the confidence level, the photovoltaic power generation capacity, the building flexible participation capacity, the energy trading strategy, and the energy storage system charging and discharging strategy.

[0013] Based on the supply and demand constraints, the day-ahead bid profit optimization model of the aggregator is solved to optimize the energy trading strategy and the charging and discharging strategy of the energy storage system.

[0014] In one implementation method, the photovoltaic power generation prediction model includes:

[0015] Obtain historical photovoltaic power generation data;

[0016] The photovoltaic power generation prediction model is pre-trained using the historical photovoltaic power generation data, wherein the photovoltaic power generation prediction model is a natural gradient boosting algorithm.

[0017] In one implementation method, determining the photovoltaic power generation based on the confidence level, the environmental data, and the photovoltaic power generation prediction model includes:

[0018] The probability distribution of each photovoltaic power generation is determined based on the environmental data and the photovoltaic power generation prediction model.

[0019] Construct a cumulative distribution function based on the probability distribution of each photovoltaic power generation;

[0020] The photovoltaic power generation is determined when the value of the cumulative distribution function is greater than or equal to the confidence level.

[0021] In one implementation method, the method for constructing the lower-level optimization model of the two-level optimization model includes:

[0022] Obtain the costs of thermal environmental discomfort, light environmental discomfort, and plug-in load unmet needs at each moment during the demand response period;

[0023] The building user cost function is determined based on the thermal environmental discomfort cost, the light environmental discomfort cost, the plug-in load non-satisfaction cost, the building flexible participation capacity, and the demand response incentive price at each time point.

[0024] The lower-level optimization model is determined based on the building user cost function and with the goal of minimizing building user costs.

[0025] In one implementation, the optimization of the upper-level optimization model of the two-level optimization model depends on the optimal solution of the lower-level optimization model, and the method for constructing the lower-level optimization model includes:

[0026] Obtain the wholesale and retail electricity prices at each point in time during the demand response period;

[0027] The aggregator cost function is determined based on the wholesale electricity price, retail electricity price, building flexible participation capacity, and demand response incentive price at each time point;

[0028] The upper-level optimization model is determined based on the aggregator cost function and with the goal of minimizing the aggregator cost.

[0029] In one implementation method, an aggregator day-ahead bid profit optimization model is constructed based on the building's flexible participation capacity, the demand response incentive price, and the energy trading strategy, including:

[0030] The aggregator's day-ahead bid profit function is determined based on the wholesale electricity price, the retail electricity price, the building flexible participation capacity, the demand response incentive price, and the energy trading strategy.

[0031] Based on the aggregator's day-ahead bid profit function, and with the objective of maximizing the aggregator's day-ahead bid profit, the aggregator's day-ahead bid profit optimization model is determined.

[0032] In one implementation method, supply and demand constraints are constructed based on the confidence level, the photovoltaic power generation capacity, the building flexible participation capacity, the energy trading strategy, and the energy storage system charging and discharging strategy, including:

[0033] The total supply is determined based on the photovoltaic power generation capacity and the energy trading strategy.

[0034] Obtain a building load baseline value, and determine the net demand based on the building load baseline value, the building flexible participation capacity, and the energy storage system charging and discharging strategy;

[0035] The probability that the total supply is greater than the net demand is greater than or equal to the confidence level is used as the supply and demand constraint.

[0036] Secondly, embodiments of the present invention also provide a risk-aware renewable energy dispatching device, wherein the risk-aware renewable energy dispatching device includes:

[0037] A photovoltaic power generation prediction module is used to acquire confidence level, environmental data, and a photovoltaic power generation prediction model, and to determine the photovoltaic power generation based on the confidence level, the environmental data, and the photovoltaic power generation prediction model.

[0038] A two-layer optimization model construction module is used to construct a two-layer optimization model, which is used to optimize the aggregator cost and the building user cost during the user demand response period;

[0039] The two-layer optimization model solving module solves the two-layer optimization model to determine the building's flexible participation capacity and demand response incentive price.

[0040] The module for constructing a day-ahead bid profit optimization model for aggregators is used to construct a day-ahead bid profit optimization model for aggregators based on the building flexible participation capacity, the demand response incentive price, and the energy trading strategy.

[0041] The supply and demand constraint construction module is used to construct supply and demand constraints based on the confidence level, the photovoltaic power generation capacity, the building flexible participation capacity, the energy trading strategy, and the energy storage system charging and discharging strategy.

[0042] The strategy determination module is used to solve the day-ahead bid profit optimization model of the aggregator based on the supply and demand constraints, and to optimize the energy trading strategy and the energy storage system charging and discharging strategy.

[0043] Thirdly, embodiments of the present invention also provide a terminal, the terminal including a memory and one or more processors; the memory stores one or more programs; the programs include instructions for executing the risk-aware renewable energy dispatching method as described above; the processor is used to execute the programs.

[0044] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a plurality of instructions, wherein the instructions are adapted to be loaded and executed by a processor to implement any of the risk-aware renewable energy scheduling methods described above.

[0045] The beneficial effects of this invention are as follows: This invention predicts photovoltaic power generation using confidence level and a photovoltaic power generation prediction model; it constructs a two-layer optimization model to coordinate aggregator costs and building user costs during demand response, and obtains building flexible participation capacity and demand response incentive price by solving the two-layer optimization model; it constructs an aggregator day-ahead bidding profit optimization model and supply and demand constraints based on confidence level, photovoltaic power generation, building flexible participation capacity, and demand response incentive price; and it optimizes the energy storage system's charging and discharging strategy and energy trading strategy based on the aggregator day-ahead bidding profit optimization model and supply and demand constraints. This effectively solves the problem that existing technologies do not consider the uncertainty of power generation, user participation costs in demand response, and willingness to respond, making it difficult to effectively balance the risks of power shortages and trading benefits, and achieving power dispatch optimization under uncertain conditions. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a flowchart illustrating the risk-aware renewable energy dispatching method provided in an embodiment of the present invention.

[0048] Figure 2 This is a schematic diagram illustrating a specific implementation of the risk-aware renewable energy dispatching method provided in this embodiment of the invention.

[0049] Figure 3 This is a schematic diagram of the photovoltaic power generation prediction results provided in an embodiment of the present invention.

[0050] Figure 4 This is a graph showing the aggregator scheduling results and actual supply situation at confidence levels of 65% and 95% provided in the embodiments of the present invention.

[0051] Figure 5 This is a schematic diagram of the internal modules of the renewable energy dispatching device based on risk perception provided in an embodiment of the present invention.

[0052] Figure 6 This is a schematic diagram of the terminal provided in the embodiment of the present invention. Detailed Implementation

[0053] This invention discloses a method, apparatus, terminal, and medium for renewable energy dispatch based on risk perception. To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention.

[0054] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0055] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0056] Most existing dispatching methods are based on deterministic predictions of renewable energy. While simple and intuitive, these methods neglect the uncertainties of power generation, easily leading to deviations in dispatching results from reality. Furthermore, existing building energy demand response mechanisms are flexible dispatching models based on market prices or predetermined incentives, failing to consider the costs of building users participating in demand response and their willingness to respond under different incentive conditions, making it difficult to fully tap into the energy flexibility of demand-side users. When formulating energy storage system charging and discharging strategies and energy trading strategies based on these existing methods, it is difficult to effectively balance the risks of power shortages with trading benefits, and to achieve optimized power dispatching under uncertain conditions.

[0057] Most existing dispatching methods are based on deterministic predictions of renewable energy. While simple and intuitive, these methods neglect the uncertainties of power generation, easily leading to deviations in dispatching results from reality. Furthermore, existing building energy demand response mechanisms are flexible dispatching models based on market prices or predetermined incentives, failing to consider the costs of building users participating in demand response and their willingness to respond under different incentive conditions, making it difficult to fully tap into the energy flexibility of demand-side users. When formulating energy storage system charging and discharging strategies and energy trading strategies based on these existing methods, it is difficult to effectively balance the risks of power shortages with trading benefits, and to achieve optimized power dispatching under uncertain conditions.

[0058] To address the aforementioned shortcomings of existing technologies, this invention provides a risk-aware renewable energy dispatching method. This method predicts photovoltaic (PV) power generation using confidence levels, environmental data, and a PV power generation prediction model; constructs a two-layer optimization model to coordinate aggregator costs and building user costs during demand response; and obtains building flexible participation capacity and demand response incentive price by solving the two-layer optimization model. Based on confidence levels, PV power generation, building flexible participation capacity, and demand response incentive price, it constructs an aggregator day-ahead bidding profit optimization model and supply and demand constraints, respectively. Based on the aggregator day-ahead bidding profit optimization model and supply and demand constraints, it optimizes the energy storage system's charging and discharging strategy and energy trading strategy. This effectively solves the problem that existing technologies do not consider the uncertainty of power generation, user participation costs in demand response, and willingness to respond, making it difficult to effectively balance the risks of power shortages and trading benefits, thus achieving power dispatching optimization under uncertain conditions.

[0059] Exemplary method:

[0060] like Figure 1 As shown, the method includes:

[0061] Step S100: Obtain confidence level, environmental data, and photovoltaic power generation prediction model; determine photovoltaic power generation based on the confidence level, environmental data, and photovoltaic power generation prediction model.

[0062] In simple terms, the confidence level is a preset confidence level. Environmental data refers to the environmental data for the prediction day, which can be obtained through weather forecasts. This environmental data includes the temperature at various times or time periods during the prediction day, whether the sun is above the horizon (a binary variable characteristic), and the minimum and maximum radiation intensities for the corresponding hours. The photovoltaic power generation prediction model predicts the probability distribution of photovoltaic power generation for the prediction day based on the environmental data. Based on this probability distribution, the prediction interval for photovoltaic power generation at different confidence levels can be calculated. Therefore, the predicted photovoltaic power generation can be obtained based on the preset confidence level and the probability distribution of photovoltaic power generation.

[0063] In one implementation, the photovoltaic power generation prediction model includes:

[0064] Obtain historical photovoltaic power generation data;

[0065] The photovoltaic power generation prediction model is pre-trained using the historical photovoltaic power generation data, wherein the photovoltaic power generation prediction model is a natural gradient boosting algorithm.

[0066] Specifically, historical photovoltaic (PV) power generation data includes historical environmental data and the corresponding historical PV power output. After acquiring the historical PV power generation data, it undergoes preprocessing to identify outliers and improve data quality. The Natural Gradient Boosting (NGBoost) algorithm is a machine learning algorithm that does not require prior knowledge of any uncertain variables. It can output not only the predicted mean but also a distribution to capture the uncertainty of the prediction, denoted as P. θ (y|x), where "y" represents the target variable, "x" represents the input feature, and θ represents the probability distribution parameter vector. The natural gradient boosting algorithm includes a regression tree as a base learner (effectively capturing nonlinear relationships and exhibiting strong robustness in handling outliers), a probability distribution (normal distribution, with parameter vectors including mean and standard deviation), and a scoring rule (logarithmic scoring).

[0067] like Figure 2 As shown, this embodiment uses the natural gradient boosting algorithm as the photovoltaic power generation prediction model. By aggregating the outputs of multiple base learners and initial parameters, the probability distribution parameters are continuously optimized to obtain the probability distribution for photovoltaic power prediction. Historical photovoltaic power generation data is used as training data to pre-train the photovoltaic power generation prediction model. Then, the pre-trained photovoltaic power generation prediction model is used to predict the probability distribution corresponding to photovoltaic power generation based on the environmental data of the prediction day.

[0068] This embodiment presents a photovoltaic power generation prediction model based on the natural gradient boosting algorithm. It eliminates the need for pre-assuming probability distributions of uncertain variables and effectively extracts uncertainty information from historical data, thus improving the accuracy of photovoltaic power prediction. By providing prediction intervals and probability density functions, aggregators can fully consider uncertainty and make more risk-aware decisions during scheduling.

[0069] In one implementation, determining the photovoltaic power generation based on the confidence level, the environmental data, and the photovoltaic power generation prediction model includes:

[0070] The probability distribution of each photovoltaic power generation is determined based on the environmental data and the photovoltaic power generation prediction model.

[0071] Construct a cumulative distribution function based on the probability distribution of each photovoltaic power generation;

[0072] The photovoltaic power generation is determined when the value of the cumulative distribution function is greater than or equal to the confidence level.

[0073] Specifically, the photovoltaic power generation prediction model predicts the probability distribution of photovoltaic power generation on the prediction day based on environmental data for that day. According to the principle of the cumulative distribution function, the cumulative distribution function value F(P) at time t can be obtained. PV,t )for The confidence level corresponds to the predicted photovoltaic power generation P PV,t ,Right now This can be expressed as the following formula:

[0074]

[0075] A specific example of predicting photovoltaic power generation based on a photovoltaic power generation prediction model is shown in the figure below. Figure 3 As shown, where Figure 3 The mean of the forecast is the mean of the photovoltaic power generation predicted by the photovoltaic power generation prediction model.

[0076] Step S200: Construct a two-layer optimization model, which is used to optimize the aggregator cost and the building user cost during the user demand response period.

[0077] Step S300: Solve the two-layer optimization model to determine the building's flexible participation capacity and demand response incentive price;

[0078] Specifically, the demand response incentive price is the economic compensation price offered by aggregators to incentivize building users (including industrial, commercial, and residential users) to change their electricity consumption behavior and participate in demand response projects. Building flexible participation capacity refers to the maximum capacity of a building to flexibly adjust its electrical load during power system operation. Building flexible participation capacity can effectively respond to the grid's demand response signals. During peak grid load periods, by adjusting the building's electrical equipment and distributed energy resources, the building's electricity consumption from the grid is reduced, alleviating grid supply pressure. In this embodiment, building flexible participation capacity includes the total load reduction of air conditioning systems, lighting systems, and plug-in devices.

[0079] During demand response, aggregators offer demand response incentive prices to building users, who then adjust their electricity consumption to regulate building flexible participation capacity. To protect the interests of both aggregators and building users, this embodiment constructs a two-level optimization model with the goal of minimizing both aggregator and building user costs. The upper-level optimization model minimizes aggregator costs, while the lower-level optimization model minimizes building user costs. The demand response incentive price and building flexible participation capacity are obtained by solving the two-level optimization model.

[0080] In one implementation, the method for constructing the lower-level optimization model of the two-level optimization model includes:

[0081] Obtain the costs of thermal environmental discomfort, light environmental discomfort, and plug-in load unmet needs at each moment during the demand response period;

[0082] The building user cost function is determined based on the thermal environmental discomfort cost, the light environmental discomfort cost, the plug-in load non-satisfaction cost, the building flexible participation capacity, and the demand response incentive price at each time point.

[0083] The lower-level optimization model is determined based on the building user cost function and with the goal of minimizing building user costs.

[0084] Specifically, relevant parameters of the building cluster are collected, including simplified building thermal models and air conditioning system parameters, energy storage system parameters (such as rated capacity, charge and discharge efficiency, power and upper and lower limits of state of charge, etc.), and user-defined discomfort and underload cost coefficients (α, β, γ).

[0085] The cost of thermal discomfort, lighting discomfort, and electrical load mismatch in building clusters is calculated based on relevant parameters from mobile phones. Among these, the cost of thermal discomfort is... △PMV represents the change in the predicted average voting index for thermal sensation, which is related to changes in indoor temperature. The indoor temperature change corresponding to the reduction in air conditioning load can be calculated using the building equivalent thermal model and the air conditioning system model; light environment discomfort cost c vis,t =β(△L) t / L b ) 2 ,△L t For changes in indoor illuminance, L b To establish an indoor illuminance benchmark without considering demand response, calculations can be made using the power reduction of the lighting system and the luminous efficacy of the luminaires; the cost of underutilized plug-in load is c. ld,t =γ(△P) ce,t / P ce,b ) 2 , △P ce,t P is the load reduction of the socket. ce,b This serves as the baseline for socket load. α, β, and γ are user-defined coefficients under the interactive mechanism, reflecting the user's willingness to respond.

[0086] Based on the costs of thermal environmental discomfort, lighting environmental discomfort, electrical load mismatch, and building flexibility participation capacity ΔP DR,t Demand response incentive price π DR,t Construct the lower-level optimization model, represented as:

[0087] J2 = min.(c th，t +c vis，t +c ld，t -ΔP DR，t) , π DR，t t∈T DR ,

[0088] Among them, T DR For the demand response period, by transforming the lower-level optimization model into Karush-Kuhn-Tucker (KKT) optimality conditions, and simultaneously solving the upper-level optimization model, the optimal demand response incentive price π is obtained. DR,t With the optimal building flexibility participation capacity ΔP DR,t .

[0089] In one implementation, the optimization of the upper-level optimization model of the two-level optimization model depends on the optimal solution of the lower-level optimization model, and the method for constructing the lower-level optimization model includes:

[0090] Obtain the wholesale and retail electricity prices at each point in time during the demand response period;

[0091] The aggregator cost function is determined based on the wholesale electricity price, retail electricity price, building flexible participation capacity, and demand response incentive price at each time point;

[0092] The upper-level optimization model is determined based on the aggregator cost function and with the goal of minimizing the aggregator cost.

[0093] Specifically, day-ahead wholesale and retail electricity prices are obtained from the electricity market. π WM,t π RM,t These are the wholesale and retail electricity prices at time t, respectively. Based on the wholesale and retail electricity prices and the building's flexible participation capacity ΔP... DR,t And demand response incentive price π DR,t The final upper-level optimization model is represented as follows:

[0094] J1=min.(πW M，t -π RM，t +π DR，t )*ΔP DR，t ,t∈T DR .

[0095] The two-layer optimization model in this embodiment designs incentives based on user indoor discomfort and plug-in load dissatisfaction indices, fully considering the wishes of building users. By optimizing incentive prices and flexible participation capacity, a win-win situation is achieved for aggregators and building users. This fully taps into the flexibility of building energy use, realizes building energy conservation, reduces the final electricity cost for building users, and increases the electricity trading revenue of resource aggregators.

[0096] Step S400: Construct an aggregator day-ahead bid profit optimization model based on the building flexible participation capacity, the demand response incentive price, and the energy trading strategy;

[0097] In simple terms, this paper constructs an aggregator day-ahead bidding profit optimization model based on building flexible participation capacity, demand response incentive prices, and energy trading strategies to optimize energy trading strategies. The aim is to maximize aggregator bidding profits when adopting this energy trading strategy, thereby improving the economic efficiency of renewable energy system operation.

[0098] In one implementation, an aggregator day-ahead bid profit optimization model is constructed based on the building's flexible participation capacity, the demand response incentive price, and the energy trading strategy, including:

[0099] The aggregator's day-ahead bid profit function is determined based on the wholesale electricity price, the retail electricity price, the building flexible participation capacity, the demand response incentive price, and the energy trading strategy.

[0100] Based on the aggregator's day-ahead bid profit function, and with the objective of maximizing the aggregator's day-ahead bid profit, the aggregator's day-ahead bid profit optimization model is determined.

[0101] Specifically, based on wholesale electricity prices, retail electricity prices, and building flexible participation capacity ΔP DR,t Demand response incentive price π DR,t The paper also includes calculations of aggregator day-ahead bidding profits using energy trading strategies. A day-ahead bidding profit function for aggregators is constructed, using energy trading strategies as variables. With the objective of maximizing aggregator bidding profits (i.e., profits from electricity sales to building users minus wholesale market electricity purchase costs and demand response payment costs), an optimization model for aggregator day-ahead bidding profits is determined based on the aggregator day-ahead bidding profit function.

[0102] The aggregator's day-to-day bidding profit optimization model is expressed as follows:

[0103]

[0104] Where T is the forecast date, P grid,t For the aggregated electricity purchase strategy, P sell,t The aggregator's electricity sales strategy, the aggregator's electricity purchase strategy, and the aggregator's electricity sales strategy constitute an energy trading strategy.

[0105] Step S500: Construct supply and demand constraints based on the confidence level, the photovoltaic power generation capacity, the building flexible participation capacity, the energy trading strategy, and the energy storage system charging and discharging strategy;

[0106] In simple terms, the constraints of the aggregator's day-ahead bid profit optimization model include the charging and discharging power of the energy storage system and the upper and lower limits of its state of charge, while also introducing opportunity constraints (satisfying confidence levels). The supply and demand balance of the system (based on the supply and demand relationship) constitutes the supply and demand constraint condition, ensuring that the probability of supply meeting demand is greater than or equal to the set confidence level. The supply and demand relationship is determined based on photovoltaic power generation capacity, building-integrated flexible capacity, energy trading strategies, and energy storage system charging and discharging strategies. Generally, when the confidence level is high, aggregators will more conservatively arrange to purchase electricity from the grid to reduce the risk of insufficient supply; while when the confidence level is low, they may more aggressively utilize photovoltaic and energy storage resources to pursue higher economic benefits.

[0107] In one implementation, supply and demand constraints are constructed based on the confidence level, the photovoltaic power generation capacity, the building's flexible participation capacity, the energy trading strategy, and the energy storage system's charging and discharging strategy, including:

[0108] The total supply is determined based on the photovoltaic power generation capacity and the energy trading strategy.

[0109] Obtain a building load baseline value, and determine the net demand based on the building load baseline value, the building flexible participation capacity, and the energy storage system charging and discharging strategy;

[0110] The probability that the total supply is greater than the net demand is greater than or equal to the confidence level is used as the supply and demand constraint.

[0111] Specifically, the supply and demand constraints can be expressed as:

[0112]

[0113] Among them, P supply,t For the total supply, P net,t Net demand, total supply P supply,t It is expressed as follows:

[0114] P supply，t =P grid，t +P PV，t ,

[0115] Among them, P PV,t Photovoltaic power generation capacity, net demand P net,t It is expressed as follows:

[0116] P net，t =P load，t -ΔP DR，t -P EES，t ,

[0117] Among them, P load,t P is the benchmark value for building load. EES,t A charging and discharging strategy for energy storage systems.

[0118] Step S600: Solve the day-ahead bid profit optimization model of the aggregator based on the supply and demand constraints, and optimize the energy trading strategy and the energy storage system charging and discharging strategy.

[0119] In simple terms, based on supply and demand constraints, the day-ahead bid profit optimization model of aggregators is solved to obtain the optimal energy storage system charging and discharging strategy and energy trading strategy under the set confidence level. Figure 4 The aggregator scheduling results and actual energy supply are presented at confidence levels of 65% and 95%.

[0120] This embodiment employs an opportunity-constrained day-ahead bidding profit optimization strategy for aggregators, enabling them to optimize bidding based on supply and demand balance constraints at different confidence levels in the electricity market. This maximizes profits while effectively managing supply shortage risks. Under varying market conditions, aggregators can flexibly adjust their strategies to ensure a balance between economic performance and supply reliability.

[0121] Based on the above embodiments, the present invention also provides a risk-aware renewable energy dispatching device, such as... Figure 5 As shown, the device includes:

[0122] The photovoltaic power generation prediction module 01 is used to obtain the confidence level and the photovoltaic power generation prediction model, and to determine the photovoltaic power generation based on the confidence level and the photovoltaic power generation prediction model.

[0123] The two-layer optimization model construction module 02 is used to construct a two-layer optimization model, which is used to optimize the aggregator cost and the building user cost during the user demand response period.

[0124] The two-layer optimization model solving module 03 solves the two-layer optimization model to determine the building's flexible participation capacity and demand response incentive price.

[0125] The aggregator day-ahead bid profit optimization model construction module 04 is used to construct an aggregator day-ahead bid profit optimization model based on the building flexible participation capacity, the demand response incentive price, and the energy trading strategy.

[0126] The supply and demand constraint construction module 05 is used to construct supply and demand constraints based on the confidence level, the photovoltaic power generation capacity, the building flexible participation capacity, the energy trading strategy, and the energy storage system charging and discharging strategy.

[0127] The strategy determination module 06 is used to solve the day-ahead bid profit optimization model of the aggregator based on the supply and demand constraints, and to optimize the energy trading strategy and the energy storage system charging and discharging strategy.

[0128] Based on the above embodiments, the present invention also provides a terminal, the principle block diagram of which can be as follows: Figure 6As shown, the terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a risk-aware renewable energy dispatch method. The display screen can be an LCD screen or an e-ink screen.

[0129] Those skilled in the art will understand that Figure 6 The block diagram shown is merely a partial structural diagram related to the present invention and does not constitute a limitation on the terminal to which the present invention is applied. A specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0130] In one implementation, the terminal's memory stores one or more programs, and these programs are configured to be executed by one or more processors, and the programs contain instructions for performing a risk-aware renewable energy dispatching method.

[0131] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0132] In summary, this invention discloses a renewable energy dispatching method, device, terminal, and medium based on risk perception. The method predicts photovoltaic (PV) power generation using confidence level, environmental data, and a PV power generation prediction model; constructs a two-layer optimization model to coordinate aggregator costs and building user costs during demand response, and obtains building flexible participation capacity and demand response incentive price by solving the two-layer optimization model; constructs an aggregator day-ahead bidding profit optimization model and supply and demand constraints based on confidence level, PV power generation, building flexible participation capacity, and demand response incentive price; and optimizes the energy storage system's charging and discharging strategy and energy trading strategy based on the aggregator day-ahead bidding profit optimization model and supply and demand constraints. This effectively solves the problem of existing technologies failing to consider the uncertainty of power generation, user participation costs in demand response, and willingness to respond, making it difficult to effectively balance the risks of power shortages and trading benefits, and achieving power dispatch optimization under uncertain conditions.

[0133] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A renewable energy dispatching method based on risk perception, characterized in that, The method includes: Acquire confidence level, environmental data, and photovoltaic power generation prediction model; determine photovoltaic power generation based on the confidence level, environmental data, and photovoltaic power generation prediction model. A two-layer optimization model is constructed to optimize the aggregator cost and the building user cost during the user demand response period; Solve the two-layer optimization model to determine the building's flexible participation capacity and demand response incentive price; A day-ahead bid profit optimization model for aggregators is constructed based on the building flexible participation capacity, the demand response incentive price, and the energy trading strategy. Supply and demand constraints are constructed based on the confidence level, the photovoltaic power generation capacity, the building flexible participation capacity, the energy trading strategy, and the energy storage system charging and discharging strategy. Based on the supply and demand constraints, the day-ahead bid profit optimization model of the aggregator is solved to optimize the energy trading strategy and the charging and discharging strategy of the energy storage system.

2. The renewable energy dispatching method based on risk perception according to claim 1, characterized in that, The photovoltaic power generation prediction model includes: Obtain historical photovoltaic power generation data; The photovoltaic power generation prediction model is pre-trained using the historical photovoltaic power generation data, wherein the photovoltaic power generation prediction model is a natural gradient boosting algorithm.

3. The renewable energy dispatching method based on risk perception according to claim 1, characterized in that, Determining photovoltaic power generation based on the confidence level, the environmental data, and the photovoltaic power generation prediction model includes: The probability distribution of each photovoltaic power generation is determined based on the environmental data and the photovoltaic power generation prediction model. Construct a cumulative distribution function based on the probability distribution of each photovoltaic power generation; The photovoltaic power generation is determined when the value of the cumulative distribution function is greater than or equal to the confidence level.

4. The renewable energy dispatching method based on risk perception according to claim 1, characterized in that, The method for constructing the lower-level optimization model of the two-level optimization model includes: Obtain the costs of thermal environmental discomfort, light environmental discomfort, and plug-in load unmet needs at each moment during the demand response period; The building user cost function is determined based on the thermal environmental discomfort cost, the light environmental discomfort cost, the plug-in load non-satisfaction cost, the building flexible participation capacity, and the demand response incentive price at each time point. The lower-level optimization model is determined based on the building user cost function and with the goal of minimizing building user costs.

5. The renewable energy dispatching method based on risk perception according to claim 4, characterized in that, The optimization of the upper-level optimization model in the two-level optimization model depends on the optimal solution of the lower-level optimization model. The method for constructing the lower-level optimization model includes: Obtain the wholesale and retail electricity prices at each point in time during the demand response period; The aggregator cost function is determined based on the wholesale electricity price, retail electricity price, building flexible participation capacity, and demand response incentive price at each time point; The upper-level optimization model is determined based on the aggregator cost function and with the goal of minimizing the aggregator cost.

6. The renewable energy dispatching method based on risk perception according to claim 5, characterized in that, Based on the aforementioned building flexible participation capacity, the aforementioned demand response incentive price, and energy trading strategies, a day-ahead bid profit optimization model for aggregators is constructed, including: The aggregator's day-ahead bid profit function is determined based on the wholesale electricity price, the retail electricity price, the building flexible participation capacity, the demand response incentive price, and the energy trading strategy. Based on the aggregator's day-ahead bid profit function, and with the objective of maximizing the aggregator's day-ahead bid profit, the aggregator's day-ahead bid profit optimization model is determined.

7. The renewable energy dispatching method based on risk perception according to claim 1, characterized in that, Supply and demand constraints are constructed based on the confidence level, the photovoltaic power generation capacity, the building flexible participation capacity, the energy trading strategy, and the energy storage system charging and discharging strategy, including: The total supply is determined based on the photovoltaic power generation capacity and the energy trading strategy. Obtain a building load baseline value, and determine the net demand based on the building load baseline value, the building flexible participation capacity, and the energy storage system charging and discharging strategy; The probability that the total supply is greater than the net demand is greater than or equal to the confidence level is used as the supply and demand constraint.

8. A renewable energy dispatching device based on risk perception, characterized in that, The device includes: A photovoltaic power generation prediction module is used to acquire confidence level, environmental data, and a photovoltaic power generation prediction model, and to determine the photovoltaic power generation based on the confidence level, the environmental data, and the photovoltaic power generation prediction model. A two-layer optimization model construction module is used to construct a two-layer optimization model, which is used to optimize the aggregator cost and the building user cost during the user demand response period; The two-layer optimization model solving module solves the two-layer optimization model to determine the building's flexible participation capacity and demand response incentive price. The module for constructing a day-ahead bid profit optimization model for aggregators is used to construct a day-ahead bid profit optimization model for aggregators based on the building flexible participation capacity, the demand response incentive price, and the energy trading strategy. The supply and demand constraint construction module is used to construct supply and demand constraints based on the confidence level, the photovoltaic power generation capacity, the building flexible participation capacity, the energy trading strategy, and the energy storage system charging and discharging strategy. The strategy determination module is used to solve the day-ahead bid profit optimization model of the aggregator based on the supply and demand constraints, and to optimize the energy trading strategy and the energy storage system charging and discharging strategy.

9. A terminal, characterized in that, The terminal includes a memory and one or more processors; the memory stores one or more programs; the programs contain instructions for executing the risk-aware renewable energy dispatching method as described in any one of claims 1-7; the processors are used to execute the programs.

10. A computer-readable storage medium storing a plurality of instructions thereon, characterized in that, The instructions are applicable to be loaded and executed by a processor to implement the steps of the risk-aware renewable energy scheduling method according to any one of claims 1-7.

Images