CN117787750A - Energy collaborative scheduling method, device, computer equipment and storage medium - Google Patents
Energy collaborative scheduling method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117787750A CN117787750A CN202311845653.5A CN202311845653A CN117787750A CN 117787750 A CN117787750 A CN 117787750A CN 202311845653 A CN202311845653 A CN 202311845653A CN 117787750 A CN117787750 A CN 117787750A
- Authority
- CN
- China
- Prior art keywords
- energy
- scheduling
- model
- power generation
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000010248 power generation Methods 0.000 claims abstract description 111
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 95
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 91
- 238000004146 energy storage Methods 0.000 claims abstract description 33
- 230000007246 mechanism Effects 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000005611 electricity Effects 0.000 claims description 25
- 239000003245 coal Substances 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 4
- 238000012946 outsourcing Methods 0.000 claims description 4
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 15
- 238000011161 development Methods 0.000 abstract description 6
- 230000006872 improvement Effects 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 14
- 238000005265 energy consumption Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 7
- 229910002092 carbon dioxide Inorganic materials 0.000 description 7
- 239000002803 fossil fuel Substances 0.000 description 6
- 230000001965 increasing effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000001737 promoting effect Effects 0.000 description 5
- 238000000513 principal component analysis Methods 0.000 description 4
- 230000000295 complement effect Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of energy management, and discloses an energy collaborative scheduling method, an energy collaborative scheduling device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring an energy collaborative scheduling model adapted to an energy scheduling task from a plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system; acquiring renewable energy source historical power generation data, and processing the renewable energy source historical power generation data through a nuclear density estimation algorithm to acquire renewable energy source power generation expected data in a mission period of an energy source scheduling mission; and inputting the renewable energy power generation expected data into an energy cooperative scheduling model, and obtaining an energy scheduling scheme which is output by the energy cooperative scheduling model and used for executing the energy scheduling task. According to the invention, the energy collaborative scheduling model is used for outputting a scheduling scheme, so that multiple aims of carbon emission reduction, power generation unit efficiency improvement, power supply stability and safety enhancement, cost optimization, clean energy development promotion and the like can be realized.
Description
Technical Field
The present invention relates to the field of energy management, and in particular, to a method and apparatus for collaborative scheduling of energy, a computer device, and a storage medium.
Background
The power system plays a vital role in the infrastructure and economic development of modern society. Currently, power systems have a high degree of dependence on fossil fuels. The use of fossil fuels increases greenhouse gas emissions and affects the global ecological environment. The development of renewable energy and energy storage systems can reduce the dependence of power systems on fossil fuels. However, wind power generation, solar power generation and other similar renewable energy sources are susceptible to environmental and climatic factors, resulting in a very unstable power generation process, which is prone to severe impacts on the power system.
Wind-solar complementary power generation systems play a vital role in improving the low carbon level of the power system. Various studies have been conducted to investigate the complementary potential of various renewable energy sources, including wind and solar power generation, wind-solar power generation and water power generation, wind-solar power generation-water-thermal power generation and energy storage, and the like. These studies indicate that the complementary application of different power supplies can increase the consumption of clean energy power generation, and is a viable approach to solve the above problems.
In order to comprehensively evaluate the influence of environmental cost on the power system, the intricate and complex interaction between the coordinated operation of the energy system and the carbon emission must be studied, and various factors such as comprehensive energy and carbon price are considered. Most of the current research focuses on how carbon pricing directly affects the electricity generation costs, but it is difficult to predict how carbon pricing will affect the electricity generation costs due to the uncertainty of the carbon pricing system. Instead, by analyzing the implementation costs of carbon pricing mechanisms to evaluate their potential for cost reduction, one can gain insight into their potential impact on the direct cost of electricity generation. Analysis of the impact of carbon transactions on energy use may also reveal the role of carbon transactions in altering the energy consumption structure. Both of these approaches can estimate how the carbon trade mechanism will change the energy price and the structure of the energy market, but neither point out how carbon trade and carbon pricing will affect the cost and environmental benefits of a carbon dioxide emitting power plant.
Further investigation of the economic benefits of carbon-emitting power plants has found that carbon trading mechanisms promote carbon emission reduction by affecting enterprise energy consumption, rather than changing the industry architecture. The carbon trading mechanism facilitates emissions reduction by affecting enterprise energy consumption, thereby significantly affecting the economic advantage of the dominant power plant in reducing carbon emissions. In general, the introduction of the carbon trade mechanism can promote the change of the operation mode of the power generation side, thereby increasing clean energy consumption and comprehensively reducing carbon emission. The main purpose of the carbon trade mechanism is to increase the cost of carbon emissions, promoting reduced use of fossil fuels by power plants, and thus the overall economic advantage of power generation may be negatively impacted by the carbon trade mechanism. While wind and solar power generation is critical to energy reform, and thermal power generation will still dominate the chinese power generation industry in the foreseeable future, multi-energy collaboration is critical to the power generation industry. However, due to the large carbon emissions of thermal power generation, and the unpredictability of wind and solar power generation, multi-energy collaboration may have adverse effects on the environment and society. In order to reduce the ecological economic loss of the power plant through carbon emission reduction and promote the consumption level of clean energy, a multi-energy collaborative scheduling model which considers both economic factors and low-carbon factors needs to be provided, and meanwhile, the influence of carbon transaction and clean energy such as wind energy, solar energy and the like on a power generation system needs to be considered.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an energy collaborative scheduling method, an apparatus, a computer device, and a storage medium.
An energy collaborative scheduling method comprises the following steps:
acquiring an energy collaborative scheduling model adapted to an energy scheduling task from a plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system;
acquiring renewable energy source historical power generation data, and processing the renewable energy source historical power generation data through a nuclear density estimation algorithm to acquire renewable energy source power generation expected data in a mission period of the energy source scheduling mission;
and inputting the renewable energy power generation expected data into the energy cooperative scheduling model, and acquiring an energy scheduling scheme which is output by the energy cooperative scheduling model and used for executing the energy scheduling task.
An energy co-scheduling apparatus comprising:
the model adapting module is used for acquiring an energy collaborative scheduling model adapted to the energy scheduling task from the plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system;
the expected electric quantity calculation module is used for acquiring renewable energy source historical power generation data, processing the renewable energy source historical power generation data through a nuclear density estimation algorithm and acquiring renewable energy source power generation expected data in a task period of the energy source scheduling task;
and the generation scheduling scheme module is used for inputting the renewable energy power generation expected data into the energy cooperative scheduling model and obtaining an energy scheduling scheme which is output by the energy cooperative scheduling model and used for executing the energy scheduling task.
A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor implementing the energy co-scheduling method described above when executing the computer readable instructions.
One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform an energy co-scheduling method as described above.
According to the energy collaborative scheduling method, the device, the computer equipment and the storage medium, the energy collaborative scheduling model which is matched with the energy scheduling task is obtained from a plurality of scheduling models; the scheduling model is incorporated into a carbon transaction mechanism and an energy storage system, so that the calculation complexity of the energy cooperative scheduling model is reduced, and the generation efficiency of an energy scheduling scheme is improved; the renewable energy source historical power generation data is obtained, the renewable energy source historical power generation data is processed through a nuclear density estimation algorithm, renewable energy source power generation expected data in a mission period of the energy source scheduling mission is obtained, uncertainty related to renewable energy source power generation is better considered, and a multi-energy source scheduling strategy can be optimized more effectively; and inputting the renewable energy power generation expected data into the energy cooperative scheduling model, and acquiring an energy scheduling scheme which is output by the energy cooperative scheduling model and is used for executing the energy scheduling task, so that carbon emission reduction is realized, and meanwhile, the power generation cost is reduced. According to the energy scheduling scheme output by the energy collaborative scheduling model, the multiple aims of carbon emission reduction, power generation unit efficiency improvement, power supply stability and safety enhancement, cost optimization, clean energy development promotion and the like can be achieved, and the method has important significance in constructing a sustainable low-carbon energy system.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of an application environment of an energy collaborative scheduling method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for collaborative scheduling according to an embodiment of the present invention;
FIG. 3 is a graph of characteristic light energy for each quarter characteristic day of a region in accordance with one embodiment of the present invention;
FIG. 4 is a graph of characteristic wind energy for each quarter characteristic day of a region in accordance with one embodiment of the present invention;
FIG. 5 is a scheduling result of model 1 in an embodiment of the present invention;
FIG. 6 is a scheduling result of model 2 in an embodiment of the present invention;
FIG. 7 is a scheduling result of model 3 in an embodiment of the present invention;
FIG. 8 is a scheduling result of model 4 in an embodiment of the present invention;
FIG. 9 is a schematic diagram of an energy co-scheduling apparatus according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a computer device in accordance with an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The energy collaborative scheduling method provided by the embodiment can be applied to an application environment as shown in fig. 1, wherein a client communicates with a server. Clients include, but are not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server may be implemented by a stand-alone server or a server cluster formed by a plurality of servers.
In an embodiment, as shown in fig. 2, an energy collaborative scheduling method is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:
s10, acquiring an energy collaborative scheduling model matched with an energy scheduling task from a plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system;
s20, acquiring renewable energy source historical power generation data, and processing the renewable energy source historical power generation data through a nuclear density estimation algorithm to acquire renewable energy source power generation expected data in a mission period of the energy source scheduling mission;
s30, inputting the renewable energy power generation expected data into the energy collaborative scheduling model, and acquiring an energy scheduling scheme which is output by the energy collaborative scheduling model and used for executing the energy scheduling task.
The energy scheduling task is to reasonably schedule and optimally configure a power supply source in a power system according to factors such as electricity market demands, running states of power generation equipment, loads of power transmission lines and the like so as to ensure safe and stable operation of a power grid and meet electricity demands of users. The energy scheduling task may be a medium-short term energy scheduling.
Mid-term energy scheduling generally refers to the scheduling and adjustment of power generation plans over weeks to months in the future. In the period, the operation mode of the power generation equipment is adjusted to meet the power consumption requirements of different time periods by taking seasonal factors, weather changes, market requirements and the like into consideration. The aim of medium-term energy scheduling is to optimize the operation of power generation equipment, reduce the cost and ensure the safe and stable operation of a power grid.
Short-term energy scheduling refers to the specific arrangement and implementation of power generation plans over the days to weeks in the future. In the period, specific scheduling and optimal configuration are required to be carried out on the power generation equipment in consideration of factors such as market demand, weather forecast, power transmission line load and the like in the future so as to cope with emergency and adjust the running state of the power system. The short-term energy scheduling aims to meet market demands to the maximum extent and ensure reasonable control of power generation cost on the premise of ensuring the safety of a power grid.
In order to reduce the calculation complexity of the scheduling model, a plurality of scheduling models are preset and are used for coping with different electricity consumption requirements. Each scheduling model corresponds to a characteristic day. The wind energy generating capacity, the light energy generating capacity and the required load electric quantity are huge in data quantity every moment in the whole year, and a plurality of characteristic days are selected to be adopted, wherein each characteristic day represents the electricity consumption requirement in a certain period, and the electricity consumption requirement can be a quarter. Each energy scheduling task may correspond to one or more characteristic days. And the energy collaborative scheduling model which is matched with the energy scheduling task is a scheduling model which is associated with the corresponding characteristic day.
It should be noted that here, the scheduling model incorporates a carbon transaction mechanism and an energy storage system. The carbon trade mechanism promotes carbon emission reduction by influencing enterprise energy consumption instead of changing an industrial structure, and the carbon trade mechanism promotes emission reduction by influencing enterprise energy consumption, so that the economic advantage of a dominant power plant for reducing carbon emission is obviously influenced. The introduction of the carbon transaction mechanism can promote the change of the operation mode of the power generation side, thereby increasing clean energy consumption and comprehensively reducing carbon emission. The main purpose of the carbon trade mechanism is to increase the cost of carbon emissions, promoting reduced use of fossil fuels by power plants, and thus the overall economic advantage of power generation may be negatively impacted by the carbon trade mechanism. Energy storage systems are critical to balancing the intermittent power characteristics of renewable energy sources because they are able to store the electricity generated when wind is not blowing or the sun is not shining and release it when needed. The inclusion of an energy storage system may enhance the stability and reliability of the power grid.
Renewable energy historical power generation data includes, but is not limited to, wind power generation data and solar power generation data. The kernel density estimation algorithm (Kernel Density Estimation, abbreviated as KDE) is a non-parametric statistical method for estimating probability density functions of random variables. The method estimates the density distribution of the entire dataset based on existing data samples by placing a smooth "kernel" function around a viewpoint and weighted averaging the contributions of all of these kernel functions. In view of the time variability and unpredictability of wind and solar power generation, renewable energy generation expected data within the mission period of an energy scheduling mission can be generated by processing renewable energy historical power generation data through a nuclear density estimation algorithm. By adopting the nuclear density estimation algorithm, the generated energy scheduling scheme can better consider the uncertainty related to renewable energy power generation and can more effectively optimize the multi-energy scheduling strategy.
The energy collaborative scheduling model is used for determining the optimal output power of each power generation unit, the input power of the power grid and the charge and discharge activities of the energy storage system during the task of the energy scheduling task. Because thermal power plants and energy storage systems are used as a means of increasing the levels of wind and solar energy consumption, fire coal in electrical power systems is a major source of carbon emissions, and reducing dependence on fossil fuels is critical to achieving maximization of social and economic benefits. Accordingly, a carbon trading mechanism is incorporated into the power generation system while taking into account the power generation costs and the carbon emissions resulting therefrom to achieve both economy and low carbon. The energy scheduling scheme output by the energy collaborative scheduling model can realize multiple targets of carbon emission reduction, improving the efficiency of the power generation unit, enhancing the power supply stability and safety, optimizing the cost, promoting the development of clean energy and the like, and has important significance for constructing a sustainable low-carbon energy system.
S10-S30, acquiring an energy collaborative scheduling model matched with an energy scheduling task from a plurality of scheduling models; the scheduling model is incorporated into a carbon transaction mechanism and an energy storage system, so that the calculation complexity of the energy cooperative scheduling model is reduced, and the generation efficiency of an energy scheduling scheme is improved; the renewable energy source historical power generation data is obtained, the renewable energy source historical power generation data is processed through a nuclear density estimation algorithm, renewable energy source power generation expected data in a mission period of the energy source scheduling mission is obtained, uncertainty related to renewable energy source power generation is better considered, and a multi-energy source scheduling strategy can be optimized more effectively; and inputting the renewable energy power generation expected data into the energy cooperative scheduling model, and acquiring an energy scheduling scheme which is output by the energy cooperative scheduling model and is used for executing the energy scheduling task, so that carbon emission reduction is realized, and meanwhile, the power generation cost is reduced. According to the energy scheduling scheme output by the energy collaborative scheduling model, the multiple targets of carbon emission reduction, power generation unit efficiency improvement, power supply stability and safety enhancement, cost optimization, clean energy development promotion and the like can be achieved, and the method has important significance in constructing a sustainable low-carbon energy system.
Optionally, before step S10, that is, before the energy collaborative scheduling model adapted to the energy scheduling task is obtained from the plurality of scheduling models, the method further includes:
s11, acquiring annual power load data;
s12, processing the annual power load data according to a principal component analysis method and a Gaussian mixture model, and clustering the annual power load data to obtain a plurality of power load sample sets;
s13, constructing the scheduling model according to each power load sample set.
Understandably, to ease the computational burden of the scheduling model, a characteristic day method is employed, i.e., the annual electricity load is represented by a set of typical days. A Principal Component Analysis (PCA) is combined with a Gaussian Mixture Model (GMM) clustering algorithm for processing annual power load data to build a scheduling model. Because of the strong linear relationship between load data per hour, if only PCA is used to compress the data with the strong linear relationship, the obtained data projection only retains a few main components, so that the original information is lost. Therefore, on the premise of ensuring the full information of the original data, the characteristic data with relatively strong linear relation is clustered by adopting the GMM so as to effectively reflect the difference between the original data sets. By adopting PCA-GMM, the calculation complexity of the scheduling model can be reduced as a whole. Experiments have shown that combining PCA with GMM clustering is more efficient in achieving optimal results than using GMM clustering alone.
After clustering the annual power load data, a plurality of power load sample sets may be obtained. These power load sample sets are used for further modeling to generate a scheduling model.
In the embodiment, the PCA-GMM is used for clustering the annual power load data, so that the calculation complexity of the scheduling model can be reduced, and the processing efficiency of the scheduling model can be improved.
Optionally, the number of the scheduling models is 7.
Understandably, when clustering annual electrical load data, the clustering performance of the clustering algorithm employed may be measured (CHI) using a Calinski Harabasz index, with higher CHI values indicating a smaller intra-cluster variance and a larger inter-cluster variance. Annual power load data is processed using GMM and PCA-GMM, respectively, an optimal 7 power load sample set may be obtained. The clustering performance of these two algorithms, based on the optimal number of clusters, is shown in table 1 below.
TABLE 1 comparison of clustering Performance of GMM and PCA-GMM
As can be seen from the clustering performance results in Table 1, too few principal components can cause poor clustering effect of samples, which may be due to the fact that the data projected onto fewer principal components cannot effectively reflect the difference between the original data points, lose the information of the original data, and cannot meet the requirement of accurate clustering; on the other hand, selecting a larger number of principal components can provide more original data information, but excessive correlation of features can lead to deviation of feature projection, and finally influence clustering effect. Through multiple rounds of training, the training result shows that the PCA-GMM can effectively cluster annual power load data, and the calculation complexity of a scheduling model is reduced.
In some application examples, the 7 scheduling models correspond to 7 feature days, respectively, each feature day representing a season, for example, feature days 2,3 representing spring (3 months 1 to 5 months 31 days), feature days 4,5 representing summer (6 months 1 to 8 months 30 days), feature day 6 representing autumn (9 months 1 to 11 months 30 days), and feature days 7,1 representing winter (12 months 1 to 2 months 28 days). The number of the characteristic days is an optimal value obtained through a GMM model and a PCI method, if the number of the characteristic days is too small, annual generating capacity and load electric quantity data cannot be reflected better, and if the number of the characteristic days is too large, the calculation amount is huge, and the operation difficulty is increased.
Optionally, the kernel density estimation algorithm includes:
wherein F is t (x) Is the nuclear density estimated value of the renewable energy generating capacity x at the moment t;
x i is n sample points { x } 1 ,...,x i ,...x n One of the };
h is bandwidth and takes value according to experience;
k is Gaussian kernel;
E t (x) Desired data is generated for renewable energy sources in a time from t=0 to t=d.
Understandably, a nuclear density estimation method is employed to determine the mathematical expectation of the power generation amount per evaluation period from the renewable energy power generation amount x. Here, the evaluation period may be one quarter and one hour. The renewable energy generation amount x may be wind energy and/or solar energy. The nuclear density estimation method can more accurately reflect different levels of wind and solar power generation in consideration of time variability and unpredictability of wind and solar power generation. By adopting the nuclear density estimation method, the energy scheduling scheme can better consider the uncertainty related to renewable energy power generation and can more effectively optimize the multi-energy scheduling strategy. Due to technical limitations, the sampling interval of wind energy and solar energy power generation data is generally 1 hour, which is shown as discreteness. Discrete power generation data may not accurately reflect continuous power generation. In order to mitigate the influence of the hourly discrete data of renewable energy power generation, a nuclear density estimation method is adopted.
In the kernel density estimation algorithm, h may be empirically valued, such as:
wherein,is the standard deviation corresponding to n sample points at time t; k is a gaussian kernel for calculating the probability distribution:
where μ is the average of the corresponding n sample points at time t.
Then, through the formula
Solving the mathematical expectation of the generated power over a period of time.
For example, when d=1h, E t (x) Is a mathematical expectation of the generated power per hour.
The embodiment provides a refinement calculation process of a nuclear density estimation algorithm, and can accurately calculate renewable energy power generation expected data. It should be noted that, here, the power generation expectation data of each renewable energy source is calculated solely by the nuclear density estimation algorithm.
In an application example, as shown in fig. 3, fig. 3 is a graph of characteristic light energy for each quarter characteristic day of a region. As shown in FIG. 4, FIG. 4 is a characteristic wind energy for each quarter characteristic day of a region.
Optionally, the energy co-scheduling model includes:
min F＝Z 1 +Z 2
and satisfies the following conditions:
the load is balanced;
the generating capacity change value of the thermal power generating unit is smaller than the maximum generating capacity change value in unit time of the thermal power generating unit;
various generator sets in the energy scheduling task are in respective transmission power ranges;
the energy storage system has balanced electric quantity and limited storage capacity;
wherein F is the total energy use cost;
Z 1 the energy use cost is used;
Z 2 is the cost of carbon trade.
It is appreciated that the energy co-scheduling model needs to satisfy multiple constraints simultaneously.
Wherein, if the load reaches balance, then:
P(t)+P w (t)+P pv (t)+P net (t)+P bsc (t)≥D(t)
wherein P (t) is the output power of the thermal generator set in the t time period;
P w (t) is the output power of the wind generating set in the t time period;
P pv (t) is the output power of the photovoltaic unit in the t time period;
P net (t) is the power of the outsourced power;
P bsc (t) is the output power of the energy storage system in the t time period;
d (t) is the electrical load for the t period.
The generating capacity change value of the thermal power generating unit is smaller than the maximum value of generating capacity change in unit time of the thermal power generating unit, and the generating capacity change value can be expressed as:
|P(t+1)-P(t)|≤P lim
wherein P (t+1) is the output power of the thermal generator set in the t+1 time period;
p (t) is the output power of the thermal generator set in the t time period;
P lim the maximum value of the power generation amount change in unit time of the thermal power generating unit.
And each type of generator set in the energy scheduling task is in the respective transmission power range. For example, if the energy scheduling task includes a thermal generator set, a wind generator set, and a photovoltaic set, then:
P min ≤P(t)≤P max
wherein P is min And P max Is the minimum and maximum output value of the thermal power unit i;
and->The minimum and maximum output values of the wind turbine generator are obtained;
and->Is the minimum and maximum output value of the photovoltaic unit.
The power balance and storage capacity limitation of the energy storage system can be specifically expressed as:
0≤P bsc (t)≤P bsc,max
P bsc (t)+P(t)+P w (t)+P pv (t)+P net (t)-D(t)＝P bsc (t+1)
P bsc (0)＝0
wherein P is bsc (t) is the electrical quantity of the energy storage system at the time t;
P bsc,max is the maximum amount of electricity that the energy storage system can store.
In this embodiment, the goal of the energy collaborative scheduling model is to pursue the minimization of the total energy usage cost while satisfying the constraints of the multi-energy power supply system.
Optionally, calculating the energy usage cost by an energy cost model; the energy cost model includes:
wherein T is the schedule period number;
p (t) is the output of the ith thermal power unit in the t period;
SU i the coal consumption is the coal consumption when the i-number unit is started;
γ c the price of the standard coal;
a c 、b c and c c Is an empirical parameter;
γ net the electricity price is outsourcing electricity price;
P net the electricity quantity is purchased externally;
Δt is the scheduling time.
Understandably, the energy use cost Z can be calculated by the energy cost model described above 1 . Wherein, gamma c For standard coal prices, the price is derived from an international market, e.g., gamma in one example c Is $ 115 per ton. Gamma ray net For outsourcing electricity prices, influenced by the source of the purchase, e.g. in aIn an example, γ net 110 dollar/megawatt hour. Δt is a scheduling time, and may be set according to actual needs, for example, may be 1 hour.
It should be noted that non-fossil energy power generation does not directly produce carbon emissions, where the energy use costs are directed to thermal power generation in the power generation system.
Optionally, calculating the carbon trade cost by a carbon trade model; the carbon transaction model includes:
wherein beta is i The carbon quota obtained for each degree of electricity of the i-number unit;
is the carbon trade price;
a CO2 、b CO2 and c CO2 Is an empirical parameter.
Understandably, in the carbon trade model, the carbon quota β i Depending on the pricing of the international carbon emissions market, this may be $ 11.5 per ton, for example.
In an application example, four different scheduling models (exemplified by united states regions) are considered: model 1, not incorporating an energy storage system and carbon transaction mechanism; model 2, incorporating only carbon transaction mechanisms; model 3, incorporating only the energy storage system; model 4 incorporates both an energy storage system and a carbon transaction mechanism. FIG. 5 is a scheduling result of model 1; FIG. 6 is a scheduling result of model 2; FIG. 7 is a scheduling result of model 3; fig. 8 is a scheduling result of model 4.
The energy cost calculation was performed on the four models, and the results are shown in table 2.
TABLE 2 energy costs for different models
As can be seen from table 2, model 1 does not incorporate an energy storage mechanism and a carbon trade mechanism, resulting in a power generation system that ignores the effects of wind energy and solar power generation on carbon emissions. In model 1, thermal power generating units face huge pressure in meeting peak energy consumption, resulting in long-time high-load operation, increased overall operation cost and increased system carbon emission. In contrast, model 2 incorporating the carbon trade mechanism showed a 8.83% reduction in coal cost and a 8.64% reduction in system carbon emissions. This suggests that the carbon trade mechanism not only can effectively reduce the cost of electricity generation, but also can effectively reduce carbon emissions. Compared with the model 1, the model 3 shows that the reduction of wind energy and solar energy power generation is small, and the energy storage system can flexibly participate in peak clipping and valley filling scheduling, so that the power generation capacity is optimized. Therefore, compared with model 1, the coal cost of model 3 is reduced by 8.47%, and the system emission is reduced by 8.53%, which highlights the effectiveness of the energy storage system in promoting consumption of wind energy and solar power generation while saving the coal cost. On the other hand, model 2 has lower coal consumption costs than model 3. However, since model 2 requires purchase of carbon quota from outside and purchase cost is high, its cost is 0.7% higher than model 3. In model 4, the use of energy storage technology further increases the level of wind and solar energy consumption. Compared with model 2, the coal consumption cost in model 4 is reduced by 6.84%, and the corresponding carbon emission is reduced by 7.19%. In addition, compared with the model 3, the total cost of the model 4 is reduced by 7.79%, the carbon emission of the system is reduced by 7.31%, and the effectiveness of a carbon transaction mechanism in promoting the wind energy and solar power generation in the power generation system is highlighted.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In an embodiment, an energy cooperative scheduling device is provided, where the energy cooperative scheduling device corresponds to the energy cooperative scheduling method in the above embodiment one by one. As shown in fig. 9, the energy collaborative scheduling apparatus includes a model adaptation module 10, a calculation expected power module 20, and a generation scheduling scheme module 30. The functional modules are described in detail as follows:
the model adapting module 10 is used for acquiring an energy collaborative scheduling model adapted to an energy scheduling task from a plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system;
the expected power calculation module 20 is configured to obtain renewable energy historical power generation data, process the renewable energy historical power generation data through a kernel density estimation algorithm, and obtain renewable energy power generation expected data in a mission period of the energy scheduling mission;
the scheduling scheme generating module 30 is configured to input the renewable energy power generation expected data into the energy cooperative scheduling model, and obtain an energy scheduling scheme output by the energy cooperative scheduling model and used for executing the energy scheduling task.
Optionally, the energy collaborative scheduling device further includes a construction scheduling model module, where the construction scheduling model module includes:
the annual power load data acquisition unit is used for acquiring annual power load data;
the clustering unit is used for processing the annual power load data according to a principal component analysis method and a Gaussian mixture model and clustering the annual power load data to obtain a plurality of power load sample sets;
and a building model unit for building the scheduling model according to each power load sample set.
Optionally, the number of the scheduling models is 7.
Optionally, the kernel density estimation algorithm includes:
wherein F is t (x) Nuclear density estimation of renewable energy power generation capacity x at time tCounting;
x i is n sample points { x } 1 ,...,x i ,...x n One of the };
h is bandwidth and takes value according to experience;
k is Gaussian kernel;
E t (x) Desired data is generated for renewable energy sources in a time from t=0 to t=d.
Optionally, the energy co-scheduling model includes:
min F＝Z 1 +Z 2
and satisfies the following conditions:
the load is balanced;
the generating capacity change value of the thermal power generating unit is smaller than the maximum generating capacity change value in unit time of the thermal power generating unit;
various generator sets in the energy scheduling task are in respective transmission power ranges;
the energy storage system has balanced electric quantity and limited storage capacity;
wherein F is the total energy use cost;
Z 1 the energy use cost is used;
Z 2 is the cost of carbon trade.
Optionally, the scheduling scheme generating module 30 is further configured to calculate the energy usage cost by means of an energy cost model; the energy cost model includes:
wherein T is the schedule period number;
p (t) is the output of the ith thermal power unit in the t period;
SU i the coal consumption is the coal consumption when the i-number unit is started;
γ c the price of the standard coal;
a c 、b c and c c Is an empirical parameter;
γ net the electricity price is outsourcing electricity price;
P net the electricity quantity is purchased externally;
Δt is the scheduling time.
Optionally, the scheduling scheme generating module 30 is further configured to calculate the carbon transaction cost through a carbon transaction model; the carbon transaction model includes:
wherein beta is i The carbon quota obtained for each degree of electricity of the i-number unit;
is the carbon trade price;
a CO2 、b CO2 and c CO2 Is an empirical parameter.
The specific limitation of the energy cooperative scheduling apparatus may be referred to the limitation of the energy cooperative scheduling method hereinabove, and will not be described herein. The modules in the energy cooperative scheduling device can be realized in whole or in part by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a readable storage medium, an internal memory. The readable storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the execution of an operating system and computer-readable instructions in a readable storage medium. The database of the computer device is used for data related to the energy storage source collaborative scheduling method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions when executed by a processor implement an energy co-scheduling method. The readable storage medium provided by the present embodiment includes a nonvolatile readable storage medium and a volatile readable storage medium.
In one embodiment, a computer device is provided that includes a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, when executing the computer readable instructions, performing the steps of:
acquiring an energy collaborative scheduling model adapted to an energy scheduling task from a plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system;
acquiring renewable energy source historical power generation data, and processing the renewable energy source historical power generation data through a nuclear density estimation algorithm to acquire renewable energy source power generation expected data in a mission period of the energy source scheduling mission;
and inputting the renewable energy power generation expected data into the energy cooperative scheduling model, and acquiring an energy scheduling scheme which is output by the energy cooperative scheduling model and used for executing the energy scheduling task.
In one embodiment, one or more computer-readable storage media are provided having computer-readable instructions stored thereon, the readable storage media provided by the present embodiment including non-volatile readable storage media and volatile readable storage media. The readable storage medium has stored thereon computer readable instructions which when executed by one or more processors perform the steps of:
acquiring an energy collaborative scheduling model adapted to an energy scheduling task from a plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system;
acquiring renewable energy source historical power generation data, and processing the renewable energy source historical power generation data through a nuclear density estimation algorithm to acquire renewable energy source power generation expected data in a mission period of the energy source scheduling mission;
and inputting the renewable energy power generation expected data into the energy cooperative scheduling model, and acquiring an energy scheduling scheme which is output by the energy cooperative scheduling model and used for executing the energy scheduling task.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by instructing the associated hardware by computer readable instructions stored on a non-volatile readable storage medium or a volatile readable storage medium, which when executed may comprise the above described embodiment methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile 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 a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (10)
1. The energy collaborative scheduling method is characterized by comprising the following steps of:
acquiring an energy collaborative scheduling model adapted to an energy scheduling task from a plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system;
acquiring renewable energy source historical power generation data, and processing the renewable energy source historical power generation data through a nuclear density estimation algorithm to acquire renewable energy source power generation expected data in a mission period of the energy source scheduling mission;
and inputting the renewable energy power generation expected data into the energy cooperative scheduling model, and acquiring an energy scheduling scheme which is output by the energy cooperative scheduling model and used for executing the energy scheduling task.
2. The energy co-scheduling method according to claim 1, further comprising, before the energy co-scheduling model adapted to the energy scheduling task is obtained from the plurality of scheduling models:
acquiring annual power load data;
processing the annual power load data according to a principal component analysis method and a Gaussian mixture model, and clustering the annual power load data to obtain a plurality of power load sample sets;
and constructing the scheduling model according to each power load sample set.
3. The energy collaborative scheduling method according to claim 1, wherein the number of scheduling models is 7.
4. The energy co-scheduling method of claim 1, wherein the kernel density estimation algorithm comprises:
wherein F is t (x) Is the nuclear density estimated value of the renewable energy generating capacity x at the moment t;
x i is n sample points { x } 1 ,...,x i ,...x n One of the };
h is bandwidth and takes value according to experience;
k is Gaussian kernel;
E t (x) Desired data is generated for renewable energy sources in a time from t=0 to t=d.
5. The energy co-scheduling method of claim 1, wherein the energy co-scheduling model comprises:
min F＝Z 1 +Z 2
and satisfies the following conditions:
the load is balanced;
the generating capacity change value of the thermal power generating unit is smaller than the maximum generating capacity change value in unit time of the thermal power generating unit;
various generator sets in the energy scheduling task are in respective transmission power ranges;
the energy storage system has balanced electric quantity and limited storage capacity;
wherein F is the total energy use cost;
Z 1 the energy use cost is used;
Z 2 is the cost of carbon trade.
6. The energy co-scheduling method of claim 5, wherein the energy use cost is calculated by an energy cost model; the energy cost model includes:
wherein T is the schedule period number;
p (t) is the output of the ith thermal power unit in the t period;
SU i the coal consumption is the coal consumption when the i-number unit is started;
γ c the price of the standard coal;
a c 、b c and c c Is an empirical parameter;
γ net the electricity price is outsourcing electricity price;
P net the electricity quantity is purchased externally;
Δt is the scheduling time.
7. The energy co-scheduling method of claim 6, wherein the carbon trade costs are calculated by a carbon trade model; the carbon transaction model includes:
wherein beta is i The carbon quota obtained for each degree of electricity of the i-number unit;
is the carbon trade price;
a CO2 、b CO2 and c CO2 Is an empirical parameter.
8. An energy co-scheduling apparatus, comprising:
the model adapting module is used for acquiring an energy collaborative scheduling model adapted to the energy scheduling task from the plurality of scheduling models; the scheduling model incorporates a carbon transaction mechanism and an energy storage system;
the expected electric quantity calculation module is used for acquiring renewable energy source historical power generation data, processing the renewable energy source historical power generation data through a nuclear density estimation algorithm and acquiring renewable energy source power generation expected data in a task period of the energy source scheduling task;
and the generation scheduling scheme module is used for inputting the renewable energy power generation expected data into the energy cooperative scheduling model and obtaining an energy scheduling scheme which is output by the energy cooperative scheduling model and used for executing the energy scheduling task.
9. A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and running on the processor, wherein the processor, when executing the computer readable instructions, implements the energy co-scheduling method of any one of claims 1 to 7.
10. One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the energy co-scheduling method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311845653.5A CN117787750A (en) | 2023-12-29 | 2023-12-29 | Energy collaborative scheduling method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311845653.5A CN117787750A (en) | 2023-12-29 | 2023-12-29 | Energy collaborative scheduling method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117787750A true CN117787750A (en) | 2024-03-29 |
Family
ID=90381269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311845653.5A Pending CN117787750A (en) | 2023-12-29 | 2023-12-29 | Energy collaborative scheduling method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117787750A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116826859A (en) * | 2023-06-09 | 2023-09-29 | 国网浙江省电力有限公司经济技术研究院 | Power supply carbon-electricity collaborative planning method, device, equipment and storage medium |
| CN116885795A (en) * | 2023-06-20 | 2023-10-13 | 华北电力大学（保定） | Micro-grid source-grid load storage collaborative scheduling method, device, equipment and storage medium |
| CN117200334A (en) * | 2023-04-12 | 2023-12-08 | 国网河北省电力有限公司信息通信分公司 | Multi-energy scheduling method and device considering new energy uncertainty |
-
2023
- 2023-12-29 CN CN202311845653.5A patent/CN117787750A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117200334A (en) * | 2023-04-12 | 2023-12-08 | 国网河北省电力有限公司信息通信分公司 | Multi-energy scheduling method and device considering new energy uncertainty |
| CN116826859A (en) * | 2023-06-09 | 2023-09-29 | 国网浙江省电力有限公司经济技术研究院 | Power supply carbon-electricity collaborative planning method, device, equipment and storage medium |
| CN116885795A (en) * | 2023-06-20 | 2023-10-13 | 华北电力大学（保定） | Micro-grid source-grid load storage collaborative scheduling method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 万一品: "装载机工作装置载荷谱及其工程应用", 31 March 2021, 西安电子科技大学出版社, pages: 107 - 108 * |
| 朱小林，刘昌，满奕，何正磊: "考虑碳交易和储能系统的风光火协同优化运行", 华北电力大学学报(自然科学版), 10 May 2023 (2023-05-10), pages 1 - 9 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yin et al. | Day-ahead stochastic coordinated scheduling for thermal-hydro-wind-photovoltaic systems | |
| Lund et al. | The role of compressed air energy storage (CAES) in future sustainable energy systems | |
| Garcia et al. | Regulatory design and incentives for renewable energy | |
| Mills et al. | Changes in the economic value of wind energy and flexible resources at increasing penetration levels in the Rocky Mountain Power Area | |
| Larsen et al. | Economic and emission impacts of energy storage systems on power-system long-term expansion planning when considering multi-stage decision processes | |
| Peng et al. | Renewable, flexible, and storage capacities: Friends or foes? | |
| Traber | Capacity remuneration mechanisms for reliability in the integrated European electricity market: effects on welfare and distribution through 2023 | |
| Emblemsvåg | On the levelised cost of energy of windfarms | |
| Franzen et al. | Optimal expansion of a hydrogen storage system for wind power (H2-WESS): A real options analysis | |
| CN115313441A (en) | New energy station energy storage configuration calculation method, system, medium and equipment | |
| Zhang et al. | Quantifying accommodated domain of wind power for flexible look-ahead unit commitment | |
| Haaskjold et al. | Long-term optimization of the Norwegian energy system under the influence of the European power market | |
| Koldingsnes | Reliability-based Derating approach for Interconnectors | |
| Brovold et al. | Implementing hydropower scheduling in a European expansion planning model | |
| Xu et al. | CVaR‐based method for optimizing the contract bidding strategy of PV power stations | |
| CN117787750A (en) | Energy collaborative scheduling method, device, computer equipment and storage medium | |
| CN115758763A (en) | Multi-energy flow system optimal configuration method and system considering source load uncertainty | |
| Yang et al. | Risk-averse two-stage distributionally robust economic dispatch model under uncertain renewable energy | |
| Chen et al. | Capacity expansion model for multi-temporal energy storage in renewable energy base considering various transmission utilization rates | |
| Mu et al. | Risk-constrained multi-period planning for park-level integrated energy system based on CVaR method | |
| Taufiqurrohman | The assessment of off-grid photovoltaic (PV) systems for rural electrification in Indonesia | |
| Tangerås et al. | Locational marginal network tariffs for intermittent renewable generation | |
| Traber | Capacity Mechanisms on Central European Electricity Markets: Effects on Consumers, Producers and Technologies until 2033 | |
| CN118572697B (en) | Virtual power plant energy management method, device, equipment and medium | |
| Wilkie et al. | Revenue Sufficiency in the Australian National Electricity Market with High Penetrations of Renewable Energy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |