CN112862215B

CN112862215B - Micro-grid energy demand prediction method, system and equipment

Info

Publication number: CN112862215B
Application number: CN202110261098.6A
Authority: CN
Inventors: 郑敏嘉; 吴杰康; 李逸新; 黄欣; 吴伟杰; 李猛; 张伊宁
Original assignee: Guangdong Power Grid Co Ltd
Current assignee: Guangdong Power Grid Co Ltd
Priority date: 2021-03-10
Filing date: 2021-03-10
Publication date: 2023-04-07
Anticipated expiration: 2041-03-10
Also published as: CN112862215A

Abstract

The invention discloses a method, a system and equipment for predicting energy demand of a microgrid, and relates to the technical field of power system dispatching automation. The method comprises the following steps: constructing a corresponding data matrix according to different types of databases of the microgrid; constructing a fuzzy clustering center matrix according to the data matrix; setting an initial value of a fuzzy clustering center matrix according to the data change characteristics, and obtaining an optimal value of the fuzzy clustering center matrix through iterative computation; and obtaining the satisfying mode and the load power value of the microgrid under different conditions by the optimal value of the fuzzy clustering center matrix, and further obtaining the predicted value of the load and the predicted values corresponding to different types of energy requirements. The invention considers the uncertainty and randomness of the influence factors in many aspects, can reduce the influence of various uncertain random and fuzzy events or parameters on the capacity configuration of the distributed photovoltaic power generation system of the microgrid and improves the accuracy of the energy demand prediction of the microgrid.

Description

Micro-grid energy demand prediction method, system and equipment

Technical Field

The invention relates to the technical field of power system dispatching automation, in particular to a method, a system and equipment for predicting energy demand of a microgrid.

Background

The Micro-Grid (Micro-Grid) refers to a small-sized power distribution system comprising a distributed power supply, an energy storage device, an energy conversion device, a load, a monitoring and protecting device and the like. The micro-grid aims to realize flexible and efficient application of distributed power supplies and solve the problem of grid connection of the distributed power supplies with large quantity and various forms. The development and extension of the micro-grid can fully promote the large-scale access of distributed power sources and renewable energy sources, realize the high-reliability supply of various energy source types of loads, and is an effective mode for realizing an active power distribution network, so that the traditional power grid is transited to a smart power grid.

The power grid form of distributed sources (natural gas, ground source heat pump, photovoltaic power generation) -load (water, electricity, gas, cold and heat load) is integrated in the interior in a certain mode, the power grid form is mainly applied to subway stations, and compared with the traditional energy system with different energy sources independently operated, the multi-energy system can integrate different energy carriers such as gas, electricity and heat (heat and cold) energy, so that synchronous energy supply is realized, and the energy utilization efficiency is improved. The regional comprehensive energy system takes combined cooling, heating and power as a core and can cooperatively schedule, operate and control natural gas and distributed energy in and among regions. The method has the advantages that the diversified energy requirements of the system are met, the cascade utilization of energy is realized, and the improvement of economic benefits and environmental benefits is an important direction for the development of future energy systems. The subway station takes a micro-grid as a core and has the characteristic of a typical multi-energy system. These all add to the difficulty and complexity of microgrid energy demand forecasting.

The distributed photovoltaic power generation system in the form of the microgrid mainly applied to the subway station is influenced by various uncertain factors, such as power generation power, power generation capacity and installed capacity. These factors are usually random uncertainties or fuzzy uncertainties, or they are random and fuzzy uncertainties, often present as random and fuzzy uncertainty events or parameters. The prior art for calculating the generated power, the generated energy and the installed capacity of the distributed photovoltaic power generation system does not take the uncertainty and the randomness of the influence factors into full consideration, and the applicability, the practicability and the applicability of the calculation method are difficult to meet.

Disclosure of Invention

The invention aims to provide a method, a system and equipment for predicting energy requirements of a microgrid, which are used for determining predicted values of electric, heat and cold loads of a subway station by utilizing a block chain cooperation mechanism and Byzantine fault-tolerant consensus requirement and considering a scene of multi-energy coupling so as to predict the energy requirements of coal, oil, natural gas and nuclear energy of the subway station.

In order to achieve the above object, an embodiment of the present invention provides a method for predicting an energy demand of a microgrid, including:

constructing a corresponding data matrix according to different types of databases of the microgrid;

constructing a fuzzy clustering center matrix according to the data matrix;

setting an initial value of the fuzzy clustering center matrix according to data change characteristics, and obtaining an optimal value of the fuzzy clustering center matrix through iterative computation;

according to the optimal values of fuzzy clustering center matrixes corresponding to all types of databases in the microgrid, obtaining satisfying modes of load power of the microgrid and power values of the load under different conditions;

and obtaining the predicted value of the load and the predicted values corresponding to different types of energy demands according to the satisfying mode of the load power under different conditions and the power value of the load.

Further, the data matrix includes a historical data matrix, a real-time data matrix, and a predictive data matrix.

Further, the fuzzy cluster center matrix comprises a minimum fuzzy cluster center matrix, an average fuzzy cluster center matrix and a maximum fuzzy cluster center matrix.

Further, the types of the databases comprise a photovoltaic power generation database, an electricity storage device charging and discharging database, a heat storage device heat storage and release database, a cold storage device cold storage and release database and a load database.

Further, the load includes an electric load, a heat load, and a cold load.

Further, the load prediction value comprises an electric load P _E Thermal load P _H And a cooling load P _C Respectively expressed as:

wherein, P _CE1 、P _CE2 、P _CE3 Minimum, average and maximum values of the electrical load power, k _CE1 、k _CE2 、k _CE3 Weight coefficients, k, for the minimum, average and maximum values of the power of the electrical load, respectively _CH1 、k _CH2 、k _CH3 Weight coefficients, k, for the minimum, average and maximum thermal load power values, respectively _CC1 、k _CC2 、k _CC3 The weight coefficients of the minimum value, the average value and the maximum value of the cold load power are respectively.

Further, the energy demand includes a coal energy demand, a petroleum energy demand, a natural gas energy demand, and a nuclear energy demand.

Further, the energy demand includes coal energy demand C, petroleum energy demand O, natural gas energy demand G, and nuclear energy demand N, which are respectively expressed as:

C＝k _C1 P _E +k _C2 P _H +k _C3 P _C

O＝k _O1 P _E +k _O2 P _H +k _O3 P _C

G＝k _G1 P _E +k _G2 P _H +k _G3 P _C

N＝k _N1 P _E +k _N2 P _H +k _N3 P _C

wherein k is _C1 、k _C2 、k _C3 The consumption proportion of coal in the predicted values of electricity, heat and cold loads, k _O1 、k _O2 、k _O3 The consumption proportion of petroleum in the predicted values of electricity, heat and cold loads, k _G1 、k _G2 、k _G3 The consumption ratios of natural gas in the predicted values of electricity, heat and cold loads, k _N1 、k _N2 、k _N3 The consumption proportions of the nuclear energy in the predicted values of the electric load, the heat load and the cold load are respectively.

The invention also provides a microgrid energy demand prediction system, which comprises:

the data matrix construction module is used for constructing corresponding data matrixes according to different types of databases of the micro-grid;

the first matrix optimization module is used for constructing a fuzzy clustering center matrix according to the data matrix;

the second matrix optimization module is used for setting an initial value of the fuzzy clustering center matrix according to data change characteristics and acquiring an optimal value of the fuzzy clustering center matrix through iterative computation;

the load analysis module is used for obtaining the satisfying modes of the load power of the microgrid and the power values of the load under different conditions according to the optimal values of the fuzzy clustering center matrixes corresponding to all types of databases in the microgrid;

and the energy demand prediction module is used for obtaining the predicted value of the load and the predicted values corresponding to different types of energy demands according to the satisfying mode of the load power under different conditions and the power value of the load.

The invention also provides a computer terminal device comprising one or more processors and a memory. A memory coupled to the processor for storing one or more programs; when executed by the one or more processors, the one or more programs cause the one or more processors to implement the microgrid energy demand prediction method of any of the embodiments described above.

The invention also provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method for predicting the energy demand of a microgrid according to any one of the embodiments described above.

Compared with the prior art, the invention has the following beneficial effects:

the data stored in different types of databases in the microgrid mainly come from the configuration of the power supply capacities of three types of microgrid, namely water, wind and light, the time-space characteristics of the water, the wind and the light are independent from each other, but the capacity configurations of the microgrid are mutually influenced and restricted, and the configuration of the water and wind power supply capacities of the microgrid and a power distribution network is very complicated due to the transmission capacity, the voltage regulation requirement, the network loss control and the like of the microgrid and the power distribution network. According to the embodiment of the invention, the predicted values of the electric load, the heat load and the cold load of the subway station are determined by utilizing the block chain cooperation mechanism and the Byzantine fault-tolerant consensus requirement and considering the scene of multi-energy coupling, so that the energy requirements of coal, oil, natural gas and nuclear energy of the subway station are predicted. The uncertainty and randomness of the influence factors are comprehensively considered, the influence of various uncertain random and fuzzy events or parameters on the capacity configuration of the distributed photovoltaic power generation system of the microgrid is reduced, and the accuracy of predicting the energy demand of the microgrid is improved.

Drawings

In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a method for predicting energy demand of a microgrid according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a microgrid energy demand prediction system according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a computer terminal device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.

Due to the characteristics of great nonlinearity, time variation and uncertainty of an energy system, the research of energy demand prediction in recent years is focused on various emerging nonlinear methods from the conventional method. Common nonlinear methods include a chaotic time series method, a grey theory, a genetic algorithm, an artificial neural network algorithm and the like. The gray prediction is favored by students from the beginning because of its simplicity, the ability to use less data, and the way to process gray for systems with unknown structure. In recent years, various computing sciences have also come to be applied to the field of energy demand prediction, such as genetic algorithms and neural network algorithms. For example, genetic algorithms are used to predict the total amount of Turkish energy demand and indicate that it is more accurate than government models; predicting the requirements of Turkish for oil, natural gas and coal by using a genetic algorithm; predicting energy consumption of canadian residents by using a neural network model; the consumption of global clean energy is analyzed by a neural network; the neural network model is used for respectively predicting the power energy demand in a short term, a medium term and a long term; the chaotic time series model is used for modeling the total energy production amount in China, and the rationality of the model is analyzed.

In the method, the chaos time series model is very sensitive to the initial condition, so that the disturbance is too large when long-term prediction is carried out, and accurate prediction is difficult to obtain. The genetic algorithm has certain subjectivity because the parameter setting mainly depends on the experience of a modeler; and different genetic techniques have different parameters, so the universality of the algorithm is limited. Because data in the energy field tends to become larger, future values easily exceed the maximum value of a learning sample, and therefore the neural network algorithm is not suitable for long-term prediction. In the gray theory, the unknown information is gray-processed, and the factor acting on the energy system is time-varying, so that the accuracy is also reduced when long-term prediction is performed.

Compared with the traditional energy system with different energy sources independently operated, the multi-energy system can integrate different energy carriers such as gas, electricity, heat (heat and cold) energy and the like, realizes synchronous energy supply and improves the energy utilization efficiency. The regional comprehensive energy system takes combined cooling, heating and power as a core and can cooperatively schedule, operate and control natural gas and distributed energy in and among regions. The method has the advantages that the diversified energy requirements of the system are met, the cascade utilization of energy is realized, and the improvement of economic benefits and environmental benefits is an important direction for the development of future energy systems. The subway station takes a micro-grid as a core and has the characteristic of a typical multi-energy system. These all add to the difficulty and complexity of energy demand forecasting at subway stations.

A distributed photovoltaic power generation system in the form of a microgrid in a subway station is a system which has random and fuzzy uncertain events or parameters with complex relationships and interaction. Under the influence of various uncertain random and fuzzy events or parameters, the generated power and the generated energy of the distributed photovoltaic power generation system of the microgrid of the subway station become more random and fuzzy, and the capacity configuration of the distributed photovoltaic power generation system of the microgrid of the subway station is greatly influenced by the characteristics. In the past, the generated power and the generated energy of a micro-grid distributed photovoltaic power generation system of a subway station usually adopt a deterministic calculation method, and some of the systems also adopt an uncertain calculation method of probability analysis. The deterministic calculation method is generally used for calculating the generating power, the generating capacity and the installed capacity of the distributed photovoltaic power generation system of the micro-grid of the subway station under the condition that the water inflow and the flow of the small hydropower station, the sunlight intensity in an area and the wind speed are all determined, the influence of factors such as the voltage regulation requirement and the flexible control mode of the micro-grid of the subway station and a power distribution network is not considered, the calculation result is unique and deterministic, and the actual conditions of the generating power, the generating capacity and the installed capacity of the distributed photovoltaic power generation system of the micro-grid of the subway station cannot be reflected. The calculation method of probability analysis is generally to calculate the generated power, the generated energy and the installed capacity of the distributed photovoltaic power generation system of the micro-grid of the subway station under the condition that only single factors such as the water inflow and the flow of the small hydropower station, the sunlight intensity in an area, the wind speed and the like are assumed as uncertainty factors, and the calculation result is a probability value with a certain confidence level. Actually, the generated power, the generated energy and the installed capacity of the distributed photovoltaic power generation system of the subway station microgrid are influenced by various uncertain factors. Moreover, these influencing factors are typically random uncertainties or fuzzy uncertainties, or they are random and fuzzy uncertainties, often present as random and fuzzy uncertainty events or quantities. Therefore, the uncertainty and randomness of the influence factors are not considered comprehensively in the prior art of calculating the generating power, the generating capacity and the installed capacity of the micro-grid distributed photovoltaic power generation system of the subway station, and the applicability, the practicability and the applicability of the calculating method are difficult to meet.

Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a method for predicting energy demand of a microgrid according to an embodiment of the present invention. The embodiment of the invention provides a method for predicting the energy demand of a microgrid, which comprises the following steps:

and step S110, constructing a corresponding data matrix according to different types of databases of the microgrid. The types of the databases comprise a photovoltaic power generation database, an electricity storage device charging and discharging database, a heat storage device heat storage and release database, a cold storage device cold storage and release database and a load database. The data matrix comprises a historical data matrix, a real-time data matrix and a prediction data matrix.

And step S120, constructing a fuzzy clustering center matrix according to the data matrix. The fuzzy clustering center matrix comprises a minimum fuzzy clustering center matrix, an average fuzzy clustering center matrix and a maximum fuzzy clustering center matrix.

And step S130, setting an initial value of the fuzzy clustering center matrix according to the data change characteristics, and obtaining an optimal value of the fuzzy clustering center matrix through iterative computation.

And step S140, obtaining satisfying modes and load power values of the microgrid under different conditions according to the optimal values of the fuzzy clustering center matrixes corresponding to all types of databases in the microgrid.

And S150, obtaining a predicted value of the load and predicted values corresponding to different types of energy demands according to the satisfying mode of the load power under different conditions and the power value of the load. The load includes an electrical load, a thermal load, and a cold load.

For example, historical data in different types of databases of the microgrid is utilized to construct a cold, heat and electricity "source" and "load" data set of the subway station, wherein the cold, heat and electricity "source" and "load" data set comprise a photovoltaic power generation data set, a charging and discharging data set of an electricity storage device, a heat storage device heat storage and release data set, a cold storage device cold storage and release data set and a cold and heat and electricity load data set. And constructing a fuzzy clustering center matrix of the data set and a fuzzy clustering center matrix of the minimum power, the average power and the maximum power of the cold, heat and electricity sources and the load. By adopting a fuzzy clustering analysis method and an iterative calculation mode, the optimal value of a fuzzy C-mean clustering matrix is determined, and the optimal values of the fuzzy clustering center matrix of the minimum quantity, the average quantity and the maximum quantity of the active power output by the subway station microgrid photovoltaic power generation system, the active power charge and discharge power of the electric automobile, the charge and discharge power of the energy storage device, the heat storage and discharge power of the heat storage device, the cold storage and discharge of the cold storage device, the electric load power, the heat load power and the cold load power are determined. And determining the satisfying mode of the minimum value, the average value and the maximum value of the electric load power of the microgrid of the subway station and the power values of the cold, the heat and the electric loads under the multi-energy coupling by using the optimal values of the minimum value, the average value and the maximum fuzzy clustering center matrix of the cold, the heat and the electric power sources and the load power of the load. And determining the predicted values of the electric load, the heat load and the cold load of the subway station and determining the predicted values of the coal energy, the petroleum energy, the natural gas energy and the nuclear energy demand of the subway station by utilizing a block chain coordination mechanism and the Byzantine fault-tolerant consensus requirement and considering a scene of multi-energy coupling.

Aiming at the complementary characteristics of the cold, heat and electricity source and the charge power of the micro-grid of the subway station, the exchange quantity of the cold, heat and electricity with the external grid on the time scales of year, season, month, week, hour and the like is determined by combining the energy coupling relationship of the power grid, the heat supply grid and the natural gas grid. The influence of an energy storage device and energy storage on energy coupling and energy flow is researched, and an energy coupling rule on different energy flow paths such as 'inside-outside', 'source-charge', 'source-storage', 'storage-charge storage vehicle' and the like is revealed by establishing a flexible dynamic model. The energy demand prediction method for the subway station considering the cooperation of cold-hot electric coupling and a block chain is provided aiming at energy utilization modes such as light-heat (heating, hot water), external grid electricity-heat (cold, storage, vehicle), external grid heat-heat (cold, storage), natural gas (light, wind, water, waste heat) -electricity (heat, cold, storage), biomass-electricity, natural gas-electricity (heat, cold), waste heat-electricity (heat, cold), heat pump-heat (cold) and the like.

In some embodiments, the installed capacity of the small hydropower stations in the power supply capacity of the micro-grid of the water, wind and light subway stations is determined by the warehousing flow of the small hydropower stations, the installed capacity of the wind power plants is determined by the wind speed of the wind power plants, and the installed capacity of the photovoltaic power stations is determined by the sunlight intensity. The system is determined by the utilization rate of new energy, the generated energy, the utilization rate of power generation equipment and the annual utilization hours, is determined by the microgrid of a subway station, the transmission capacity of a power distribution network, the voltage regulation requirement, the network loss control and the like, and has great influence on the installed capacity of a photovoltaic power generation system in different time and space due to the sunshine intensity, the sunshine time, the sunshine shadow, the sunshine deflection angle, the uncertainty and the randomness of the sunshine deflection angle. The space-time characteristics of water, wind and light are independent from each other, but the capacity configurations of the water and wind power supplies are mutually influenced and restricted when the water, wind and light are integrated in the micro-grid of the subway station, and the capacity configurations of the water and wind power supplies of the micro-grid of the subway station become more complicated due to the power transmission capacity, voltage regulation requirements, network loss control and the like of the micro-grid of the subway station and a power distribution network. The method comprises the steps of calculating the probability and the average value of the small hydropower station warehousing flow, the wind speed of a wind power plant and the change of the sunlight intensity of a photovoltaic power station according to a normal distribution rule by adopting a probability analysis method, calculating the initial installed capacity values of the small hydropower station, the wind power plant and the photovoltaic power station, and reducing the installed capacity according to the occupation ratio of the initial installed capacity values of the small hydropower station, the wind power plant and the photovoltaic power station according to the voltage change limitation of the inside of a microgrid of the subway station and the access node of the microgrid of the subway station to a power distribution network.

In some embodiments, the method is directed to the construction of a photovoltaic power generation data matrix in a subway station microgrid. Acquiring data of multi-year photovoltaic power generation system output active power, sunshine intensity, sunshine duration, sunshine shadow, sunshine deflection angle and the like in the ith subway station microgrid from a historical database, a real-time data acquisition system and a future prediction system, and constructing a photovoltaic power generation history, real-time and prediction data matrix in the ith subway station microgrid through processing, calculation and analysis:

wherein the content of the first and second substances,

are photovoltaic power generation history, real-time and prediction data matrixes in the microgrid of the ith subway station, i =1,2 _MG ,N _MG The number of the micro-grids of the subway station. />

Respectively representing the historical photovoltaic power generation data matrix in the i-th subway station microgrid>

The jth element data set of active power, sunlight intensity, sunlight duration, sunlight shadow and sunlight deflection angle of the interior photovoltaic power generation system>

Respectively for the photovoltaic power generation real-time data matrix in the i-th subway station microgrid>

Active power, sunshine intensity, sunshine duration, sunshine shadow and sunshine of interior photovoltaic power generation systemThe angled data set, based on the measured value of the angle of deflection>

A data set of active power, sunshine intensity, sunshine duration, sunshine shadow and sunshine deflection angle of the photovoltaic power generation system,

are respectively:

/>

wherein the content of the first and second substances,

The jth of the active power, the sunshine intensity, the sunshine duration, the sunshine shadow and the sunshine deflection angle of the interior photovoltaic power generation systemData value of element period t, <' > greater or lesser>

The real-time data values of active power, sunshine intensity, sunshine duration, sunshine shadow and sunshine deflection angle time period t of the interior photovoltaic power generation system are judged and judged>

The prediction data values of the active power, the sunshine intensity, the sunshine duration, the sunshine shadow and the sunshine deflection angle of the photovoltaic power generation system in the period t are j =1,2 _PDi ,N _PDi The number of photovoltaic power generation historical data sets of the ith subway station microgrid is set; t =1,2,.. T, T is the number of time periods of daily operation of the microgrid of the subway station.

In some embodiments, the construction of the charge and discharge data matrix of the power storage device in the microgrid of the subway station comprises the following steps: acquiring data of the number of the electricity storage devices, the charging active power, the charging duration and the like in the i-th subway station microgrid from a historical database, a real-time data acquisition system and a future prediction system, and constructing a charging and discharging history, real-time and prediction data matrix of the electricity storage devices in the i-th subway station microgrid through processing, calculation and analysis:

wherein the content of the first and second substances,

respectively is a charging and discharging history, real-time and prediction data matrix of the power storage device in the microgrid of the ith subway station, i =1,2 _ME ,N _ME The number of the micro-grids of the subway station. />

Respectively in the ith subway station microgrid, charging and discharging history data matrix>

The jth element data set of the number of the electricity storage devices, the charging active power and the charging duration>

Charging and discharging real-time data matrix for the electricity storage device in the i-th subway station microgrid respectively>

A data set of the number of the electricity storage devices, the charging active power and the charging time,

mathematically, the following are respectively:

/>

wherein the content of the first and second substances,

respectively taking charge and discharge historical data matrix of the electricity storage device in the ith microgrid>

The number of the internal electricity storage devices,The charging active power, the data value of the jth element time interval t of the charging time length,

The real-time data values of the number of the rechargeable devices, the charging active power and the charging time period t are stored in the accumulator>

The predicted data values of the number of the power storage devices, the charging active power and the charging time period t are j =1,2 _PDEi ,N _PDEi The number of the charging and discharging historical data sets of the electricity storage device of the ith microgrid is set; t =1,2,.. T, T is the number of time periods during which the microgrid day is operating.

In some embodiments, the construction of the heat storage and release data matrix of the heat storage device in the microgrid of the subway station comprises the following steps: acquiring data of the quantity, the heat storage active power, the heat storage duration and the like of the heat storage devices in the i-th subway station microgrid from a historical database, a real-time data acquisition system and a future prediction system, and constructing a heat storage and release history, real-time and prediction data matrix of the heat storage devices in the i-th subway station microgrid through processing, calculation and analysis:

wherein the content of the first and second substances,

respectively storing and releasing heat history, real-time and prediction data matrixes i =1,2, N in the heat storage device in the microgrid of the ith subway station _MH ,N _MH The number of the micro-grids of the subway station. />

Respectively storing and releasing heat history data matrixes for the heat storage device in the microgrid of the ith subway station>

The jth element data set of the number of the heat storage devices, the heat storage active power and the heat storage duration is combined in a manner of combining the heat storage devices and the heat storage duration>

Respectively storing and releasing heat of a heat storage device in the microgrid of the ith subway station>

The data set of the quantity of the heat storage devices, the heat storage active power and the heat storage duration,

Data sets of the number of the inner heat storage devices, the heat storage active power and the heat storage duration>

Mathematically, the following are respectively:

wherein the content of the first and second substances,

respectively performing heat accumulation and release historical data matrix on the heat accumulation device in the ith microgrid>

The number of the heat storage devices, the heat storage active power and the data value of the jth element time interval t of the heat storage duration,

The real-time data values of the number of the heat storage devices, the heat storage active power and the heat storage duration t are judged and judged>

The predicted data values of the number of the heat storage devices, the heat storage active power and the heat storage duration in the time period t are j =1,2 _PDHi ,N _PDHi The number of heat storage historical data sets for the heat storage device of the ith microgrid; t =1,2,.. T, T is the number of time periods during which the microgrid day is operating.

In some embodiments, the method is directed to the construction of a cold storage and discharge data matrix of a cold storage device in a microgrid of a subway station. Acquiring data of the number of cold storage devices, cold storage active power, cold storage duration and the like in the i-th subway station micro-grid from a historical database, a real-time data acquisition system and a future prediction system, and constructing a cold storage and release history, real-time and prediction data matrix of the cold storage devices in the i-th subway station micro-grid through processing, calculation and analysis:

wherein the content of the first and second substances,

respectively storing and releasing cold history, real-time and prediction data matrixes of the cold storage device in the microgrid of the ith subway station, i =1,2 _MC ,N _MC The number of the micro-grids of the subway station. />

Respectively storing and releasing cold historical data matrixes for the cold storage device in the microgrid of the ith subway station>

The jth element data set of the number of the cold storage devices, the active power of the cold storage and the cold storage duration in the cold storage device, and/or the cold storage duration>

Respectively storing and releasing cold for the cold storage device in the microgrid of the ith subway station>

The data set of the number of the cold storage devices, the active power of cold storage and the cold storage time,

mathematically, the following are respectively:

wherein the content of the first and second substances,

are respectively the ith micro-currentCold storage history data matrix of cold storage and release device in net>

The number of cold storage devices, the active power of cold storage, and the data value of the jth element time interval t of the cold storage time,

respectively storing and releasing cold historical data matrixes for the cold storage device in the ith microgrid>

The real-time data values of the number of the cold storage devices, the active power of the cold storage and the cold storage time period t are stored in the cold storage device and are then judged>

The number of cold storage devices, cold storage active power and the predicted data value of the cold storage time interval t, j =1,2 _PDCi ,N _PDCi Storing the number of cold release historical data sets for a cold storage device of the ith microgrid; t =1,2,.. T, T is the number of time periods during which the microgrid day is operating.

In some embodiments, the method is directed to the construction of a microgrid load data matrix of a subway station. Acquiring data of electric load power, heat load power, cold load power, indoor temperature, outdoor temperature and the like in the i-th subway station microgrid from a historical database, a real-time data acquisition system and a future prediction system, and constructing a load historical, real-time and prediction data matrix in the i-th subway station microgrid through processing, calculation and analysis:

/>

wherein the content of the first and second substances,

respectively are load history, real-time and prediction data matrixes in the microgrid of the ith subway station, i =1,2 _MG ,N _MG The number of the micro-grids of the subway station. />

Respectively is the load historical data matrix in the micro-grid of the ith subway station>

The jth element data set of the internal electric load power, the heat load power, the cold load power, the indoor temperature and the outdoor temperature is judged and judged>

Respectively is the load real-time data matrix in the microgrid of the ith subway station>

Data set of interior electric load power, heat load power, cold load power, indoor temperature and outdoor temperature, and/or>

Data sets of internal electrical load power, thermal load power, cold load power, indoor temperature, outdoor temperature,

mathematically, the following are respectively:

wherein the content of the first and second substances,

respectively for load history data matrix in the microgrid of the ith subway station>

The data value of the jth element time interval t of the interior electric load power, the heat load power, the cold load power, the indoor temperature and the outdoor temperature is judged and judged>

Real-time data values of the internal electrical load power, the thermal load power, the cold load power, the indoor temperature and the outdoor temperature time period t,

Predicted data values of time periods t of the indoor temperature, the outdoor temperature, the indoor load power, the heat load power, the cold load power, j =1,2 _PDi ,N _PDi The number of the load historical data sets of the micro-grid of the ith subway station is the number of the load historical data sets of the micro-grid of the ith subway station; t =1,2,.. T, T is the number of time periods of daily operation of the microgrid of the subway station.

In some embodiments, the extraction of the "source" and "load" power characteristics for the microgrid of a subway station comprises the following steps:

(1) And (5) constructing a fuzzy clustering center matrix. Adopting a fuzzy clustering analysis method to construct a fuzzy clustering center matrix of the data set: c _i ＝{C _i1 ,C _i2 ,C _i3 },(i＝1,2,...,N _MG )，C _i1 、C _i2 、C _i3 The fuzzy clustering center matrixes are minimum quantity, average quantity and maximum quantity respectively.

(2) And initializing a fuzzy clustering center matrix. Setting initial values of a minimum quantity, an average quantity and a maximum quantity fuzzy clustering center matrix. The method is characterized in that the average value of the output active power of the photovoltaic power generation system of the i-th subway station microgrid, the charge and discharge active power of the electric automobile, the charge and discharge active power of the energy storage device, the electric load power, the heat load power and the cold load power in many years is P _MAPVi 、P _MAEVi 、P _MADSi 、P _MAEi 、P _MAHi 、P _MACi Then, the minimum, average and maximum fuzzy clustering center matrix initial values of the output active power, the charging and discharging active power of the electric automobile, the charging and discharging active power of the energy storage device, the electric load power, the heat load power and the cold load power of the i-th subway station microgrid photovoltaic power generation system are respectively as follows:

wherein k is _MAPV1 ＝k _MAEV1 ＝k _MADS1 ＝k _MAE1 ＝k _MAH1 ＝k _MAC1 ＝0.2

k _MAPV2 ＝k _MAEV2 ＝k _MADS2 ＝k _MAE2 ＝k _MAH2 ＝k _MAC2 ＝1.0

k _MAPV3 ＝k _MAEV3 ＝k _MADS3 ＝k _MAE3 ＝k _MAH3 ＝k _MAC3 ＝1.5

The initial value of the fuzzy clustering center matrix is

(3) And (4) performing iterative calculation on the optimal fuzzy clustering matrix and the optimal fuzzy clustering center matrix. And determining the optimal value of a fuzzy C-mean clustering matrix and the optimal value of the minimum, average and maximum fuzzy clustering center matrix of the output active power of the i-th subway station microgrid photovoltaic power generation system, the charge and discharge active power of the electric automobile, the charge and discharge active power of the energy storage device, the electric load power, the heat load power and the cold load power by adopting a fuzzy clustering analysis method and an iterative calculation mode.

Aiming at the micro-grid of the ith subway station, the optimal value of the fuzzy C-mean clustering matrix is as follows:

the minimum, average and maximum fuzzy clustering center matrix of the ith subway station microgrid photovoltaic power generation system output active power, electric vehicle charging and discharging active power, the energy storage device charging and discharging active power, electric load power, heat load power and cold load power have the following optimal values:

wherein, P _CDSEi1 、P _CDSEi2 、P _CDSEi3 Respectively are the optimal values of the fuzzy clustering center matrix P of the minimum, average and maximum charge-discharge power of the i-th subway station microgrid power storage device _CDSHi1 、P _CDSHi2 、P _CDSHi3 Respectively are the optimal values of the fuzzy clustering center matrix of the minimum charge-discharge power, the average charge and the maximum charge-discharge power and the average charge of the i-th subway station micro-grid heat storage device, P _CDSCi1 、P _CDSCi2 、P _CDSCi3 Respectively are the optimal values of the minimum charge-discharge power, the average charge and the maximum fuzzy clustering center matrix, P, of the i-th subway station micro-grid cold storage device _CEi1 、P _CEi2 、P _CEi3 Respectively are the optimal values of the fuzzy clustering center matrix of the minimum power load, the average power load and the maximum power load of the i-th subway station microgrid, P _CHi1 、P _CHi2 、P _CHi3 Respectively are the optimal values of the fuzzy clustering center matrix of the minimum, average and maximum heat load power of the i-th subway station microgrid, P _CCi1 、P _CCi2 、P _CCi3 And respectively obtaining the optimal values of the minimum cold load power, the average cold load power and the maximum fuzzy clustering center matrix of the i-th subway station microgrid.

The iterative computation of the optimal fuzzy clustering matrix and the optimal fuzzy clustering center matrix in the steps comprises the following specific steps:

(a) Setting blur coefficients

The iterative computation end decision error value e =0.001 is set.

(b) Using a random function at [0,1]Randomly generating random numbers to initialize a fuzzy clustering matrix U ⁽⁰⁾ 。

(c) The number of iterations t =1 is set.

(d) Computing a fuzzy clustering matrix U in the t-th iteration ^(t) Element value of (2), element value

The iterative update formula is:

where d () is a distance function.

(e) Computing fuzzy clustering center matrix C in the t-th iteration ^(t) Element value of (1), minimum, average, maximum fuzzy cluster center matrix element value

The iterative update formula is respectively:

wherein i =1,2., c, j =1,2., m.

(f) If it is

The iterative calculation ends, otherwise let t = t +1 and go to step (d).

In some embodiments, the following is included for source power calculations that consider blockchain coordination:

(1) Calculation of the electric power injected by the subway station from the large power grid: the electric power injected from the large power grid by the ith subway station micro-grid depends on the electric load demand in the micro-grid, the time-interval electric price and the like, and the time-interval electric price and the electric load demand are assumed to randomly change along with normal distribution.

In N _MGi Price of electricity p in individual history data _MGij At the j time interval of electricity price

The probability of (c) is:

wherein the content of the first and second substances,

injecting electric power P from large power grid into block node of micro-power grid of ith subway station _MGij In the jth power interval

The probability of (c) is:

ensuring the fault-tolerant consensus requirement of Byzantine, wherein the frequency of injecting electric power from the large power grid into the block node of the micro power grid of the ith subway station is more than that of injecting electric power from the large power grid

The probability of (c) is:

wherein N is _MGNi Is at N _MGi The number of times the i-th subway station microgrid injected electric power from the large power grid in the historical data.

In the prediction period, the predicted value of the electric power injected from the large power grid by the ith subway station micro-grid is as follows:

wherein p is _MGij The time period electricity price.

(2) Calculating the CCHP power generation power of the natural gas combined cooling heating and power supply system of the subway station: the CCHP power generation power of the natural gas, heat and power triple supply system of the ith subway station microgrid depends on the power load demand, the time period price and the like in the microgrid, and the time period price and the power, heat and cold load demands are assumed to be randomly changed according to normal distribution.

Assuming that the natural gas power generation cost is c _Gi In N, at _MGi Electricity price c in individual history data _Gi1 ≤p _MGi <c _Gi2 The probability at electricity price is:

k _Gpi ＝F(c _G1i )-F(c _G2i )

wherein the content of the first and second substances,

natural gas, heating and power combined supply system CCHP power generation P for ith subway station microgrid _Gij In the jth power interval

The probability of (c) is:

the requirement of Byzantine fault tolerance consensus is ensured, the frequency of the CCHP power generation of the i-th subway station microgrid natural gas combined cooling heating and power supply system is greater than that of the CCHP power generation

The probability of (c) is:

wherein N is _GNi Is at N _MGi And the frequency of the natural gas, heat and power triple supply system CCHP in the ith subway station micro-grid in the historical data.

In the prediction period, the predicted value of the CCHP power generation power of the natural gas cooling, heating and power triple supply system of the ith subway station microgrid is as follows:

wherein, P _GNEi The rated value of the CCHP power generation power of the natural gas combined cooling heating and power supply system.

(3) Calculating the CCHP heating power and the cooling power of the natural gas combined cooling heating and power system of the subway station: the heating power and the cooling power of the natural gas cooling, heating and power triple supply system CCHP of the ith subway station micro-grid are as follows:

P _GHi ＝k _GHi P _GEi

P _GCi ＝k _GCi P _GEi

wherein, P _GHi And k _GHi 、P _GCi And k _GCi The heat-generating power and the cooling power of the CCHP system and the regulation coefficient of the natural gas combined cooling heating and power system are provided.

(4) Calculating the charging and discharging power of a power storage device in a microgrid of a subway station: the charging power and the discharging power of the electricity storage device in the microgrid of the subway station of the ith subway station depend on the electric load demand in the microgrid, the time-interval electricity price and the like. In the prediction period, the predicted value P of the charging and discharging power of the i-th subway station microgrid storage device _DSEi Comprises the following steps:

wherein k is _DSECij 、k _DSESij Respectively the charging and discharging efficiency and the charging and discharging state, k, of the i-th subway station micro-grid power storage device _DSESij =1 denotes in charged state, k _DSESij And =1 indicates a discharge state. k is a radical of _DSEpij 、k _DSEPij 、k _DSENij The micro-grid power storage devices of the ith subway station are respectively arranged at N _MGi Charge and discharge electricity price p in individual history data _MGij At the j time interval of electricity price

Probability of (D), charging/discharging power P _DSEij Is in the jth power interval->

Has a probability of being greater than or equal to>

Probability of (c):

wherein N is _DSENi Is at N _MGi And (4) the number of charging and discharging times of the micro-grid of the ith subway station in the historical data.

(5) Calculating the stored electric power of the heat storage device in the microgrid of the subway station: the heat storage power and the heat release power of the heat storage device in the microgrid of the ith subway station microgrid depend on the heat load demand in the microgrid and the like. In the prediction period, the heat storage and discharge power prediction value P of the i-th subway station micro-grid heat storage device _DSHi Comprises the following steps:

P _DSHi ＝k _DSHpij k _DSHPij k _DSHNij k _DSHCij k _DSHSij P _CDSHij

wherein k is _DSHCij 、k _DSHSij Respectively storing and discharging heat efficiency and heat storage and discharge state, k, of the i-th subway station micro-grid heat storage device _DSHSij K denotes a state of heat storage, k _DSHSij And =1 denotes an exothermic state. k is a radical of _DSHpij 、k _DSHPij 、k _DSHNij The i-th subway station micro-grid heat storage devices are respectively arranged at N _MGi Storing the electricity price p of heat release in the history data _MGij At the j time interval of electricity price

Probability of (3), heat storage and discharge power P _DSHij Is in the jth heating power interval->

Has a probability of storing heat greater than &>

Probability of (c):

wherein N is _DSHNi Is at N _MGi And (4) storing the heat storage and release times of the micro-grid of the ith subway station in the historical data.

(6) Calculating the storage and discharge cold power of a cold storage device in the micro-grid of the subway station: the cold storage power and the cold discharge power of a cold storage device in the microgrid of the ith subway station microgrid depend on the heat load requirement in the microgrid and the like. In the prediction period, the storage and discharge cold power prediction value P of the i-th subway station micro-grid cold storage device _DSCi Comprises the following steps:

P _DSCi ＝k _DSCpi k _DSCPi k _DSCNi k _DSCCi k _DSCSi P _CDSCi2

wherein k is _DSCCij 、k _DSCSij The cold storage efficiency and the cold storage state, k, of the i-th subway station micro-grid cold storage device are respectively _DSCSij =1 denotes in cold storage state, k _DSCSij And =1 denotes a state of cooling. k is a radical of _DSCpij 、k _DSCPij 、k _DSCNij The micro-grid cold storage devices of the ith subway station are respectively arranged at N _MGi Storing the cold time electricity price p in the history data _MGij At the j time interval of electricity price

Probability of (2), cold storage power P _DSCij Is in the jth heating power interval->

Has a probability that the number of cold stores is greater than >>

Probability of (c):

wherein N is _DSCNi Is at N _MGi And (4) storing and releasing cold times of the micro-grid of the ith subway station in the historical data.

In some embodiments, the power calculation for the multi-energy coupling includes the following:

(1) Electric power calculation considering multi-energy coupling: under the multi-energy coupling, the minimum value, the average value and the maximum value of the electric load power of the micro-grid of the ith subway station are respectively satisfied in the following modes:

P _CEi1 ＝k _MGi1 P _MGi1 +k _GEi1 P _GEi1 +k _DSEi1 P _DSEi1 +k _PVi3 P _PVi3 +k _EVi1 k _EVSi P _EVi1

P _CEi2 ＝k _MGi2 P _MGi2 +k _GEi2 P _GEi2 +k _DSEi2 P _DSEi2 +k _PVi3 P _PVi3 +k _EVi2 k _EVSi P _EVi2

P _CEi3 ＝k _MGi3 P _MGi3 +k _GEi3 P _GEi3 +k _DSEi3 P _DSEi3 +k _PVi3 P _PVi3 +k _EVi3 k _EVSi P _EVi3

wherein, P _MGi1 、P _MGi2 、P _MGi3 Respectively injecting minimum, average and maximum power, P, from the main power grid to the micro-grid of the ith subway station _GEi1 、P _GEi2 、P _GEi3 The minimum value, the average value and the maximum value of the CCHP power generation power of the natural gas, cooling and power triple supply system of the i-th subway station are respectively the P _DSEi1 、P _DSEi2 、P _DSEi3 Respectively is the minimum value, the average value and the maximum value of the charging and discharging power of the i-th subway station micro-grid power storage device, P _PVi3 The maximum value of the generated power of the photovoltaic power generation system of the micro-grid of the ith subway station is obtained; p is _EVi1 、k _EVSi The minimum value and the charge-discharge state k of the charge-discharge power of the electric automobile of the micro-grid of the ith subway station are respectively _EVSi =1 denotes in a charged state, k _EVSi =0 represents being in a discharge state; p _EVi2 、P _EVi3 The average value and the maximum value of the charging and discharging power of the electric automobile of the microgrid of the ith subway station are respectively; k is a radical of _MGi1 、k _MGi2 、k _MGi3 Adjusting coefficients, k, of minimum, average and maximum values of power injected from the main power grid to the i-th subway station microgrid respectively _DSEi1 、k _DSEi2 、k _DSEi3 The adjustment coefficients k are the minimum value, the average value and the maximum value of the charging and discharging power of the i-th subway station microgrid power storage device respectively _GEi1 、k _GEi2 、k _GEi3 The adjustment coefficients k are the minimum value, the average value and the maximum value of the CCHP power generation power of the natural gas, heating and power triple supply system of the ith subway station microgrid respectively _PVi1 、k _PVi2 、k _PVi3 Adjustment coefficients k of the minimum value, the average value and the maximum value of the generated power of the i-th subway station micro-grid photovoltaic power generation system _EVi1 、k _EVi2 、k _EVi3 Respectively is the minimum value, the average value and the sum of the charging and discharging power of the micro-grid electric automobile of the ith subway stationAdjustment factor of the maximum value.

(2) Thermal power calculation considering the multi-functional coupling: under the multi-energy coupling, the minimum value, the average value and the maximum value of the heat load power of the microgrid of the ith subway station are respectively satisfied in the following modes:

P _CHi1 ＝k _EHi1 P _EHi1 +k _GHi1 P _GHi1 +k _DSHi1 P _DSHi1 +k _HSi1 P _HSi1 +k _PHi1 P _PHi1

P _CHi2 ＝k _EHi2 P _EHi2 +k _GHi2 P _GHi2 +k _DSHi2 P _DSHi2 +k _HSi2 P _HSi2 +k _PHi2 P _PHi2

P _CHi3 ＝k _EHi3 P _EHi3 +k _GHi3 P _GHi3 +k _DSHi3 P _DSHi3 +k _HSi3 P _HSi3 +k _PHi3 P _PHi3

wherein, P _EHi1 、P _EHi2 、P _EHi3 Respectively is the minimum value, the average value and the maximum value P of the heating power of the micro-grid electric heating equipment/system of the ith subway station _GHi1 、P _GHi2 、P _GHi3 Respectively is the minimum value, the average value and the maximum value P of the heating power of the CCHP system of the natural gas, heating and power triple supply system of the i-th subway station microgrid _DSEi1 、P _DSEi2 、P _DSEi3 Respectively is the minimum value, the average value and the maximum value of the charging and discharging power of the i-th subway station micro-grid power storage device, P _HSi1 、P _HSi2 、P _HSi3 Respectively is the minimum value, the average value and the maximum value of the heating power of the ground source/air source/water source heat pump unit of the microgrid of the ith subway station, P _PHi1 、P _PHi2 、P _PHi3 Respectively is the minimum value, the average value, the maximum value, k, of the heating power of the micro-grid photo-thermal system of the ith subway station _EHi1 、k _EHi2 、k _EHi3 The adjustment coefficients are the minimum value, the average value and the maximum value of the heating power of the i-th subway station micro-grid electric heating equipment/system respectively, k _GHi1 、k _GHi2 、k _GHi3 CCHP system of natural gas, heating and power triple generation system for i-th subway station microgridAdjustment coefficients of the minimum, average, maximum values of the thermal power, k _DSEi1 、k _DSEi2 、k _DSEi3 Adjustment coefficients k of the minimum value, the average value and the maximum value of the charge-discharge power of the i-th subway station microgrid power storage device respectively _HSi1 、k _HSi2 、k _HSi3 The adjustment coefficients k of the minimum value, the average value and the maximum value of the heating power of the ground source/air source/water source heat pump unit of the microgrid of the ith subway station are respectively _PHi1 、k _PHi2 、k _PHi3 The adjusting coefficients are respectively the minimum value, the average value and the maximum value of the heating power of the micro-grid photo-thermal system of the ith subway station.

(3) Cold power calculation considering the multi-energy coupling: under the multi-energy coupling, the minimum value, the average value and the maximum value of the cold load power of the micro-grid of the ith subway station are respectively satisfied in the following modes:

P _CCi1 ＝k _ECi1 P _ECi1 +k _GCi1 P _GCi1 +k _DSCi1 P _DSCi1 +k _CSi1 P _CSi1

P _CCi2 ＝k _ECi2 P _ECi2 +k _GCi2 P _GCi2 +k _DSCi2 P _DSCi2 +k _CSi2 P _CSi2

P _CCi3 ＝k _ECi3 P _ECi3 +k _GCi3 P _GCi3 +k _DSCi3 P _DSCi3 +k _CSi3 P _CSi3

wherein, P _ECi1 、P _ECi2 、P _ECi3 Respectively is the minimum value, the average value and the maximum value P of the refrigeration power of the micro-grid electric refrigeration equipment/system of the ith subway station _GCi1 、P _GCi2 、P _GCi3 Respectively is the minimum value, the average value and the maximum value P of the refrigeration power of the natural gas cold-electricity triple supply system CCHP of the i-th subway station micro-grid _DSCi1 、P _DSCi2 、P _DSCi3 Respectively is the minimum value, the average value and the maximum value of the charging and discharging power of the i-th subway station micro-grid power storage device, P _CSi1 、P _CSi2 、P _CSi3 Respectively is the minimum value, the average value and the maximum value of the refrigeration power of the ground source/air source/water source heat pump unit of the microgrid of the ith subway station,k _ECi1 、k _ECi2 、k _ECi3 respectively is the minimum value, the average value and the adjustment coefficient of the maximum value, k, of the refrigeration power of the i-th subway station micro-grid electric refrigeration equipment/system _GCi1 、k _GCi2 、k _GCi3 Respectively is the adjustment coefficient k of the minimum value, the average value and the maximum value of the refrigeration power of the natural gas cold-electricity triple supply system CCHP of the ith subway station microgrid _DSCi1 、k _DSCi2 、k _DSCi3 The adjustment coefficients k are the minimum value, the average value and the maximum value of the charging and discharging power of the i-th subway station microgrid power storage device respectively _CSi1 、k _CSi2 、k _CSi3 And the adjusting coefficients are respectively the minimum value, the average value and the maximum value of the refrigeration power of the ground source/air source/water source heat pump unit of the i-th subway station microgrid.

In some embodiments, the following are included for the subway station electric, thermal, and cold load prediction:

under the coordination of a block chain, a multi-energy coupling scene is considered, and the predicted values of the electric load, the heat load and the cold load of the subway station are respectively as follows:

wherein, P _CE1 、P _CE2 、P _CE3 Minimum, average and maximum values of the electrical load power, k _CE1 、k _CE2 、k _CE3 Weight coefficients, k, for the minimum, average and maximum values of the power of the electrical load, respectively _CH1 、k _CH2 、k _CH3 Weight coefficients, k, for the minimum, average and maximum thermal load power values, respectively _CC1 、k _CC2 、k _CC3 Respectively minimum power for cold loadValue, average value, and weight coefficient of maximum value.

In some embodiments, the prediction of the demand for coal, oil, gas, nuclear energy in the subway station comprises the following contents:

under the coordination of block chains, considering the scene of multi-energy coupling, the predicted values of the energy demands of coal, oil, natural gas and nuclear energy of the subway station are respectively as follows:

C＝k _C1 P _E +k _C2 P _H +k _C3 P _C

O＝k _O1 P _E +k _O2 P _H +k _O3 P _C

G＝k _G1 P _E +k _G2 P _H +k _G3 P _C

N＝k _N1 P _E +k _N2 P _H +k _N3 P _C

wherein C, O, G, N is the predicted value of the energy demand of the coal, oil, natural gas and nuclear energy of the subway station, k _C1 、k _C2 、k _C3 The consumption proportion of coal in the predicted values of electricity, heat and cold loads, k _O1 、k _O2 、k _O3 The consumption proportion of petroleum in the predicted values of electricity, heat and cold loads, k _G1 、k _G2 、k _G3 The consumption ratios of natural gas in the predicted values of electricity, heat and cold loads, k _N1 、k _N2 、k _N3 The consumption proportions of the nuclear energy in the predicted values of the electric load, the heat load and the cold load are respectively.

By utilizing the subway station energy demand prediction method considering the cold-hot electric coupling and block chain cooperation, which is provided by the invention, the energy coupling relation between the large-scale urban subway station and the power grid, the heat supply network and the natural gas network is clarified, and the exchange quantity of the cold-hot electric with the external network on the time scales of year, season, month, week, hour and the like is determined. The method comprises the steps of determining the minimum value, the average value and the maximum value of the electric load power of the micro-grid of the subway station under multi-energy coupling, determining the power values of cold, heat and electric loads of the subway station, determining the predicted values of the electric, heat and cold loads of the subway station, determining the predicted values of the coal, petroleum, natural gas and nuclear energy requirements of the subway station, providing theoretical guidance for capacity configuration of cold and heat power sources of the water-wind-light subway station, power generation output prediction and operation scheduling, and providing necessary technical support for distributed new energy power generation and intelligent power grid scheduling operation.

Referring to fig. 2, fig. 2 is a schematic structural diagram of a microgrid energy demand prediction system according to an embodiment of the present invention. The same portions of this embodiment as those of the above embodiments will not be described herein again. The microgrid energy demand prediction system provided by the embodiment comprises:

the data matrix construction module 210 is configured to construct a corresponding data matrix according to different types of databases of the microgrid.

And the first matrix optimization module 220 is configured to construct a fuzzy clustering center matrix according to the data matrix.

The second matrix optimization module 230 is configured to set an initial value of the fuzzy clustering center matrix according to the data change characteristic, and obtain an optimal value of the fuzzy clustering center matrix through iterative computation.

And the load analysis module 240 is configured to obtain the satisfying modes of the load power of the microgrid and the power values of the load under different conditions according to the optimal values of the fuzzy clustering center matrixes corresponding to all types of databases in the microgrid.

The energy demand prediction module 250 is configured to obtain a predicted value of the load and predicted values corresponding to different types of energy demands according to the satisfying mode of the load power under different conditions and the power value of the load.

In a specific embodiment, the data matrix construction module 210 collectively obtains data such as the annual daily radial flow and the warehousing flow of the hydropower station drainage basin in the microgrid of the subway station from the annual history and the real-time data, obtains data such as the annual daily wind speed and the wind direction of the wind farm, obtains data such as the annual daily sunlight intensity and the sunlight deflection angle of the photovoltaic power station, and constructs a data matrix through processing, calculation and analysis:

wherein the content of the first and second substances,x _i1 、x _i2 、x _i3 、x _i4 、x _i5 、x _i6 the unit of the sunlight deflection angle is as follows: cubic meter, cubic meter per second, degree, watt per square meter, degree. The number of data samples N =10 × 365, the number of data sets N =6, i =1, 2.

The first matrix optimization module 220 adopts a fuzzy clustering analysis method, selects c =3, and constructs a fuzzy clustering center matrix of the data set: c = { C ₁ ,C ₂ ,C ₃ In which C is _i ＝{C _i1 ,C _i2 ,...,C _im }(i＝1,2,...,c)，C ₁ 、C ₂ 、C ₃ The fuzzy clustering center matrixes are minimum quantity, average quantity and maximum quantity respectively.

The second matrix optimization module 230 sets initial values of a minimum, an average and a maximum fuzzy clustering center matrix according to the capacity configuration principle of the distributed photovoltaic power generation system in the microgrid of the subway station and according to data change characteristics of daily diameter flow, warehousing flow, wind speed, wind direction, sunlight intensity, sunlight deflection angle and the like. Assuming that the average value of runoff, warehousing flow, wind speed, wind direction, sunlight intensity and sunlight deflection angle for many years is J _MJLL 、Q _MJLL 、v _M 、A _MW 、E _MPV 、A _MPV Then, the initial values of the minimum, average and maximum fuzzy clustering center matrixes are set as follows:

wherein the content of the first and second substances, k is a radical of _MJLL1 ＝k _MI1 ＝k _MW1 ＝k _MAW1 ＝k _MPV1 ＝k _MAPV1 ＝0.2

k _MJLL2 ＝k _MI2 ＝k _MW2 ＝k _MAW2 ＝k _MPV2 ＝k _MAPV2 ＝1.0

k _MJLL3 ＝k _MI3 ＝k _MW3 ＝k _MAW3 ＝k _MPV3 ＝k _MAPV3 ＝1.5

The initial value of the fuzzy clustering center matrix is

A process and method for iterative computation of an optimal fuzzy cluster matrix and an optimal fuzzy cluster center matrix. And determining the optimal value of a fuzzy C-mean clustering matrix and the optimal values of a minimum, average and maximum fuzzy clustering center matrix by adopting a fuzzy clustering analysis method and an iterative calculation mode.

The optimal value of the fuzzy C-means clustering matrix is as follows:

the optimal values of the minimum, average and maximum fuzzy clustering center matrixes are as follows:

wherein, J _CJJL1 、J _CJLL2 、J _CJLL3 Respectively the optimal values of the fuzzy clustering center matrix of the minimum amount, the average amount and the maximum amount of the runoff amount, Q _CI1 、Q _CI2 、Q _CI3 Respectively are the optimal values of the fuzzy clustering center matrix of the minimum quantity, the average quantity and the maximum quantity of the flow in storage, v _CW1 、v _CW2 、v _CW3 Respectively the optimal values of the fuzzy clustering center matrix of the minimum, average and maximum wind speeds, A _CAW1 、A _CAW2 、A _CAW3 Respectively the wind direction minimum, average and maximum modesOptimal value of the fuzzy clustering center matrix, E _CPV1 、E _CPV2 、E _CPV3 Respectively the optimal values of the fuzzy clustering center matrix of the minimum amount, the average amount and the maximum amount of the sunlight intensity, A _CAPV1 、A _CAPV2 、A _CAPV3 Respectively are the optimal values of the sunshine deflection angle minimum quantity, the average quantity and the maximum fuzzy clustering center matrix.

The iterative computation comprises the following steps:

(a) Setting blur coefficients

The iterative computation end decision error value e =0.001 is set.

(c) The number of iterations t =1 is set.

The iterative update formula is:

where d () is a distance function.

The iterative update formula is respectively:

wherein i =1,2., c, j =1,2., m.

(f) If it is

The iterative computation ends, otherwise let t = t +1 and go to step (d).

The average value of the warehousing flow of the small hydropower stations in the micro-grid of the subway station not only considers the average quantity of years, but also considers the increment of the warehousing flow caused by the increase of the runoff, and the calculation formula is as follows:

/>

wherein k is _JLL And the influence coefficient of the runoff volume on the warehousing volume is shown.

Considering the influence of wind direction, the calculation formula of the wind speed average value of the small wind power station in the micro-grid of the subway station is as follows:

wherein k is _WX 、k _WA 、k _WD The weight coefficients k are respectively the minimum, average and maximum wind speed _AV Is the influence coefficient of the wind direction on the output power of the wind turbine generator.

Calculating the average value of the sunlight intensity of the photovoltaic power station in the microgrid of the subway station:

wherein k is _PVX 、k _PVA 、k _PVD Weight coefficients for the minimum, average and maximum solar intensity, k _AE The influence coefficient of the sunlight deflection angle on the output power of the photovoltaic power generation panel is shown.

The capacity allocation of the small hydropower station generator set not only considers the restriction of natural conditions such as warehousing flow and the like, but also considers the demand of local load power of a micro-grid of a subway station and the allowable injection power of a power distribution network, and the installed capacity of the small hydropower station is as follows:

P _SH ＝min(0.0098HQ _I ,max(P _XD +P _DD ,P _KD +P _DD ))

wherein H is the water head of the small hydropower station, k _GH Weight coefficient P in distribution of local load power of micro-grid of subway station and allowable injection power of distribution network for small hydropower station _DD Respectively allowing the size of the injection power, P, of the micro-grid of the subway station for the distribution network _XD 、P _KD Respectively the heavy and heavy load demands.

The capacity configuration of the small wind turbine generator of the wind power plant needs to consider the restriction of natural conditions such as wind speed and the like, also needs to consider the demand of local load power of a micro grid of a subway station and the allowable injection power of a power distribution network, and the installed capacity of the wind power plant is as follows:

wherein the content of the first and second substances,

N _GW maximum and minimum installed number of wind farm allowed, k _W2 、k _W1 、k _W0 And the coefficient is the correlation coefficient of the wind turbine generator output power and the wind speed.

The capacity configuration of the photovoltaic power generation panel of the photovoltaic power station not only considers the restriction of natural conditions such as sunlight intensity, but also considers the demand of the local load power of the microgrid of the subway station and the allowable injection power of the power distribution network, and the installed capacity of the photovoltaic power station is as follows:

wherein the content of the first and second substances,

S _GPV the maximum and minimum installed area, k, allowed by a photovoltaic power generation board of a photovoltaic power station _PV2 、k _PV1 、k _PV0 For photovoltaic power generation station photovoltaic power generation panel outputPower versus solar intensity.

Referring to fig. 3, an embodiment of the invention provides a computer terminal device, which includes one or more processors and a memory. The memory is coupled to the processor and configured to store one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the microgrid energy demand prediction method as in any one of the above embodiments.

The processor is used for controlling the overall operation of the computer terminal equipment so as to complete all or part of the steps of the micro-grid energy demand forecasting method. The memory is used to store various types of data to support the operation at the computer terminal device, which data may include, for example, instructions for any application or method operating on the computer terminal device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically Erasable Programmable Read-Only Memory (EEPROM), erasable Programmable Read-Only Memory (EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.

In an exemplary embodiment, the computer terminal Device may be implemented by one or more Application Specific 1 integrated circuits (AS 1C), digital Signal Processors (DSP), digital Signal Processing Devices (DSPD), programmable Logic Devices (PLD), field Programmable Gate Arrays (FPGA), controllers, microcontrollers, microprocessors, or other electronic components, and is configured to perform the foregoing microgrid energy demand prediction method and achieve the technical effects consistent with the foregoing methods.

In another exemplary embodiment, a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the microgrid energy demand prediction method in any one of the above embodiments is also provided. For example, the computer readable storage medium may be the memory including the program instructions, which are executable by the processor of the computer terminal device to perform the microgrid energy demand prediction method and achieve the technical effects consistent with the method.

While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.

Claims

1. A microgrid energy demand prediction method is characterized by comprising the following steps:

constructing corresponding data matrixes according to different types of databases of the microgrid, wherein the types of the databases comprise a photovoltaic power generation database, an electricity storage device charging and discharging database, a heat storage device heat storage and release database, a cold storage device cold storage and release database and a load database;

constructing a fuzzy clustering center matrix according to the data matrix;

according to the optimal values of fuzzy clustering center matrixes corresponding to all types of databases in the microgrid, obtaining satisfying modes of load power of the microgrid and power values of the load under different conditions, which specifically comprises the following steps: calculating to obtain the minimum value, the average value and the maximum value of the electric load power, the heat load power and the cold load power of the microgrid according to the optimal value of the fuzzy clustering center matrix;

obtaining the load power according to the satisfying mode of the load power under different conditions and the power value of the loadThe method comprises the steps of predicting values and predicting values corresponding to different types of energy demands, wherein the load predicting values comprise electric loads P _E Thermal load P _H And a cooling load P _C Respectively expressed as:

wherein, P _CE1 、P _CE2 、P _CE3 Minimum, average and maximum values of the electrical load power, k _CE1 、k _CE2 、k _CE3 Weight coefficients, P, for the minimum, average and maximum values of the power of the electrical load, respectively _CH1 、P _CH2 、P _CH3 Minimum, average and maximum thermal load power, k _CH1 、k _CH2 、k _CH3 Weight coefficients, k, for the minimum, average and maximum thermal load power values, respectively _CC1 、k _CC2 、k _CC3 Weight coefficients, P, for the minimum, average and maximum power of the cooling load, respectively _CC1 、P _CC2 、P _CC3 Respectively, a minimum value, an average value and a maximum value of the cooling load power.

2. The microgrid energy demand prediction method of claim 1, wherein the data matrices include historical data matrices, real-time data matrices and predictive data matrices.

3. The microgrid energy demand prediction method of claim 1, wherein the fuzzy cluster center matrices include a minimum fuzzy cluster center matrix, an average fuzzy cluster center matrix, and a maximum fuzzy cluster center matrix.

4. The microgrid energy demand prediction method of claim 1, wherein the loads comprise electrical loads, thermal loads and cold loads.

5. The microgrid energy demand prediction method of claim 1, wherein the energy demand comprises a coal energy demand, a petroleum energy demand, a natural gas energy demand, and a nuclear energy demand.

6. The microgrid energy demand prediction method of claim 5, wherein the energy demands include coal energy demand C, petroleum energy demand O, natural gas energy demand G and nuclear energy demand N, respectively expressed as:

C＝k _C1 P _E +k _C2 P _H +k _C3 P _C

O＝k _O1 P _E +k _O2 P _H +k _O3 P _C

G＝k _G1 P _E +k _G2 P _H +k _G3 P _C

N＝k _N1 P _E +k _N2 P _H +k _N3 P _C

7. A microgrid energy demand prediction system applied to the microgrid energy demand prediction method according to any one of claims 1 to 6, comprising:

8. A computer terminal device, comprising:

one or more processors;

a memory coupled to the processor for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the microgrid energy demand prediction method of any of claims 1 to 6.