Energy interconnection intelligent management control method and device, computer equipment and medium

Abstract

The invention discloses an energy interconnection intelligent management control method and device, computer equipment and a medium, and the method comprises the steps: firstly obtaining a day energy scheduling strategy corresponding to a building energy access scene and a current energy scheduling data set corresponding to the current system time, inputting the day energy scheduling strategy and the current energy scheduling data set into a prediction model, and obtaining a current energy scheduling prediction data set; determining a current decision variable; and determining a current optimized energy scheduling strategy by combining a current objective function comprising the energy storage system basic model and the photovoltaic system basic model and a current decision variable, and correspondingly updating a current day energy scheduling strategy according to the current optimized energy scheduling strategy. According to the embodiment of the invention, different types of energy storage products and building scenes corresponding to photovoltaic, energy storage, charging piles, direct-current power distribution and flexible electric equipment can be managed in a unified manner, all-around real-time monitoring of various types of energy storage products is realized, the operation states of different products are automatically adjusted, and efficient operation of the system is ensured.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology of new energy, and in particular to energy interconnection intelligent management control methods, devices, computer equipment and media. Background Art

[0002] As the proportion of building energy consumption in the global total energy consumption increases, how to effectively manage and optimize building energy has become the focus of current attention. At present, building energy management technology has gradually transitioned from single energy management to comprehensive management of multiple energy forms. In particular, with the popularization of photovoltaic power generation, energy storage systems, electric vehicle charging, DC power distribution and flexible power equipment, how to achieve unified management of these energy forms in building scenarios has become an important challenge for energy management systems.

[0003] Existing energy interconnection management and control module systems can usually only handle a single or limited type of building energy scenarios. For example, the above system may only be able to manage photovoltaic power generation or energy storage, but it cannot take into account the comprehensive management and control of photovoltaics, energy storage, charging piles, DC power distribution and flexible power equipment at the same time, resulting in these energy systems being unable to work together, limiting the improvement of overall energy efficiency. At the same time, existing systems are often designed for specific building types (such as public buildings or residential buildings), lack the ability to adapt to a variety of building scenarios, and cannot meet the complex and diverse building energy interconnection management and control needs of commercial complexes, industrial parks, etc. Summary of the invention

[0004] The embodiments of the present invention provide an energy interconnection intelligent management and control method, device, computer equipment and medium, aiming to solve the problem that the energy interconnection management and control module system in the prior art can usually only handle a single or limited type of building energy scenarios, and cannot simultaneously take into account the comprehensive management and control of photovoltaics, energy storage, charging piles, DC distribution and flexible power equipment, resulting in these energy systems being unable to work together, limiting the improvement of overall energy efficiency.

[0005] In a first aspect, an embodiment of the present invention provides an energy interconnection intelligent management and control method, which includes: In response to an energy intelligent control instruction, obtaining a building energy access scenario corresponding to the energy intelligent control instruction; Obtaining a daily energy scheduling strategy corresponding to the building energy access scenario; wherein the daily energy scheduling strategy is used to determine the energy scheduling working mode for photovoltaic energy power supply, energy storage system power supply and city power supply in the building energy access scenario; If it is determined that the current system time meets the preset prediction data acquisition conditions, then obtain the current energy scheduling data set corresponding to the building energy access scenario and the current system time; wherein the current energy scheduling data set includes at least a photovoltaic power generation data subset, an energy storage system data subset, a load demand data subset and an electricity price data subset; Based on the current energy dispatching data set and the pre-trained prediction model, a current energy dispatching prediction data set corresponding to the current energy dispatching data set is obtained; wherein the current energy dispatching prediction data set at least includes current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and current load demand prediction data corresponding to the load demand data subset; Obtaining a basic model of an energy storage system and a basic model of a photovoltaic system corresponding to the building energy access scenario; Determining a current objective function based on the energy storage system basic model and the photovoltaic system basic model; Determining current decision variables based on the current energy scheduling data set and the current energy scheduling prediction data set; Based on the current decision variables and the current objective function, the current optimized energy scheduling strategy is determined, the energy scheduling strategy for the day is updated correspondingly with the current optimized energy scheduling strategy, and the step of obtaining the current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition conditions is returned to execute until an energy scheduling strategy stop updating instruction is detected.

[0006] In a second aspect, an embodiment of the present invention further provides an energy interconnection intelligent management and control device, which includes: An access scenario acquisition unit, configured to respond to an energy intelligent control instruction and acquire a building energy access scenario corresponding to the energy intelligent control instruction; A daily energy scheduling strategy acquisition unit, used to acquire the daily energy scheduling strategy corresponding to the building energy access scenario; wherein the daily energy scheduling strategy is used to determine the energy scheduling working mode for photovoltaic energy power supply, energy storage system power supply and city power supply in the building energy access scenario; An energy scheduling data set acquisition unit is used to acquire a current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition conditions; wherein the current energy scheduling data set includes at least a photovoltaic power generation data subset, an energy storage system data subset, a load demand data subset and an electricity price data subset; A prediction unit, configured to obtain a current energy scheduling prediction data set corresponding to the current energy scheduling data set based on the current energy scheduling data set and a pre-trained prediction model; wherein the current energy scheduling prediction data set includes at least current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and current load demand prediction data corresponding to the load demand data subset; A basic model acquisition unit, used to acquire a basic model of an energy storage system and a basic model of a photovoltaic system corresponding to the building energy access scenario; A current objective function acquisition unit, used to determine a current objective function based on the energy storage system basic model and the photovoltaic system basic model; A current decision variable acquisition unit, configured to determine a current decision variable based on the current energy scheduling data set and the current energy scheduling prediction data set; An energy scheduling strategy optimization unit is used to determine the current optimized energy scheduling strategy based on the current decision variables and the current objective function, update the energy scheduling strategy for the day corresponding to the current optimized energy scheduling strategy, and return to execute the step of obtaining the current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition conditions, until it detects an energy scheduling strategy stop updating instruction.

[0007] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0008] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method described in the first aspect above can be implemented.

[0009] The embodiment of the present invention provides an energy interconnection intelligent management and control method, device, computer equipment and medium, the method comprising: in response to an energy intelligent control instruction, obtaining a building energy access scenario corresponding to the energy intelligent control instruction; obtaining a daily energy scheduling strategy corresponding to the building energy access scenario; wherein the daily energy scheduling strategy is used to determine the energy scheduling working mode for photovoltaic energy power supply, energy storage system power supply and city power supply in the building energy access scenario; if it is determined that the current system time meets the preset prediction data acquisition conditions, then obtaining the current energy scheduling data set corresponding to the building energy access scenario and the current system time; wherein the current energy scheduling data set includes at least a photovoltaic power generation data subset, an energy storage system data subset, a load demand data subset and an electricity price data subset; based on the current energy scheduling data set and a pre-trained prediction model, obtaining the current energy scheduling corresponding to the current energy scheduling data set. Prediction data set; wherein, the current energy scheduling prediction data set includes at least the current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and the current load demand prediction data corresponding to the load demand data subset; obtain the basic model of the energy storage system and the basic model of the photovoltaic system corresponding to the building energy access scenario; determine the current objective function based on the basic model of the energy storage system and the basic model of the photovoltaic system; determine the current decision variables based on the current energy scheduling data set and the current energy scheduling prediction data set; determine the current optimization energy scheduling strategy based on the current decision variables and the current objective function, update the energy scheduling strategy of the day with the current optimization energy scheduling strategy, and return to execute if it is determined that the current system time meets the preset prediction data acquisition conditions, then obtain the steps of the current energy scheduling data set corresponding to the building energy access scenario and the current system time, until the energy scheduling strategy stops updating instructions are detected. The embodiment of the present invention can uniformly manage different types of energy storage products and building scenarios corresponding to photovoltaic, energy storage, charging piles, DC power distribution and flexible power consumption equipment, realize all-round real-time monitoring of various energy storage products, automatically adjust the operating status between different products, and ensure efficient operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0011] Figure 1 A schematic diagram of an application scenario of the energy interconnection intelligent management and control method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of an energy interconnection intelligent management and control method provided by an embodiment of the present invention; Figure 3 A schematic diagram of a sub-process of an energy interconnection intelligent management and control method provided by an embodiment of the present invention; Figure 4 A schematic diagram of another sub-process of the energy interconnection intelligent management control method provided by an embodiment of the present invention; Figure 5 A schematic block diagram of an energy interconnection intelligent management and control device provided in an embodiment of the present invention; Figure 6 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0013] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0014] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0015] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0016] Please also refer to Figure 1 and Figure 2 ,in Figure 1 Schematic diagram of a scenario of an energy interconnection intelligent management and control method according to an embodiment of the present invention. Figure 2 FIG. 1 is a flow chart of the energy interconnection intelligent management and control method provided by an embodiment of the present invention. Figure 1As shown, the energy interconnection intelligent management and control method provided by the embodiment of the present invention is applied to the server 10, and the building energy equipment 30 in multiple scenarios can be connected to the server 10 through the intelligent gateway 20. For example, the energy intelligent management and control of one of the building scenarios in the scenarios such as public buildings (i.e., public buildings), residential buildings, commercial complexes, industrial parks, etc. is taken as an example, and more specifically, the energy intelligent management and control of the building scenario of the commercial complex is taken as an example. A photovoltaic power generation system and an energy storage system (such as an energy storage battery) are deployed in a commercial complex, and the mains power grid is also connected. When the server performs intelligent scheduling for the specific electricity consumption of the commercial complex, the intelligent gateway can be deployed at the photovoltaic power generation system, the energy storage system, the mains power grid (specifically, the access end of the mains power grid) and each power load device in the commercial complex, so that the photovoltaic power generation data, energy storage data, power load data and other data in the commercial complex are collected and processed by the intelligent gateway, and then uploaded to the server for flexible scheduling of multiple power sources. The server dynamically allocates power sources under the principle of photovoltaic priority and energy storage second by real-time data collection of energy supply and load demand, ensuring that the power demand is met in the most economical and environmentally friendly way.

[0017] like Figure 2 As shown, the method includes the following steps S110-S180.

[0018] S110. In response to an energy intelligent control instruction, obtain a building energy access scenario corresponding to the energy intelligent control instruction.

[0019] In this embodiment, when the server detects an energy intelligent control instruction, it means that the server needs to perform energy intelligent control for a building scene. For example, the building scene corresponds to a unique building scene ID number. When the server detects the energy intelligent control instruction, it is first necessary to determine the unique building scene ID number corresponding to the energy intelligent control instruction, and determine the building energy access scene corresponding to the unique building scene ID number. The server can uniquely determine the controlled object (such as the commercial complex in the above example) that currently needs to be energy intelligently controlled through the unique building scene ID number and the building energy access scene. In the building corresponding to the controlled object, a photovoltaic power generation system and an energy storage system (for example, including multiple energy storage batteries or multiple batteries) are deployed, and the city power grid is also connected; in the building corresponding to the controlled object, charging piles, energy storage water heaters, air conditioners and other power load equipment are also deployed. When the controlled object is the object of energy intelligent control by the server, the photovoltaic power generation data, energy storage data, power load data and other data in the commercial complex are collected and processed by the corresponding intelligent gateway deployed in the commercial complex, and then uploaded to the server for flexible scheduling of multiple power sources.

[0020] S120. Obtain a daily energy scheduling strategy corresponding to the building energy access scenario; wherein the daily energy scheduling strategy is used to determine an energy scheduling working mode for photovoltaic energy power supply, energy storage system power supply and municipal power supply in the building energy access scenario.

[0021] In this embodiment, the server can also obtain the energy scheduling strategy in advance for the controlled object corresponding to each unique building scene ID number. For example, at a specified time point every day (such as 00:30 every day), taking the process of obtaining the energy scheduling strategy of a controlled object on the day as an example, the historical energy scheduling data set of the controlled object can be first obtained in the server (for example, the historical energy scheduling data of the controlled object in the time interval of the previous week, the previous half month, the previous month, the previous quarter, the previous half year, the previous year, etc. before the day), and then combined with the prediction model pre-trained locally on the server, the energy scheduling strategy for the next day corresponding to the building energy access scene is obtained. That is, the energy scheduling strategy for the next day has been obtained at the specified time point of the day, and the energy scheduling strategy for the day has been obtained at the specified time point of the previous day. This energy scheduling strategy for the day obtained in advance is to ensure that the controlled object can obtain an energy scheduling strategy that can be initially applied in time on the day, rather than using it to obtain the energy scheduling strategy for the day in real time based on the prediction model when the day arrives.

[0022] Moreover, the energy dispatch strategy for the day obtained the previous day, which predicts the load demand forecast data for the next day and the electricity price fluctuation data of the city electricity, can reasonably dispatch the energy storage system in the controlled object for charging and discharging. For example, when it is predicted that the photovoltaic power generation of the controlled object will be insufficient and the load demand will be high the next day, the energy storage system will be charged during the low-price period of the city electricity (such as the off-peak period) to cope with the upcoming peak load demand.

[0023] S130: If it is determined that the current system time satisfies a preset prediction data acquisition condition, a current energy scheduling data set corresponding to the building energy access scenario and the current system time is acquired.

[0024] The current energy dispatch data set includes at least a photovoltaic power generation data subset, an energy storage system data subset, a load demand data subset and an electricity price data subset.

[0025] In this embodiment, because the energy scheduling strategy for the day is not necessarily the optimal energy scheduling strategy for the day, within the time interval of the whole day, the energy scheduling data set within the time interval corresponding to the fixed time length of the day can also be obtained at fixed intervals, and then the above energy scheduling data set is used as input data to the prediction model, so as to obtain the current energy scheduling prediction data set obtained based on the prediction of the current energy scheduling data set. This current energy scheduling prediction data set includes at least the current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and the current load demand prediction data corresponding to the load demand data subset. The obtained current energy scheduling prediction data set can be used in combination with the subsequent optimization algorithm to determine the current optimized energy scheduling strategy.

[0026] In one embodiment, if Figure 3 As shown, step S130 includes: S131. If it is determined that the time interval between the current system time and the last energy scheduling strategy update time is equal to the preset update period, then it is determined that the current system time meets the preset prediction data acquisition condition; S132: Determine a current target time interval based on the current system time and the preset update cycle; wherein the current target time interval is [current system time - preset update cycle, current system time); S133, acquiring the photovoltaic power generation data subset corresponding to the building energy access scenario and the current target time interval in the local data storage space; wherein the photovoltaic power generation data subset includes at least current light intensity, photovoltaic panel power generation power and weather forecast information; S134. Acquire the energy storage system data subset corresponding to the building energy access scenario and the current target time interval in the local data storage space; wherein the energy storage system data subset includes at least the remaining power of the energy storage device, the charging and discharging status, and the health status of the device; S135. Acquire a load demand data subset corresponding to the building energy access scenario and the current target time interval in a local data storage space; wherein the load demand data subset includes at least the current power load, the equipment power consumption and the power demand forecast value; S136, acquiring, in a local data storage space, a subset of electricity price data corresponding to the building energy access scenario and the current target time interval; wherein the subset of electricity price data includes several characteristic electricity prices of the city electricity on that day; S137. The current energy scheduling data set is composed of the photovoltaic power generation data subset, the energy storage system data subset, the load demand data subset and the electricity price data subset.

[0027] In this embodiment, if it is determined that the time interval between the current system time and the last energy scheduling strategy update time is equal to the preset update cycle (such as setting the preset update cycle to 15 minutes, 30 minutes, 1 hour, etc., which is not limited to the above durations during specific implementation and can be flexibly set according to actual needs), then it is determined that the current system time meets the preset forecast data acquisition conditions. Afterwards, the current target time interval is determined based on the current system time and the preset update cycle, specifically [current system time-preset update cycle, current system time) as the current target time interval.

[0028] The operation or use of the photovoltaic power generation system, energy storage system, and mains power grid in the controlled object (such as the commercial complex in the above example) corresponding to the building energy access scenario and the unique building scenario ID number, as well as the operation or use of power load equipment such as charging piles, energy storage water heaters, and air conditioners, can be collected within the time period corresponding to the current target time interval and uploaded to the server by the intelligent gateway. Specifically, the photovoltaic power generation data subset, the energy storage system data subset, the load demand data subset, and the electricity price data subset corresponding to the building energy access scenario and the current target time interval are obtained in the local data storage space; wherein the photovoltaic power generation data subset includes at least the current light intensity, photovoltaic panel power generation power, and weather forecast information; the energy storage system data subset includes at least the remaining power of the energy storage device, the charging and discharging status, and the health status of the equipment; the load demand data subset includes at least the current power load, equipment power consumption, and power demand forecast value; the electricity price data subset includes several characteristic electricity prices of the mains electricity on that day.

[0029] After the server obtains the photovoltaic power generation data subset, the energy storage system data subset, the load demand data subset and the electricity price data subset of the controlled object within the current target time interval, the current energy scheduling data set can be formed.

[0030] S140. Based on the current energy scheduling dataset and a pre-trained prediction model, obtain a current energy scheduling prediction dataset corresponding to the current energy scheduling dataset.

[0031] The current energy dispatch prediction data set includes at least current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and current load demand prediction data corresponding to the load demand data subset.

[0032] In this embodiment, after the current energy scheduling data set of the controlled object in the current target time interval is known, it can be processed into input data (such as in the form of an input vector) and then input into the prediction model, thereby obtaining the current energy scheduling prediction data set used as prediction data. In the specific implementation, all or part of the data subsets in the current energy scheduling data set have corresponding sub-prediction models in the prediction model, and in this way, the prediction data of the corresponding dimensions obtained by different data subsets based on the corresponding sub-prediction models can be obtained for subsequent adjustment of the energy scheduling strategy.

[0033] In one embodiment, if Figure 4 As shown, step S140 includes: S141, obtaining the photovoltaic power generation data subset in the current energy scheduling data set and the photovoltaic power generation prediction model in the prediction model, inputting the photovoltaic power generation data subset into the photovoltaic power generation prediction model, and obtaining the current photovoltaic power generation prediction data; S142, obtaining the load demand data subset in the current energy dispatch data set and the load prediction model in the prediction model, inputting the load demand data subset into the load prediction model, and obtaining the current load demand prediction data; S143. The current photovoltaic power generation prediction data and the current load demand prediction data form the current energy scheduling prediction data set.

[0034] In this embodiment, the prediction model includes two sub-prediction models, a photovoltaic power generation prediction model and a load prediction model, when implemented specifically. The photovoltaic power generation data subset is input as input data into the photovoltaic power generation prediction model to obtain the current photovoltaic power generation prediction data, and the load demand data subset is input into the load prediction model to obtain the current load demand prediction data. Through the current energy scheduling prediction data set including at least the current photovoltaic power generation prediction data and the current load demand prediction data, the energy scheduling strategy of the day in the controlled object can be updated in real time in combination with the current energy scheduling prediction data set. For example, when the current energy scheduling prediction data set predicts that the photovoltaic power generation of the controlled object is high in a certain period of time in the future of the day, the photovoltaic power generation system will be used for photovoltaic power generation first, and the excess electric energy obtained by photovoltaic power generation (mainly the extra electric energy other than powering the power load equipment) will be stored through the energy storage system. If it is predicted that the photovoltaic power generation will be less during cloudy days or at night in a certain period of time in the future of the day, the use of energy storage or city power supplement is planned in advance. It can be seen that the process of inputting the current energy scheduling data set into the prediction model to obtain the current energy scheduling prediction data set can be regarded as an analysis of factors such as lighting conditions and weather changes to predict the photovoltaic power generation in future time periods; predicting future electricity demand fluctuations based on historical load data, user electricity consumption behavior data and external factors; obtaining future city electricity price data at peak, normal and low times to plan future city electricity usage; predicting future electricity demand based on user needs, historical electricity consumption data and current equipment operation conditions, and rationally planning energy supply.

[0035] S150: Obtain a basic model of an energy storage system and a basic model of a photovoltaic system corresponding to the building energy access scenario.

[0036] In this embodiment, the obtained current energy dispatch prediction data set cannot be directly used to optimize the energy dispatch strategy for the day, but needs to be combined with at least the basic model of the energy storage system and the basic model of the photovoltaic system to determine the current objective function. The basic model of the energy storage system is a basic model related to the energy storage system in the controlled object, and the basic model of the photovoltaic system is a basic model related to the photovoltaic power generation system in the controlled object.

[0037] In one embodiment, before step S150, the method further includes: Based on the energy storage capacity, charging and discharging efficiency, service life, remaining power, charging / discharging power, health status, maximum charging and discharging power, minimum remaining power, maximum charging and discharging times, energy storage constraints and operation risk information of the energy storage system in the overall system, a basic model of the energy storage system is constructed accordingly; Based on the grid connection data of the photovoltaic power generation system, the consumption data of photovoltaic power generation, the fluctuation data of photovoltaic power generation and the constraints of photovoltaic power generation, the basic model of the photovoltaic system is constructed accordingly.

[0038] In this embodiment, the basic model of the energy storage system is as follows (1): (1) In formula (1), For the battery in the energy storage system t of time period SOC State (i.e. the state of charge of the battery in the energy storage system at the end of the dispatch cycle), The initial charge of the battery in the energy storage system SOC State (i.e. the initial state of charge of the battery in the energy storage system), and The batteries are t Charging power and discharging power in each period; is the unit time interval, T The total number of time periods.

[0039] The constraints that the energy storage system needs to meet are: A1) Constraints on charge and discharge power and state: (2) In formula (2), C is the rated charging and discharging power of the energy storage system, for example, the specific value is 150kW; and is an auxiliary variable, b =0 means the energy storage system is charging, b =1 indicates that the energy storage system is discharging (because the energy storage system cannot be in the charging state and discharging state at the same time, equation (2) also reflects the constraints on the charging and discharging power and the charging and discharging state of the energy storage system).

[0040] A2) Constraints on charge and discharge times: Charge and discharge state sequence , introduce auxiliary variables Represents the absolute value of the subtraction of adjacent states: (3) when When the adjacent charge and discharge states change from 0 to 1, or from 1 to 0, it means that a charge and discharge cycle is completed. Therefore, the total charge and discharge times limit constraint can be expressed as: (4) A3) Energy Storage System SOC Upper and lower limit constraints: Energy storage system SOCThe time cannot exceed its upper and lower limits: (5) In formula (5), and They are the upper and lower limits of charging and discharging of the energy storage system, with values ​​of 0.05 and 0.95 respectively.

[0041] A4) Energy storage system charging SOC Constraints that are equal at the beginning and end: Energy storage system SOC The constraint that the optimization scheduling cycle is equal at the beginning and end should be met: (6) In formula (6), and They are the initial state of charge of the energy storage system and the state of charge at the end of the scheduling period.

[0042] A5) Constraints on the number of power changes of the energy storage system: In order to smooth out the power fluctuations caused by frequent charging and discharging of the energy storage system, the charging and discharging intervals of the energy storage system should be as large as possible, and the number of power changes should be as small as possible: (7) In formula (7), Indicates the cumulative value of charging power fluctuation of the energy storage system, Indicates the cumulative value of discharge power fluctuation of the energy storage system.

[0043] The basic model of the constructed photovoltaic system is as follows (8): (8) In formula (8), is the output power of the photovoltaic power generation system (W), E is the light intensity (W / m 2 ), A is the area of ​​the photovoltaic cell (m 2 ), is the conversion efficiency of the photovoltaic cell, is the performance ratio of the photovoltaic cell.

[0044] The constraints that the photovoltaic power generation system needs to meet are: B1) Constraints on the power destination of photovoltaic power generation systems: The output power of photovoltaics has three destinations: load consumption, energy storage system absorption and access to the grid. The constraints that need to be met are: (9) In formula (9), , , They are the power absorbed by the energy storage system, the power consumed by the load locally, and the power connected to the grid. is the output power of the photovoltaic power generation system.

[0045] B2) Constraints on complete absorption of photovoltaic power generation: When charging, the energy storage system is equivalent to the load. The charging power of the energy storage system and the required power of the load should be greater than or equal to the output power of the photovoltaic system, so as to achieve full absorption of photovoltaic power. The constraint is: (10) In formula (10), The power demanded by the load.

[0046] It can be seen that when constructing the basic model of the energy storage system, key parameters such as energy storage capacity, charging and discharging efficiency, and service life are covered, and the remaining power, charging / discharging power, health status, maximum charging and discharging power, minimum remaining power, maximum charging and discharging times of the energy storage system, and energy storage constraints (such as the operating time cannot exceed the preset time, etc.) and operating risk information (such as thermal runaway, inverter failure, etc.) of the energy storage system are also taken into account.

[0047] When constructing the basic model of the photovoltaic system, the operation of the photovoltaic power generation system is simulated, and the grid connection data of photovoltaic power generation and the consumption data of photovoltaic power generation, the fluctuation data of photovoltaic power generation and the constraints of photovoltaic power generation (for example, the constraints of photovoltaic power generation include the minimum load capacity and the maximum power supply capacity). The basic model of the energy storage system and the basic model of the photovoltaic system obtained are the basic models corresponding to the building energy access scenario and the controlled object, which can be used to comprehensively construct the objective function.

[0048] S160: Determine a current objective function based on the energy storage system basic model and the photovoltaic system basic model.

[0049] In this embodiment, when determining the current objective function based on the energy storage system basic model and the photovoltaic system basic model, at least two conditions C1) and C2) need to be met, as follows: C1) The energy storage system has the greatest benefits: The strategy of discharging during peak hours and charging during valley hours is adopted, and the output value of the output energy storage is calculated with the maximum peak-valley price difference as the optimization target, which can reduce the electricity cost and realize peak shaving and valley filling. The objective function is shown in formula (11): (11) In formula (11), f 1 It is the difference between the gain of the energy storage system when discharging and the loss when charging; and The energy storage system is t Charging power and discharging power in each period; is the unit time interval, T is the total number of time periods; is the discharge price, It is the charging electricity price.

[0050] C2) Photovoltaic power generation system has the greatest benefits: (12) In formula (12), is the discharge price, It is the charging electricity price. It is the on-grid electricity price.

[0051] It can be seen that when determining the current objective function, the basic model of the energy storage system and the basic model of the photovoltaic system are combined, and the consumption data of the photovoltaic power generation system, the scheduling of the virtual power plant, and the maximum energy storage benefits are taken as the goal to maximize the utilization of renewable energy. In addition, by optimizing the charging and discharging of the energy storage system in the controlled object, the economic benefits of storing electricity during low-price periods and using electricity during high-price periods are obtained. The overall operating benefits and long-term economic benefits of the controlled object system are comprehensively considered, and energy from different sources is reasonably allocated.

[0052] S170. Determine current decision variables based on the current energy scheduling data set and the current energy scheduling prediction data set.

[0053] In this embodiment, when obtaining the current decision variable corresponding to the objective function, it is necessary to comprehensively consider the current energy scheduling data set and the current energy scheduling prediction data set, and obtain relevant data that can be used as decision variables therefrom to form the current decision variable.

[0054] In one embodiment, step S170 includes: Based on the current energy dispatching data set and the current energy dispatching prediction data set, the charging / discharging power of the energy storage system, the charging amount of the charging pile and the power purchase amount of the power grid are obtained to form the current decision variables.

[0055] In this embodiment, the charging / discharging power of the energy storage system, the charging amount of the charging pile and the power purchase amount of the power grid can be obtained by screening the current energy scheduling data set and the current energy scheduling prediction data set, and form the current decision variables. t The charging power and discharging power of each period (i.e. and ) and state of charge (i.e. including and ,in and The initial state of charge of the energy storage system and the state of charge at the end of the dispatch cycle are key variables that describe the operating state of the energy storage system. The state of charge increases when the energy storage is charged, and decreases when it is discharged. Through these variables, the operating behavior of the energy storage system can be simulated and its charging and discharging strategy can be optimized to improve the overall performance and economy of the system. Among them, the charging / discharging power of the energy storage system can be dynamically adjusted according to the current state of the energy storage system and the load demand data.

[0056] Moreover, it should be noted that when the energy storage system and photovoltaic power generation system in the controlled object cannot simultaneously meet the electricity demand corresponding to the load demand data, the use of city electricity should be appropriately increased (i.e., electricity purchased from the power grid), and the amount of electricity purchased should be optimized to reduce costs. The output and input of the photovoltaic system and energy storage system can also be adjusted in real time according to external conditions such as weather and load.

[0057] S180. Based on the current decision variables and the current objective function, determine the current optimized energy scheduling strategy, update the energy scheduling strategy for the day with the current optimized energy scheduling strategy, and return to execute the step of obtaining the current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition conditions, until the energy scheduling strategy stop updating instruction is detected.

[0058] In this embodiment, the technical solution is explained by taking the process of obtaining a current energy scheduling data set corresponding to a current target time interval for a controlled object, and specifically and finally determining the current objective function and solving the current objective function to obtain the current optimized energy scheduling strategy as an example. Afterwards, after entering the next current target time interval, the current optimized energy scheduling strategy is determined with reference to steps S110 to S180, and the process of updating the energy scheduling strategy for the day is corresponding to the current optimized energy scheduling strategy. After solving the current objective function under the premise of taking into account the current decision variables, the current optimized energy scheduling strategy can be obtained, and the energy scheduling strategy for the day is updated with the current optimized energy scheduling strategy. In this way, the energy scheduling strategy for the day is continuously updated and optimized to obtain the optimal energy scheduling strategy. The above method can adapt to dynamically changing environments and needs and maximize energy efficiency.

[0059] For example, after the controlled object obtains the current load demand forecast data by combining the forecast of the energy dispatch strategy for the day and the current energy dispatch forecast data set, it can adjust the opening and closing time of the power load equipment. For example, when it is predicted that the total power load of the power load equipment is high, the operation of some non-essential power load equipment (such as energy storage water heaters, air conditioners, etc.) can be reduced, and the power load equipment as key equipment can be supplied first.

[0060] Moreover, when carrying out energy scheduling in the buildings corresponding to the controlled objects, the following principles are also followed: 1) Energy priority principle, that is, giving priority to the use of renewable energy (such as photovoltaic power generation) and energy storage equipment for charging, so as to maximize the use of renewable energy and reduce dependence on the mains. By properly arranging the discharge of energy storage equipment, the needs of fast charging and super charging can be met, energy utilization efficiency can be improved, electricity costs can be saved, and carbon emissions can be reduced; 2) Demand priority principle, that is, when the city electricity price is high or during peak hours, the system will give priority to using the energy storage system for charging to balance the supply and demand of energy, reduce the load pressure on the city electricity during peak hours, and achieve the effect of peak shaving and valley filling; 3) The principle of reservation and planned power supply, that is, to support users or managers (such as the actual managers of the controlled objects in the above example) to make reservations and plan future energy usage needs in advance, and ensure that sufficient power is provided within the specified time by reasonably arranging energy dispatch. It can also optimize energy distribution to meet actual needs based on the reservation time and energy storage status of the load; 4) Load priority principle, that is, different power supply strategies can be set according to the importance and demand priority of the load; for example, for key equipment, its energy supply will be guaranteed first, while non-critical loads will be reduced or delayed to ensure the stability of the overall system; 5) The principle of utilizing price differences, that is, dynamically adjusting the power supply source in combination with the electricity prices of the city electricity during the "peak, peak, flat and valley" periods. During the period when the electricity price of the city electricity is low, the system will make full use of the city electricity for power supply or charging; during the period when the electricity price is high, the system will give priority to dispatching photovoltaic power generation and energy storage equipment to reduce electricity costs.

[0061] In one embodiment, step S180 includes: The current decision variables are input into the current objective function and the objective function is solved using an improved sparrow search algorithm to obtain the current optimized energy scheduling strategy.

[0062] In this embodiment, an improved sparrow search algorithm is specifically used to solve the current objective function. Among them, the full name of the improved sparrow search algorithm in English is Improved Sparrow Search Algorithm and is abbreviated as ISSA. It is based on the sparrow search algorithm (i.e. SSA) and proposes a normal offset strategy for the follower to enhance its exploration ability, introduces a dynamic sinusoidal perturbation strategy to realize the discoverer's two-way requirements for search step size and convergence speed, and adds a reverse learning mechanism to help the algorithm jump out of the local optimal processing solution. The specific implementation process of solving the objective function using the ISSA algorithm is as follows: D1) Initialize the sparrow population and related parameters; D2) determining the objective function; D3) Calculate the fitness value of each sparrow in the initialized sparrow population, select the discoverer in the initialized sparrow population, and the rest are followers. The guards are randomly generated in each iteration; D4) Introducing the dynamic sinusoidal perturbation strategy to improve the position update formula of the discoverer, the follower follows the discoverer according to the original SSA algorithm position update formula; D5) Sparrow population undergoes normal deviation; D6) After the current iteration is completed, the fitness value and other parameters of the individual sparrow are updated; D7) Determine whether the maximum number of iterations has been reached, if yes, exit the loop, otherwise continue iterating and return to step D3) D8)End.

[0063] Based on the ISSA algorithm, the microgrid model in this example is constructed to have a complete microgrid operation system, and then an economic dispatch simulation experiment is carried out on the constructed system model.

[0064] The period from 0 to 6 o'clock is the valley period, during which the photovoltaic power generation system is out of operation and the power grid provides the power required by the load. The period from 7 to 10 o'clock enters the level period, during which the load demand increases rapidly. During this period, the power generation of the photovoltaic power generation system is used by the load. If the power generation of the photovoltaic power generation system exceeds the power required by the load, the remaining power is absorbed by the energy storage system. The area enters the peak period from 14 to 19 o'clock, during which the photovoltaic power generation system maintains the highest power generation and the power gap is filled by the battery. The area enters the peak period again from 19 to 22 o'clock, during which the energy storage system serves as the main power source. To prevent over-discharge of the energy storage system, electricity can be purchased from the power grid.

[0065] In this example, the ISSA algorithm has good economic optimization capabilities. The ISSA algorithm using the level, valley, and peak strategies has lower dispatch costs than other optimization algorithms, and plays a certain optimization role in the economic dispatch of the microgrid.

[0066] In one embodiment, after step S180, the method further includes: Acquire virtual power plant data corresponding to the building energy access scenario and upload it to the virtual power plant; Obtain carbon emission data corresponding to the building energy access scenario and upload it to the carbon management platform.

[0067] In this embodiment, in addition to updating the daily energy dispatch strategy for the controlled object corresponding to the building energy access scenario in real time, the server can also obtain the virtual power plant data corresponding to the controlled object and upload it to the virtual power plant, and obtain the corresponding carbon emission data and upload it to the carbon management platform. Specifically, the obtained virtual power plant data at least includes: the name of the responsive device, the capacity of the responsive device, the historical data of the responsive device, and the maximum control time of the responsive device obtained from the controlled object corresponding to the building energy access scenario. The above virtual power plant data is processed by missing values, null value exceptions, and data classification, and the processed results are uploaded to the virtual power plant. The obtained virtual power plant data at least includes the building electricity consumption data, building status data, and building permanent population data obtained from the controlled object corresponding to the building energy access scenario, so as to form carbon emission data and upload it to the carbon management platform. In the above manner, it is possible to seamlessly connect with the virtual power plant and the carbon management platform, support virtual power plant transactions, enhance the monitoring and optimization capabilities of carbon emission data, and achieve effective control of carbon footprint.

[0068] It can be seen that the implementation example of the method can uniformly manage different types of energy storage products and building scenarios corresponding to photovoltaics, energy storage, charging piles, DC power distribution and flexible power equipment, realize all-round real-time monitoring of various energy storage products, automatically adjust the operating status of different products, and ensure efficient operation of the system.

[0069] Figure 5 is a schematic block diagram of an energy interconnection intelligent management and control device provided by an embodiment of the present invention. Figure 5 As shown, corresponding to the above energy interconnection intelligent management and control method, the present invention also provides an energy interconnection intelligent management and control device 100. The energy interconnection intelligent management and control device 100 includes: an access scenario acquisition unit 110, a daily energy dispatch strategy acquisition unit 120, an energy dispatch data set acquisition unit 130, a prediction unit 140, a basic model acquisition unit 150, a current objective function acquisition unit 160, a current decision variable acquisition unit 170 and an energy dispatch strategy optimization unit 180.

[0070] The access scenario acquisition unit 110 is used to respond to the energy intelligent control instruction and acquire the building energy access scenario corresponding to the energy intelligent control instruction.

[0071] In this embodiment, when the server detects an energy intelligent control instruction, it means that the server needs to perform energy intelligent control for a building scene. For example, the building scene corresponds to a unique building scene ID number. When the server detects the energy intelligent control instruction, it is first necessary to determine the unique building scene ID number corresponding to the energy intelligent control instruction, and determine the building energy access scene corresponding to the unique building scene ID number. The server can uniquely determine the controlled object (such as the commercial complex in the above example) that currently needs to be energy intelligently controlled through the unique building scene ID number and the building energy access scene. In the building corresponding to the controlled object, a photovoltaic power generation system and an energy storage system (for example, including multiple energy storage batteries or multiple batteries) are deployed, and the city power grid is also connected; in the building corresponding to the controlled object, charging piles, energy storage water heaters, air conditioners and other power load equipment are also deployed. When the controlled object is the object of energy intelligent control by the server, the photovoltaic power generation data, energy storage data, power load data and other data in the commercial complex are collected and processed by the corresponding intelligent gateway deployed in the commercial complex, and then uploaded to the server for flexible scheduling of multiple power sources.

[0072] The daily energy scheduling strategy acquisition unit 120 is used to obtain the daily energy scheduling strategy corresponding to the building energy access scenario; wherein the daily energy scheduling strategy is used to determine the energy scheduling working mode for photovoltaic energy power supply, energy storage system power supply and municipal power supply in the building energy access scenario.

[0073] In this embodiment, the server can also obtain the energy scheduling strategy in advance for the controlled object corresponding to each unique building scene ID number. For example, at a specified time point every day (such as 00:30 every day), taking the process of obtaining the energy scheduling strategy of a controlled object on the day as an example, the historical energy scheduling data set of the controlled object can be first obtained in the server (for example, the historical energy scheduling data of the controlled object in the time interval of the previous week, the previous half month, the previous month, the previous quarter, the previous half year, the previous year, etc. before the day), and then combined with the prediction model pre-trained locally on the server, the energy scheduling strategy for the next day corresponding to the building energy access scene is obtained. That is, the energy scheduling strategy for the next day has been obtained at the specified time point of the day, and the energy scheduling strategy for the day has been obtained at the specified time point of the previous day. This energy scheduling strategy for the day obtained in advance is to ensure that the controlled object can obtain an energy scheduling strategy that can be initially applied in time on the day, rather than using it to obtain the energy scheduling strategy for the day in real time based on the prediction model when the day arrives.

[0074] Moreover, the energy dispatch strategy for the day obtained the previous day, which predicts the load demand forecast data for the next day and the electricity price fluctuation data of the city electricity, can reasonably dispatch the energy storage system in the controlled object for charging and discharging. For example, when it is predicted that the photovoltaic power generation of the controlled object will be insufficient and the load demand will be high the next day, the energy storage system will be charged during the low-price period of the city electricity (such as the off-peak period) to cope with the upcoming peak load demand.

[0075] The energy scheduling data set acquisition unit 130 is used to acquire the current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition condition.

[0076] The current energy dispatch data set includes at least a photovoltaic power generation data subset, an energy storage system data subset, a load demand data subset and an electricity price data subset.

[0077] In this embodiment, because the energy scheduling strategy for the day is not necessarily the optimal energy scheduling strategy for the day, within the time interval of the whole day, the energy scheduling data set within the time interval corresponding to the fixed time length of the day can also be obtained at fixed intervals, and then the above energy scheduling data set is used as input data to the prediction model, so as to obtain the current energy scheduling prediction data set obtained based on the prediction of the current energy scheduling data set. This current energy scheduling prediction data set includes at least the current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and the current load demand prediction data corresponding to the load demand data subset. The obtained current energy scheduling prediction data set can be used in combination with the subsequent optimization algorithm to determine the current optimized energy scheduling strategy.

[0078] In one embodiment, the energy scheduling data set acquisition unit 130 is specifically used to: If it is determined that the time interval between the current system time and the last energy scheduling strategy update time is equal to the preset update period, then it is determined that the current system time meets the preset prediction data acquisition condition; Determine a current target time interval based on the current system time and the preset update period; wherein the current target time interval is [current system time-preset update period, current system time); Acquire the photovoltaic power generation data subset corresponding to the building energy access scenario and the current target time interval in the local data storage space; wherein the photovoltaic power generation data subset includes at least current light intensity, photovoltaic panel power generation power and weather forecast information; Acquire the energy storage system data subset corresponding to the building energy access scenario and the current target time interval in the local data storage space; wherein the energy storage system data subset includes at least the remaining power of the energy storage device, the charging and discharging status, and the health status of the device; Acquire a load demand data subset corresponding to the building energy access scenario and the current target time interval in a local data storage space; wherein the load demand data subset includes at least the current power load, equipment power consumption and power demand forecast value; Acquire a subset of electricity price data corresponding to the building energy access scenario and the current target time interval in a local data storage space; wherein the subset of electricity price data includes several characteristic electricity prices of the city electricity on that day; The current energy dispatch data set is composed of the photovoltaic power generation data subset, the energy storage system data subset, the load demand data subset and the electricity price data subset.

[0079] In this embodiment, if it is determined that the time interval between the current system time and the last energy scheduling strategy update time is equal to the preset update cycle (such as setting the preset update cycle to 15 minutes, 30 minutes, 1 hour, etc., which is not limited to the above durations during specific implementation and can be flexibly set according to actual needs), then it is determined that the current system time meets the preset forecast data acquisition conditions. Afterwards, the current target time interval is determined based on the current system time and the preset update cycle, specifically [current system time-preset update cycle, current system time) as the current target time interval.

[0080] The operation or use of the photovoltaic power generation system, energy storage system, and mains power grid in the controlled object (such as the commercial complex in the above example) corresponding to the building energy access scenario and the unique building scenario ID number, as well as the operation or use of power load equipment such as charging piles, energy storage water heaters, and air conditioners, can be collected within the time period corresponding to the current target time interval and uploaded to the server by the intelligent gateway. Specifically, the photovoltaic power generation data subset, the energy storage system data subset, the load demand data subset, and the electricity price data subset corresponding to the building energy access scenario and the current target time interval are obtained in the local data storage space; wherein the photovoltaic power generation data subset includes at least the current light intensity, photovoltaic panel power generation power, and weather forecast information; the energy storage system data subset includes at least the remaining power of the energy storage device, the charging and discharging status, and the health status of the equipment; the load demand data subset includes at least the current power load, equipment power consumption, and power demand forecast value; the electricity price data subset includes several characteristic electricity prices of the mains electricity on that day.

[0081] After the server obtains the photovoltaic power generation data subset, the energy storage system data subset, the load demand data subset and the electricity price data subset of the controlled object within the current target time interval, the current energy scheduling data set can be formed.

[0082] The prediction unit 140 is configured to obtain a current energy scheduling prediction data set corresponding to the current energy scheduling data set based on the current energy scheduling data set and a pre-trained prediction model.

[0083] The current energy dispatch prediction data set includes at least current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and current load demand prediction data corresponding to the load demand data subset.

[0084] In this embodiment, after the current energy scheduling data set of the controlled object in the current target time interval is known, it can be processed into input data (such as in the form of an input vector) and then input into the prediction model, thereby obtaining the current energy scheduling prediction data set used as prediction data. In the specific implementation, all or part of the data subsets in the current energy scheduling data set have corresponding sub-prediction models in the prediction model, and in this way, the prediction data of the corresponding dimensions obtained by different data subsets based on the corresponding sub-prediction models can be obtained for subsequent adjustment of the energy scheduling strategy.

[0085] In one embodiment, the prediction unit 140 is specifically configured to: Acquire the photovoltaic power generation data subset in the current energy scheduling data set and the photovoltaic power generation prediction model in the prediction model, input the photovoltaic power generation data subset into the photovoltaic power generation prediction model, and obtain the current photovoltaic power generation prediction data; Obtaining the load demand data subset in the current energy dispatch data set and the load forecasting model in the forecasting model, inputting the load demand data subset into the load forecasting model, and obtaining the current load demand forecasting data; The current energy scheduling prediction data set is composed of the current photovoltaic power generation prediction data and the current load demand prediction data.

[0086] In this embodiment, the prediction model includes two sub-prediction models, a photovoltaic power generation prediction model and a load prediction model, when implemented specifically. The photovoltaic power generation data subset is input as input data into the photovoltaic power generation prediction model to obtain the current photovoltaic power generation prediction data, and the load demand data subset is input into the load prediction model to obtain the current load demand prediction data. Through the current energy scheduling prediction data set including at least the current photovoltaic power generation prediction data and the current load demand prediction data, the energy scheduling strategy of the day in the controlled object can be updated in real time in combination with the current energy scheduling prediction data set. For example, when the current energy scheduling prediction data set predicts that the photovoltaic power generation of the controlled object is high in a certain period of time in the future of the day, the photovoltaic power generation system will be used for photovoltaic power generation first, and the excess electric energy obtained by photovoltaic power generation (mainly the extra electric energy other than powering the power load equipment) will be stored through the energy storage system. If it is predicted that the photovoltaic power generation will be less during cloudy days or at night in a certain period of time in the future of the day, the use of energy storage or city power supplement is planned in advance. It can be seen that the process of inputting the current energy scheduling data set into the prediction model to obtain the current energy scheduling prediction data set can be regarded as an analysis of factors such as lighting conditions and weather changes to predict the photovoltaic power generation in future time periods; predicting future electricity demand fluctuations based on historical load data, user electricity consumption behavior data and external factors; obtaining future city electricity price data at peak, normal and low times to plan future city electricity usage; predicting future electricity demand based on user needs, historical electricity consumption data and current equipment operation conditions, and rationally planning energy supply.

[0087] The basic model acquisition unit 150 is used to acquire a basic model of an energy storage system and a basic model of a photovoltaic system corresponding to the building energy access scenario.

[0088] In this embodiment, the obtained current energy dispatch prediction data set cannot be directly used to optimize the energy dispatch strategy for the day, but needs to be combined with at least the basic model of the energy storage system and the basic model of the photovoltaic system to determine the current objective function. The basic model of the energy storage system is a basic model related to the energy storage system in the controlled object, and the basic model of the photovoltaic system is a basic model related to the photovoltaic power generation system in the controlled object.

[0089] In one embodiment, the energy interconnection intelligent management and control device 100 further includes: The energy storage system basic model construction unit is used to construct the energy storage system basic model based on the energy storage capacity, charging and discharging efficiency, service life, remaining power, charging / discharging power, health status, maximum charging and discharging power, minimum remaining power, maximum charging and discharging times, energy storage constraints and operation risk information of the energy storage system in the overall system; The photovoltaic system basic model building unit is used to build the photovoltaic system basic model based on the grid connection data of the photovoltaic power generation system, the photovoltaic power generation consumption data, the photovoltaic power generation fluctuation data and the photovoltaic power generation constraint conditions.

[0090] In this embodiment, when constructing the basic model of the energy storage system, key parameters such as energy storage capacity, charging and discharging efficiency, and service life are covered, and the remaining power, charging / discharging power, health status, maximum charging and discharging power, minimum remaining power, maximum charging and discharging times of the energy storage system are also taken into account, as well as the energy storage constraints (for example, the operating time cannot exceed the preset time, etc.) and operating risk information (for example, thermal runaway, inverter failure, etc.) of the energy storage system.

[0091] When constructing the basic model of the photovoltaic system, the operation of the photovoltaic power generation system is simulated, and the grid connection data of photovoltaic power generation and the consumption data of photovoltaic power generation, the fluctuation data of photovoltaic power generation and the constraints of photovoltaic power generation (for example, the constraints of photovoltaic power generation include the minimum load capacity and the maximum power supply capacity). The basic model of the energy storage system and the basic model of the photovoltaic system obtained are the basic models corresponding to the building energy access scenario and the controlled object, which can be used to comprehensively construct the objective function.

[0092] The current objective function acquisition unit 160 is used to determine the current objective function based on the energy storage system basic model and the photovoltaic system basic model.

[0093] In this embodiment, the basic model of the energy storage system and the basic model of the photovoltaic system are combined, and the consumption data of the photovoltaic power generation system, the scheduling of the virtual power plant, and the maximum energy storage benefits are taken as the goal to maximize the utilization of renewable energy. In addition, by optimizing the charging and discharging of the energy storage system in the controlled object, the economic benefits of storing electricity during low-price periods and using electricity during high-price periods are obtained. The overall operating benefits and long-term economic benefits of the controlled object system are comprehensively considered, and energy from different sources is reasonably allocated.

[0094] The current decision variable acquisition unit 170 is used to determine the current decision variable based on the current energy scheduling data set and the current energy scheduling prediction data set.

[0095] In this embodiment, when obtaining the current decision variable corresponding to the objective function, it is necessary to comprehensively consider the current energy scheduling data set and the current energy scheduling prediction data set, and obtain relevant data that can be used as decision variables therefrom to form the current decision variable.

[0096] In one embodiment, the current decision variable acquisition unit 170 is specifically used to: Based on the current energy dispatching data set and the current energy dispatching prediction data set, the charging / discharging power of the energy storage system, the charging amount of the charging pile and the power purchase amount of the power grid are obtained to form the current decision variables.

[0097] In this embodiment, the charging / discharging power of the energy storage system, the charging amount of the charging pile and the power purchase amount of the power grid can be obtained by screening the current energy scheduling data set and the current energy scheduling prediction data set, and form the current decision variables. t The charging power and discharging power of each period (i.e. and ) and state of charge (i.e. including and ,in and The initial state of charge of the energy storage system and the state of charge at the end of the dispatch cycle are key variables that describe the operating state of the energy storage system. The state of charge increases when the energy storage is charged, and decreases when it is discharged. Through these variables, the operating behavior of the energy storage system can be simulated and its charging and discharging strategy can be optimized to improve the overall performance and economy of the system. Among them, the charging / discharging power of the energy storage system can be dynamically adjusted according to the current state of the energy storage system and the load demand data.

[0098] Moreover, it should be noted that when the energy storage system and photovoltaic power generation system in the controlled object cannot simultaneously meet the electricity demand corresponding to the load demand data, the use of city electricity should be appropriately increased (i.e., electricity purchased from the power grid), and the amount of electricity purchased should be optimized to reduce costs. The output and input of the photovoltaic system and energy storage system can also be adjusted in real time according to external conditions such as weather and load.

[0099] The energy scheduling strategy optimization unit 180 is used to determine the current optimized energy scheduling strategy based on the current decision variables and the current objective function, update the energy scheduling strategy for the day corresponding to the current optimized energy scheduling strategy, and return to execute the step of obtaining the current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition conditions, until it detects an energy scheduling strategy stop updating instruction.

[0100] In this embodiment, the technical solution is explained by taking the process of obtaining a current energy scheduling data set corresponding to a current target time interval for a controlled object, and specifically and finally determining the current objective function and solving the current objective function to obtain the current optimized energy scheduling strategy as an example. Afterwards, after entering the next current target time interval, the current optimized energy scheduling strategy is also determined by referring to the access scenario acquisition unit 110, the energy scheduling strategy acquisition unit 120 for the day, the energy scheduling data set acquisition unit 130, the prediction unit 140, the basic model acquisition unit 150, the current objective function acquisition unit 160, the current decision variable acquisition unit 170 and the energy scheduling strategy optimization unit 180, and the current optimized energy scheduling strategy is used to update the energy scheduling strategy for the day. After solving the current objective function under the premise of considering the current decision variables, the current optimized energy scheduling strategy can be obtained, and the energy scheduling strategy for the day is updated with the current optimized energy scheduling strategy. In this way, the energy scheduling strategy for the day is continuously updated and optimized to obtain the optimal energy scheduling strategy. The above method can adapt to the dynamically changing environment and needs and maximize energy efficiency.

[0101] For example, after the controlled object obtains the current load demand forecast data by combining the forecast of the energy dispatch strategy for the day and the current energy dispatch forecast data set, it can adjust the opening and closing time of the power load equipment. For example, when it is predicted that the total power load of the power load equipment is high, the operation of some non-essential power load equipment (such as energy storage water heaters, air conditioners, etc.) can be reduced, and the power load equipment as key equipment can be supplied first.

[0102] In one embodiment, the energy scheduling strategy optimization unit 180 is specifically used to: The current decision variables are input into the current objective function and the objective function is solved using an improved sparrow search algorithm to obtain the current optimized energy scheduling strategy.

[0103] In this embodiment, an improved sparrow search algorithm is specifically used to solve the current objective function. The full name of the improved sparrow search algorithm is Improved Sparrow Search Algorithm and is abbreviated as ISSA. It is based on the sparrow search algorithm (i.e. SSA), proposes a normal offset strategy for the follower to enhance its exploration ability, introduces a dynamic sinusoidal perturbation strategy to achieve the discoverer's two-way requirements for search step size and convergence speed, and adds a reverse learning mechanism to help the algorithm jump out of the local optimal processing solution.

[0104] In one embodiment, the energy interconnection intelligent management and control device 100 further includes: A virtual power plant data uploading unit, used to obtain virtual power plant data corresponding to the building energy access scenario and upload it to the virtual power plant; The carbon emission data uploading unit is used to obtain the carbon emission data corresponding to the building energy access scenario and upload it to the carbon management platform.

[0105] In this embodiment, in addition to updating the daily energy dispatch strategy for the controlled object corresponding to the building energy access scenario in real time, the server can also obtain the virtual power plant data corresponding to the controlled object and upload it to the virtual power plant, and obtain the corresponding carbon emission data and upload it to the carbon management platform. Specifically, the obtained virtual power plant data at least includes: the name of the responsive device, the capacity of the responsive device, the historical data of the responsive device, and the maximum control time of the responsive device obtained from the controlled object corresponding to the building energy access scenario. The above virtual power plant data is processed by missing values, null value exceptions, and data classification, and the processed results are uploaded to the virtual power plant. The obtained virtual power plant data at least includes the building electricity consumption data, building status data, and building permanent population data obtained from the controlled object corresponding to the building energy access scenario, so as to form carbon emission data and upload it to the carbon management platform. In the above manner, it is possible to seamlessly connect with the virtual power plant and the carbon management platform, support virtual power plant transactions, enhance the monitoring and optimization capabilities of carbon emission data, and achieve effective control of carbon footprint.

[0106] It can be seen that the implementation example of the device can uniformly manage different types of energy storage products and building scenarios corresponding to photovoltaics, energy storage, charging piles, DC power distribution and flexible power equipment, realize all-round real-time monitoring of various energy storage products, automatically adjust the operating status of different products, and ensure efficient operation of the system.

[0107] The energy interconnection intelligent management and control device can be implemented in the form of a computer program. The computer program can be used in Figure 6 Runs on the computer device shown.

[0108] See also Figure 6 , Figure 6 The schematic block diagram of a computer device provided by an embodiment of the present invention is shown in FIG. The computer device integrates any energy interconnection intelligent management and control device provided by an embodiment of the present invention.

[0109] See also Figure 6 The computer device 400 includes a processor 402 , a memory and a network interface 405 connected via a system bus 401 , wherein the memory may include a storage medium 403 and an internal memory 404 .

[0110] The storage medium 403 can store an operating system 4031 and a computer program 4032. The computer program 4032 includes program instructions, and when the program instructions are executed, the processor 402 can execute the above-mentioned energy interconnection intelligent management and control method.

[0111] The processor 402 is used to provide computing and control capabilities to support the operation of the entire computer device.

[0112] The internal memory 404 provides an environment for the operation of the computer program 4032 in the storage medium 403. When the computer program 4032 is executed by the processor 402, the processor 402 can execute the above-mentioned energy interconnection intelligent management and control method.

[0113] The network interface 405 is used to communicate with other devices over the network. Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] The processor 402 is used to run a computer program 4032 stored in a memory to implement the energy interconnection intelligent management and control method as described above.

[0115] It should be understood that in the embodiment of the present invention, the processor 402 may be a central processing unit (CPU), and the processor 402 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0116] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0117] Therefore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the energy interconnection intelligent management and control method as described above.

[0118] The computer-readable storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0119] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0120] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0121] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0123] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for intelligent management and control of energy interconnection, It is characterized in that include: In response to an energy intelligent control instruction, obtaining a building energy access scenario corresponding to the energy intelligent control instruction; Obtaining a daily energy scheduling strategy corresponding to the building energy access scenario; wherein the daily energy scheduling strategy is used to determine the energy scheduling working mode for photovoltaic energy power supply, energy storage system power supply and city power supply in the building energy access scenario; If it is determined that the current system time meets the preset prediction data acquisition conditions, then obtain the current energy scheduling data set corresponding to the building energy access scenario and the current system time; wherein the current energy scheduling data set includes at least a photovoltaic power generation data subset, an energy storage system data subset, a load demand data subset and an electricity price data subset; Based on the current energy dispatching data set and the pre-trained prediction model, a current energy dispatching prediction data set corresponding to the current energy dispatching data set is obtained; wherein the current energy dispatching prediction data set at least includes current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and current load demand prediction data corresponding to the load demand data subset; Obtaining a basic model of an energy storage system and a basic model of a photovoltaic system corresponding to the building energy access scenario; Determining a current objective function based on the energy storage system basic model and the photovoltaic system basic model; Determining current decision variables based on the current energy scheduling data set and the current energy scheduling prediction data set; Based on the current decision variables and the current objective function, the current optimized energy scheduling strategy is determined, the energy scheduling strategy for the day is updated correspondingly with the current optimized energy scheduling strategy, and the step of obtaining the current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition conditions is returned to execute until an energy scheduling strategy stop updating instruction is detected.

2. The method according to claim 1, It is characterized in that If it is determined that the current system time meets the preset prediction data acquisition condition, then obtaining a current energy scheduling data set corresponding to the building energy access scenario and the current system time includes: If it is determined that the time interval between the current system time and the last energy scheduling strategy update time is equal to the preset update period, then it is determined that the current system time meets the preset prediction data acquisition condition; Determine a current target time interval based on the current system time and the preset update period; wherein the current target time interval is [current system time-preset update period, current system time); Acquire the photovoltaic power generation data subset corresponding to the building energy access scenario and the current target time interval in the local data storage space; wherein the photovoltaic power generation data subset includes at least current light intensity, photovoltaic panel power generation power and weather forecast information; Acquire the energy storage system data subset corresponding to the building energy access scenario and the current target time interval in the local data storage space; wherein the energy storage system data subset includes at least the remaining power of the energy storage device, the charging and discharging status, and the health status of the device; Acquire a load demand data subset corresponding to the building energy access scenario and the current target time interval in a local data storage space; wherein the load demand data subset includes at least the current power load, equipment power consumption and power demand forecast value; Acquire a subset of electricity price data corresponding to the building energy access scenario and the current target time interval in a local data storage space; wherein the subset of electricity price data includes several characteristic electricity prices of the city electricity on that day; The current energy dispatch data set is composed of the photovoltaic power generation data subset, the energy storage system data subset, the load demand data subset and the electricity price data subset.

3. The method according to claim 1, It is characterized in that The acquiring, based on the current energy scheduling dataset and the pre-trained prediction model, a current energy scheduling prediction dataset corresponding to the current energy scheduling dataset comprises: Acquire the photovoltaic power generation data subset in the current energy scheduling data set and the photovoltaic power generation prediction model in the prediction model, input the photovoltaic power generation data subset into the photovoltaic power generation prediction model, and obtain the current photovoltaic power generation prediction data; Obtaining the load demand data subset in the current energy dispatch data set and the load forecasting model in the forecasting model, inputting the load demand data subset into the load forecasting model, and obtaining the current load demand forecasting data; The current energy scheduling prediction data set is composed of the current photovoltaic power generation prediction data and the current load demand prediction data.

4. The method according to claim 1, It is characterized in that Before the step of obtaining a basic model of the energy storage system and a basic model of the photovoltaic system corresponding to the building energy access scenario, the method further includes: Based on the energy storage capacity, charging and discharging efficiency, service life, remaining power, charging / discharging power, health status, maximum charging and discharging power, minimum remaining power, maximum charging and discharging times, energy storage constraints and operation risk information of the energy storage system in the overall system, a basic model of the energy storage system is constructed accordingly; Based on the grid connection data of the photovoltaic power generation system, the consumption data of photovoltaic power generation, the fluctuation data of photovoltaic power generation and the constraints of photovoltaic power generation, the basic model of the photovoltaic system is constructed accordingly.

5. The method according to claim 1, It is characterized in that The determining of current decision variables based on the current energy scheduling data set and the current energy scheduling prediction data set includes: Based on the current energy dispatching data set and the current energy dispatching prediction data set, the charging / discharging power of the energy storage system, the charging amount of the charging pile and the power purchase amount of the power grid are obtained to form the current decision variables.

6. The method according to claim 1, It is characterized in that The determining of the current optimization energy scheduling strategy based on the current decision variables and the current objective function includes: The current decision variables are input into the current objective function and the objective function is solved using an improved sparrow search algorithm to obtain the current optimized energy scheduling strategy.

7. The method according to claim 1, It is characterized in that After the step of determining the current optimized energy scheduling strategy based on the current decision variables and the current objective function, updating the energy scheduling strategy for the day with the current optimized energy scheduling strategy, and returning to execute the step of obtaining the current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition condition, until the step of stopping when the energy scheduling strategy stop updating instruction is detected, the method further includes: Acquire virtual power plant data corresponding to the building energy access scenario and upload it to the virtual power plant; Obtain carbon emission data corresponding to the building energy access scenario and upload it to the carbon management platform.

8. An energy interconnection intelligent management and control device, It is characterized in that include: An access scenario acquisition unit, configured to respond to an energy intelligent control instruction and acquire a building energy access scenario corresponding to the energy intelligent control instruction; A daily energy scheduling strategy acquisition unit, used to acquire the daily energy scheduling strategy corresponding to the building energy access scenario; wherein the daily energy scheduling strategy is used to determine the energy scheduling working mode for photovoltaic energy power supply, energy storage system power supply and city power supply in the building energy access scenario; An energy scheduling data set acquisition unit is used to acquire a current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition conditions; wherein the current energy scheduling data set includes at least a photovoltaic power generation data subset, an energy storage system data subset, a load demand data subset and an electricity price data subset; A prediction unit, configured to obtain a current energy scheduling prediction data set corresponding to the current energy scheduling data set based on the current energy scheduling data set and a pre-trained prediction model; wherein the current energy scheduling prediction data set includes at least current photovoltaic power generation prediction data corresponding to the photovoltaic power generation data subset, and current load demand prediction data corresponding to the load demand data subset; A basic model acquisition unit, used to acquire a basic model of an energy storage system and a basic model of a photovoltaic system corresponding to the building energy access scenario; A current objective function acquisition unit, used to determine a current objective function based on the energy storage system basic model and the photovoltaic system basic model; A current decision variable acquisition unit, configured to determine a current decision variable based on the current energy scheduling data set and the current energy scheduling prediction data set; An energy scheduling strategy optimization unit is used to determine the current optimized energy scheduling strategy based on the current decision variables and the current objective function, update the energy scheduling strategy for the day corresponding to the current optimized energy scheduling strategy, and return to execute the step of obtaining the current energy scheduling data set corresponding to the building energy access scenario and the current system time if it is determined that the current system time meets the preset prediction data acquisition conditions, until it detects an energy scheduling strategy stop updating instruction.

9. A computer device, It is characterized in that The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the energy interconnection intelligent management and control method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the energy interconnection intelligent management and control method as described in any one of claims 1 to 7 can be implemented.

Images