An energy router-based optical storage direct flexible building energy system coordination control method, system, device and medium

Abstract

The application discloses an energy router-based photovoltaic storage direct flexible building energy system coordinated control method, system, device and medium, and belongs to the technical field of power system coordinated control, which comprises the following steps: acquiring energy operation data of the photovoltaic storage direct flexible building energy system and preprocessing the energy operation data, constructing an energy operation state data set, performing energy modeling on energy ports in the photovoltaic storage direct flexible building energy system, obtaining a dynamic energy model, and determining a candidate energy routing regulation scheme of the energy ports; performing energy supply safety risk assessment on the candidate energy routing regulation scheme according to energy operation prediction data in a preset scheduling time window, determining a target energy routing regulation scheme according to an assessment result, and realizing coordinated control of the photovoltaic storage direct flexible building energy system. The application solves the problem that the energy supply safety risk of the photovoltaic storage direct flexible building energy system is not fully considered in the prior art.

Description

Technical Field

[0001] This invention relates to the field of power system coordination and control technology, specifically to a method, system, equipment, and medium for coordinated control of a building energy system based on energy routers, including photovoltaic, energy storage, direct current, and flexible energy transmission. Background Technology

[0002] The photovoltaic-storage-DC-flexible system combines photovoltaic power generation with energy storage technology to dynamically balance power supply and demand. DC power distribution eliminates the AC-DC conversion stage, thus improving energy efficiency. Traditional building energy supply mainly deals with the relationship between power supply and building energy consumption, while flexible technology addresses a much more complex problem, involving the coordinated operation of grid power, distributed photovoltaics, energy storage, and building energy consumption. Therefore, developing flexible technology to solve the current problem of prominent peak power loads and to match future high-proportion renewable energy generation models is of great significance.

[0003] Current energy regulation methods primarily focus on directly allocating power based on photovoltaic output, building load, and energy storage operating status. However, existing technologies do not fully consider the spatiotemporal differences and abnormal disturbances in operating data, and lack a comprehensive assessment of power supply and demand, energy storage state of charge, and DC bus voltage before executing candidate energy routing regulation schemes. This can easily lead to inaccurate port power regulation or energy supply risks.

[0004] This invention aims to address the problems of insufficient data processing, poor coordination of energy ports, and lack of pre-implementation energy supply security risk assessment in existing energy regulation systems. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is: how to address the issue of insufficient consideration of energy supply security risks in existing photovoltaic-storage-direct-flexible building energy systems; this invention achieves coordinated control of photovoltaic-storage-direct-flexible building energy systems by constructing a dynamic energy model, evaluating candidate energy routing and control schemes, determining the target energy routing and control scheme, and so on.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a coordinated control method for a building energy system based on energy routers, comprising the following steps:

[0008] Acquire and preprocess the energy operation data of the photovoltaic-storage-flexible building energy system to construct an energy operation status dataset;

[0009] Based on the energy operation status dataset, energy modeling is performed on the energy ports of the photovoltaic-storage-direct-flexible building energy system to obtain a dynamic energy model;

[0010] Based on the dynamic energy model, candidate energy routing and control schemes for the energy port are determined;

[0011] The candidate energy routing control schemes are evaluated under preset conditions to obtain evaluation results;

[0012] Based on the evaluation results, a target energy routing and control scheme will be determined.

[0013] The photovoltaic-storage-direct-flexible building energy system is coordinated and controlled according to the target energy routing and control scheme.

[0014] As a preferred embodiment of the coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router according to the present invention, the step of constructing the energy operation status dataset includes:

[0015] Step 1.1: Perform spatiotemporal alignment and standardization processing on the collected energy operation data to obtain aligned energy operation data;

[0016] Step 1.2: Perform outlier processing, data fusion, and state estimation on the aligned energy operation data to construct the energy operation state dataset.

[0017] As a preferred embodiment of the coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router as described in this invention, the step of obtaining the dynamic energy model includes:

[0018] Step 2.1: Based on the energy operation status dataset, dynamically divide the energy port into power regions to obtain a dynamic power management unit;

[0019] Step 2.2: Determine the energy interaction relationship based on the differences in operating status between the energy ports, and construct a local energy interaction topology and energy port coupling relationship matrix based on the energy interaction relationship;

[0020] Step 2.3: Determine the power supply and demand deviation based on the power balance relationship between the energy port and the DC bus, and construct the dynamic energy model based on the dynamic power control unit, the local energy interaction topology, the energy port coupling relationship matrix, and the power supply and demand deviation.

[0021] As a preferred embodiment of the coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router according to the present invention, the step of determining the candidate energy routing control scheme includes:

[0022] Step 3.1: Configure the energy port as an energy port agent, and input the dynamic energy model and the energy operation status dataset into the multi-agent algorithm;

[0023] Step 3.2: Under the constraints of system operation, perform collaborative optimization on each energy port agent to determine the power regulation action corresponding to each energy port;

[0024] Step 3.3: Determine the candidate energy routing control scheme based on the power control action and energy port control priority corresponding to each energy port.

[0025] As a preferred embodiment of the coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router according to the present invention, the step of obtaining the evaluation result includes:

[0026] Step 4.1: Obtain the predicted energy port power, energy storage state of charge, and DC bus voltage based on the candidate energy routing control scheme within the preset scheduling time window;

[0027] Step 4.2: Based on the energy port power prediction data, the energy storage state of charge prediction data, and the DC bus voltage prediction data, determine the power supply and demand risk, the energy storage state of charge over-limit risk, and the DC bus voltage over-limit risk, respectively.

[0028] Step 4.3: Determine the comprehensive energy supply security risk index and energy supply security risk level based on the power supply and demand risk, the energy storage state of charge exceeding the limit risk, and the DC bus voltage exceeding the limit risk, and determine the comprehensive energy supply security risk index and the energy supply security risk level as the evaluation result.

[0029] As a preferred embodiment of the coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router according to the present invention, the step of determining the target energy routing control scheme includes:

[0030] Step 5.1: Determine the corresponding differentiated energy routing and control rules based on the energy supply security risk level;

[0031] Step 5.2: Adjust the power control actions in the candidate energy routing control scheme according to the differentiated energy routing control rules to obtain the adjusted power control actions;

[0032] Step 5.3: Determine the energy routing allocation order based on the energy port control priority of each energy port, the energy supply security risk level, and the power control cost, and arrange the adjusted power control actions according to the energy routing allocation order to obtain the target energy routing control scheme.

[0033] As a preferred embodiment of the coordinated control method for a photovoltaic-storage-direct-drive-flexible building energy system based on an energy router according to the present invention, the coordinated control of the photovoltaic-storage-direct-drive-flexible building energy system according to the target energy routing control scheme includes:

[0034] Step 6.1: Determine the power scheduling authority of each energy port according to the target energy routing and control scheme, and generate a coordination control command according to the power scheduling authority;

[0035] Step 6.2: Send the coordination control command to the energy router, and determine the energy port to be adjusted and its corresponding power adjustment amount according to the coordination control command;

[0036] Step 6.3: Control the energy router to adjust the power of the energy port to be adjusted according to the power adjustment amount, so as to adjust the DC bus voltage;

[0037] Step 6.4: Collect the actual power operation status, energy storage state of charge change data, DC bus voltage fluctuation data, and green electricity consumption data of each energy port after adjustment to obtain system operation feedback data;

[0038] Step 6.5: Preprocess the system operation feedback data to construct the energy operation status dataset for the next control cycle;

[0039] Step 6.6: Update the control parameters of the multi-agent algorithm based on the system operation feedback data, and determine the candidate energy routing control scheme for the next control cycle based on the updated multi-agent algorithm.

[0040] This invention provides a coordinated control system for a building energy system based on an energy router, comprising an energy operation data processing module, an energy modeling module, a candidate scheme determination module, a scheme evaluation module, a target scheme determination module, and a coordinated control module.

[0041] The energy operation data processing module is used to acquire the energy operation data of the photovoltaic-storage-direct-flexible building energy system, preprocess the energy operation data, and construct an energy operation status dataset.

[0042] The energy modeling module is used to determine the energy interaction relationship and power supply-demand deviation between energy ports in the photovoltaic-storage-direct-flexible building energy system based on the energy operation status dataset, and to construct a dynamic energy model based on the energy interaction relationship and the power supply-demand deviation.

[0043] The candidate scheme determination module is used to input the dynamic energy model and the energy operation status dataset into a multi-agent algorithm, perform collaborative optimization on the energy port agents corresponding to each energy port, determine the power regulation action, and determine the candidate energy routing regulation scheme based on the power regulation action and the energy supply priority.

[0044] The scheme evaluation module is used to evaluate the candidate energy routing control schemes under preset conditions and obtain evaluation results.

[0045] The target scheme determination module is used to determine differentiated energy routing control rules based on the evaluation results, and adjust the power control actions in the candidate energy routing control schemes according to the differentiated energy routing control rules to obtain the target energy routing control scheme.

[0046] The coordination control module is used to determine the power scheduling authority of each energy port according to the target energy routing and control scheme, generate coordination control instructions, and control the energy router to adjust the energy ports according to the coordination control instructions.

[0047] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the aforementioned coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router.

[0048] The present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the aforementioned coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router.

[0049] The beneficial effects of this invention are as follows: By constructing a dynamic energy model, the energy interaction relationship and power balance relationship between energy ports are jointly involved in energy modeling; by inputting the dynamic energy model and energy operation status dataset into a multi-agent algorithm, power regulation actions are determined under system operation constraints, and candidate energy routing regulation schemes are formed by combining energy supply priorities, so that the operation status and energy supply sequence of each energy port are coordinated with each other, reducing power conflicts caused by independent regulation; by assessing the power supply and demand risks, energy storage state of charge limit risks, and DC bus voltage limit risks of the candidate energy routing regulation schemes, the target energy routing regulation scheme is determined based on the assessment results, so that power regulation is combined with energy supply safety risk management, avoiding the direct execution of candidate energy routing regulation schemes without assessment. Attached Figure Description

[0050] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating the overall process of a coordinated control method for a building energy system based on an energy router, specifically a method for coordinating photovoltaic-storage-direct-drive-flexible systems, according to an embodiment of the present invention.

[0052] Figure 2 This is a comparison chart showing the convergence performance of a multi-agent algorithm before and after an improvement of a coordinated control method for a building energy system based on an energy router, according to an embodiment of the present invention.

[0053] Figure 3 This invention provides a method for coordinated control of a photovoltaic-storage-direct-flexible building energy system based on an energy router, which measures the changes in green electricity utilization, photovoltaic output, and building load within a 24-hour scheduling cycle. Detailed Implementation

[0054] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0055] It should be noted that existing photovoltaic-storage-direct-drive-flexible building energy systems suffer from inconsistencies in energy operation data regarding time references and data status. This can easily lead to power supply and demand conflicts if power regulation is implemented. Furthermore, candidate energy routing and regulation schemes often lack risk assessments before implementation, potentially resulting in power regulation outcomes at the energy port that do not align with energy supply security requirements.

[0056] Therefore, in response to the problems of insufficient energy operation data processing, lack of coordination in energy port power regulation, and insufficient consideration of energy supply security risks before the implementation of candidate energy routing regulation schemes in existing technologies, this embodiment provides a coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router.

[0057] During the operation of the photovoltaic-storage-direct-drive-flexible building energy system, energy operation data is acquired and preprocessed to construct an energy operation status dataset. Subsequently, energy models are performed on the energy ports based on the energy operation status dataset to obtain a dynamic energy model, and candidate energy routing and control schemes are determined based on the dynamic energy model.

[0058] Furthermore, candidate energy routing and control schemes are evaluated under preset conditions to obtain evaluation results, and a target energy routing and control scheme is determined based on the evaluation results. Finally, the photovoltaic-storage-direct-drive-flexible building energy system is coordinated and controlled according to the target energy routing and control scheme.

[0059] By combining energy operation data processing, energy port energy modeling, and candidate energy routing control scheme evaluation in the above manner, the energy interaction relationship between energy ports and the energy supply security risk are jointly involved in the determination of the target energy routing control scheme, thereby reducing the power conflict caused by independent control of energy ports.

[0060] Reference Figure 1 This is an embodiment of a coordinated control method for a building energy system based on an energy router, which is a photovoltaic-storage-direct-flexible building energy system.

[0061] In this embodiment of the invention, acquiring and preprocessing energy operation data of a photovoltaic-storage-direct-flexible building energy system to construct an energy operation status dataset includes the following steps:

[0062] Step 1.1: Perform spatiotemporal alignment and standardization on the collected energy operation data to obtain aligned energy operation data.

[0063] As an example, a sliding window time-series registration algorithm is used to perform timestamp calibration and phase compensation on time-of-use electricity prices, photovoltaic output, building load, energy storage operation status, DC bus voltage and port interactive power, and to obtain aligned energy operation data using a three-dimensional energy domain coordinate system-data interaction format of power, voltage and time series.

[0064] Step 1.2: Perform outlier processing, data fusion, and state estimation on the aligned energy operation data to construct an energy operation state dataset.

[0065] As an example, outlier processing is performed on photovoltaic fluctuation noise, random load disturbances, and acquisition offset data in the aligned energy operation data. Data fusion weights are determined based on data source reliability, and state estimation is performed using square root unscented Kalman filtering to construct an energy operation state dataset. It should be noted that the specific form of data source reliability is as follows:

[0066] ;

[0067] In the formula, Indicates the first Data sources at time Credibility, Indicates the data source number. Indicates the sampling time number. Indicates the first Data sources at time The observed values, This indicates that the photovoltaic-storage-direct-drive-flexible building energy system is available at any time. The actual operating status, Indicates that the observed values ​​were obtained Under the condition that the actual operating state is The conditional probability.

[0068] Furthermore, based on the credibility of each data source, the data fusion weights of each data source are normalized, so that data sources with higher credibility have higher data fusion weights during the data fusion process, and the impact of abnormal data and measurement disturbances on the fusion results is reduced.

[0069] The specific manifestation of data fusion weights is as follows:

[0070] ;

[0071] In the formula, Indicates the first Data sources at time The fusion weight; Indicates the first The credibility of each data source; This represents the sum of the credibility of all data sources.

[0072] Furthermore, based on the data fusion weights, the observation states provided by each data source are weighted and fused, and the weighted and fused states are estimated by square root unscented Kalman filtering to obtain an energy operation state dataset that includes the power of each energy port, the state of charge of energy storage, the DC bus voltage, and the power supply and demand deviation.

[0073] The specific format of the energy operation status dataset is as follows:

[0074] ;

[0075] In the formula, Indicates time Data set of building DC microgrid operation status. This represents the system state vector after filtering and estimation; Indicates to The observation status of each data source is weighted and fused.

[0076] In this embodiment of the invention, based on an energy operation status dataset, energy modeling is performed on the energy ports of the photovoltaic-storage-direct current-flexible building energy system to obtain a dynamic energy model, comprising the following steps:

[0077] Step 2.1: Based on the energy operation status dataset, dynamically divide the energy port into power regions to obtain the dynamic power control unit.

[0078] As an example, based on the principle of weighted triangulation graph theory, the real-time power interaction status of photovoltaic port, energy storage port, DC load port and AC grid port is used as the generator element. The power control unit boundary is divided according to the power supply and demand intensity, building load power, line loss and power conversion loss to obtain the dynamic power control unit.

[0079] Step 2.2: Determine the energy interaction relationship based on the differences in operating status between energy ports, and construct a local energy interaction topology and energy port coupling relationship matrix based on the energy interaction relationship.

[0080] As an example, an improved firefly neighbor association algorithm is used to determine the energy interaction association strength between energy ports based on the electrical or topological distance between energy ports, as well as power differences, voltage differences, and energy storage state of charge differences.

[0081] The specific manifestations of the strength of energy interaction correlation are as follows:

[0082] ;

[0083] In the formula, Indicates time No. The port and the first The energy interaction correlation strength between ports Indicates the first The port and the first The square of the electrical or topological distance between ports. This represents the power difference weighting coefficient. This represents the voltage difference weighting coefficient. Indicates the weighting coefficient for differences in energy storage status. and They represent the first The port and the first Each port at time The power; and They represent the first The port and the first Each port at time voltage, and They represent the first The port and the first Each port at time The state of charge.

[0084] Furthermore, the energy interaction correlation strength is compared with a preset correlation strength threshold. When the energy interaction correlation strength is greater than the preset correlation strength threshold, an energy interaction correlation relationship is determined to exist between the two corresponding energy ports, and the corresponding matrix element is set to 1. When the energy interaction correlation strength is not greater than the preset correlation strength threshold, an energy interaction correlation relationship is determined to exist between the two corresponding energy ports, and the corresponding matrix element is set to zero.

[0085] The specific form of the energy port coupling relationship matrix is ​​as follows:

[0086] ;

[0087] In the formula, Indicates time The coupling relationship matrix of the port intelligent agent; Representation matrix The Middle line, number The elements of the column; when When =1, it means the first... The port and the first There is a local energy interaction relationship between the ports; when When =0, it means that there is no direct energy interaction between the two.

[0088] It should be noted that when the correlation strength between ports exceeds a preset threshold, =1, otherwise =0.

[0089] Furthermore, based on the matrix elements in the energy port coupling relationship matrix, the corresponding energy ports are connected, and energy ports with energy interaction relationships are designated as adjacent energy ports, forming a local energy interaction topology. The energy interaction relationship strength between each energy port is arranged according to the energy port number to form an energy port coupling weight matrix.

[0090] Step 2.3: Determine the power supply and demand deviation based on the power balance relationship between the energy port and the DC bus, and construct a dynamic energy model based on the local energy interaction topology, the energy port coupling relationship matrix, and the power supply and demand deviation.

[0091] As an example, the power supply and demand deviation is calculated based on photovoltaic output power, energy storage port power, AC grid interaction power, building DC load power, and power loss.

[0092] The specific manifestations of power supply and demand deviation are as follows:

[0093] ;

[0094] In the formula, Indicates time The power supply and demand imbalance of building DC microgrids; Indicates the amount of change or deviation; Indicates time The photovoltaic output power; This represents the energy storage port power at time k, where it is positive during energy storage discharge and negative during energy storage charging. denoted by the AC grid interaction power at time k, where the value is positive when the grid supplies power to the DC microgrid; and These represent the building's DC load power, line loss, and power conversion loss at time k, respectively.

[0095] It should be noted that a dynamic energy model is constructed by combining the energy operation status dataset, the energy port coupling relationship matrix, the energy port coupling weight matrix, the power supply and demand deviation, the DC bus voltage, and the energy storage state of charge.

[0096] The specific form of the dynamic energy model is as follows:

[0097] ;

[0098] In the formula, Indicates time Dataset of building DC microgrid operation status; Indicates time The coupling relationship matrix of the port intelligent agent; Indicates time The port coupling weight matrix; Indicates time The power supply and demand deviation; Indicates time DC bus voltage; Indicates time The energy storage state of charge.

[0099] In this embodiment of the invention, determining candidate energy routing control schemes for energy ports based on a dynamic energy model includes the following steps:

[0100] Step 3.1: Configure the energy port as an energy port agent and input the dynamic energy model and energy operation status dataset into the multi-agent algorithm.

[0101] As an example, the photovoltaic port, energy storage port, DC load port and AC grid port are configured as energy port intelligent agents, and corresponding energy port operating status and power regulation action space are set for each energy port intelligent agent.

[0102] Furthermore, the energy port coupling matrix, energy port coupling weight matrix, power supply and demand deviation, DC bus voltage, and energy storage state of charge from the dynamic energy model, along with the energy operating state dataset, are input into the improved multi-agent algorithm. During the centralized training phase, a global operating state is constructed based on the energy port operating states of each energy port agent, and this global operating state is used to train the commentator network and the actor network.

[0103] Furthermore, during the distributed execution phase, each energy port agent obtains the operational information of associated energy ports based on the local energy interaction topology, and uses its own operational information and the operational information of associated energy ports as decision inputs.

[0104] Step 3.2: Under the constraints of system operation, perform collaborative optimization on the intelligent agents of each energy port to determine the power regulation action corresponding to each energy port.

[0105] As an example, building electricity efficiency, energy supply flexibility, and the proportion of green electricity consumption are set as the optimization objectives of the multi-agent algorithm, and the operating range of energy port power, energy storage state of charge, and DC bus voltage are set as system operating constraints. Based on the operating status of each energy port agent in the current control cycle, the electricity efficiency benefit, energy supply flexibility benefit, green electricity consumption benefit, power limit violation penalty, energy storage state of charge violation penalty, and DC bus voltage violation penalty are determined respectively. A multi-objective composite reward function is then constructed based on the benefits and penalty terms.

[0106] The specific form of the continuous action vector is as follows:

[0107] ;

[0108] In the formula, Indicates the first Each port at time The amount of power regulation; Indicates time Energy storage charging and discharging power commands; Indicates time The amount of flexible load regulation in the building; Indicates time AC power grid interactive power commands.

[0109] Furthermore, based on the continuous action vectors output by the intelligent agents at each energy port, the power adjustment amount or power command corresponding to each energy port is extracted, and the power adjustment amount or power command is determined as the power control action of the corresponding energy port.

[0110] like Figure 2 The figure shows the convergence performance comparison between the improved multi-agent algorithm and the traditional multi-agent algorithm.

[0111] As the number of training iterations increases, the convergence loss of the improved multi-agent algorithm decreases faster than that of the traditional multi-agent algorithm, and the convergence loss after stabilization is lower. This indicates that the improved multi-agent algorithm can quickly form a stable power regulation strategy, providing an algorithmic basis for determining the power regulation actions corresponding to each energy port.

[0112] Step 3.3: Determine candidate energy routing control schemes based on the power control actions and energy port control priorities corresponding to each energy port.

[0113] As an example, a multi-agent algorithm is used to perform game-theoretic calculations on the agents at each energy port to obtain the power allocation priority corresponding to each energy port, and this power allocation priority is determined as the energy port control priority. The energy ports are then sorted according to their control priorities, and their energy port identifiers, power control actions, and order are associated to form candidate energy routing control schemes. Each candidate energy routing control scheme includes the energy port to be controlled, the corresponding power adjustment amount or power command, and the control order among the energy ports to be controlled.

[0114] In an embodiment of the present invention, evaluating candidate energy routing control schemes under preset conditions to obtain evaluation results includes the following steps:

[0115] Step 4.1: Obtain the predicted power data of energy ports, the predicted state of charge data of energy storage, and the predicted DC bus voltage data based on the candidate energy routing control scheme within the preset scheduling time window.

[0116] As an example, based on the candidate energy routing control scheme, the power prediction curve, energy storage state of charge change trend and DC bus voltage fluctuation data of each energy port within the preset scheduling time window are obtained, and the energy port power prediction data, energy storage state of charge prediction data and DC bus voltage prediction data are obtained respectively.

[0117] Step 4.2: Based on the energy port power prediction data, energy storage state of charge prediction data, and DC bus voltage prediction data, determine the power supply and demand risk, energy storage state of charge over-limit risk, and DC bus voltage over-limit risk, respectively.

[0118] As an example, the power supply-demand deviation is calculated based on energy port power forecast data, and the power supply-demand risk is determined based on the proportion of the power supply-demand deviation relative to the preset rated power threshold. The energy storage state of charge (SOC) exceedance risk is determined based on energy storage SOC forecast data and energy storage charge / discharge margin. The DC bus voltage exceedance risk is determined based on DC bus voltage forecast data and DC bus voltage offset.

[0119] Step 4.3: Determine the comprehensive energy supply safety risk index and energy supply safety risk level based on the power supply and demand risk, the energy storage state of charge over-limit risk, and the DC bus voltage over-limit risk, and determine the comprehensive energy supply safety risk index and energy supply safety risk level as the assessment result.

[0120] As an example, corresponding risk weights are set for power supply and demand risks, energy storage state of charge exceeding limits risks, and DC bus voltage exceeding limits risks. The risks are then weighted and combined with their corresponding risk weights to obtain a comprehensive energy supply security risk index.

[0121] The specific manifestations of the comprehensive energy supply security risk indicators are as follows:

[0122] ;

[0123] In the formula, Indicates power risk weight; Indicates the risk weight of energy storage SOC; Indicates the risk weight of DC bus voltage; Indicates time The risk of predicted power exceeding the limit; This indicates the predicted SOC (State of Charge) exceedance risk at time k. This indicates the predicted risk of DC bus voltage exceeding the limit at time k;

[0124] Furthermore, the comprehensive energy supply security risk indicators are compared with preset risk thresholds to determine the energy supply security risk level.

[0125] The specific manifestations of energy supply security risk levels are as follows:

[0126] ;

[0127] In the formula, Indicates time Energy supply security risk level, Indicates time Comprehensive energy supply security risk indicators This indicates a preset general risk threshold. This indicates that a preset high-risk threshold is set, and the preset general risk threshold is lower than the preset high-risk threshold.

[0128] Furthermore, the comprehensive energy supply security risk indicators and energy supply security risk levels corresponding to each prediction time are correlated, and the comprehensive energy supply security risk indicators and energy supply security risk levels within the preset scheduling time window are determined as the evaluation results.

[0129] In this embodiment of the invention, determining the target energy routing and control scheme based on the evaluation results includes the following steps:

[0130] Step 5.1: Determine the corresponding differentiated energy routing and control rules based on the energy supply security risk level.

[0131] As an example, when the energy supply security risk level is at the safe risk level, the candidate energy routing control scheme is kept unchanged. When the energy supply security risk level is at the general risk level, the charging and discharging power or charging and discharging rate of the energy storage port is prioritized for adjustment. When the energy supply security risk level is at the high risk level, the output power of the photovoltaic port, the charging and discharging power of the energy storage port, the building flexible load power of the DC load port, and the interactive power of the AC grid port are adjusted synchronously.

[0132] Step 5.2: Adjust the power control actions in the candidate energy routing control schemes according to the differentiated energy routing control rules to obtain the adjusted power control actions.

[0133] As an example, when the energy supply security risk level is at the safe risk level, the power regulation actions in the candidate energy routing control scheme remain unchanged. When the energy supply security risk level is at the general risk level, the energy storage charging and discharging power commands in the candidate energy routing control scheme are adjusted. When the energy supply security risk level is at the high risk level, the photovoltaic port output power, energy storage port charging and discharging power, building flexible load regulation, and AC grid port interaction power in the candidate energy routing control scheme are adjusted synchronously to obtain the adjusted power regulation actions.

[0134] Step 5.3: Determine the energy routing allocation sequence based on the energy port control priority, energy supply security risk level, and power control cost of each energy port, and arrange the adjusted power control actions according to the energy routing allocation sequence to obtain the target energy routing control scheme.

[0135] As an example, port energy consumption priority and critical load guarantee level are incorporated into the energy port regulation priority. For energy ports undertaking critical energy supply guarantee tasks, the priority power scheduling order is determined based on their energy port regulation priority. For the remaining energy ports, energy routing allocation coefficients are calculated based on port energy consumption priority, critical load guarantee level, energy supply security risk level, and power regulation cost.

[0136] The specific form of the energy routing allocation coefficient is as follows:

[0137] ;

[0138] In the formula, Indicates the first Each energy port at time Energy routing allocation coefficient, Indicates the first Each energy port at time The port priority is used. Indicates the first Each energy port at time Energy supply security risk level, Indicates the first Each energy port at time Critical load guarantee level or energy supply importance, Indicates the first Each energy port at time The cost of power regulation This indicates a positive number used to prevent the denominator from being zero. , and These represent the weighting coefficients corresponding to the port energy consumption priority, energy supply security risk level, and critical load guarantee level, respectively.

[0139] It should be noted that the energy consumption priority at the port and the critical load guarantee level together characterize the energy port regulation priority.

[0140] In an embodiment of the present invention, the step of coordinating and controlling the photovoltaic-storage-direct-flexible building energy system according to the target energy routing and control scheme includes the following steps:

[0141] Step 6.1: Based on the energy routing allocation order in the target energy routing control scheme, assign priority power scheduling permissions to high-priority energy ports undertaking critical energy supply guarantee tasks, and assign corresponding power scheduling permissions to the remaining energy ports. Based on the power scheduling permissions and power control actions of each energy port, generate corresponding power scheduling permission instructions or power avoidance instructions, and use these instructions as coordination control commands.

[0142] Step 6.2: Send the coordination control command to the energy router and determine the energy port to be regulated and its corresponding power regulation amount according to the coordination control command.

[0143] As an example, the coordinated control command is sent to the port execution module of the energy router. The port execution module reads the energy port identifier and power regulation amount from the coordinated control command, identifies the energy port corresponding to the energy port identifier as the energy port to be regulated, and determines the power regulation amount corresponding to the energy port to be regulated.

[0144] Step 6.3: Control the energy router to adjust the power of the energy port to be adjusted according to the power adjustment amount, so as to regulate the DC bus voltage.

[0145] As an example, the energy router adjusts the output power of the photovoltaic port, the charging and discharging power of the energy storage port, the building flexible load power of the DC load port, or the interactive power of the AC grid port according to the power regulation amount through the multi-port power conversion module and the port execution module, and controls the DC bus voltage through the micro DC bus module.

[0146] Step 6.4: Collect data on the actual power operation status after adjustment of each energy port, changes in the state of charge of energy storage, DC bus voltage fluctuation data, and green energy consumption data to obtain system operation feedback data;

[0147] As an example, after the coordinated control command is executed, the actual power operation status of each energy port, the change data of energy storage charge status, the DC bus voltage fluctuation data, and the green electricity consumption data are collected, and the collected data are correlated to obtain system operation feedback data.

[0148] Step 6.5: Preprocess the system operation feedback data to construct the energy operation status dataset for the next control cycle.

[0149] As an example, the system operation feedback data is sent to the multi-source data sensing module. Following the data preprocessing methods in steps 1.1 and 1.2, the system operation feedback data is subjected to spatiotemporal alignment, standardization, outlier handling, data fusion, and state estimation to construct the energy operation status dataset for the next control cycle.

[0150] Step 6.6: Update the control parameters of the multi-agent algorithm based on the system operation feedback data, and determine the candidate energy routing control scheme for the next control cycle based on the updated multi-agent algorithm.

[0151] As an example, the weight factors and reward function parameters of the improved multi-agent algorithm are updated based on system operation feedback data. The energy operation status dataset for the next regulation cycle and the corresponding dynamic energy model are input into the updated improved multi-agent algorithm to determine the power regulation actions and energy port regulation priorities for each energy port, thereby obtaining candidate energy routing regulation schemes for the next regulation cycle.

[0152] like Figure 3 The figure shows the changes in green energy utilization rate, photovoltaic output, and building load during a 24-hour scheduling cycle. The green energy utilization rate corresponding to the improved multi-agent algorithm is generally higher than that of the traditional multi-agent algorithm and rule-based control method, and it can dynamically adjust with changes in photovoltaic output and building load. This indicates that the coordinated control method provided in this embodiment can improve the matching relationship between photovoltaic energy and building load through coordinated adjustment between energy ports, thereby increasing the green energy utilization rate.

[0153] This technical solution also provides a coordinated control system for a building energy system based on energy routers, including an energy operation data processing module, an energy modeling module, a candidate scheme determination module, a scheme evaluation module, a target scheme determination module, and a coordinated control module.

[0154] The energy operation data processing module is used to acquire energy operation data of photovoltaic-storage-direct-drive-flexible building energy systems, and to perform spatiotemporal alignment, standardization, outlier handling, data fusion, and state estimation to construct an energy operation status dataset.

[0155] The energy modeling module is used to divide dynamic power control units based on the energy operation status dataset, construct local energy interaction topology and energy port coupling relationship matrix, determine power supply and demand deviation, and construct dynamic energy model.

[0156] The candidate scheme determination module is used to configure energy ports as energy port agents, input dynamic energy models and energy operation status datasets into a multi-agent algorithm, determine the power regulation actions and energy port regulation priorities corresponding to each energy port, and obtain candidate energy routing and regulation schemes.

[0157] The scheme evaluation module is used to obtain energy port power prediction data, energy storage state of charge prediction data and DC bus voltage prediction data within a preset scheduling time window, determine power supply and demand risks, energy storage state of charge over-limit risks and DC bus voltage over-limit risks, and obtain comprehensive energy supply security risk indicators and energy supply security risk levels.

[0158] The target scheme determination module is used to determine differentiated energy routing control rules based on the energy supply security risk level, adjust the power control actions in the candidate energy routing control schemes, and determine the energy routing allocation order based on the energy port control priority, energy supply security risk level and power control cost to obtain the target energy routing control scheme.

[0159] The coordination and control module is used to generate coordination and control commands based on the target energy routing and regulation scheme, control the energy router to adjust the power of the energy port, collect system operation feedback data, construct the energy operation status dataset for the next regulation cycle, and update the regulation parameters of the multi-agent algorithm.

[0160] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0161] 1. Compared with the method of power distribution using a fixed energy topology, the dynamic energy model of this invention can reflect the energy interaction relationship between photovoltaic, energy storage, DC load and AC grid as the operating state changes.

[0162] 2. This invention combines a dynamic energy model with a multi-agent algorithm to collaboratively optimize the agents at each energy port under system operational constraints. First, candidate energy routing and control schemes are formed, and then these schemes are evaluated before execution. This two-stage processing method ensures that the collaborative optimization of power regulation actions and the verification of energy supply security risks mutually constrain each other, avoiding situations where the energy storage state of charge or DC bus voltage exceeds limits due to using only power allocation results as coordinated control commands.

[0163] 3. This invention combines power supply and demand risk, energy storage state of charge exceeding limit risk, and DC bus voltage exceeding limit risk into a comprehensive energy supply safety risk index, and determines differentiated energy routing control rules based on the energy supply safety risk level. Compared with monitoring power, energy storage state of charge, or DC bus voltage separately, this invention can select the corresponding power control range based on the combination results of multiple risks, so that the local adjustment of the energy storage port and the synchronous adjustment of multiple energy ports have a unified risk judgment basis.

[0164] 4. This invention combines the priority of energy port control, the level of energy supply security risk and the cost of power control to determine the energy routing allocation order, and executes the target energy routing control scheme through the energy router. Then, it updates the control parameters of the multi-agent algorithm based on the system operation feedback data, so as to avoid the fixed control order from being out of touch with the actual energy operation status.

[0165] It should be noted that if the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0166] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0167] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0168] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination of all three. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0169] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A coordinated control method for a building energy system based on energy routers, characterized in that, include: Acquire and preprocess the energy operation data of the photovoltaic-storage-flexible building energy system to construct an energy operation status dataset; Based on the energy operation status dataset, energy modeling is performed on the energy ports of the photovoltaic-storage-direct-flexible building energy system to obtain a dynamic energy model; Based on the dynamic energy model, candidate energy routing and control schemes for the energy port are determined; Based on the energy operation prediction data within the preset scheduling time window, the candidate energy routing control scheme is assessed for energy supply security risks, and the assessment results are obtained. Based on the evaluation results, a target energy routing and control scheme will be determined. The photovoltaic-storage-direct-flexible building energy system is coordinated and controlled according to the target energy routing and control scheme.

2. The coordinated control method for a building energy system based on energy routers, as described in claim 1, is characterized in that... The steps for constructing the energy operation status dataset include: Step 1.1: Perform spatiotemporal alignment and standardization processing on the collected energy operation data to obtain aligned energy operation data; Step 1.2: Perform outlier processing, data fusion, and state estimation on the aligned energy operation data to construct the energy operation state dataset.

3. The coordinated control method for a building energy system based on energy routers, characterized in that, as described in claim 2, The steps to obtain the dynamic energy model include: Step 2.1: Based on the energy operation status dataset, dynamically divide the energy port into power regions to obtain a dynamic power management unit; Step 2.2: Determine the energy interaction relationship based on the differences in operating status between the energy ports, and construct a local energy interaction topology and energy port coupling relationship matrix based on the energy interaction relationship; Step 2.3: Determine the power supply and demand deviation based on the power balance relationship between the energy port and the DC bus, and construct the dynamic energy model based on the local energy interaction topology, the energy port coupling relationship matrix, and the power supply and demand deviation.

4. The coordinated control method for a building energy system based on energy routers, characterized in that, as described in claim 3, The steps for determining the candidate energy routing and control scheme include: Step 3.1: Configure the energy port as an energy port agent, and input the dynamic energy model and the energy operation status dataset into the multi-agent algorithm; Step 3.2: Under the constraints of system operation, perform collaborative optimization on each energy port agent to determine the power regulation action corresponding to each energy port; Step 3.3: Determine the candidate energy routing control scheme based on the power control action and energy port control priority corresponding to each energy port.

5. The coordinated control method for a building energy system based on energy routers, characterized in that, as described in claim 4, The steps to obtain the evaluation results include: Step 4.1: Obtain the predicted energy port power, energy storage state of charge, and DC bus voltage based on the candidate energy routing control scheme within the preset scheduling time window; Step 4.2: Based on the energy port power prediction data, the energy storage state of charge prediction data, and the DC bus voltage prediction data, determine the power supply and demand risk, the energy storage state of charge over-limit risk, and the DC bus voltage over-limit risk, respectively. Step 4.3: Determine the comprehensive energy supply security risk index and energy supply security risk level based on the power supply and demand risk, the energy storage state of charge exceeding the limit risk, and the DC bus voltage exceeding the limit risk, and determine the comprehensive energy supply security risk index and the energy supply security risk level as the evaluation result.

6. The coordinated control method for a building energy system based on energy routers, as described in claim 5, is characterized in that... The steps for determining the target energy routing and control scheme include: Step 5.1: Determine the corresponding differentiated energy routing and control rules based on the energy supply security risk level; Step 5.2: Adjust the power control actions in the candidate energy routing control scheme according to the differentiated energy routing control rules to obtain the adjusted power control actions; Step 5.3: Determine the energy routing allocation order based on the energy port control priority of each energy port, the energy supply security risk level corresponding to each energy port, and the power control cost, and arrange the adjusted power control actions according to the energy routing allocation order to obtain the target energy routing control scheme.

7. The coordinated control method for a building energy system based on energy routers, as described in claim 6, is characterized in that... The steps for coordinating and controlling the photovoltaic-storage-direct-flexible building energy system according to the target energy routing and control scheme include: Step 6.1: Determine the power scheduling authority of each energy port according to the target energy routing and control scheme, and generate a coordination control command according to the power scheduling authority; Step 6.2: Send the coordination control command to the energy router, and determine the energy port to be adjusted and its corresponding power adjustment amount according to the coordination control command; Step 6.3: Control the energy router to adjust the power of the energy port to be adjusted according to the power adjustment amount, so as to adjust the DC bus voltage; Step 6.4: Collect the actual power operation status, energy storage state of charge change data, DC bus voltage fluctuation data, and green electricity consumption data of each energy port after adjustment to obtain system operation feedback data; Step 6.5: Preprocess the system operation feedback data to construct the energy operation status dataset for the next control cycle; Step 6.6: Update the control parameters of the multi-agent algorithm based on the system operation feedback data, and determine the candidate energy routing control scheme for the next control cycle based on the updated multi-agent algorithm.

8. A coordinated control system for a building energy system based on energy routers, characterized in that, It includes an energy operation data processing module, an energy modeling module, a candidate solution determination module, a solution evaluation module, a target solution determination module, and a coordination and control module. The energy operation data processing module is used to acquire the energy operation data of the photovoltaic-storage-direct-flexible building energy system, preprocess the energy operation data, and construct an energy operation status dataset. The energy modeling module is used to determine the energy interaction relationship and power supply-demand deviation between energy ports in the photovoltaic-storage-direct-flexible building energy system based on the energy operation status dataset, and to construct a dynamic energy model based on the energy interaction relationship and the power supply-demand deviation. The candidate scheme determination module is used to input the dynamic energy model and the energy operation status dataset into a multi-agent algorithm, perform collaborative optimization on the energy port agents corresponding to each energy port, determine the power regulation action, and determine the candidate energy routing regulation scheme based on the power regulation action and the energy supply priority. The scheme evaluation module is used to evaluate the candidate energy routing control schemes under preset conditions and obtain evaluation results. The target scheme determination module is used to determine differentiated energy routing control rules based on the evaluation results, and adjust the power control actions in the candidate energy routing control schemes according to the differentiated energy routing control rules to obtain the target energy routing control scheme. The coordination control module is used to determine the power scheduling authority of each energy port according to the target energy routing and control scheme, generate coordination control instructions, and control the energy router to adjust the energy ports according to the coordination control instructions.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router, as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the coordinated control method for a photovoltaic-storage-direct-flexible building energy system based on an energy router, as described in any one of claims 1 to 7.

Images