A distributed resource aggregation analysis method and system

Abstract

The application relates to the technical field of electric power intelligent management, and discloses a distributed resource aggregation analysis method and system, which comprises a resource processing module, a data analysis module, an aggregation analysis module and a collaborative regulation module; the resource processing module is used for data acquisition and protocol analysis on the accessed distributed energy supply end; the data analysis module is used for receiving and processing multi-source heterogeneous data from the resource processing module, constructing a resource portrait, constructing a load model and outputting load prediction data for the I-type energy supply end, constructing a random process model of output and response of the II-type energy supply end and outputting new energy output data; the aggregation analysis module is used for setting optimal charging and discharging plans of each energy storage unit and a benchmark scheduling scheme of adjustable load; and the collaborative regulation module is used for generating a scheduling instruction and delivering the scheduling instruction to the corresponding energy supply end. The application can efficiently integrate power supply resources and accurately quantify, and effectively improves the observable, measurable and controllable level of the distributed power supply resources.

Description

Technical Field

[0001] This invention relates to the field of intelligent power management technology, specifically to a distributed resource aggregation analysis method and system. Background Technology

[0002] Currently, new energy sources, represented by wind power and photovoltaics, have become an important part of the power system. Their decentralized and intermittent characteristics pose a significant challenge to the traditional centralized dispatching model of "source follows load." Particularly in regional power grids like Xinjin District, the surge in air conditioning load during the summer heat coincides with the midday peak output of photovoltaic power plants, further widening the peak-to-valley difference. Meanwhile, the low load period at night can lead to curtailment of solar power due to high output. Traditional power grid dispatching methods struggle to accurately perceive and efficiently coordinate massive distributed resources. There is an urgent need to utilize digital technologies such as virtual power plants to aggregate and optimize the control of distributed power sources, energy storage systems, and controllable loads. This will enhance the flexibility, reliability, and renewable energy absorption capacity of the power grid, which is crucial for building a new power system, ensuring regional energy security, and promoting a low-carbon energy transition.

[0003] In the field of virtual power plant resource aggregation technology, a series of research and practices have been carried out both domestically and internationally. Existing technical solutions typically rely on Supervisory Control and Data Acquisition (SCADA) systems or Energy Management Systems (EMS) for data collection and monitoring, and utilize optimization algorithms to schedule aggregated resources. However, most existing systems still focus on scheduling traditional controllable loads, lacking adaptability to scenarios with high proportions of renewable energy integration. In terms of modeling, traditional methods often employ deterministic predictions or simple statistical models to describe renewable energy output, failing to fully characterize its inherent randomness and volatility. In terms of architectural design, existing platforms often adopt a relatively centralized data processing model, making it difficult to support the real-time access and efficient computation of massive heterogeneous resources. Furthermore, existing systems largely ignore spatiotemporal characteristics such as geographical distribution and meteorological correlations during resource aggregation, limiting the reliability and accuracy of the aggregation results.

[0004] Despite the widespread attention garnered by virtual power plant technology, constructing an efficient distributed resource aggregation system for scenarios with high proportions of renewable energy integration still faces numerous technical challenges. First, renewable energy output is highly dependent on weather conditions; its strong randomness and intermittency make accurate forecasting and reliable modeling exceptionally difficult, rendering traditional deterministic models inapplicable. Second, distributed resources are diverse and varied, including power-side resources such as photovoltaics and energy storage, as well as various flexible loads. Their heterogeneity, dispersion, and differences in response characteristics make unified modeling and collaborative optimization extremely complex. Third, the coordination and integration between day-ahead, intraday, and real-time multi-timescale scheduling present significant challenges. Achieving rolling optimization and rapid decision-making in high-dimensional uncertainty environments, while ensuring the robustness and economy of the scheduling plan, is a core challenge in practical applications. Furthermore, the real-time access of massive numbers of devices, high-frequency data acquisition and processing, and low-latency communication and control also place extremely high demands on the system's infrastructure and computing power. Summary of the Invention

[0005] The present invention aims to provide a distributed resource aggregation analysis method and system that can efficiently integrate power supply resources and accurately quantify them, thereby effectively improving the observability, measurability and controllability of distributed power supply resources.

[0006] To achieve the above objectives, the present invention provides the following basic solution:

[0007] Option 1

[0008] A distributed resource aggregation and analysis system includes a resource processing module, a data analysis module, an aggregation analysis module, and a collaborative control module;

[0009] The resource processing module is used to collect data and parse protocols from the connected distributed energy supply terminals; the distributed energy supply terminals include Class I energy supply terminals whose energy source is controllable load and Class II energy supply terminals whose energy source is new energy.

[0010] The data analysis module is used to receive and process multi-source heterogeneous data from the resource processing module to build a resource profile; and for Class I energy supply terminals, to build a load model and output load forecast data; and for Class II energy supply terminals, to build a stochastic process model of their output and response and output new energy output data.

[0011] The aggregation analysis module is used to receive and process data from the data analysis module, and set the optimal charging and discharging plan and the baseline scheduling scheme of adjustable load for each energy storage unit according to the preset strategy. The preset strategy includes solving the optimal charging and discharging plan and the baseline scheduling scheme using the MILP algorithm based on load forecast data and new energy output data on the day-ahead time scale, and performing periodic updates on the intraday time scale.

[0012] The coordinated control module is used to generate scheduling instructions and send them to the corresponding power supply end based on the optimal charging and discharging plan and the benchmark scheduling scheme.

[0013] Option 2

[0014] A distributed resource aggregation analysis method, using a distributed resource aggregation analysis system as described in Scheme 1, includes the following steps:

[0015] Data is collected and protocol parsed from the connected distributed power supply terminals, and resource profiles are built for each power supply terminal based on historical data, and resource profile tags that characterize their operating characteristics are generated.

[0016] For Class I energy supply terminals, a load model is constructed and load forecast data is output; and for Class II energy supply terminals, a stochastic process model of their output and response is constructed and renewable energy output data is output.

[0017] The optimal charging and discharging plan and the baseline scheduling scheme for adjustable loads of each energy storage unit are set according to a preset strategy. The preset strategy includes solving the optimal charging and discharging plan and the baseline scheduling scheme using the MILP algorithm based on load forecast data and new energy output data on the day-ahead time scale, and periodically updating them on the intraday time scale.

[0018] Based on the optimal charging and discharging plan and the benchmark scheduling scheme, scheduling instructions are generated and sent to the corresponding energy supply end, and execution deviations are monitored in real time. When the deviation between the actual output of new energy and the predicted value exceeds the preset threshold and continues for a certain period of time, the emergency collaborative mitigation strategy is automatically triggered, and the energy storage unit in the optimal working range is prioritized for power compensation.

[0019] The working principle and advantages of this invention are as follows:

[0020] This invention presents a distributed resource aggregation analysis method and system that efficiently integrates and accurately quantifies power supply resources, effectively improving the observability, measurability, and controllability of distributed power supply resources. The key feature is that this scheme specifically addresses scenarios with a high proportion of renewable energy access, employing differentiated aggregation analysis. Specifically, the data analysis module models different energy supply types: for Type I energy supply, a load forecasting model captures patterns in human electricity consumption behavior; for Type II energy supply, a stochastic process model quantifies the uncertainties of energy sources such as wind and solar power. This differentiated approach significantly improves the accuracy of resource characteristic modeling, providing reliable input for subsequent optimized scheduling. Furthermore, compared to existing research that often focuses on scheduling at a single time scale, this scheme uses a mixed-integer linear programming (MILP) algorithm to solve for the optimal plan at the day-ahead scale, while simultaneously performing periodic rolling updates at the intraday scale, ensuring both the forward-looking nature of the planning and the flexibility of real-time adjustments. In addition, this scheme coordinates and optimizes controllable loads and renewable energy within a unified framework. By jointly solving energy storage charging and discharging plans and load scheduling schemes, complementary regulation across resource types can be achieved, resulting in a more flexible and comprehensive scheduling mechanism. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the system structure of an embodiment of a distributed resource aggregation analysis method and system according to the present invention. Detailed Implementation

[0022] The following detailed explanation illustrates the specific implementation methods:

[0023] The basic implementation examples are as follows: Figure 1 As shown: A distributed resource aggregation analysis system includes a resource processing module, a data analysis module, an aggregation analysis module, a collaborative control module, a resource aggregation visualization module, and a simulation and deduction module.

[0024] The resource processing module is used to collect data and parse protocols from the connected distributed energy supply terminals. The distributed energy supply terminals include Class I energy supply terminals whose energy source is controllable load and Class II energy supply terminals whose energy source is new energy.

[0025] When the resource processing module collects data, the types of data collected include: operational data and environmental data of the distributed energy supply terminals; the operational data includes real-time active power, reactive power, state of charge, temperature of energy supply equipment, grid connection point voltage, and historical charging and discharging data of energy storage units; the environmental data includes real-time meteorological data within a 5-kilometer radius centered on the geographical location of each distributed energy supply terminal, and the real-time meteorological data includes irradiance, ambient temperature, wind speed, and wind direction.

[0026] Specifically, in this embodiment, data is collected from Supervisory Control and Data Acquisition (SCADA), Energy Management System (EMS), Remote Terminal Units (RTUs) of each plant, or Internet of Things (IoT) gateways. For Class I energy supply terminals (controllable loads, including industrial adjustable equipment, flexible residential loads, etc.): macroscopic power consumption data such as total active power, total reactive power, switch status, and critical circuit current are collected at a time interval of minutes (e.g., 5-15 minutes). For Class II energy supply terminals (new energy sources, including photovoltaic power plants, distributed photovoltaic / wind power, etc.): detailed operating status data are collected at a high frequency of seconds (e.g., 1-5 seconds), including but not limited to: real-time active / reactive power, DC-side voltage / current, AC-side voltage / current, internal temperature, alarm information, grid connection frequency, and energy storage device-specific status of charge (SOC), state of health (SOH), and number of charge / discharge cycles.

[0027] Furthermore, the resource processing module has a built-in protocol adaptation engine for performing protocol parsing functions; it supports establishing connections with common protocols for communication with Class I power supply terminals (such as industrial programmable logic controllers PLCs) such as Profinet and MPI / PPI, as well as common protocols for communication with Class II power supply terminals (photovoltaic inverters, energy storage converters PCS, wind turbine controllers) such as IEC 61850, Modbus TCP, MQTT, and DNP3.

[0028] The resource processing module also includes a preprocessing unit for data cleaning and quality verification. Specifically, in this embodiment, preset data validity rules are applied for real-time cleaning and verification. These rules include: range verification – checking whether the data is within a reasonable physical range (e.g., SOC value between 0-100%); jump verification – identifying abrupt changes between adjacent data points (e.g., power change rate exceeding 20% ​​of the rated value) and smoothing or marking them; correlation verification – for Class II energy supply terminals, cross-validating meteorological data (e.g., when nighttime irradiance is zero, photovoltaic output should be zero).

[0029] The data analysis module receives and processes multi-source heterogeneous data from the resource processing module to construct resource profiles. For Class I energy supply terminals, it constructs a load model and outputs load forecast data; for Class II energy supply terminals, it constructs a stochastic process model of their output and response and outputs new energy output data.

[0030] Specifically, the process of constructing resource profiles includes the following steps: Based on data from various energy supply terminals, a resource identifier is attached to each energy supply terminal. The resource identifier includes Class I resource tags—interruptible load, shiftable load, maximum power reduction, minimum response time, and comfort constraints; and Class II resource tags—PV / energy storage type, rated capacity, current adjustable capacity, weather dependence, volatility level, and State of Health (SOH) status.

[0031] The data analysis module includes the following steps when constructing a stochastic process model:

[0032] Stochastic differential equations are used to model the power output fluctuations of Type II energy supply terminals. Specifically, for Type II energy supply terminals with solar energy as the primary renewable energy source, the photovoltaic power output is... The dynamic changes are described by Jacobi processes:

[0033] ;

[0034] in, The change in output over time; mean recovery rate. Conditional mean Volatility coefficient The Jacobi process parameters are dynamically generated through a gradient boosting decision tree model pre-trained with real-time irradiance and ambient temperature. Specifically, real-time collected meteorological data, including total irradiance, diffuse irradiance, cloud cover, ambient temperature, wind speed, and humidity, form a feature vector M(t). A pre-trained gradient boosting decision tree (GBDT) regression model is then used, taking M(t) and its historical window data as input, and outputting the Jacobi process parameters at the current moment in real time. The GBDT model excels at capturing complex nonlinear relationships between features and can effectively learn how meteorological conditions affect the fluctuation characteristics of power output.

[0035] By selecting the Jacobi process instead of the traditional single deterministic prediction point, its inherent ability to constrain random variables within a fixed interval is utilized. Its characteristics perfectly match the normalized photovoltaic power output. The physical boundary can simultaneously describe the fluctuation range of photovoltaic power output (limited to 0 and maximum available power) and its mean recovery and random diffusion characteristics, thus enabling accurate assessment of photovoltaic power output.

[0036] The data analysis module includes an energy storage health status assessment unit, which calculates the cumulative throughput based on the collected historical charge / discharge data of the energy storage unit (including cycle start / end SOC, total charge, total discharge, average charge / discharge power, duration, average temperature, etc.) using the ampere-hour integration method, and combines this with its rated cycle life according to the formula:

[0037] It dynamically estimates the health status of energy storage units and automatically reduces the adjustable capacity limit of energy storage units with an SOH value below 80% to 90% of their nominal value.

[0038] The energy storage health status assessment unit periodically (e.g., daily) calculates the latest SOH value. If the SOH value is below 80%, a capacity correction factor (0.9) is automatically generated and sent to the aggregation analysis module and the collaborative control module. When formulating scheduling plans, these downstream modules multiply the maximum chargeable and dischargeable power and maximum available capacity of the energy storage by this capacity correction factor. This effectively takes into account the capacity degradation caused by equipment aging during control, avoids issuing instructions that exceed the actual capacity of the equipment, and helps to extend its service life.

[0039] The data analysis module also includes a power output characteristic index calculation unit, used to calculate the volatility index and ramp-up risk index of photovoltaic power output. Specifically, when calculating volatility, the photovoltaic power output is calculated within a rolling time window (e.g., 15 minutes). The standard deviation of the first difference (the difference between consecutive data points) is used as a quantitative indicator of short-term volatility, i.e., the volatility index. When calculating ramp-up risk, based on historical photovoltaic power output data and corresponding environmental data, the maximum increase and decrease ramp-up rates of photovoltaic power output within a unit time (e.g., 1 minute, 5 minutes) under different weather types are statistically analyzed to form a ramp-up event probability distribution. In this embodiment, when the increase ramp-up rate exceeds a certain large value (e.g., 50 kW / min), or the absolute value of the decrease ramp-up rate exceeds a certain large value (e.g., -60 kW / min, with the absolute value taken as 60 kW / min), it is identified as an extreme ramp-up event. Based on the previously obtained ramp-up event probability distribution, the probability of an extreme ramp-up event is calculated as the ramp-up risk index. For example, under a certain weather type and a certain unit time, the probability of an extreme increase ramp-up event = the number of samples with an increase ramp-up rate exceeding the threshold under that weather type and unit time / the total number of samples in that category.

[0040] The aggregation analysis module is used to receive and process data from the data analysis module, and set the optimal charging and discharging plan for each energy storage unit and the baseline scheduling scheme for adjustable load according to the preset strategy.

[0041] The preset strategy includes, on the day-ahead time scale, using the MILP algorithm to solve for the optimal charging and discharging plan and the baseline scheduling scheme based on load forecast data and renewable energy output data; and periodically updating it on the intraday time scale.

[0042] When using the MILP algorithm to solve for the optimal charging and discharging plan and the baseline scheduling scheme, a MILP model is established with the objective of minimizing the total operating cost of the virtual power plant. The objective function of the MILP model is:

[0043] ;

[0044] in, The cost of purchasing electricity from the main grid during time period t. It's the online electricity price. It refers to the power consumption of electricity purchased. The revenue from selling electricity to the main grid during time period t. It's the grid connection price. This refers to the electricity sold; the negative sign represents revenue. For energy storage loss costs, It is the energy storage depreciation factor. It is the sum of the absolute values ​​of the charging and discharging power of the i energy storage units.

[0045] The constraints of the MILP model include: system power balance constraints, dynamic update constraints of energy storage SOC and its operating boundary constraints, uncertainty constraints of new energy output, constraints on the amount that can be reduced, and duration constraints.

[0046] In this embodiment, the system power balance constraint is specifically expressed as follows:

[0047] .

[0048] in, This represents the power purchased from the main grid during time period t. Let represent the total output of all photovoltaic units (i units) during time period t. It represents the total charging and discharging power of all energy storage units (i units) during time period t (charging is negative and discharging is positive). This represents the load demand during time period t. This represents the load reduction amount during time period t.

[0049] The dynamic update constraint of the energy storage SOC is specifically expressed as follows:

[0050] ;

[0051] in, This represents the state of charge of the i-th energy storage unit at time t (with a value of 0-100%). This represents the charging and discharging power of the i-th energy storage unit during time period t; Indicates the time step. This represents the rated capacity of the i-th energy storage unit.

[0052] The operational boundary constraints of the energy storage SOC are specifically expressed as follows:

[0053] .

[0054] In this embodiment, The value can range from 10% to 20%. The value can be 90% to 95%.

[0055] The uncertainty constraint on the output of new energy sources is specifically expressed as follows:

[0056] .

[0057] in, This represents the maximum charging power of the i-th energy storage unit; the negative sign indicates that the power is negative during charging. is the maximum discharge power of the i-th energy storage unit.

[0058] The reduction constraint is specifically expressed as follows: .in, This represents the power reduction of the j-th controllable load during time period t. This represents the maximum allowable power reduction for the j-th controllable load during time period t.

[0059] The duration constraint is specifically expressed as follows: a load can be called a maximum of N times per day, or the continuous calling time cannot exceed M time periods. The values ​​of M and N are set according to the actual power supply demand.

[0060] By using the above constraints, the feasible domain for the MILP model to operate can be defined, allowing the MILP model to optimize scheduling strategies while satisfying physical rules.

[0061] In the preset strategy, an update is performed every 15 minutes on the intraday time scale. Based on the latest actual SOC data and new energy output data, with the goal of minimizing the adjustment amount, the optimal charging and discharging plan and benchmark scheduling scheme of the day are corrected using the MPC framework (Model Predictive Control Framework), and the equivalent adjustable power upper limit, equivalent adjustable power lower limit and ramp rate curve of the aggregate are output.

[0062] In the preset strategy, the objective function constructed with the goal of minimizing the adjustment amount on an intraday time scale is:

[0063] ;

[0064] in, That is the energy storage capacity planned in the previous period. This is the adjusted power.

[0065] The coordinated control module is used to generate scheduling instructions based on the optimal charging and discharging plan and the baseline scheduling scheme, and then send them to the corresponding power supply terminals. Specifically, in this embodiment, the coordinated control module receives the optimal charging and discharging plan and the baseline scheduling scheme (in JSON format) from the aggregation and analysis module through a message queue (such as Kafka), and extracts the scheduling instructions for each power supply terminal at each time point (for example, for energy storage units, the scheduling instructions include the power setpoint, expected state of charge, and operating mode at each time point; for controllable loads, the scheduling instructions include the planned power reduction, baseline load forecast, and instruction status at each time point), and then sends them to the device gateway or controller corresponding to each power supply terminal. All instructions are accompanied by a unique instruction ID, a generation timestamp, and an execution validity period (e.g., automatically expires if no response is received within 15 minutes), and are sent through a standardized protocol (such as MQTT-SN) to adapt to the communication capabilities of different power supply terminals.

[0066] The resource aggregation visualization module is used to perform the following operations: on a web-based GIS map, different resource types, including photovoltaics and energy storage, are represented by circular markers of different colors. The size of the marker area represents its rated capacity, and the color of the marker represents the proportion of its current adjustable capacity to the rated capacity. For example, dark red represents an adjustable capacity close to 100%, and light pink represents an adjustable capacity of less than 20%.

[0067] The simulation and extrapolation module is used to allow users to customize meteorological scenarios (such as by using sliders, drop-down boxes, or table entry to customize meteorological parameters, including setting light intensity, temperature, wind speed, cloud cover coefficient, and irradiance attenuation rate), and drive the data analysis module and aggregation analysis module to perform simulation calculations. The module outputs an assessment report on the total output range, expected revenue, and expected scheduling risks (such as load shedding risk, i.e., the probability of load shedding due to insufficient output of new energy sources and depletion of energy storage power) of the aggregate in the next 24 hours under the customized scenario.

[0068] During simulation calculations, the environmental data source for both the data analysis module and the aggregation analysis module is switched to the user-defined meteorological scenario. Specifically, when the simulation is triggered, the simulation module intercepts regular environmental data acquisition requests (such as data from real-time meteorological monitoring systems and historical databases) from the data analysis module and the aggregation analysis module through middleware (such as message queues), and redirects them to the simulation scenario data cache. The simulation scenario data cache generates simulated environmental data according to the user-defined meteorological scenario, in a time series (with a time step of 15 minutes or 1 hour), including photovoltaic irradiance prediction sequences, temperature sequences, etc., and injects them into the data analysis module in the original data format and frequency, ensuring that the module logic can run based on the simulated data without modification.

[0069] This embodiment also provides a distributed resource aggregation analysis method, which applies the distributed resource aggregation analysis system described above to perform resource aggregation analysis; it includes the following steps:

[0070] Data is collected and protocol parsed from the connected distributed power supply terminals, and resource profiles are built for each power supply terminal based on historical data, generating resource profile tags that characterize their operating features.

[0071] For Class I energy supply terminals, a load model is constructed and load forecast data is output; for Class II energy supply terminals, a stochastic process model of their output and response is constructed and renewable energy output data is output.

[0072] The optimal charging and discharging plan and the baseline scheduling scheme for adjustable loads of each energy storage unit are set according to a preset strategy. The preset strategy includes solving the optimal charging and discharging plan and the baseline scheduling scheme using the MILP algorithm based on load forecast data and new energy output data on the day-ahead time scale, and periodically updating them on the intraday time scale.

[0073] Based on the optimal charging and discharging plan and the benchmark scheduling scheme, scheduling instructions are generated and sent to the corresponding energy supply end, and the execution deviation is monitored in real time. When the deviation between the actual output of new energy and the predicted value exceeds the preset threshold (e.g., 15%, which can be temporarily relaxed to 20% if the photovoltaic prediction error is large on cloudy days) and lasts for a certain period of time (e.g., 3 min to 5 min), the emergency collaborative suppression strategy is automatically triggered, and the energy storage unit in the optimal working range is prioritized for power compensation.

[0074] In this embodiment, the optimal operating range is defined as: SOC between 40% and 80% (balancing charging and discharging flexibility and lifespan protection). (In good health) (Low energy consumption) and no fault alarms within 30 minutes.

[0075] When performing power compensation, the initial compensation amount is set to be equal to the actual output deviation of the new energy source (if the actual output is lower than the predicted value, the energy storage needs to discharge to compensate; otherwise, the energy storage will charge to absorb). The compensation amount is allocated to the selected energy storage units according to the proportion of the energy storage capacity (e.g., if the total compensation demand is 500kW, energy storage A has a capacity of 2MWh and energy storage B has a capacity of 3MWh, then A will bear 200kW and B will bear 300kW). At the same time, the compensation power of a single energy storage unit is limited to no more than 80% of its rated power to avoid overload.

[0076] During execution, the compensation effect is updated every 30 seconds: if the deviation drops below the threshold, the current compensation amount is maintained; if the deviation still exceeds the threshold, secondary energy storage (SOC 30%-40% or 80%-90%) is activated to supplement the compensation; if the deviation does not converge after 3 consecutive updates, the Class I power supply is linked for adjustment (such as calling interruptible loads to temporarily reduce power). When the deviation remains below the threshold for 2 minutes, the strategy automatically exits, and the energy storage gradually resumes to the original charging and discharging plan (the recovery rate does not exceed 50% of its maximum ramp rate to avoid impacting the power grid). At the same time, the emergency process data (trigger time, compensation amount, energy storage response speed, etc.) is uploaded to the aggregation analysis module for optimizing the charging and discharging plan for the next day.

[0077] This embodiment provides a distributed resource aggregation analysis method and system that can efficiently integrate power supply resources and accurately quantify them, effectively improving the observability, measurability, and controllability of distributed power supply resources.

[0078] At the resource access and sensing level, a protocol adaptation engine ensures broad compatibility with heterogeneous modeling devices, guaranteeing comprehensive and real-time data acquisition. Furthermore, it deeply integrates meteorological data with equipment operation data, providing a reliable data foundation for subsequent accurate modeling and forecasting. At the modeling level, this solution abandons traditional deterministic methods, specifically employing stochastic differential equation theory, particularly the Jacobi process, to characterize the non-Gaussian and non-stationary fluctuations of photovoltaic power output. The model parameters are dynamically generated from real-time meteorological data through a machine learning model. This not only provides a solid mathematical and physical foundation for the model but also allows it to dynamically adapt to changes in the external environment, significantly improving the quantitative accuracy of uncertainties in new energy power output.

[0079] At the aggregation and scheduling level, this scheme establishes an optimization framework that closely links day-ahead and intraday multi-timescales. Day-ahead optimization formulates the preliminary plan with the best economic efficiency, while intraday rolling optimization corrects deviations in real time based on ultra-short-term forecasts. Through a hierarchical and progressive optimization mechanism, the scheme effectively balances the economy and robustness of the scheduling plan, which helps to improve the grid's ability to absorb distributed renewable energy and its operational safety.

[0080] In addition, to verify the application effect of this solution, a case study of power dispatching during the summer peak season in an industrial park in Xinjin District was selected for simulation analysis. The application scenario was set as a week in August, with the weather forecast showing sunny skies turning cloudy the next day, and short-term scattered showers in the afternoon. The power grid issued a demand response instruction from 14:00 to 15:00 the next day, requiring the area to reduce its load by 1.5MW.

[0081] Aggregated resources include: Category II energy supply (new energy) – rooftop photovoltaic power station in the park (total capacity 4MW), distributed energy storage station (total capacity 2MW / 4MWh); Category I energy supply (controllable load) – Factory A (interruptible production line, maximum reduction of 800kW), Technology Company B (adjustable central air conditioning, maximum reduction of 400kW), Data Center C (adjustable cooling system, maximum reduction of 300kW).

[0082] Day-ahead Phase – Developing the Economically Optimal Plan: The resource processing module collects the status of all resources, showing an average SOC of 65% for energy storage. The data analysis module, based on the weather forecast (sunny turning cloudy), generates a probabilistic prediction of photovoltaic output using the Jacobi process model, showing an expected output of 3.2MW at 14:00 the following day, but with high uncertainty (70% probability between 2.8MW and 3.5MW). The aggregation analysis module performs MILP day-ahead optimization. The calculation shows that the most economical solution to meet the 1.5MW reduction target is: utilizing Class I resources, allowing Plant A to reduce 800kW, Company B to reduce 400kW, and Data Center C to reduce 300kW (totaling 1.5MW). This solution has the lowest cost, requires no use of energy storage, and avoids depreciation losses. This baseline dispatch plan is then generated and submitted to the grid dispatch center.

[0083] Intraday Phase – Real-time Adjustment: At 13:45 the following day, the weather changed abruptly, with rain arriving ahead of schedule. Real-time monitoring by the resource processing module showed that the actual photovoltaic output dropped sharply to 1.8MW, 1.4MW lower than the previous forecast. If the load is reduced by only 1.5MW as originally planned, the total load of the park will have a power deficit of 1.4MW (PV shortfall) + 1.5MW (planned reduction) = 2.9MW, which will lead to a decrease in the frequency of the power grid within the park or even a power outage.

[0084] In this situation, the data analysis module immediately triggers an ultra-short-term forecast update, predicting that photovoltaic output will remain low for the next hour. The MPC rolling optimization of the aggregation analysis module is triggered. Under the new constraints (significantly reduced photovoltaic output), the calculation is recalculated with the goal of "minimizing adjustments and avoiding power outages." A new decision is output: immediately terminate the load reduction order for Data Center C (due to its high priority, power is restored to ensure server safety), and initiate a coordinated energy storage mitigation strategy. The coordinated control module issues an instruction to the energy storage station: discharge at maximum power of 1MW. Instructions are issued to Factory A and Company B: maintain the original load reduction plan (800kW + 400kW). At this point, the total compensation power is: 1MW (energy storage) + 1.2MW (load reduction) = 2.2MW, making up for most of the shortfall.

[0085] Therefore, this system can quickly compensate for power shortages and intelligently avoid grid frequency fluctuations and potential power outages. Specifically, under undisturbed conditions, the system selects the lowest-cost load response scheme through day-ahead optimization, saving on energy storage depreciation costs. In extreme cases, rapid adjustments prevent potentially huge economic losses due to power outages, protecting production safety. Furthermore, through accurate stochastic forecasting and multi-timescale optimization, it maximizes the utilization of photovoltaic power generation, converting it into stable output even under fluctuating conditions through energy storage, significantly reducing curtailment rates.

[0086] The above descriptions are merely embodiments of the present invention. Commonly known structures and characteristics of the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent.

Claims

1. A distributed resource aggregation analysis system, characterized in that, It includes a resource processing module, a data analysis module, an aggregation analysis module, and a collaborative control module; The resource processing module is used to collect data and parse protocols from the connected distributed energy supply terminals; the distributed energy supply terminals include Class I energy supply terminals whose energy source is controllable load and Class II energy supply terminals whose energy source is new energy. The data analysis module is used to receive and process multi-source heterogeneous data from the resource processing module, construct resource profiles, and construct load models and output load forecast data for Class I energy supply terminals. Furthermore, for Class II energy supply terminals, a stochastic process model of their output and response is constructed, and new energy output data is output. The data analysis module includes the following steps when constructing a stochastic process model: Stochastic differential equations are used to model the power output fluctuations of Type II energy supply terminals. Specifically, for Type II energy supply terminals with solar energy as the primary renewable energy source, the photovoltaic power output is... The dynamic changes are described by Jacobi processes: ； in, The change in output over time; mean recovery rate. Conditional mean Volatility coefficient It is dynamically mapped by a gradient boosting decision tree model pre-trained from real-time irradiance and ambient temperature; The aggregation analysis module is used to receive and process data from the data analysis module, and set the optimal charging and discharging plan and the baseline scheduling scheme of adjustable load for each energy storage unit according to the preset strategy. The preset strategy includes solving the optimal charging and discharging plan and the baseline scheduling scheme using the MILP algorithm based on load forecast data and new energy output data on the day-ahead time scale, and performing periodic updates on the intraday time scale. When using the MILP algorithm to solve for the optimal charging and discharging plan and the baseline scheduling scheme, a MILP model is established with the objective of minimizing the total operating cost of the virtual power plant. The objective function of the MILP model is: ； in, The cost of purchasing electricity from the main grid during time period t. It's the online electricity price. It refers to the power consumption of electricity purchased. The revenue from selling electricity to the main grid during time period t. It's the grid connection price. This refers to the electricity sold; the negative sign represents revenue. For energy storage loss costs, It is the energy storage depreciation factor. It is the sum of the absolute values ​​of the charging and discharging power of the i energy storage units; The constraints of the MILP model include: system power balance constraints, dynamic update constraints of energy storage SOC and its operating boundary constraints, and uncertainty constraints of new energy output. The coordinated control module is used to generate scheduling instructions and send them to the corresponding power supply end based on the optimal charging and discharging plan and the benchmark scheduling scheme.

2. The distributed resource aggregation analysis system according to claim 1, characterized in that, When the resource processing module collects data, the types of data collected include: operational data and environmental data of the distributed energy supply terminals; the operational data includes real-time active power, reactive power, state of charge, temperature of energy supply equipment, grid connection point voltage, and historical charging and discharging data of energy storage units; the environmental data includes real-time meteorological data within a 5-kilometer radius centered on the geographical location of each distributed energy supply terminal, and the real-time meteorological data includes irradiance, ambient temperature, wind speed, and wind direction.

3. The distributed resource aggregation analysis system according to claim 2, characterized in that, The data analysis module includes an energy storage health status assessment unit, which calculates the cumulative throughput based on the collected historical charge and discharge data of the energy storage unit using the ampere-hour integral method, and combines this with its rated cycle life according to the formula: It dynamically estimates the health status of energy storage units and automatically reduces the adjustable capacity limit of energy storage units with an SOH value below 80% to 90% of their nominal value.

4. The distributed resource aggregation analysis system according to claim 1, characterized in that, In the preset strategy, an update is performed every 15 minutes on the intraday time scale. Based on the latest actual SOC data and new energy output data, with the goal of minimizing the adjustment amount, the MPC framework is used to revise the day-ahead optimal charging and discharging plan and benchmark scheduling scheme, and output the equivalent adjustable power upper limit, equivalent adjustable power lower limit and ramp rate curve of the aggregate.

5. A distributed resource aggregation analysis system according to claim 4, characterized in that, In the preset strategy, the objective function constructed with the goal of minimizing the adjustment amount on an intraday time scale is: ； in, That is the energy storage capacity planned in the previous period. This is the adjusted power.

6. The distributed resource aggregation analysis system according to claim 1, characterized in that, It also includes a resource aggregation visualization module; the resource aggregation visualization module is used to perform the following operations: on a web-based GIS map, different resource types, including photovoltaics and energy storage, are represented by circular markers of different colors. The size of the marker area represents its rated capacity, and the color depth of the marker represents the proportion of its current adjustable capacity to the rated capacity.

7. A distributed resource aggregation analysis system according to claim 1, characterized in that, It also includes a simulation and extrapolation module, which allows users to customize meteorological scenarios and drives the data analysis module and the aggregation analysis module to perform simulation calculations, outputting an assessment report on the total output range, expected revenue, and expected scheduling risks of the aggregate in the next 24 hours under the customized scenario.

8. A distributed resource aggregation analysis method, characterized in that, The application of a distributed resource aggregation analysis system as described in any one of claims 1-7 for resource aggregation analysis includes the following steps: Data is collected and protocol parsed from the connected distributed power supply terminals, and resource profiles are built for each power supply terminal based on historical data, and resource profile tags that characterize their operating characteristics are generated. For Class I energy supply terminals, a load model is constructed and load forecast data is output; and for Class II energy supply terminals, a stochastic process model of their output and response is constructed and renewable energy output data is output. The optimal charging and discharging plan and the baseline scheduling scheme for adjustable loads of each energy storage unit are set according to a preset strategy. The preset strategy includes solving the optimal charging and discharging plan and the baseline scheduling scheme using the MILP algorithm based on load forecast data and new energy output data on the day-ahead time scale, and periodically updating them on the intraday time scale. Based on the optimal charging and discharging plan and the benchmark scheduling scheme, scheduling instructions are generated and sent to the corresponding energy supply end, and execution deviations are monitored in real time. When the deviation between the actual output of new energy and the predicted value exceeds the preset threshold and continues for a certain period of time, the emergency collaborative mitigation strategy is automatically triggered, and the energy storage unit in the optimal working range is prioritized for power compensation.

Images