Industrial park incremental power distribution network energy transaction and management system based on big data

Abstract

The invention discloses an industrial park incremental power distribution network energy transaction and management system based on big data, and relates to the technical field of energy management. According to the system, multi-source supply data is collected in real time according to incremental power distribution network industrial park power measurement, power interaction characteristic data management is carried out according to a power distribution network state monitoring result, and then capacity-demand prediction matching is carried out according to a power interaction characteristic data management result. The method comprises the steps of carrying out prediction matching on industrial park energy transaction data, carrying out prediction supply management adjustment according to a prediction matching result, carrying out supply adjustment monitoring and dynamic correction according to multi-source supply data and prediction supply management adjustment, carrying out classified storage on industrial park interaction data used for reflecting an interaction state in a park energy transaction whole process, and uploading the data to a platform for archiving. The problem that in the prior art, the collaboration between the execution state of power distribution network energy transaction management and energy supply and demand data is low in the scenes of industrial production electricity consumption increment, cross-regional transaction electricity quantity increment and the like in an industrial park is solved.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, and in particular to an energy trading and management system for incremental distribution networks in industrial parks based on big data. Background Technology

[0002] Under the dual-carbon and power system, relying on core technologies such as big data, IoT, blockchain, digital twins, and artificial intelligence, the realization of energy trading and management in industrial parks firstly involves collecting multi-dimensional data on power generation output, grid equipment operation status, and user load through distribution IoT terminals and sensing devices. Data is then split and transmitted along different paths based on path optimization, and after consistency verification via gateway aggregation, a request is submitted to the blockchain. Subsequently, a big data platform, such as a comprehensive energy management platform, integrates and processes multi-source data, combining industry load characteristic clustering analysis and economic variable correlation mining to construct an electricity demand forecasting model. In terms of electricity trading, an electricity price forecasting model integrating historical data, load characteristics, and meteorological parameters provides auxiliary functions such as electricity price trend forecasting, trading deviation analysis, and strategy recommendation. This supports optimizing electricity purchase and sale decisions and constructing a complete equipment asset ledger, covering equipment information management, operation status monitoring, and data archiving.

[0003] For example, Chinese invention patent CN118839945B discloses a scheduling method for the coupled operation of trading and spot trading in a multi-energy system, including: acquiring day-ahead spot trading related data, loading day-ahead spot trading related data in real time, outputting the electricity price prediction result and its corresponding risk trading value from the electricity price prediction model, and comprehensively optimizing the scheduling model to calculate the predicted output value of thermal power units and the predicted output value of new energy based on the electricity price prediction result and the trading risk value.

[0004] The above-mentioned technology has at least the following technical problems: In the process of energy data trading and management, high-frequency dynamic data such as energy transaction results and real-time supply adjustment instructions from the supply and demand side, as well as related data generated in management stages such as data archiving and energy efficiency assessment, are mostly temporarily stored in high-speed caches to meet real-time access needs, rather than being permanently stored. However, the time dimension benchmark of the entire data chain is not uniform. At this time, the complete data required for energy transaction efficiency assessment needs to spend additional time for calibration and conversion. If the intermediate links of data calibration and conversion are hindered by time format differences, data transmission packet loss, etc., it will lead to a disconnect between energy data management and actual energy dispatch strategies in power supply parks. That is, the data processing progress lags behind the dispatch decision requirements or the strategy update cannot keep up with the data dynamics. This makes it difficult for data to quickly match dispatch requirements or for strategy execution to adapt to data changes in a timely manner, resulting in a disconnect between data and strategy processing. This lengthens the entire process response chain and ultimately leads to low coordination between the execution status of distribution network energy trading management and energy supply and demand data when industrial parks face scenarios such as increased new energy installed capacity, increased industrial production electricity consumption, and increased cross-regional transaction electricity volume. Summary of the Invention

[0005] To address the technical problem of low coordination between the execution status of energy trading management in existing distribution networks and energy supply and demand data, this invention provides a big data-based incremental distribution network energy trading and management system for industrial parks. The technical solution is as follows: On the one hand, a big data-based energy trading and management system for incremental distribution networks in industrial parks is provided. This system includes the following modules: a power interaction characteristic data management module, a forecast capacity and demand supply management module, and a supply adjustment execution monitoring and correction module. The power interaction characteristic data management module collects multi-source supply data reflecting the supply capacity of the incremental distribution network in the industrial park in real time based on power metering, and manages the power interaction characteristic data according to the distribution network status monitoring results. The forecast capacity and demand supply management module performs capacity-demand forecast matching based on the results of the power interaction characteristic data management and historical park energy trading correlation data, and adjusts the forecast supply management based on the forecast matching results. The supply adjustment execution monitoring and correction module monitors and dynamically corrects supply adjustments based on multi-source supply data and forecast supply management adjustments, and classifies, stores, and uploads the industrial park interaction data reflecting the interaction status throughout the entire energy trading process to the platform for archiving.

[0006] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: 1. By employing categorized power calculation, supply-demand gap assessment, and scenario-based collaborative scheduling, precise and efficient supply interaction and collaborative management has resolved issues such as disordered supply source scheduling, insufficient green energy consumption, and excessive distribution network losses. First, categorized power calculation is performed based on multi-source supply data. Then, combined with load-side load power, the supply-demand gap is accurately calculated, and targeted collaborative strategies are formulated. This achieves deep collaboration between grid power supply and distributed energy. By dynamically adjusting the output ratio and power supply curves of both, priority consumption of green energy is ensured, reducing energy waste, while optimizing the power supply structure reduces distribution network line losses. Simultaneously, scenario-based strategies avoid over- or under-adjustment of scheduling, ensuring that the supply-demand relationship remains in a dynamic equilibrium. Whether facing fluctuations in distributed energy output or changes in load-side demand, it can quickly respond and adapt, effectively improving the orderliness and flexibility of incremental distribution network supply-side scheduling, and providing a stable and reliable supply foundation for park energy trading.

[0007] 2. By implementing closed-loop optimization through classification of verification time and dynamic adjustment of deviation ratios, the problems of low data verification efficiency and abnormal data interfering with transactions are solved. Data is classified and processed based on the verification time corresponding to each data identifier, and flexible handling is performed according to the matching relationship between the verification time and the preset interval. By dynamically adjusting the number of parallel shards, the problem of excessively long data verification time can be specifically solved, avoiding transaction process delays caused by verification delays. The categorized processing mechanism effectively filters invalid and abnormal data, ensuring that the data entering the subsequent prediction and matching stage has a high degree of accuracy and consistency. This verification optimization not only provides reliable data support for energy trading and reduces transaction deviations and disputes caused by data errors, but also shortens the end-to-end response time through process optimization, enabling data processing to keep pace with transaction decision-making needs.

[0008] 3. By constructing an adaptive power supply curve update and combining it with load allocation optimization logic, the problem of low adaptability to dynamic changes in supply and demand in existing technologies is solved. In the power supply curve update stage, the multi-source supply data is first normalized to eliminate interference caused by differences in data format. The problem of excessive deviation is solved by step-type power correction. Finally, the moving average algorithm is used to smooth the curve to ensure the continuity and stability of the power supply strategy. In the load allocation adjustment stage, the output ratio of grid power supply and distributed power source is optimized according to the principle of proportional step-up, realizing dual dynamic optimization of power supply curve and load allocation. The step-type correction and smoothing of the power supply curve avoids distribution network fluctuations caused by power mutations and ensures the stability of power supply.

[0009] 4. By implementing a closed-loop optimization process involving accurate monitoring of supply and demand matching, energy efficiency analysis, anomaly location, and dynamic correction, the technology addresses the lag in supply adjustment execution found in existing technologies. In the supply and demand matching accuracy monitoring stage, the step size is dynamically adjusted and updated based on the real-time execution progress of adjustment commands. In the energy efficiency analysis stage, the calculation method combines green electricity consumption efficiency with distribution network operation efficiency, quantifying the overall supply and demand energy efficiency by calculating the positive difference compared to standard benchmark values. This allows for real-time verification of the effectiveness of predictive matching and supply adjustments, timely detection and correction of execution deviations, and precise energy efficiency anomaly location to avoid wasting optimization resources. It ensures that every corrective measure directly addresses the core issue, improving the synergy of energy trading and management, and simultaneously promoting continuous improvement in the park's energy utilization efficiency. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in 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.

[0011] Figure 1 A schematic diagram of the structure of the industrial park incremental distribution network energy trading and management system based on big data provided in an embodiment of the present invention; Figure 2 A flowchart corresponding to the power interaction feature data management module provided in this embodiment of the invention; Figure 3 The flowchart corresponding to the predicted capacity demand supply management module provided in the embodiments of the present invention; Figure 4 The flowchart corresponds to the supply adjustment execution monitoring and correction module provided in the embodiments of the present invention. Detailed Implementation

[0012] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0013] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0014] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0015] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0016] This invention provides an energy trading and management system for incremental power distribution networks in industrial parks based on big data, such as... Figure 1 The diagram shows the structure of an industrial park incremental distribution network energy trading and management system based on big data. The system's processing flow can include the following modules: a power interaction characteristic data management module, a forecast capacity and demand supply management module, and a supply adjustment execution monitoring and correction module. Specifically, the power interaction characteristic data management module collects multi-source supply data in real time, reflecting the supply side and supply capacity of the newly added distribution network and load in the industrial park, based on the corresponding power metering. It then manages the power interaction characteristic data according to the distribution network status monitoring results. The forecast capacity and demand supply management module performs capacity-demand forecast matching based on the results of the power interaction characteristic data management, combined with historical industrial park energy trading correlation data. It also adjusts the forecast supply management based on the forecast matching results. The supply adjustment execution monitoring and correction module monitors and dynamically corrects supply adjustments based on multi-source supply data and forecast supply management adjustments. It also categorizes, stores, and uploads the industrial park interaction data reflecting the interaction status throughout the entire energy trading process to the platform for archiving.

[0017] In this embodiment, the newly added distribution network and new loads are the core components and operational foundation of the incremental distribution network. The efficient operation of the incremental distribution network relies on the coordinated adaptation of the newly added distribution network and new loads. This solution addresses issues such as incomplete supply-side data collection, inaccurate capacity-demand matching, and untimely supply adjustment response under new distribution networks and new loads. It achieves real-time collection of multi-source supply data, accurate capacity-demand prediction and matching, and dynamic monitoring and correction of supply adjustments through the coordinated operation of three modules: power interaction characteristic data management, predictive capacity-demand supply management, and supply adjustment execution monitoring and correction. Simultaneously, it completes the archiving of data throughout the entire energy trading process, effectively improving the supply-demand balance control capability and operational efficiency of the incremental distribution network, providing strong support for the high-quality development of the energy system in industrial parks.

[0018] In a practical application in an industrial park, when the output of distributed photovoltaic (PV) systems fluctuates due to weather changes, the power interaction characteristic data management module not only quickly captures core data such as the DC output of PV modules and the AC output power of inverters, but also simultaneously collects multi-dimensional data such as the voltage, current, and power factor of the grid supply, the real-time power consumption of the park's industrial production load and flexible load, and the charging and discharging status of the energy storage system. This achieves full coverage of supply-side and load-side data collection. After format unification and anomaly removal, the data is synchronized to the predicted capacity and demand supply management module. This module uses timestamp precision alignment technology and linear interpolation to fill in occasional data gaps, ensuring the integrity and accuracy of the output data. On the one hand, it retrieves the PV output fluctuation curves and the time-sharing distribution patterns of the park's production load under similar weather conditions in the same period in history. On the other hand, it combines meteorological data to initiate multi-dimensional predictions that integrate time series methods and physical statistics. This ensures the efficient consumption of redundant PV power and reduces distribution network line losses through dynamic coordination between the grid and distributed energy, while providing precise strategic support for energy trading.

[0019] like Figure 2 The diagram shows a flowchart of the power interaction feature data management module provided in this embodiment of the invention. This data management is divided into supply interaction coordination management and interaction consistency verification optimization. Supply interaction coordination management obtains the supply-demand difference and energy supply, performs distributed-distribution output coordination or maintains the current power supply strategy unchanged. Output coordination selects to implement distribution network output restriction and priority scheduling instructions. After the distribution network output is restricted, the power supply curve is updated, followed by tiered power correction and load allocation ratio update. Interaction consistency verification optimization classifies and processes the data, performs re-verification, capacity-demand forecast matching, and adjusts the number of parallel operations.

[0020] Furthermore, power interaction characteristic data management includes: supply interaction collaborative management to improve the orderly dynamic scheduling of multi-source supply, and interaction consistency verification optimization to improve data accuracy requirements during supply adjustment. The specific process of supply interaction collaborative management is as follows: based on the acquired multi-source supply data, categorized power calculations are performed to obtain the energy supply power reflecting the power data of the supply source. Combined with the load power on the load side, the supply-demand difference is obtained. The supply-demand difference generates a preliminary collaborative strategy including power supply strategies and corresponding power supply curves. The power supply curve uses time as the horizontal axis and power values ​​as the vertical axis. It reflects the real-time power supply at a certain moment and marks the cumulative power consumption value, showing the changes in power supply intensity and total amount over different periods. The supply sources include grid power supply and distributed power supply. Grid power supply and distributed power supply are parallel and work together to supply energy to the demand side. The multi-source supply data includes grid power supply data and distributed power output data. Grid power supply data includes operating parameters such as power line loss, supply-side voltage, current, frequency, and power supply. Distributed power output data includes output parameters such as output power, output electricity, and output voltage of various distributed power sources such as photovoltaic and wind power.

[0021] If the energy supply corresponding to the multi-source supply data is greater than the preset energy supply, and the supply-demand difference is greater than the preset supply-demand difference, then the current distribution network in the park is determined to be in an energy-sufficient state, and distributed power generation coordination is carried out. The energy supply is the total energy supply scale of the park's distribution network supply side, which is obtained by summing the energy supplied by the grid and the energy output of distributed power sources, reflecting the total supply capacity of the supply side. If only the energy supply corresponding to the multi-source supply data is greater than the preset energy supply, or only the supply-demand difference is greater than the preset supply-demand difference, then it indicates that the green electricity supply is in excess relative to the load demand, and the proportion of distributed green electricity output in the current power supply structure has exceeded the actual demand matching range. At this time, it is determined that the current distributed power output is in excess. Green energy redundancy involves issuing instructions to reduce grid power supply to decrease distribution network line losses, and simultaneously feeding these instructions back to the power supply strategy to update the corresponding power supply period and capacity. If the energy supply corresponding to the multi-source supply data is not greater than the preset energy supply, and the supply-demand difference is not greater than the preset supply-demand difference, it indicates that the total supply scale matches the preset standard, the energy difference between the supply side and the load side is within a reasonable control range, and there is no risk of oversupply or shortage. In this case, it is determined that the energy supply and demand of the current park distribution network is in a balanced state, and the current power supply strategy and power supply curve remain unchanged. In addition to the above situations, it is determined that the current park distribution network supply matching is incorrect, and the preset personnel are prompted to intervene, for example, by inspecting the distribution facilities involved in the current distribution network.

[0022] Specifically, the distributed power distribution coordination involves the following: When the proportion of grid power supply data in the multi-source supply data is higher than the proportion of distributed power output data, the power output limit of the distribution network corresponding to grid power supply is adjusted. Based on the portion where the proportion of grid power supply data exceeds the proportion of distributed power output data (if this portion is within 5%, the grid output limit is reduced by 10%; similarly, if this portion is greater than 5%, the grid output limit is reduced by 20%), the currently executing power supply curve is dynamically corrected to update the power supply curve and generate a new power supply strategy. When the proportion of grid power supply data in the multi-source supply data is not higher than the proportion of distributed power output data, a distributed power output priority scheduling instruction is issued, and the proportion of grid power supply load is appropriately reduced to prioritize matching redundant green electricity with the flexible load demand within the park, and the load allocation ratio of the corresponding power supply curve is updated synchronously. The specific process of updating the power supply curve is as follows: [The text abruptly ends here, likely due to an incomplete sentence or a missing section.] Multi-source supply data is normalized to obtain the normalized result. Within a preset period, the median of the target total power corresponding to the normalized result is obtained as the target power reference value. First, the target total power (covering the total power of grid supply and distributed generation) corresponding to the multi-source supply data for each time period is continuously collected within the preset period. Then, the total power values ​​for all time periods are arranged in ascending order. If the number of values ​​is odd, the value in the middle position after sorting is taken; if it is even, the average of the two middle values ​​is taken. Using the same time node within the preset period as a benchmark, the actual power value of the real-time power supply curve (including the superimposed value of grid supply and distributed generation output) and the target power value of the expected power supply curve (set by the preset personnel based on the actual operating characteristics of the incremental distribution network) are extracted respectively. The power deviation value for each time node is obtained by the difference between the actual power value and the target power value. If the result is positive, it means that the real-time output exceeds expectations; if negative, it means that the real-time output is insufficient, accurately reflecting the supply-demand matching deviation at each node, and calculating the power deviation value for each time node.

[0023] If the absolute value of the power deviation at any time point exceeds the preset allowable power deviation, a step-wise power correction is performed, and the power supply curve after the power correction is qualified is smoothed using a moving average algorithm to obtain a power supply curve that meets the current supply and demand balance requirements, which is used as the power supply strategy for the next cycle. If the absolute value of the power deviation at each time point does not exceed the preset allowable power deviation, each curve segment after point-by-point comparison is smoothed to obtain a power supply curve that meets the current supply and demand balance requirements, which is used as the power supply strategy for the next cycle. The step-wise power correction is performed as follows: if the current power at the corresponding time point is higher than the target power supply reference value, the power supply is reduced by the step size corresponding to the target power supply power difference; otherwise, the power supply is increased. If, after the step-wise power correction, the absolute value of the power deviation at any time point still exceeds the preset allowable power deviation, an abnormal power supply warning is issued; if no such warning is issued, it indicates that the step-wise power correction is qualified.

[0024] In this embodiment, an industrial park distribution network model is pre-constructed. This model includes distribution network topology and parameter modeling, supply and demand balance calculation, and target constraints under different conditions. The distribution network topology and parameter modeling adopts the node impedance matrix method, which calculates the voltage of each node and the power loss of each branch through the matrix, quantifies the operation characteristics of the distribution network, and establishes controllable models for controllable resources such as distributed power sources, energy storage, and flexible loads, marking their adjustment range, response speed, and other characteristic parameters. This model has different input-output pairs. For example, if the output ratio of one party is higher than that of another party, it can output the corresponding grid ratio limit adjustment value. The supply and demand balance calculation takes the output and output curves corresponding to the multi-source supply data and the load data as input, and outputs the distributed output-load demand.

[0025] The supply-demand gap is specifically represented by the difference between the energy supply power and the load power. The preset energy supply is the result of summing and averaging the historical energy supply corresponding to the historical power interaction characteristic data management process. The preset supply-demand gap is based on the load power of the load side with different time period characteristics in history as a reference, and is preset according to the corresponding load power. The generation and issuance of the grid power reduction instruction is based on the redundancy corresponding to the current distributed power output data (the part where the supply-demand gap is greater than the preset supply-demand gap) to obtain the part of the distributed power output that exceeds the current load demand (i.e., the part where the energy supply corresponding to the multi-source supply data is greater than the preset energy supply). On this part, it conforms to the preset distribution network safety constraint verification rules (line and equipment constraint rules to avoid overload damage, and power supply voltage safety constraint rules to ensure power supply) to obtain the required reduction in grid power supply. The determination of the execution period is based on the distributed power source predicted output curve, verifying the distribution network status within the potential period, and prioritizing the period with low distribution network load rate and stable voltage as the final execution period.

[0026] The adjustment of the distribution network output limit corresponding to grid power supply is based on the portion of grid power supply data that is higher than the distributed generation output data, multiplied by the effective redundancy of green electricity to obtain the redundant output of distributed generation replacing the distribution network output limit; the reduction of the grid power supply load ratio is based on the portion of distributed generation output data that is higher than the grid power supply data ratio, selecting a reduction ratio that meets the pre-set distribution network safety constraint verification rules, that is, the grid power supply load ratio is reduced to the minimum ratio specified by the distribution network safety constraint verification rules; the preset period is preset based on the frequency of power supply demand changes in the current period, and the preset allowable power deviation is the result of summing and averaging the target constraint and historical power deviation. The target power supply difference is the difference between the current power at the corresponding time node and the target power supply reference value. The target power supply reference value is the result of summing and averaging the power supply at the corresponding nodes in the historical time nodes. The step size corresponding to the target power supply difference is the value corresponding to the difference used as the step size for the upward / downward adjustment.

[0027] By integrating and collaboratively analyzing multi-source supply data, we can accurately perceive changes in the relationship between energy supply and load demand, and respond promptly to scheduling and trading needs under different supply conditions, thus avoiding operational imbalances caused by supply-demand mismatch. The utilization efficiency of green energy resources is effectively improved, and redundant distributed power output is transformed into effective energy suitable for distribution network operation through scientific scheduling, leveraging the environmental value of distributed power. At the same time, interactive consistency verification optimization lays a solid data foundation for the supply adjustment process, ensuring the authenticity and reliability of various data on which scheduling decisions rely, avoiding scheduling errors caused by data deviations, and making the formulation and adjustment of power supply strategies more targeted and effective. Overall, this improves the economy and stability of distribution network operation, providing a solid guarantee for the efficient operation of the park's energy system.

[0028] Subsequently, through distributed power distribution processing coordination and dynamic updates of power supply curves, the adaptability to different supply structures has been further enhanced, making energy dispatch and trading management more flexible and accurate. Based on the changes in the proportion of grid power supply and distributed power output, the power supply priority and output configuration can be intelligently adjusted to maximize the output value of distributed power sources and significantly improve the green electricity consumption rate. Redundant green electricity can accurately meet the load demand of the park, realize the efficient on-site utilization of energy resources, reduce unnecessary losses in the energy transmission process, and continuously adapt to the real-time changes in energy supply and load demand, thereby improving the park's energy trading efficiency, management and operation reliability, and sustainability.

[0029] Furthermore, the load allocation ratio of the updated power supply curve is specifically as follows: The load ratios of grid power supply and distributed generation output in the current power supply curve are obtained. Simultaneously, based on the predicted value of redundant green electricity and the adjustable capacity of flexible loads, the target difference for increasing the proportion of distributed generation output is calculated. Based on the obtained target difference, the corresponding increase in the proportion of distributed generation output for the corresponding power supply period is obtained by mapping it to a preset target difference-period adjustment range mapping table. For power supply periods that have reached the increase corresponding to the target difference, the current load allocation ratio is maintained. For power supply periods that have not yet reached the increase corresponding to the target difference within a preset period, the increase is increased by a preset ratio (e.g., 5%). After completing the load allocation ratio adjustment for all power supply periods, a moving average algorithm is used to smooth the curves for all power supply periods, resulting in power supply curves reflecting the load power that grid power supply and distributed generation should each bear under different power supply periods.

[0030] The optimization of interactive consistency verification involves the following steps: Based on preset verification rules (taking electricity price and billing verification as an example, the electricity price type must match the user category, and transmission and distribution fees must meet standards; pricing outside the range cannot be saved) and the updated power supply curve, an identifier verification is performed to obtain the identifier verification duration of each data node in the power supply curve. Then, based on the identifier verification duration of each data node, data classification processing is performed. A data node represents a discrete data collection point in the power supply curve divided according to a preset time granularity (e.g., 15 minutes / hour). Each node contains core operating parameters such as the grid power supply, distributed power output, total load power, and supply-demand difference for the corresponding time period. If the identifier verification duration is less than the minimum value of the preset verification duration range, the identifier verification is performed again. If the verification duration is within the preset verification duration range, capacity-demand prediction matching is performed. If the verification duration exceeds the maximum value of the preset verification duration range, the deviation ratio between the obtained verification duration and the maximum value of the preset verification duration range is calculated. That is, the ratio obtained by dividing the difference between the obtained verification duration and the maximum value of the preset verification duration range into the numerator and the maximum value of the preset verification duration range into the denominator, is used to obtain the adjustment range of the number of parallel shards through the preset deviation ratio-adjustment range mapping rule, so as to adjust the number of parallel shards corresponding to the data imported for verification. The verification duration refers to the total time consumed from starting the preset verification rule to completing the entire verification process (pass / fail and record the result) for a specific category of data corresponding to a single data identifier.

[0031] In this embodiment, both increasing the output curve value of the distributed power source and decreasing the corresponding power supply curve value are based on the proportional step increase ratio of grid power supply and the load corresponding to the distributed power source output. The adjustment range of the preset ratio is based on the difference between the target value and the target value, and the preset verification rules are stored in the target constraints in the industrial park distribution network model. The preset verification time interval is based on the currently acquired multi-source supply data and load data, with the median as the core, and the upper and lower limits are adjusted by preset personnel according to the actual scenario. The highest upper limit is the maximum value of the preset verification time interval, and the lowest lower limit is the minimum value of the preset verification time interval. The preset deviation ratio-adjustment range mapping rule uses historical associated data as samples. For each deviation ratio interval, different adjustment ranges are statistically analyzed, and a mapping relationship is obtained with the deviation ratio as input and the adjustment range as output.

[0032] Load allocation better aligns with the needs of green energy consumption and supply-demand balance, while ensuring the accuracy of data-driven energy trading and the efficiency of process implementation. Dynamic adjustments to the load allocation ratio allow distributed generation to fully utilize its power output, with the ratio of grid power supply to distributed generation output adapting to supply and demand changes at different times. Furthermore, the application of the moving average algorithm keeps the power supply curve consistently stable, effectively mitigating the impact of sudden power fluctuations on distribution network operation and ensuring stable power supply.

[0033] The optimization of interactive consistency verification lays a solid foundation for the implementation of power supply strategies from a data perspective. By classifying and processing the verification duration, it ensures the high reliability of data entering the subsequent prediction and matching stage, avoiding interference from invalid or abnormal data in decision-making. It also allows for flexible adjustment of the number of parallel segments based on the deviation in verification duration, improving verification quality without affecting process efficiency and enabling data processing and strategy execution to work in tandem. This synergy allows the power supply strategy to accurately adapt to green energy consumption and loss reduction targets while possessing robust data support, making distribution network operation more flexible and stable. Simultaneously, it provides dual guarantees for the orderly development of energy trading in the park and the precise advancement of supply and demand matching.

[0034] like Figure 3 The flowchart shown is the corresponding flowchart of the predicted capacity and demand supply management module provided in the embodiment of the present invention. Through capacity-demand prediction matching, the power grid supply data and its corresponding transaction-related data are predicted, the distributed power generation output data and the load side predicted demand data are predicted. The three are combined to obtain the predicted supply and demand difference. The supply and demand difference is classified into different situations to perform different operations: maintain the current supply and demand balance, continuously monitor, maintain the existing supply configuration, and predict the supply and demand difference and provide feedback.

[0035] Furthermore, the capacity-demand forecasting and matching process is as follows: Based on historical grid power supply data, current grid power supply data on the supply side, and their power supply curves and corresponding transaction-related data, a time series method is used to generate predicted grid power supply data and corresponding predicted transaction-related data. The predicted grid power supply data represents the predicted power and electricity data obtained from the main grid in the park's distribution network. The predicted transaction-related data represents the expected transaction volume and execution period in the electricity market corresponding to the predicted grid power supply data. Based on historical distributed generation output data, predicted grid power supply data, and meteorological forecast data, theoretical output is obtained through physical statistical calculations. The historical distributed generation output data is categorized by power source type and meteorological scenario, and the deviation rate between the physical theoretical value and the actual output under different scenarios is calculated (deviation rate = (actual value - physical theoretical value) / physical theoretical value). The theoretical output is obtained through statistical analysis, and regression analysis is used based on historical data... Based on the quantification of deviations and correction of the theoretical output, short-term predicted distributed power output data is obtained, such as predicted output power and predicted cumulative power generation. The predicted grid power supply data and distributed power output data are summarized to form the energy storage regulation capacity used to characterize the predicted total energy supply and structure on the supply side. Based on historical load data, current load data, and meteorological forecast data, the artificial neural network method is used to generate predicted load demand data, including but not limited to predicted load power and predicted cumulative electricity demand. The energy storage regulation capacity is compared with the electricity demand corresponding to the predicted load demand data to obtain the predicted supply-demand difference. Simultaneously, prediction interval matching is performed based on the obtained predicted supply-demand difference. The meteorological forecast data includes but is not limited to wind speed prediction and light intensity prediction, all of which represent historical meteorological observation data, satellite cloud images, and station data, and are used as the prediction results output by artificial intelligence models such as numerical weather prediction models.

[0036] Specifically, the forecast interval matching process is as follows: If the forecast supply-demand difference is greater than the maximum value of the preset positive forecast supply-demand difference range, it indicates that there is a risk of energy surplus, and the forecast grid power supply data and its corresponding forecast power supply strategy are adjusted accordingly to improve the utilization rate of distributed power generation output data; if the forecast supply-demand difference is within the preset positive forecast supply-demand difference range, it indicates that the supply is balanced for the current supply period, and the existing supply configuration is maintained; if the forecast supply-demand difference is less than the minimum value of the preset negative forecast supply-demand difference range, it indicates that there is a risk of energy shortage. The system feeds back the current predicted supply-demand difference to predict power supply strategies. If the predicted supply-demand difference is within the preset negative predicted supply-demand difference range, it indicates that there is fluctuation in the predicted energy supply. The supply-demand difference is continuously monitored. The ranges are sorted in ascending order: minimum value of the negative range, negative range, positive range, and maximum value of the positive range. The negative and positive ranges are connected. The preset positive / negative predicted supply-demand difference range is based on historical predicted supply-demand difference data to obtain its fluctuation range. The normal fluctuation range obtained after verification is used as the preset positive / negative predicted supply-demand difference range.

[0037] In this embodiment, the preset predicted supply and demand difference range includes a positive range and a negative range. The positive range reflects the situation where the predicted supply and demand difference is greater than the demand, but the negative range means that the predicted supply and demand difference is unstable in this range. Feedback to adjust the predicted power grid power supply data and its corresponding predicted power supply strategy means feeding back to preset personnel to adjust the corresponding energy trading strategy. Based on the predicted supply and demand imbalance type (surplus / deficient), imbalance scale and time period, a targeted implementation plan is formulated for the trading direction and execution method. The core is to balance supply and demand through electricity market transactions.

[0038] The integration of multi-source data and forecasting makes the supply-side and demand-side forecast data more closely aligned with actual operating scenarios. Historical data provides a stable reference for forecasting, while current real-time data ensures the timeliness of forecasts. The incorporation of external influencing factors such as meteorology further reduces forecast bias, making the main grid's power supply forecast, distributed output forecast, and load-side demand forecast all reliable. The integration and analysis of energy storage regulation capacity clearly presents the total energy supply and structural distribution on the supply side, providing a clear basis for accurate supply-demand comparison. This makes the calculation of the supply-demand difference more accurate, enabling energy supply strategies to accurately adapt to load demand while fully leveraging the value of distributed energy. At the same time, it reduces transaction losses and electricity risks caused by supply-demand imbalances, providing strong support for the orderly development of energy trading in the park and the stable operation of the distribution network.

[0039] like Figure 4The diagram shows a flowchart of the supply adjustment execution monitoring and correction module provided in this embodiment of the invention. Supply adjustment monitoring is divided into supply and demand matching accuracy monitoring and energy efficiency analysis. Supply and demand matching accuracy monitoring is achieved by monitoring the execution of instructions to adjust the update step size of the execution progress. Energy efficiency analysis is achieved by determining the preset value of the obtained comprehensive energy efficiency index of supply and demand. When the value is greater than the preset value, the current operation strategy is maintained. When the value is less than the preset value, abnormal energy efficiency is located and corrected.

[0040] Furthermore, supply adjustment execution monitoring includes supply-demand matching accuracy monitoring to verify the predictive matching effect, and energy efficiency analysis to check the energy efficiency of energy interaction in the park. The specific process of supply-demand matching accuracy monitoring is as follows: based on the real-time execution progress of adjustment instructions, the actual execution status of each adjustment instruction is monitored. If the execution response time of the adjustment instruction is found to be greater than the preset execution response time, it indicates that there is a lag in the supply-demand matching status, and the update step size of the corresponding execution progress is adjusted to increase the perception and response range of dynamic changes in the supply-demand status; otherwise, it indicates that the supply-demand matching status is qualified, and the execution status of the adjustment instructions continues to be monitored.

[0041] The specific process of energy efficiency analysis is as follows: Based on the energy efficiency of green electricity consumption and the energy efficiency of distribution network operation, a comprehensive energy efficiency index for supply and demand is obtained to quantify the stability of supply and demand balance and energy utilization efficiency. The comprehensive energy efficiency index is obtained by: retrieving the respective standard benchmark values ​​of green electricity consumption efficiency (represented by the ratio of actual green electricity consumption to the total amount that can be consumed) and distribution network operation efficiency (represented by the measured value of distribution network transmission efficiency), including the benchmark values ​​for green electricity consumption efficiency and distribution network operation efficiency, both set by pre-set personnel based on the actual operating characteristics of the incremental distribution network; calculating the positive difference between the two energy efficiency indicators and their corresponding benchmark values ​​(if the indicator is lower than the benchmark value, the difference is taken as 0), and directly superimposing the two positive differences to obtain the comprehensive energy efficiency index for supply and demand; the specific expression for the comprehensive energy efficiency index E is as follows: ; In the formula, E G1 E represents the actual consumption of green electricity (distributed grid output power). B The energy efficiency benchmark value for green electricity consumption is η1, which represents the measured value of distribution network transmission efficiency, i.e., the ratio of the effective value of output electrical energy to the total input electrical energy. BThis represents the benchmark value corresponding to the energy efficiency of the distribution network operation. In this formula, the benchmark value is used as the standard for the comprehensive energy efficiency index of supply and demand. When the corresponding green electricity consumption energy efficiency and distribution network operation energy efficiency exceed the benchmark value, an improvement is made. By separately quantifying and superimposing the positive improvement of green electricity consumption energy efficiency and distribution network operation energy efficiency, it is ensured that the index avoids interference from the non-compliant part, and can accurately identify problems such as insufficient green electricity consumption and inefficient distribution network transmission. This provides the park with a clear direction for energy efficiency optimization and promotes the coordinated improvement of efficient green electricity consumption and distribution network loss reduction.

[0042] If the obtained comprehensive energy efficiency index for supply and demand is not less than the preset comprehensive energy efficiency index for supply and demand, it indicates that the current energy efficiency for supply and demand is within an acceptable range, and the current industrial park interaction data and existing operation strategy should be maintained. If the obtained comprehensive energy efficiency index for supply and demand is less than the preset comprehensive energy efficiency index for supply and demand, it indicates that the current energy efficiency for supply and demand has not met expectations, and energy efficiency anomaly location needs to be performed. Specifically: if only the actual value of green electricity consumption energy efficiency is lower than its benchmark value, then green electricity consumption is determined to be the current energy efficiency anomaly point; if only the actual value of distribution network operation energy efficiency is lower than its benchmark value, then the distribution network operation efficiency is determined to be... The current energy efficiency anomaly point is identified. If both the actual energy efficiency value of green electricity consumption and the actual energy efficiency value of distribution network operation are lower than their benchmark values, then a dual energy efficiency anomaly point is identified. The above energy efficiency anomaly location results are fed back to prompt dynamic correction management based on different scenarios and priorities. For example, if only green electricity consumption is abnormal, the priority of distributed power generation output is increased, and the range of flexible load matching is expanded. If only distribution network operation is abnormal, the distribution network operation mode is adjusted. If there are dual anomalies, they are sorted by deviation magnitude, and the anomaly item with the more significant impact is rectified first, while manual investigation is carried out simultaneously.

[0043] In this embodiment, the preset execution response time is the result of summing and averaging the historical execution response times during the historical monitoring process. The update step size adjustment of the execution progress is based on historical operating data and core business requirements. Based on historical adjustment effect data, a fixed step size adjustment ratio is set for each interval. When there is a slight lag (0-30%), the step size is increased incrementally (for example, by 1-2 steps). When there is no slight lag, the step size is increased proportionally (for example, by 2%). The preset comprehensive energy efficiency index of supply and demand is preset according to the time period of the industrial park, as well as the electricity demand and power supply. The benchmark value corresponding to the green electricity consumption energy efficiency and distribution network operation energy efficiency is obtained from the value corresponding to the best green electricity consumption energy efficiency and distribution network operation energy efficiency under the same historical scenario.

[0044] Supply and demand matching accuracy monitoring enhances responsiveness to dynamic changes in supply and demand by monitoring the execution progress of adjustment instructions and adjusting the update step size of the execution progress. This avoids supply and demand imbalances caused by untimely instruction execution and ensures that supply adjustments are always synchronized with real-time supply and demand status. Energy efficiency analysis, through anomaly location, makes subsequent corrective management more targeted, improving the adequacy of green electricity consumption and reducing distribution network operation losses. It guides the park's energy trading and management resources towards genuine energy efficiency improvement. The synergy between the two not only allows the execution effect of supply adjustments to be verified in real time, but also provides a clear direction for energy efficiency optimization, effectively improving energy utilization efficiency, supply stability, and the rationality of transactions.

[0045] To meet the digital and intelligent needs of incremental power distribution network energy management in industrial parks, the project focuses on automatic metering data collection, accurate electricity billing, and power trading decision support. It adopts a modular and open architecture, is compatible with market models, and is equipped with localized technical support. This will enable intelligent metering and electricity billing, build power trading decision support capabilities, improve the market-oriented trading management system, promote the digital collection of asset and transaction data, and support the digital transformation of enterprises.

[0046] The functional modules cover metering and marketing (business expansion, assets, billing, collection, etc.), power trading, equipment asset ledger (query, change, maintenance and repair) and integrated source-grid-load-storage management and control (panoramic monitoring, source-load forecasting, etc.), which can promote the transformation of park energy management and improve energy efficiency.

[0047] It should be understood that, in various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0048] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0049] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0050] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0051] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0052] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0053] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this 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 of the various embodiments of this 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.

[0054] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A big data-based energy trading and management system for incremental power distribution networks in industrial parks, characterized in that: It includes the following modules: power interaction characteristic data management module, forecast capacity and demand supply management module, and supply adjustment execution monitoring and correction module; The power interaction feature data management module is used to collect multi-source supply data in real time, reflecting the supply side and supply capacity of the new distribution network in the industrial park, based on the power metering of the corresponding supply side under the new distribution network and new load in the industrial park, and to manage the power interaction feature data. The predicted capacity-demand supply management module is used to perform capacity-demand prediction matching based on the results of power interaction characteristic data management and combined with historical energy transaction correlation data of industrial parks, and to adjust the predicted supply management based on the prediction matching results. The supply adjustment execution monitoring and correction module is used to monitor and dynamically correct supply adjustments based on multi-source supply data and predicted supply management adjustments, and to classify, store and upload industrial park interaction data that reflects the interaction status of the entire energy trading process in the industrial park to the platform for archiving.

2. The industrial park incremental distribution network energy trading and management system based on big data as described in claim 1, characterized in that, The power interaction feature data management includes: supply interaction collaborative management to improve the orderliness of dynamic scheduling of multi-source supply, and interaction consistency verification optimization to improve the accuracy requirements of data during supply adjustment. The specific process of the aforementioned supply interaction and collaborative management is as follows: Based on the acquired multi-source supply data, the energy supply power reflecting the power data of the supply sources is obtained. Combined with the load power on the load side, the supply-demand difference is obtained, and a preliminary coordination strategy including power supply strategy and corresponding power supply curve is generated. The supply sources include grid power supply and distributed power supply, and the multi-source supply data includes grid power supply data and distributed power output data. If the energy supply corresponding to the multi-source supply data is greater than the preset energy supply, and the supply-demand difference is greater than the preset supply-demand difference, then the current distribution network of the park is determined to be in a state of sufficient energy, and distributed power distribution processing coordination is carried out. If only the energy supply corresponding to the multi-source supply data is greater than the preset energy supply, or only the supply-demand difference is greater than the preset supply-demand difference, then it is determined that the current distributed power output has green electricity redundancy, and a power grid power supply instruction is issued to reduce the distribution network line loss. The instruction is then fed back to the power supply strategy to update the corresponding power supply period and power supply capacity. If the energy supply corresponding to the multi-source supply data is not greater than the preset energy supply, and the supply-demand difference is not greater than the preset supply-demand difference, then the current distribution network of the park is determined to be in a state of energy supply and demand balance, and the current power supply strategy and power supply curve remain unchanged. In all cases except those mentioned above, the current supply and demand of the power distribution network in the park is determined to be mismatched, and manual intervention is prompted.

3. The industrial park incremental distribution network energy trading and management system based on big data as described in claim 2, characterized in that, The distributed power distribution processing coordination specifically includes: When the proportion of grid power supply data in the multi-source supply data is higher than the proportion of distributed power output data, the output limit of the distribution network corresponding to grid power supply is adjusted, and the power supply curve currently being executed is dynamically corrected to update the power supply curve and generate a new power supply strategy. When the proportion of grid power supply data in the multi-source supply data is not higher than the proportion of distributed power output data, a distributed power output priority dispatch instruction is issued, the proportion of grid power supply load is reduced, and the load allocation ratio of the corresponding power supply curve is updated in accordance with the flexible load demand in the park.

4. The industrial park incremental distribution network energy trading and management system based on big data as described in claim 3, characterized in that, The specific process of updating the power supply curve is as follows: Within a preset period, the median of the total target power supply corresponding to the multi-source supply data is obtained and used as the target power supply reference value; The real-time power supply curve within the preset period is compared point by point with the expected power supply curve based on the target power supply reference value, and the power deviation value at each time node is calculated. If the absolute value of the power deviation at any time point exceeds the preset allowable power deviation, a step-wise power correction is performed, and a moving average algorithm is used to smooth the power supply curve after the power correction is qualified, so as to obtain a power supply curve that meets the current supply and demand balance requirements, which is used as the power supply strategy for the next cycle. If the absolute value of the power deviation at each time point does not exceed the preset allowable power deviation, the power supply curve segment obtained after point-by-point comparison will be smoothed to obtain a power supply curve that meets the current supply and demand balance requirements, and will be used as the power supply strategy for the next cycle. The power supply curve includes the output curve of the distributed power source and the power supply curve of the distribution network. The step-wise power correction is specifically as follows: If the power supply at the corresponding time point is higher than the target power supply reference value, the power supply will be reduced by the step size corresponding to the difference in target power supply; otherwise, the power supply will be increased. If, after the step-by-step power correction, the absolute value of the power deviation at any time point still exceeds the preset allowable power deviation, an abnormal power supply warning will be issued. If no such warning is issued, it indicates that the step-by-step power correction is qualified.

5. The industrial park incremental distribution network energy trading and management system based on big data as described in claim 3, characterized in that, The updated load distribution ratio for the corresponding power supply curve is specifically as follows: Obtain the load proportions of grid power supply and distributed generation output in the current power supply curve, and simultaneously calculate the target difference that needs to be increased in the proportion of distributed generation output based on the predicted value of redundant green energy and the adjustable capacity of flexible load. Based on the obtained target difference, the increase in the output ratio of distributed power sources during the corresponding power supply period is obtained by mapping it in the preset target difference-time period adjustment range mapping table; For power supply periods that have reached the target difference corresponding to the increase, the current load allocation ratio is maintained; for power supply periods that have not yet reached the target difference corresponding to the increase within the preset period, the increase of the preset ratio is increased. After adjusting the load distribution ratio for all power supply periods, a moving average algorithm is used to smooth the curves for all power supply periods, resulting in power supply curves that reflect the load power that the grid power supply and distributed power sources should each bear under different power supply periods.

6. The industrial park incremental distribution network energy trading and management system based on big data as described in claim 5, characterized in that, The optimization of the interaction consistency check involves the following steps: Based on the preset verification rules and the updated power supply curve, the identifier verification is performed to obtain the identifier verification duration of each data node in the power supply curve. Based on the identifier verification duration of each data node, the data is classified. The data node represents the discrete data collection point in the power supply curve divided according to the preset time granularity. The specific process of data classification and processing is as follows: If the identifier verification time is less than the minimum value of the preset verification time range, the identifier verification will be performed again. If the verification duration is within the preset verification duration range, then capacity-demand prediction matching will be performed. If the identifier verification duration is greater than the maximum value of the preset verification duration range, the deviation ratio between the obtained identifier verification duration and the maximum value of the preset verification duration range is calculated. Through the preset deviation ratio-adjustment range mapping rule, the adjustment range of the number of shards in parallel is obtained to adjust the number of shards in parallel corresponding to the identifier verification imported data.

7. The industrial park incremental distribution network energy trading and management system based on big data as described in claim 1, characterized in that, The capacity-demand forecasting and matching process is as follows: Based on historical power grid supply data, current power grid supply data and power grid supply curves, and corresponding transaction-related data, time-based estimation processing is performed to generate predicted power grid supply data and corresponding predicted transaction-related data. The predicted power supply data represents the predicted power supply and power supply period obtained from the main power grid in the park's distribution network; The predicted transaction-related data represents the expected transaction volume and execution period in the electricity market, corresponding to the predicted grid power supply data. Based on historical distributed generation power output data, predicted grid power supply data and meteorological forecast data, statistical processing is performed to obtain short-term predicted distributed generation power output data and distributed generation predicted power output curves. The meteorological forecast data is used to quantify the degree of influence of meteorological conditions on distributed generation power output. The predicted grid power supply data and distributed power output data are aggregated to form the energy storage regulation capacity used to characterize the predicted total energy supply on the supply side. Based on historical load data, current load data, and meteorological forecast data, forecast processing is performed to generate load forecast demand data. The energy storage regulation capacity is compared with the electricity demand in the load-side forecast demand data to obtain the forecast supply-demand difference. Based on the obtained forecast supply-demand difference, forecast interval matching is performed.

8. The industrial park incremental distribution network energy trading and management system based on big data as described in claim 7, characterized in that, The process of predicting interval matching is as follows: If the predicted supply-demand difference is greater than the maximum value of the preset positive predicted supply-demand difference range, it indicates that there is a risk of energy surplus. Feedback will be given to adjust the predicted power grid supply data and the corresponding predicted power supply strategy to improve the utilization rate of distributed power generation output data. If the predicted supply-demand difference is within the preset positive predicted supply-demand difference range, it indicates that the supply is balanced during the current supply period, and the existing supply configuration is maintained. If the predicted supply-demand difference is less than the minimum value of the preset negative predicted supply-demand difference range, it indicates that there is a risk of insufficient energy supply. The current predicted supply-demand difference will be fed back to predict the power supply strategy. If the predicted supply-demand difference is within the preset negative predicted supply-demand difference range, it indicates that the energy storage regulation capacity is fluctuating, and the supply-demand difference will be continuously monitored.

9. The industrial park incremental distribution network energy trading and management system based on big data as described in claim 1, characterized in that, The supply adjustment execution monitoring includes supply and demand matching accuracy monitoring to verify the effect of prediction matching, and energy efficiency analysis to check the energy interaction efficiency of the park. The specific process for monitoring the accuracy of supply and demand matching is as follows: The execution status of each adjustment command is monitored. If the execution response time of the adjustment command is less than the preset execution response time, it indicates that there is a lag in the supply and demand matching status. The update step size of the corresponding execution progress is adjusted to increase the perception and response range to the dynamic changes in the supply and demand status. The execution response time is used to quantify the degree of response to the dynamic changes in the supply and demand status during the process from the issuance to the completion of the execution of each adjustment command. Conversely, if the supply and demand match is satisfactory, the execution of the adjustment instructions will continue to be monitored.

10. The energy trading and management system for incremental distribution networks in industrial parks based on big data as described in claim 9, characterized in that, The energy efficiency analysis process is as follows: Based on the energy efficiency of green electricity consumption and the energy efficiency of distribution network operation, a comprehensive energy efficiency index for supply and demand is obtained to quantify the stability of supply and demand balance and energy utilization efficiency. The comprehensive energy efficiency index for supply and demand is obtained by: retrieving the respective standard benchmark values ​​of green electricity consumption energy efficiency and distribution network operation energy efficiency, calculating the positive difference between the two energy efficiency indicators and the corresponding benchmark values, and directly superimposing the two positive differences to obtain the comprehensive energy efficiency index for supply and demand. If the obtained comprehensive energy efficiency index of supply and demand is not less than the preset comprehensive energy efficiency index of supply and demand, it indicates that the current energy efficiency of supply and demand is within an acceptable range, and the current industrial park interaction data and existing operation strategy are maintained. If the obtained comprehensive energy efficiency index for supply and demand is lower than the preset comprehensive energy efficiency index for supply and demand, it indicates that the current energy efficiency for supply and demand has not met expectations, and it is necessary to locate the energy efficiency anomaly, specifically: If only the actual value of green electricity consumption efficiency is lower than its benchmark value, then green electricity consumption is determined to be the current energy efficiency anomaly point; If the actual energy efficiency value of the distribution network is lower than its benchmark value, the distribution network operation efficiency is determined to be an abnormal point in the current energy efficiency. If both the actual value of green electricity consumption energy efficiency and the actual value of distribution network operation energy efficiency are lower than their benchmark values, it is determined that there is a dual energy efficiency anomaly. The above energy efficiency anomaly location results will be fed back to prompt dynamic correction management based on different scenarios and priorities.

Images