A park energy storage data digital management system and method based on multi-source data

Abstract

The present invention discloses a digital management system and method for park energy storage data based on multi-source data, which relates to the technical field and includes: an energy consumption data integration module, an energy demand prediction module, a charging and discharging strategy optimization module and an energy evaluation and adjustment module. The energy consumption data integration module collects energy cost data and integrates the energy cost data. The energy demand cost prediction module constructs and optimizes a model regarding energy demand cost. The charging strategy optimization module establishes a charging strategy optimization model and then analyzes the comprehensive charging cost. The energy evaluation and adjustment module evaluates existing energy storage resources and the energy demand of the park. When it is predicted that the existing energy storage resources cannot meet the energy demand of the park at any time, a charging plan is established according to the charging and discharging strategy optimization model. The present invention fully considers the number of charging and discharging times and capacity attenuation factors to establish a charging strategy optimization model, thereby achieving efficient utilization and cost optimization of park energy storage and improving the overall energy management efficiency of the park.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy storage data digital management, in particular to a park energy storage data digital management system and method based on multi-source data. BACKGROUND

[0002] In today's society, with the acceleration of industrialization and urbanization, the scale of various parks is expanding, and energy consumption is increasing dramatically. The traditional park energy management mode often faces many challenges. On the one hand, the energy consumption data in the park is widely and scattered, including various energy-using equipment in different areas, such as production machinery, lighting systems, air conditioning equipment, etc. These data have differences in format, collection time and precision, and it is difficult to integrate and analyze them effectively, which leads to inaccurate accounting of energy costs and cannot provide reliable basis for energy management decision-making.

[0003] On the other hand, the park lacks scientific and effective means to predict energy demand. Changes in enterprise production plans, changes in weather conditions, and fluctuations in energy costs will have a complex impact on energy demand, and existing prediction methods are difficult to consider these multi-source factors comprehensively, so there is often a gap between energy supply plans and actual demand, which can easily cause energy waste or insufficient supply.

[0004] At the same time, in the management of charging and discharging of energy storage equipment, the traditional way cannot fully balance the relationship between power input cost, equipment operation and maintenance cost, and energy supply stability. Charging and discharging times and capacity attenuation have a significant impact on equipment operation and maintenance costs, and energy supply interruptions directly affect the continuity and stability of park production and operation, but previous methods have failed to integrate these key factors into a unified model for optimization analysis, making it difficult to develop a comprehensive cost-optimal charging strategy.

[0005] Therefore, a park energy storage data digital management system and method based on multi-source data are needed to solve the above problems. SUMMARY

[0006] The purpose of the present application is to provide a park energy storage data digital management system and method based on multi-source data to solve the problems raised in the background.

[0007] In order to solve the above technical problems, the present application provides the following technical scheme: a park energy storage data digital management system based on multi-source data, the system comprising: an energy consumption data integration module, an energy demand prediction module, a charging and discharging strategy optimization module, and an energy evaluation and adjustment module;

[0008] The energy consumption data integration module collects energy cost data and integrates the energy cost data;

[0009] The energy demand cost prediction module performs model construction and optimization on energy demand cost;

[0010] The charging strategy optimization module establishes a charging strategy optimization model through energy supply stability, and then analyzes the comprehensive charging cost;

[0011] The energy evaluation adjustment module evaluates whether the existing energy storage resources can meet the energy demand of the park, and when the existing energy storage resources cannot meet the energy demand of the park at any time, a charging plan is established according to the charging and discharging strategy optimization model.

[0012] Further, the energy consumption data integration module includes a multi-source data acquisition unit and a data integration and preprocessing unit. The multi-source data acquisition unit collects historical energy consumption data of different types of energy-using equipment in different areas of the park through intelligent electric meters and sensors, and simultaneously labels the historical energy consumption data with timestamps;

[0013] The data integration and preprocessing unit performs format unification and standardization processing on the collected multi-source data, converts data of different formats and different sources into a unified format, identifies and eliminates error information in the data using rule-based methods (such as setting reasonable value ranges for data to filter out outliers) and model-based methods (such as clustering analysis, anomaly detection models, etc.), calibrates and aligns the timestamps, ensures the consistency of the data, and summarizes the energy supply interruption data in different time periods; The multi-source data acquisition unit collects historical energy consumption data of various energy-using equipment in the park with the help of intelligent electric meters and sensors and labels the data with timestamps, providing a basic data source for comprehensively mastering the details of energy use in the park, and is the first step in achieving precise energy management; The data integration and preprocessing unit performs format unification, standardization processing, and error information elimination on multi-source data, ensuring reliable data quality and effectively avoiding analysis bias caused by data confusion, providing solid data support for subsequent energy management decisions; By summarizing energy supply interruption data in different time periods, the weak links and risk periods of the park's energy supply can be accurately located, so that targeted strategies can be developed to ensure the stability and continuity of the park's energy supply and improve the overall energy management efficiency of the park.

[0014] Further, the energy demand cost prediction module uses a combination of time series analysis and regression analysis to construct a medium-term energy demand prediction model: E = a + b1*A + b2*B + b3*C + b4*D, where E represents energy demand, A represents enterprise production plan related indicators, B represents meteorological factors, C represents energy cost factors, and D represents park development plan related indicators, a is the planned energy demand, b1, b2, b3, and b4 are regression coefficients related to A, B, C, and D, respectively;

[0015] The random forest algorithm is used to train the energy demand prediction model, the prediction accuracy of the model is improved by adjusting the number and depth of decision trees, the energy demand prediction model is optimized, the energy demand cost prediction module adopts time series and regression analysis to construct a medium-term prediction model and is trained and optimized by the random forest algorithm, and the energy demand is accurately predicted by comprehensively considering multiple factors, so as to provide key and reliable decision basis for park energy planning, cost control and resource reasonable allocation.

[0016] Further, the charging strategy optimization module analyzes the charging comprehensive cost of any time period t i , wherein the time period t i represents the i-th time period, the power input cost C i =P ti *E ti , wherein P ti is the energy input cost of the t i period, E ti is the energy input amount of the period;

[0017] The device operation and maintenance cost e i =k N *N ti +m*C is analyzed considering the number of charging and discharging times and the capacity attenuation factor, wherein k N is the maintenance cost coefficient of each charging and discharging, N ti is the number of charging and discharging, the number of charging and discharging N ti is predicted by summarizing the charging and discharging times in a monitoring period, m is the capacity attenuation cost coefficient, and C is the capacity of the energy storage device, so as to establish a charging strategy optimization model: F ti =C i +e i , wherein F ti is the total energy input cost of the t i period;

[0018] The energy supply stability R is measured by the number and duration of energy supply interruptions:

[0019] ;

[0020] The closer R is to 1, the more stable the energy supply is, and the closer R is to 0, the more chaotic the energy supply is, wherein Y x is the duration of the x-th energy supply interruption, X is the interruption number, and T is the total charging time period, and then the charging comprehensive cost analysis model is obtained:

[0021] ;

[0022] , wherein i={1,2,…,Z}, J is planned in the time period {t1,t2,…,t ZThe charging comprehensive cost of charging, k R The weight related to the energy supply stability.

[0023] Further, the energy evaluation adjustment module adjusts the energy evaluation according to the current planning demand power W T , the remaining power of the park energy storage module W V , and the charging comprehensive cost J, when W T ≤ W V -W0, the park energy storage module does not charge, the park energy storage module is a self-provided energy storage module of the park, and W0 is the minimum energy storage power of the park energy storage module set by the system; when W T > W V -W0, the total charging task amount of W T -W V +W0 is distributed by time period, substituted into the charging comprehensive cost model, so as to obtain the charging comprehensive costs {J1, J2, …, J N} of N charging plans, and select the minimum J n as the recommended cost, that is, take the nth charging plan as the recommended plan; the method of distributing the total charging task amount by time period is to randomly select a time period for charging to randomly generate a charging plan, the charging plan refers to a plan of charging in any time period, for example, the charging time period of any charging plan is {t1, t2, t3}, at this time, the charging amount is comprehensive: E = E t1 +E t2 +E t3 , if E < W T -W V +W0, the charging plan does not meet the total charging task amount, and the charging plan is deleted, if E ≥ W T -W V +W0, the charging plan is retained, and i = {1, 2, 3} is substituted into the comprehensive cost analysis model, so as to calculate the charging comprehensive cost of the charging plan with the charging time period {t1, t2, t3}.

[0024] A park energy storage data digital management method based on multi-source data, comprising the following steps:

[0025] S1: collecting energy cost data and integrating the energy cost data;

[0026] S2: constructing a model of energy demand cost and optimizing the model;

[0027] S3: establishing a charging strategy optimization model through energy supply stability, and then analyzing the charging comprehensive cost;

[0028] S4: The energy evaluation adjustment module evaluates whether the existing energy storage resources can meet the energy demand of the park, and when the existing energy storage resources cannot meet the energy demand of the park at any time, a charging plan is established according to the charging and discharging strategy optimization model.

[0029] Further, in step S1, historical energy consumption data of different regions and different types of energy-using equipment in the park are collected, and the historical energy consumption data are labeled with timestamps, and the timestamps are calibrated and aligned to ensure the consistency of the data, so that the energy supply interruption data of different time periods are summarized.

[0030] Further, in step S2, a method combining time series analysis and regression analysis is used to construct a medium-term energy demand prediction model, a random forest algorithm is used to train the energy demand prediction model, the number and depth of decision trees are adjusted to improve the prediction accuracy of the model, and the energy demand prediction model is optimized.

[0031] Further, in step S3, a charging strategy optimization model is established by analyzing the power input cost and equipment operation and maintenance cost, the energy supply stability is measured by the number and duration of energy supply interruptions, and then the charging comprehensive cost analysis model is obtained by comprehensively considering the charging strategy optimization model and the energy supply stability.

[0032] Further, in step S4, the energy is evaluated and adjusted according to the current planning demand power, when the planning demand power is less than or equal to the park storage power, the park does not charge, when the planning demand power is greater than the park storage power, the total charging task quantity is distributed according to time period, and the plan with the minimum charging comprehensive cost is selected as the recommended plan.

[0033] Compared with the prior art, the beneficial effects achieved by the present application are:

[0034] On the one hand, the energy demand cost prediction module adopts a method combining time series analysis and regression analysis to construct a medium-term energy demand prediction model, and uses a random forest algorithm to train and optimize. The enterprise production plan related indicators, meteorological factors, energy cost factors, and park development planning related indicators are comprehensively considered, and the energy demand is accurately predicted, which helps the park to plan energy supply in advance, effectively prevents the energy supply plan from deviating from the actual demand, reduces energy waste and supply shortage, and provides key and reliable decision basis for park energy planning, cost control and resource rational allocation.

[0035] In one aspect, the charging strategy optimization module deeply analyzes the power input cost and the equipment operation and maintenance cost, establishes a charging strategy optimization model by fully considering the charging and discharging times and the capacity attenuation factor, and measures the energy supply stability in combination with the energy supply interruption to obtain a charging comprehensive cost analysis model. The charging strategy with the optimal comprehensive cost can be formulated while ensuring the stability of the energy supply, so as to realize efficient utilization and cost optimization of the park energy storage, and improve the overall energy management efficiency of the park.

[0036] On the other hand, the energy evaluation adjustment module evaluates and adjusts the energy according to the current planning demand power, the remaining power of the park energy storage module and the charging comprehensive cost. The charging can be intelligently judged according to the actual situation, and the plan with the minimum charging comprehensive cost is selected as the recommended plan through multi-scheme comparison when charging is needed, so as to ensure the balance between energy supply and demand, realize the reasonable allocation and efficient utilization of energy resources, and also reduce the loss of energy storage equipment. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation on the present application. In the drawings:

[0038] Figure 1 is a structural diagram of a park energy storage data digital management system based on multi-source data according to the present application;

[0039] Figure 2 is a flowchart of a park energy storage data digital management method based on multi-source data according to the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0041] Please refer to Figure 1 and Figure 2 The present application provides a technical solution: a park energy storage data digital management system based on multi-source data, which comprises: an energy consumption data integration module, an energy demand prediction module, a charging and discharging strategy optimization module and an energy evaluation adjustment module.

[0042] The energy consumption data integration module collects energy cost data and integrates the energy cost data;

[0043] The energy demand cost prediction module constructs and optimizes the model about the energy demand cost;

[0044] The charging strategy optimization module establishes a charging strategy optimization model through energy supply stability, and then analyzes charging comprehensive cost;

[0045] The energy assessment adjustment module assesses whether existing energy storage resources can meet the energy demand of the park, and when existing energy storage resources do not meet the energy demand of the park at any time, establishes a charging plan according to the charging and discharging strategy optimization model.

[0046] The energy consumption data integration module includes a multi-source data acquisition unit and a data integration and preprocessing unit. The multi-source data acquisition unit collects historical energy consumption data of different types of energy-using equipment in different areas of the park through smart meters and sensors, and simultaneously labels the historical energy consumption data with timestamps;

[0047] The data integration and preprocessing unit performs format unification and standardization processing on the collected multi-source data, converts data of different formats and different sources into a unified format, identifies and eliminates errors in the data using rule-based methods (such as setting reasonable value ranges for data to filter out outliers) and model-based methods (such as clustering analysis, anomaly detection models, etc.), calibrates and aligns the timestamps, ensures data consistency, and summarizes energy supply interruption data in different time periods; The multi-source data acquisition unit collects historical energy consumption data of various energy-using equipment in the park with the help of smart meters and sensors and labels the data with timestamps, providing a basic data source for comprehensively mastering the details of energy use in the park, and is the first step in achieving precise energy management; The data integration and preprocessing unit performs format unification, standardization processing, and error elimination on multi-source data, ensuring reliable data quality and effectively avoiding analysis bias caused by data chaos, providing solid data support for subsequent energy management decisions; By summarizing energy supply interruption data in different time periods, the weak links and risk periods of the park's energy supply can be accurately located, so that targeted strategies can be developed to ensure the stability and continuity of the park's energy supply and improve the overall energy management efficiency of the park.

[0048] The energy demand cost prediction module uses a combination of time series analysis and regression analysis to construct a medium-term energy demand prediction model: E = a + b1*A + b2*B + b3*C + b4*D, where E represents energy demand, A represents enterprise production plan-related indicators, B represents meteorological factors, C represents energy cost factors, and D represents park development plan-related indicators, a is the planned energy demand, b1, b2, b3, and b4 are regression coefficients related to A, B, C, and D, respectively;

[0049] The random forest algorithm is used to train the energy demand prediction model, the prediction accuracy of the model is improved by adjusting the number and depth of decision trees, the energy demand prediction model is optimized, the energy demand cost prediction module adopts time series and regression analysis to construct a medium-term prediction model and is trained and optimized by the random forest algorithm, and the energy demand is accurately predicted by comprehensively considering multiple factors, so as to provide key and reliable decision basis for park energy planning, cost control and rational allocation of resources.

[0050] The charging strategy optimization module analyzes the charging comprehensive cost of any time period t i , wherein the time period t i represents the i-th time period, the power input cost C i =P ti *E ti , wherein P ti is the energy input cost of the t i period, and E ti is the energy input amount of the period;

[0051] The device operation and maintenance cost e i =k N *N ti +m*C is analyzed by considering the number of charging and discharging times and the capacity attenuation factor, wherein k N is the maintenance cost coefficient of each charging and discharging, N ti is the number of charging and discharging, the number of charging and discharging N ti is predicted by summarizing the charging and discharging times of the last monitoring period, m is the capacity attenuation cost coefficient, and C is the capacity of the energy storage device, so as to establish a charging strategy optimization model: F ti =C i +e i , wherein F ti is the total energy input cost of the t i period;

[0052] The energy supply stability R is measured by the number and duration of energy supply interruptions:

[0053] ;

[0054] The closer R is to 1, the more stable the energy supply is, and the closer R is to 0, the more chaotic the energy supply is, wherein Y x is the duration of the x-th energy supply interruption, X is the interruption number, and T is the total charging time period, and then the charging comprehensive cost analysis model is obtained:

[0055] ;

[0056] , wherein i={1,2,…,Z}, J is planned in the time period {t1,t2,…,t ZThe charging comprehensive cost of charging, k R The weight related to the energy supply stability.

[0057] The energy evaluation adjustment module evaluates the current planning demand power W T , the remaining power of the park energy storage module W V , and the charging comprehensive cost J, and adjusts the energy evaluation when W T ≤ W V -W0, the park energy storage module does not charge, the park energy storage module is a self-provided energy storage module of the park, and W0 is the minimum energy storage power of the park energy storage module set by the system; when W T > W V -W0, the total charging task amount of W T -W V +W0 is distributed by time period, substituted into the charging comprehensive cost model, so as to obtain the charging comprehensive costs {J1, J2, …, J N} of N charging plans, and select the minimum J n as the recommended cost, that is, take the nth charging plan as the recommended plan.

[0058] A park energy storage data digital management method based on multi-source data, comprising the following steps:

[0059] S1: collecting energy cost data and integrating the energy cost data;

[0060] S2: constructing a model of energy demand cost and optimizing it;

[0061] S3: establishing a charging strategy optimization model based on energy supply stability, and then analyzing the charging comprehensive cost;

[0062] S4: The energy evaluation adjustment module evaluates whether the existing energy storage resources can meet the energy demand of the park, and when the existing energy storage resources cannot meet the energy demand of the park at any time, a charging plan is established according to the charging and discharging strategy optimization model.

[0063] In step S1, the historical energy consumption data of different regions and different types of energy-using equipment in the park are collected, and the historical energy consumption data are labeled with time stamps. The time stamps are calibrated and aligned to ensure the consistency of the data, so as to summarize the energy supply interruption data in different time periods.

[0064] In step S2, a medium-term energy demand prediction model is constructed by combining time series analysis and regression analysis, a random forest algorithm is used to train the energy demand prediction model, the number and depth of decision trees are adjusted to improve the prediction accuracy of the model, and the energy demand prediction model is optimized.

[0065] In step S3, the power input cost and equipment operation and maintenance cost are analyzed to establish a charging strategy optimization model, and the energy supply stability is measured by the number and duration of energy supply interruptions. Then, the charging strategy optimization model and energy supply stability are comprehensively considered to obtain a charging comprehensive cost analysis model.

[0066] In step S4, energy assessment and adjustment are performed based on the current planned power demand. When the planned power demand is less than or equal to the park's stored power, the park does not charge. When the planned power demand is greater than the park's stored power, the total charging task is allocated by time period, and the plan with the lowest comprehensive charging cost is selected as the recommended plan.

[0067] Example 1: In an actual operation scenario, the energy consumption data integration module comprehensively collects energy cost data of various energy-consuming equipment in the park, covering energy consumption information of large machinery in the production workshop, electrical equipment in the office area, and public facilities, and completes data integration.

[0068] The energy demand cost forecasting module uses a medium-term energy demand forecasting model constructed by combining time series and regression analysis to make accurate forecasts based on multiple factors, including the company's recent production plans (such as a 20% increase in output), current meteorological factors (temperatures are expected to rise in the next week, increasing cooling demand), cost changes caused by energy market fluctuations, and the park's long-term development plan (preparation for new factory construction).

[0069] The charging strategy optimization module starts to work. i (e.g. 2pm to 3pm), the energy input cost at that time is P ti is 0.6, energy input E ti =80, the electricity input cost C is calculated i =0.6×80=48. At the same time, considering that the capacity of the energy storage device C is 300, the number of charge and discharge times N in the last monitoring cycle ti An average of 4 times a day, and the maintenance cost coefficient for each charge and discharge is k N =6, capacity attenuation cost coefficient m is 0.15, calculate the equipment operation and maintenance cost e i =6×4+0.15×300=24+45=69, the total energy input cost F during this period ti =48+69=117. By analyzing historical energy supply interruptions, within a 60-day charging period T, with X=8 interruptions and a total duration of 30 hours, we calculated the energy supply stability R=0.958. This allows us to calculate the cost impact of low energy supply stability and, in turn, the overall charging cost J for that period.

[0070] The energy assessment and adjustment module is based on the current planned power demand W TWhen W V and the comprehensive charging cost J are evaluated and adjusted. When W T > W V -W0 (the minimum energy storage amount set by the system), the charging task amount of W T -W V +W0 is distributed in time periods, substituted into the comprehensive charging cost model, the cost of multiple charging plans is calculated, the plan with the minimum comprehensive charging cost is finally selected for execution, the stability of energy supply in the park is ensured, and the cost is optimal, and the intelligent and refined level of overall energy management in the park is effectively improved.

[0071] It is apparent for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, but can be implemented in other concrete forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered in all aspects as illustrative and not restrictive, and the scope of the present application is defined by the appended claims rather than the above description, and all changes falling within the meaning and range of the equivalent elements of the claims are intended to be embraced in the present application. Any reference signs in the claims should not be considered as limiting the claims involved.

Claims

1. A digital management system for campus energy storage data based on multi-source data, characterized by: The system includes: an energy consumption data integration module, an energy demand forecasting module, a charge and discharge strategy optimization module, and an energy assessment and adjustment module; The energy consumption data integration module collects energy cost data and integrates the energy cost data; The energy demand cost prediction module builds and optimizes the model of energy demand cost; The charging strategy optimization module establishes a charging strategy optimization model based on energy supply stability, and then analyzes the comprehensive charging cost; The energy assessment and adjustment module evaluates whether existing energy storage resources can meet the energy needs of the park. If it predicts that existing energy storage resources cannot meet the energy needs of the park at any time, it will establish a charging plan based on the charging and discharging strategy optimization model. The energy demand cost prediction module uses a method combining time series analysis and regression analysis to construct a medium-term energy demand prediction model: E=a+b1*A+b2*B+b3*C+b4*D, where E represents energy demand, A represents indicators related to the enterprise's production plan, B represents meteorological factors, C represents energy cost factors, and D represents indicators related to the park development plan. a represents the established planned energy demand, and b1, b2, b3, and b4 are regression coefficients related to A, B, C, and D, respectively. The energy demand forecasting model was trained using the random forest algorithm. The prediction accuracy of the model was improved by adjusting the number and depth of decision trees, and the energy demand forecasting model was optimized. The charging strategy optimization module performs the following operations on any time period t i The comprehensive charging cost is analyzed, and the time period t i Indicates the electricity input cost C in the i-th time period i =P ti *E ti , where P ti t i Energy input cost for the period, E ti is the energy input during the period; Analyze equipment operation and maintenance costs by considering charge and discharge times and capacity attenuation factors i =k N *N ti +m*C, where k N is the maintenance cost coefficient for each charge and discharge, N ti is the number of charge and discharge times, m is the capacity attenuation cost coefficient, and C is the capacity of the energy storage device, thereby establishing a charging strategy optimization model: F ti =C i +e i , the F ti t i Total energy input cost during the period; Energy supply stability R is measured by the number and duration of energy supply interruptions: ； where Y x is the duration of the x-th energy supply interruption, X is the number of interruptions, and T is the total charging time period, thereby obtaining the comprehensive charging cost analysis model: ； Where i={1,2,…,Z}, J is the planned time period {t1,t2,…,t Z The comprehensive charging cost of charging, k R The weights related to energy supply stability.

2. The digital management system for energy storage data in a park based on multi-source data according to claim 1, characterized in that: The energy consumption data integration module includes a multi-source data acquisition unit and a data integration and preprocessing unit. The multi-source data acquisition unit collects historical energy consumption data of different areas and different types of energy-consuming equipment in the park through smart meters and sensors, and marks the historical energy consumption data with timestamps. The data integration and preprocessing unit unifies and standardizes the format of the collected multi-source data, converts data of different formats and sources into a unified format, uses rule-based and model-based methods to identify and eliminate erroneous information in the data, calibrates and aligns timestamps to ensure data consistency, and thus summarizes energy supply interruption data in different time periods.

3. The digital management system for energy storage data in a park based on multi-source data according to claim 2, characterized in that: The energy assessment and adjustment module is based on the current planned power demand W T 、Surplus power of the park energy storage module W V Energy evaluation and adjustment are performed based on the comprehensive charging cost J. When W T ≤W V -W0, the park energy storage module is not charged. The park energy storage module is the energy storage module that comes with the park. W0 is the minimum energy storage capacity of the park energy storage module set by the system. When W T >W V -W0, W T -W V The total charging task of +W0 is allocated according to time periods, so as to obtain the comprehensive charging cost of N charging plans {J1,J2,…,J N }, select J with the lowest comprehensive charging cost n As the recommended cost, the nth charging plan is taken as the recommended plan.

4. A method for digital management of campus energy storage data based on multi-source data, applied to the digital management system for campus energy storage data based on multi-source data according to claim 1, characterized in that: The following steps are involved: S1: Collect energy cost data and integrate the energy cost data; S2: Construct and optimize the energy demand cost model; S3: Establish a charging strategy optimization model based on energy supply stability, and then analyze the comprehensive charging cost; S4: Evaluate whether existing energy storage resources can meet the energy needs of the park. When it is predicted that the existing energy storage resources cannot meet the energy needs of the park at any time, establish a charging plan based on the charging and discharging strategy optimization model.

5. The method for digital management of park energy storage data based on multi-source data according to claim 4, characterized in that: In step S1, historical energy consumption data of different areas and different types of energy-consuming equipment in the park are collected, and timestamps are marked on the historical energy consumption data. The timestamps are calibrated and aligned to ensure data consistency, thereby summarizing energy supply interruption data in different time periods.

6. The method for digital management of park energy storage data based on multi-source data according to claim 5, characterized in that: In step S2, a medium-term energy demand forecasting model is constructed by combining time series analysis with regression analysis. The energy demand forecasting model is trained using a random forest algorithm. The prediction accuracy of the model is improved by adjusting the number and depth of decision trees, and the energy demand forecasting model is optimized.

7. The method for digital management of park energy storage data based on multi-source data according to claim 6, characterized in that: In step S3, the power input cost and equipment operation and maintenance cost are analyzed to establish a charging strategy optimization model, and the energy supply stability is measured by the number and duration of energy supply interruptions. Then, the charging strategy optimization model and energy supply stability are comprehensively considered to obtain a charging comprehensive cost analysis model.

8. The method for digital management of park energy storage data based on multi-source data according to claim 7, characterized in that: In step S4, energy assessment and adjustment are performed based on the current planned power demand. When the planned power demand is less than or equal to the park's stored power, the park does not charge. When the planned power demand is greater than the park's stored power, the total charging task is allocated by time period, and the plan with the lowest comprehensive charging cost is selected as the recommended plan.

Images