Production plan adjustment method and system based on peak-valley electricity utilization and electricity price analysis

Abstract

The invention discloses a production plan adjustment method and system based on peak-valley electricity utilization and electricity price analysis. The method comprises the steps of collecting multi-source data and performing data preprocessing; constructing an electricity consumption cost prediction model based on historical electricity consumption data, peak-valley electricity price information and a production plan, and predicting electricity consumption costs under different production arrangements by taking future production plan data and peak-valley electricity price information as input; for equipment or production links of which the production time can be flexibly adjusted, establishing an off-peak production task list, and arranging off-peak production tasks in valley periods or ordinary periods with lower electricity prices for production according to the electricity price information and the priorities of the production tasks; for a production link in which peak shifting cannot be carried out, equipment operation parameters are optimized, and the electric power in a peak period is reduced; real-time monitoring and feedback are achieved, and the power utilization strategy is adjusted in time. According to the method, the accurate analysis of the peak-valley electricity price and the production electricity consumption condition is realized, the electricity consumption strategy is formulated and dynamically adjusted, the production energy consumption cost of an enterprise is reduced, and the optimization of the power grid load is facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of power energy management and cost control, and particularly relates to a production plan adjustment method and system based on peak-valley electricity consumption and electricity price analysis. Background Art

[0002] The statements herein only provide background art related to the present invention and do not necessarily constitute prior art.

[0003] In the industrial production process, the electricity cost occupies an important part of the enterprise production cost. Currently, most enterprises have many deficiencies in electricity management. On the one hand, many enterprises do not make full use of the peak-valley electricity price policy. The peak-valley electricity price aims to encourage users to use electricity during the low valley period to balance the power grid load. However, some enterprises, due to the lack of in-depth understanding and analysis of the peak-valley electricity price, still arrange production electricity in the conventional way, resulting in a large amount of electricity consumption during the peak electricity price period and increasing the production cost. On the other hand, the existing electricity monitoring and analysis means are relatively simple and cannot accurately formulate the optimal electricity consumption strategy by combining the peak-valley electricity price and the actual production situation. For example, it is difficult for enterprises to grasp the electricity consumption situation of different production links in real time and cannot adjust the production plan in time according to the fluctuations of the peak-valley electricity price, resulting in high production energy costs. Moreover, with the continuous change of the power market, the peak-valley electricity price period and price are also adjusted, and enterprises lack an effective response mechanism to dynamically adapt to these changes.

[0004] Therefore, there is an urgent need for a method and system that can comprehensively and accurately analyze peak-valley electricity consumption and electricity price and formulate a scientific strategy to reduce production energy costs accordingly. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above-mentioned deficiencies existing in the prior art and provide a production plan adjustment method and system based on peak-valley electricity consumption and electricity price analysis, so as to achieve accurate analysis of the peak-valley electricity price and production electricity consumption situation, formulate and dynamically adjust the electricity consumption strategy, thereby effectively reducing the enterprise production energy cost, improving the economic benefit of the enterprise, and at the same time contributing to optimizing the power grid load.

[0006] To achieve the above purpose, the present invention is realized by the following technical solutions:

[0007] On the one hand, the technical solution of the present invention provides a production plan adjustment method based on peak-valley electricity consumption and electricity price analysis, including:

[0008] Collect multi-source data and perform data preprocessing;

[0009] Construct an electricity cost prediction model based on historical electricity consumption data, peak-valley electricity price information, and production plan, and use future production plan data and peak-valley electricity price information as inputs to predict the electricity cost under different production arrangements;

[0010] For equipment or production links that can flexibly adjust production time, establish a list of off-peak production tasks, and arrange off-peak production tasks during off-peak hours or normal hours when electricity prices are lower, based on electricity price information and production task priorities; for production links that cannot be off-peaked, optimize equipment operating parameters to reduce power consumption during peak hours;

[0011] The actual cost reduction under the current electricity consumption strategy is monitored in real time and compared with the expected cost reduction effect. If the actual cost reduction effect does not meet expectations, feedback information is sent to the electricity cost prediction model to re-output the electricity cost under different production arrangements and readjust the electricity consumption strategy.

[0012] In at least one embodiment, the multi-source data includes electricity price data, production data, equipment data, and energy consumption data;

[0013] The preprocessing includes data format unification, missing data filling, outlier processing and data integration.

[0014] In at least one embodiment, missing data filling specifically includes: if the missing ratio is within 10%, for numerical data, using the mean filling method based on similar equipment or production links; for categorical data, using the category with the highest frequency of occurrence; if the missing ratio is between 10% and 30%, using the K nearest neighbor algorithm to fill in according to the similarity of data features;

[0015] The specific processing of outliers is as follows: based on the statistical 3σ principle, the mean and standard deviation of the data are calculated, and the data that deviates from the mean by more than 3 times the standard deviation is initially identified as an outlier. Then, the outliers are further confirmed in combination with the isolation forest algorithm; for the identified outliers, if the data has a reasonable basis for correction, they are corrected; if a reasonable value cannot be determined, they are eliminated;

[0016] Data integration specifically includes: formulating unified data standards and establishing association rules, integrating data from different sources into a data warehouse according to unified standards and association rules.

[0017] In at least one embodiment, the method further includes: using a correlation analysis method to analyze the correlation coefficients between the power consumption of different production links and the peak and valley electricity prices, and finding the production links with higher correlation;

[0018] By grouping and counting historical data, we draw the electricity load curve and electricity price change curve for different time periods and summarize the electricity consumption patterns.

[0019] In at least one embodiment, when peak and valley electricity prices are adjusted or electricity prices fluctuate greatly, the electricity usage schedule is re-evaluated and the production plan is dynamically adjusted based on the latest electricity price information.

[0020] In at least one embodiment, a differentiated electricity consumption strategy is formulated according to different production scenarios to ensure the optimization of energy consumption costs while meeting production requirements.

[0021] In at least one embodiment, electricity consumption cost data is obtained in real time. By performing real-time analysis on the collected electricity consumption data and cost data, the actual cost reduction under the current electricity consumption strategy is calculated and compared in detail with the expected cost reduction effect. If the actual cost reduction effect does not meet the expectation, feedback information is sent to the electricity consumption cost prediction model to re-output the electricity consumption costs under different production arrangements and re-adjust the electricity consumption strategy.

[0022] On the other hand, the technical solution of the present invention also provides a production plan adjustment system based on peak-valley electricity consumption and electricity price analysis, including:

[0023] A data acquisition module, configured to: collect multi-source data and perform data preprocessing;

[0024] An electricity consumption cost prediction module, configured to: build an electricity consumption cost prediction model based on historical electricity consumption data, peak-valley electricity price information, and production plans, and use future production plan data and peak-valley electricity price information as inputs to predict the changes in electricity consumption costs under different production arrangements;

[0025] A production plan adjustment module, configured to: for equipment or production links that can flexibly adjust production time, establish a peak-shifting production task list, and arrange peak-shifting production tasks during valley periods or normal periods with lower electricity prices according to electricity price information and the priority of production tasks; for production links that cannot shift peaks, optimize equipment operation parameters to reduce the electricity consumption power during peak periods;

[0026] A monitoring and feedback module, configured to: monitor in real time the actual cost reduction under the current electricity consumption strategy and compare it with the expected cost reduction effect. If the actual cost reduction effect does not meet the expectation, feedback information is sent to the electricity consumption cost prediction model to re-output the electricity consumption costs under different production arrangements and re-adjust the electricity consumption strategy.

[0027] The beneficial effects of the above technical solution of the present invention are as follows:

[0028] 1) Reduce production energy consumption costs

[0029] Through the analysis of peak-valley periods of electricity demand and the accurate prediction of electricity price market fluctuations, the start-up and shutdown times of production equipment can be intelligently scheduled to avoid high-energy consumption production during peak electricity price periods, thereby effectively reducing the energy costs of enterprises. Especially in a market environment with large electricity price fluctuations, the production rhythm can be adjusted and the electricity consumption strategy can be optimized to reduce electricity bills and enhance the cost competitiveness of enterprises.

[0030] 2) Optimize energy use efficiency

[0031] By integrating energy management and monitoring technologies, the electricity consumption data of each production link is monitored and analyzed in real time to identify inefficient links in electricity use and provide targeted optimization suggestions. This not only helps enterprises reduce unnecessary electricity waste but also improves the overall efficiency of energy utilization and promotes the green and low-carbon use of energy.

[0032] 3) Flexible adaptation to different electricity markets

[0033] With the gradual opening of the electricity market and diverse electricity price policies, the traditional fixed electricity price structure may lead to uncontrollable energy costs. Through intelligent electricity price market analysis technology, it is possible to cope with the electricity price fluctuations in different electricity markets. Whether in the spot market or under long-term contracts, production scheduling can be flexibly adjusted to reduce the uncertainty risks brought about by electricity price fluctuations.

[0034] 4) Real-time feedback

[0035] Real-time feedback prompts enterprises to respond immediately to electricity price fluctuations and flexibly adjust the production rhythm to ensure that the entire production process closely follows the optimal electricity cost path, maximizing the energy economic benefits.

[0036] 5) Reduction of energy waste and environmental burden

[0037] Through multi-dimensional data analysis and strategy optimization, it is possible to effectively reduce energy waste, lower unnecessary energy consumption in the production process, thereby saving energy costs for enterprises and improving economic benefits. In addition, reasonable energy-saving strategies contribute to reducing carbon emissions and other environmental burdens. Description of the drawings

[0038] The schematic diagrams in the specification forming a part of the present invention are used to provide a further understanding of the present invention. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0039] Figure 1 It is a schematic diagram of a production plan adjustment method based on peak-valley electricity consumption and electricity price analysis of the present invention;

[0040] Figure 2 It is an interactive schematic diagram of each link of a production plan adjustment method based on peak-valley electricity consumption and electricity price analysis of the present invention;

[0041] Figure 3 It is a schematic diagram of data flow of each module of a production plan adjustment system based on peak-valley electricity consumption and electricity price analysis of the present invention. Detailed implementation manners

[0042] It should be noted that the following detailed description is illustrative and aims to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention pertains.

[0043] As introduced in the background art, the object of the present invention is to overcome the deficiencies existing in the above-mentioned prior art, and to provide a production plan adjustment method and system based on peak-valley electricity consumption and electricity price analysis, so as to achieve accurate analysis of peak-valley electricity prices and production electricity consumption, formulate and dynamically adjust electricity consumption strategies, thereby effectively reducing the production energy consumption cost of enterprises, improving the economic benefits of enterprises, and at the same time contributing to optimizing the power grid load.

[0044] Embodiment 1

[0045] In a typical embodiment of the present invention, this embodiment discloses a production plan adjustment method based on peak-valley electricity consumption and electricity price analysis, including:

[0046] Collect multi-source data and perform data preprocessing;

[0047] Based on historical electricity consumption data, peak-valley electricity price information, and production plans, construct an electricity consumption cost prediction model, using future production plan data and peak-valley electricity price information as inputs to predict the electricity consumption costs under different production arrangements;

[0048] For equipment or production links that can flexibly adjust production time, establish a peak-shaving production task list, and according to the electricity price information and the priority of production tasks, arrange the peak-shaving production tasks to be produced during the valley period or normal period with lower electricity prices; for production links that cannot perform peak shaving, optimize the equipment operation parameters to reduce the electricity consumption power during the peak period;

[0049] Real-time monitor the actual cost reduction situation under the current electricity consumption strategy, and compare it with the expected cost reduction effect. If the actual cost reduction effect does not meet the expectation, send feedback information to the electricity consumption cost prediction model, re-output the electricity consumption costs under different production arrangements, and re-adjust the electricity consumption strategy.

[0050] The following is a detailed introduction.

[0051] In this embodiment, data is obtained from multi-source data collection channels. This multi-source data includes electricity price data, production data, equipment data, energy consumption data, etc. Then, taking the equipment as the main business object, construct a unique primary key for the multi-source data to ensure the uniqueness and stability of the main business object, and complete the integration of energy consumption, production, and equipment data.

[0052] Among them, the electricity price data refers to obtaining time-of-use electricity prices (i.e., electricity prices during peak periods, normal periods, and valley periods) and future electricity price prediction curves through the power market API.

[0053] Specifically, configure the access to the electricity market API to ensure a stable connection with the electricity market data platform. According to the API interface document, send requests at specific time intervals (such as every 15 minutes) to obtain the latest time-of-use electricity price (peak, flat, valley) data.

[0054] For the future electricity price prediction curve, confirm the data update frequency and format with the electricity market data provider, obtain the prediction curve data through API calls, and store it in a dedicated electricity price data storage table. The table structure includes fields such as timestamp, electricity price type (peak, flat, valley), electricity price value, and prediction time range.

[0055] Production data is extracted from the MES system, including the task volume of production work orders, equipment list, process energy consumption, and delivery deadline.

[0056] Specifically, obtain the data access rights and interface specifications of the MES system, and through the interfaces provided by the MES system, regularly extract the detailed information of production work orders in the order of creation time of production work orders.

[0057] For each production work order, extract data such as task volume (expressed in specific measurement units such as product quantity, processing batch, etc.), equipment list (including information such as equipment number, equipment name, and affiliated production line), process energy consumption (recording energy consumption data for each production step), and delivery deadline. After organizing these data, store them in the production data database to provide a basis for subsequent analysis.

[0058] Equipment data is collected from IoT terminals such as PLC / SCADA, including the start-stop status, power curve, and minimum running duration of the equipment.

[0059] Specifically, for systems such as PLC / SCADA, use corresponding communication protocols (such as Modbus, OPC, etc.) to connect to the system. According to the distribution of equipment and data collection requirements, configure data collection points to ensure that key data such as the start-stop characteristics of the equipment (recording the start time, stop time, start-stop times, etc. of the equipment), power curve (recording the real-time power values of the equipment in a time series), and minimum running duration can be collected.

[0060] Establish an equipment data collection log to record information such as the time of each data collection, the number of collected equipment, and data transmission status, etc., so as to promptly discover and solve problems that occur during the data collection process. The collected data is stored in the equipment data warehouse and classified and stored according to dimensions such as equipment type and equipment number.

[0061] Energy consumption data is extracted from smart meters using IoT technology. The energy consumption data of the meters can be collected in real time through smart meters, data collectors, equipment sensors, etc., and the energy consumption situation of the equipment can be monitored in real time and analyzed historically.

[0062] After acquiring data from multiple data collection channels, you will face problems such as inconsistent data formats, missing data, and the presence of outliers. Before proceeding to subsequent steps, you need to perform pre-processing operations on the acquired data, such as unifying the data format, filling in missing data, processing outliers, and integrating data.

[0063] First, the data formats are unified. For example, the date format is unified as "YYYY-MM-DDHH:MM:SS" and the decimal places of numerical data are standardized.

[0064] For the problem of missing data, first calculate the actual proportion of each data field. If the missing proportion is within 10%, for numerical data, query the data of similar equipment or production links in the same time period, calculate the mean and fill in the data; for classified data, count the frequency of occurrence of each category and fill in the data with the category with the highest frequency.

[0065] If the missing ratio is between 10% and 30%, the K nearest neighbor algorithm is used to fill in the missing data based on the similarity of data features. Specifically, the K value is optimized through cross-validation and other methods to determine the appropriate K value. The distance between data points is calculated based on the data's equipment type, production process stage, time and other feature vectors, and the nearest K data points are selected to fill in the missing data based on the attribute values ​​of these data points.

[0066] For outlier processing, we first use the 3σ principle based on statistics to calculate the mean and standard deviation of the data, and preliminarily identify data that deviates from the mean by more than 3 times the standard deviation as outliers. Then, we further confirm the outliers by combining the isolation forest algorithm. For the identified outliers, if the data has a reasonable basis for correction (such as by comparing with actual production records), they will be corrected; if the reasonable value cannot be determined, they will be eliminated.

[0067] In terms of data integration, first formulate unified data standards, such as stipulating coding rules for equipment numbers and specifications for production process names; then establish association rules, such as associating equipment data with energy consumption data through equipment numbers, and associating production data with equipment data and energy consumption data through production work order numbers; then use ETL (Extract, Transform, Load) tools to integrate data from different sources into a data warehouse according to unified standards and association rules.

[0068] After completing data preprocessing, based on historical electricity consumption data, peak and valley electricity price information, and production plans, a Python machine learning library (such as Scikit-learn) is used to build an electricity cost prediction model. First, the historical electricity consumption data is preprocessed, including data standardization and feature engineering (such as extracting electricity consumption time characteristics, seasonal characteristics, etc.).

[0069] Then, select a suitable model algorithm, such as linear regression, decision tree regression, or neural network, etc., and train and optimize the model with the training data. During the training process, use methods such as cross-validation to evaluate the performance of the model and adjust the model parameters to improve the prediction accuracy. After the model is built, input the future production plan data (including equipment operation time, task volume, etc.) and peak-valley electricity price information into the model to predict the changes in electricity consumption costs under different production arrangements. This model can simulate the changes in electricity consumption costs under different production arrangements and provide a scientific decision-making basis for the enterprise. For example, by comparing the electricity consumption costs during peak hours and off-peak hours, the system can quantify the economic benefits brought by adjusting the production plan.

[0070] Then, adopt the correlation analysis method and use statistical analysis software (such as SPSS) to deeply explore the correlation between production electricity consumption and peak-valley electricity prices, analyze the correlation coefficients between the electricity consumption in different production links and peak-valley electricity prices, and find out the production links with higher correlations, so as to identify the production links that have the greatest impact on electricity consumption costs. For example, for high-energy-consuming production links, calculate the Pearson correlation coefficient between the increase in electricity consumption costs during peak hours and the product output to judge the strength of the correlation between the two.

[0071] At the same time, analyze the differences in peak-valley electricity prices and the changes in electricity consumption patterns in different seasons, weekdays and non-weekdays. Through grouped statistics of historical data, draw the electricity load curves and electricity price change curves for different time periods and summarize the electricity consumption patterns. For example, through analysis, it is found that from July to September in summer, the electricity load increases significantly from 14:00 to 17:00 every day due to the use of air conditioners, while from December to February in winter, the electricity load rises from 8:00 to 10:00 every day due to the use of heating equipment. By summarizing these patterns, the system can provide more targeted electricity consumption optimization suggestions for the enterprise to help it minimize the energy consumption costs in different time cycles.

[0072] Based on the output results of the electricity consumption cost prediction model, formulate a scientific and reasonable electricity consumption strategy aimed at reducing the electricity consumption cost by optimizing the production arrangement and equipment operation parameters. The specific strategies include the following aspects:

[0073] (1) Peak-shaving production strategy: Sort out production equipment and production processes, and classify them according to the flexibility of their production time. For equipment or production processes whose production time can be flexibly adjusted, establish a peak-shaving production task list. The list records information such as equipment number, production process name, estimated production duration, adjustable time range, etc. According to the electricity price information and the priority of production tasks, arrange the peak-shaving production tasks to be carried out during the valley period or normal period with lower electricity prices; for production processes that cannot be peak-shaved, optimize the equipment operation parameters to reduce the electricity consumption power during the peak period. For example, give priority to arranging tasks with longer estimated production duration and lower priority during the valley period to make full use of the low electricity price advantage during the low valley period. When arranging tasks, consider the minimum operation duration of the equipment and the production sequence constraints between equipment to ensure the feasibility of the production plan.

[0074] (2) Dynamic electricity price response mechanism: Considering the dynamic adjustment of electricity prices, this embodiment designs a flexible electricity consumption strategy adjustment mechanism. Real-time monitor the peak-valley electricity price adjustment information released by the power supplier. When the peak-valley electricity price is adjusted or the electricity price fluctuates greatly, re-evaluate the electricity consumption arrangement in real time, and, based on the new electricity price information and current production task progress, equipment operation status and other data, recalculate the electricity consumption costs under different electricity consumption strategies, and dynamically adjust the production plan. For example, if the peak electricity price rises, calculate the cost savings brought by postponing some adjustable production tasks to a period with lower electricity prices, and compare it with the additional costs that may be generated by adjusting the production plan (such as equipment start-stop costs, production schedule delay costs, etc.), and select the electricity consumption strategy adjustment plan with the optimal cost. Send the adjusted electricity consumption strategy to the control systems of each production equipment in a timely manner to ensure that the enterprise can quickly respond to electricity price changes and reduce electricity consumption costs.

[0075] Multi-scenario strategy optimization: According to different production scenarios (such as seasonal production, emergency order processing, etc.), establish a corresponding production scenario database, which records information such as production characteristics, equipment usage, electricity consumption demand, etc. under each scenario. Develop differentiated electricity consumption strategies for different production scenarios to ensure the optimization of energy consumption costs while meeting production requirements. For example, during the peak electricity consumption period in summer, establish a summer electricity consumption strategy template, give priority to arranging high-energy-consuming equipment to operate during the night valley period, and at the same time adjust the operation parameters of the equipment's cooling system to reduce the energy consumption increase caused by the high-temperature environment of the equipment. In the scenario of emergency order processing, develop an emergency order electricity consumption strategy, give priority to ensuring the electricity consumption demand of emergency order production equipment, and at the same time try to arrange equipment operation during periods with lower electricity prices to balance production progress and electricity consumption costs.

[0076] In this embodiment, for equipment or production processes with adjustable production times, a peak-shaving production strategy is formulated and arranged to produce during valley periods or normal periods. For production processes that cannot be peak-shaved, the operating parameters of the equipment are optimized to reduce the power consumption during peak periods. At the same time, considering the dynamic adjustment of electricity prices, a flexible electricity consumption strategy adjustment mechanism is formulated. When the peak-valley electricity prices change, the electricity consumption arrangement is re-evaluated and adjusted in a timely manner.

[0077] In this embodiment, after determining the electricity consumption strategy, it is encapsulated in the format of a strategy transmission protocol and sent to the control systems of each production equipment. The strategy transmission protocol uses encryption technologies such as SSL / TLS to encrypt the transmission of electricity consumption strategy data, and at the same time uses technologies such as message authentication code (MAC) for data integrity verification.

[0078] After receiving the electricity consumption strategy, the control systems of each production equipment analyze the strategy content and regulate the operation of the equipment according to the strategy instructions. For equipment that can flexibly adjust the operation time, the control system starts the equipment on time during valley electricity periods through the start-stop control interface of the equipment, and reasonably reduces the operation power of the equipment by controlling the operation state of the equipment (such as pausing, reducing the operation speed, etc.) during peak electricity periods. For equipment that needs to run continuously, the control system optimizes the operation parameters of the equipment according to the strategy requirements by adjusting the parameter setting interface of the equipment (such as inverter parameters, temperature control system parameters, etc.) to achieve energy consumption reduction.

[0079] Install high-precision intelligent electricity meters and other real-time data acquisition devices on each production equipment. These devices are connected to the data acquisition server through wired or wireless communication methods, and upload data such as the real-time electricity consumption, electricity consumption duration, and power change of the equipment to the data acquisition server at a set frequency (such as once per second).

[0080] Through the data docking interface with the enterprise financial system and the electricity billing system, the electricity consumption cost data is obtained in real time. The collected electricity consumption data and cost data are stored in the real-time monitoring database, and a real-time data analysis model is established to calculate the actual cost reduction under the current electricity consumption strategy. For example, by calculating the difference between the electricity consumption cost in the current period and the electricity consumption cost in the same period before implementing the electricity consumption strategy, and then dividing it by the electricity consumption cost before implementing the electricity consumption strategy, the actual cost reduction rate is obtained. Compare the actual cost reduction rate with the expected cost reduction effect. If the difference between the two exceeds the set threshold (such as 3%), the difference analysis process is started.

[0081] When the actual cost reduction effect does not meet the expectation, the strategy implementation and monitoring module sends feedback information such as detailed actual electricity consumption data, cost data, and the difference from the expected effect to the data analysis module. After receiving the feedback, the data analysis module re-mines and analyzes the historical electricity consumption data, production data, and current equipment operation status data in depth.

[0082] On the one hand, recheck the analysis process of historical electricity consumption data and production data to find possible analysis omissions or deviations, such as whether there are abnormal data that have not been correctly processed, whether there are errors in the analysis of data correlation relationships, etc. On the other hand, combine the real-time operating parameters of the current equipment, and changing factors such as the temperature and humidity of the production environment to evaluate the rationality of the current electricity consumption strategy. For example, if it is found that the performance of the equipment decreases due to long-term operation, resulting in increased energy consumption and affecting the implementation effect of the electricity consumption strategy, then the equipment needs to be maintained or the electricity consumption strategy needs to be adjusted.

[0083] Based on the results of the reanalysis, the electricity consumption strategy formulation module quickly adjusts the electricity consumption strategy and generates a new strategy plan. Push the new strategy to the control systems of each production equipment again according to the accurate push and execution process of the electricity consumption strategy for implementation, forming an efficient and dynamic closed-loop management mechanism, continuously optimizing the electricity consumption strategy, and reducing the production energy consumption cost.

[0084] Comprehensively analyze the new electricity price information with the current equipment electricity consumption data, production plan, and historical electricity consumption cost data. Use the electricity consumption cost prediction model and the electricity consumption strategy adjustment algorithm to evaluate the impact degree of the electricity price adjustment on the current electricity consumption strategy. For example, calculate the change in electricity consumption cost according to the original electricity consumption strategy under the new electricity price, and the possible cost savings after adjusting the electricity consumption strategy.

[0085] Then, the electricity consumption strategy formulation module quickly adjusts the electricity consumption strategy according to the evaluation results. For example, re-plan the operation arrangements of the equipment during different peak and valley periods. For high-energy-consuming equipment that originally operates during peak periods, if the electricity price increases significantly, adjust its operation time to the valley period; optimize the power distribution of the equipment, adjust the operation parameters of the equipment according to the new electricity price, and make the energy consumption and cost of the equipment reach the optimal balance during different electricity price periods.

[0086] After the adjusted electricity consumption strategy is reviewed again, it is promptly pushed to the control systems of each production equipment to ensure that the enterprise can quickly adapt to the new electricity price environment after the electricity price adjustment and continuously maintain the optimized state of the electricity consumption cost.

[0087] Embodiment 2

[0088] In a typical implementation manner of the present invention, this embodiment discloses a production plan adjustment system based on peak-valley electricity consumption and electricity price analysis, including:

[0089] A data acquisition module, configured to: acquire multi-source data and perform data preprocessing;

[0090] The electricity consumption cost prediction module is configured to: build an electricity consumption cost prediction model based on historical electricity consumption data, peak-valley electricity price information, and production plans, use future production plan data and peak-valley electricity price information as inputs, and predict the changes in electricity consumption costs under different production arrangements;

[0091] The production plan adjustment module is configured to: for equipment or production processes that can flexibly adjust production time, establish a peak-shaving production task list, and arrange peak-shaving production tasks during the valley period or normal period with lower electricity prices according to electricity price information and the priority of production tasks; for production processes that cannot perform peak shaving, optimize the operating parameters of the equipment to reduce the electricity consumption power during the peak period;

[0092] The monitoring and feedback module is configured to: monitor the actual cost reduction under the current electricity consumption strategy in real time, compare it with the expected cost reduction effect, and if the actual cost reduction effect does not meet the expectation, send feedback information to the electricity consumption cost prediction model, re-output the electricity consumption costs under different production arrangements, and re-adjust the electricity consumption strategy.

[0093] Embodiment 3

[0094] In a typical implementation manner of the present invention, this embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the steps in a production plan adjustment method based on peak-valley electricity consumption and electricity price analysis as introduced in Embodiment 1. The steps include:

[0095] Collect multi-source data and perform data preprocessing;

[0096] Build an electricity consumption cost prediction model based on historical electricity consumption data, peak-valley electricity price information, and production plans, use future production plan data and peak-valley electricity price information as inputs, and predict the electricity consumption costs under different production arrangements;

[0097] For equipment or production processes that can flexibly adjust production time, establish a peak-shaving production task list, and arrange peak-shaving production tasks during the valley period or normal period with lower electricity prices according to electricity price information and the priority of production tasks; for production processes that cannot perform peak shaving, optimize the operating parameters of the equipment to reduce the electricity consumption power during the peak period;

[0098] Monitor the actual cost reduction under the current electricity consumption strategy in real time, compare it with the expected cost reduction effect, and if the actual cost reduction effect does not meet the expectation, send feedback information to the electricity consumption cost prediction model, re-output the electricity consumption costs under different production arrangements, and re-adjust the electricity consumption strategy.

[0099] Embodiment 4

[0100] In a typical embodiment of the present invention, this embodiment provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps in a production plan adjustment method based on peak-valley electricity consumption and electricity price analysis introduced in Embodiment 1. The steps include:

[0101] Collect multi-source data and perform data preprocessing;

[0102] Construct an electricity cost prediction model based on historical electricity consumption data, peak-valley electricity price information, and production plans, and use future production plan data and peak-valley electricity price information as inputs to predict the electricity costs under different production arrangements;

[0103] For equipment or production links that can flexibly adjust production time, establish a peak-shaving production task list, and arrange the peak-shaving production tasks to be produced during the valley period or normal period with lower electricity prices according to the electricity price information and the priority of production tasks; for production links that cannot perform peak shaving, optimize the equipment operation parameters to reduce the electricity consumption power during the peak period;

[0104] Real-time monitor the actual cost reduction under the current electricity consumption strategy and compare it with the expected cost reduction effect. If the actual cost reduction effect does not meet the expectation, send feedback information to the electricity cost prediction model, re-output the electricity costs under different production arrangements, and re-adjust the electricity consumption strategy.

[0105] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A production plan adjustment method based on peak-valley electricity consumption and electricity price analysis, characterized in that include: Collect multi-source data and perform data preprocessing; Based on historical electricity consumption data, peak and valley electricity price information and production plan, an electricity cost prediction model is built. With future production plan data and peak and valley electricity price information as input, the electricity cost under different production arrangements is predicted. For equipment or production links that can flexibly adjust production time, establish a list of off-peak production tasks, and arrange off-peak production tasks during off-peak hours or normal hours when electricity prices are lower, based on electricity price information and production task priorities; for production links that cannot be off-peaked, optimize equipment operating parameters to reduce power consumption during peak hours; The actual cost reduction under the current electricity consumption strategy is monitored in real time and compared with the expected cost reduction effect. If the actual cost reduction effect does not meet expectations, feedback information is sent to the electricity cost prediction model to re-output the electricity cost under different production arrangements and readjust the electricity consumption strategy.

2. The production plan adjustment method based on peak-valley electricity consumption and electricity price analysis according to claim 1, characterized in that, The multi-source data includes electricity price data, production data, equipment data and energy consumption data; The preprocessing includes data format unification, missing data filling, outlier processing and data integration.

3. The production plan adjustment method based on peak-valley electricity consumption and electricity price analysis according to claim 1, characterized in that, The missing data filling process includes: if the missing ratio is within 10%, for numerical data, the mean filling method based on similar equipment or production links is used; for categorical data, the category with the highest frequency is used for filling; if the missing ratio is between 10% and 30%, the K nearest neighbor algorithm is used to fill in the missing data based on the similarity of data features; The specific outlier processing is as follows: based on the statistical 3σ principle, the mean and standard deviation of the data are calculated, and the data that deviates from the mean by more than 3 times the standard deviation is initially identified as an outlier; then, the outlier is further confirmed by combining the isolation forest algorithm; for the identified outliers, if the data has a reasonable basis for correction, it will be corrected; if a reasonable value cannot be determined, it will be eliminated; Data integration specifically includes: formulating unified data standards and establishing association rules, integrating data from different sources into a data warehouse according to unified standards and association rules.

4. A production plan adjustment method based on peak-valley electricity consumption and electricity price analysis according to claim 1, characterized in that, It also includes: using correlation analysis methods to analyze the correlation coefficients between electricity consumption in different production links and peak and valley electricity prices, and finding production links with higher correlations; By grouping and counting historical data, we draw the electricity load curve and electricity price change curve for different time periods and summarize the electricity consumption patterns.

5. The production plan adjustment method based on peak-valley electricity consumption and electricity price analysis according to claim 1, characterized in that, When adjusting peak and valley electricity prices or when electricity prices fluctuate greatly, re-evaluate electricity usage arrangements and dynamically adjust production plans based on the latest electricity price information.

6. The production plan adjustment method based on peak-valley electricity consumption and electricity price analysis according to claim 1, characterized in that, Develop differentiated electricity consumption strategies based on different production scenarios to ensure that energy costs are optimized while meeting production needs.

7. The production plan adjustment method based on peak-valley electricity consumption and electricity price analysis according to claim 1, characterized in that, Obtain electricity cost data in real time, calculate the actual cost reduction under the current electricity strategy through real-time analysis of the collected electricity data and cost data, and make a detailed comparison with the expected cost reduction effect; if the actual cost reduction effect does not meet expectations, send feedback information to the electricity cost prediction model, re-output the electricity cost under different production arrangements, and readjust the electricity strategy.

8. A production plan adjustment system based on peak-valley electricity consumption and electricity price analysis, characterized in that, include: The data acquisition module is configured to: collect multi-source data and perform data preprocessing; The electricity cost prediction module is configured to: build an electricity cost prediction model based on historical electricity consumption data, peak-valley electricity price information, and production plans, use future production plan data and peak-valley electricity price information as inputs, and predict the changes in electricity costs under different production arrangements; The production plan adjustment module is configured to: for equipment or production links whose production time can be flexibly adjusted, establish a peak-shifting production task list, and arrange peak-shifting production tasks to be carried out during the valley period or normal period with lower electricity prices according to the electricity price information and the priority of production tasks; for production links that cannot shift peaks, optimize the operating parameters of the equipment to reduce the electricity consumption power during the peak period; The monitoring and feedback module is configured to: monitor the actual cost reduction situation under the current electricity consumption strategy in real time, and compare it with the expected cost reduction effect. If the actual cost reduction effect does not meet the expectation, send feedback information to the electricity cost prediction model, re-output the electricity costs under different production arrangements, and re-adjust the electricity consumption strategy.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that , When the program is executed by the processor, it implements the steps in a production plan adjustment method based on peak-valley electricity consumption and electricity price analysis as described in any one of claims 1-7.

10. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that , When the processor executes the program, it implements the steps in a production plan adjustment method based on peak-valley electricity consumption and electricity price analysis as described in any one of claims 1-7.

Images