Multi-period multi-medium energy prediction closed-loop scheduling system and method

Abstract

The invention relates to a multi-period multi-medium energy prediction closed-loop scheduling system and method, and the system comprises a data collection and processing module which is used for continuously collecting energy data of multi-energy equipment, and processing the energy data to obtain effective energy data; the back-end service module is used for generating a dynamic energy fluctuation prediction curve and constructing an optimal scheduling model according to the effective energy data of the historical scheduling period; the front-end operation module is used for generating an optimal scheduling instruction according to the optimal scheduling model and the effective energy data of the current scheduling period and issuing the optimal scheduling instruction to corresponding energy equipment for execution; the data acquisition and processing module is also used for feeding back equipment execution parameters and instruction execution conditions of the multi-energy equipment to the back-end service module; and the back-end service module is also used for generating a scheduling evaluation result of each energy device. According to the invention, the integrated closed-loop control of the dynamic energy scheduling instruction and equipment cooperative operation is realized, and the overall scheduling efficiency and operation economy of the multi-energy system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy scheduling, in particular to a multi-period and multi-medium energy prediction closed-loop scheduling system and method. BACKGROUND

[0002] The typical process industry production has the characteristics of resource and energy intensive, which involves a variety of energy, including coal gas, electricity, steam, etc. These energies are both independent and closely related. How to realize the optimization of multi-medium energy under different working conditions and ensure the balance between supply and demand of energy has become an important issue.

[0003] At present, when solving the energy scheduling problem, a static scheduling mode based on historical data is mostly used, or stage adjustment is made relying on artificial experience. Once the static scheduling plan is made, it is difficult to make flexible adjustment according to the real-time working condition; for example, when the blast furnace suddenly stops blowing, resulting in a sharp decrease in coal gas production, or the rolling mill accelerates rolling, resulting in a large increase in steam demand, it is impossible to make timely adaptive adjustment, which can easily cause problems such as coal gas emission and imbalance of steam pipe network pressure. For another example, the production and consumption link of the coal gas system is long, the user points are widely distributed and the rhythm is variable, even if the power plant receives the scheduling instruction, the power plant operator is also difficult to quickly allocate the fluctuation of coal gas, and it is difficult to ensure the quality requirements of heat supply and power supply. At the same time, in the face of dynamic scenarios such as equipment sudden failure, the static scheduling model cannot quickly respond and generate alternative energy supply strategies, resulting in production interruption or energy waste. In addition, the real-time energy demand changes of each production process cannot be included in the scheduling decision, and it is difficult to realize the efficient use of energy and cost optimization of the whole process. SUMMARY

[0004] In view of the above analysis, the embodiments of the present application aim to provide a multi-period and multi-medium energy prediction closed-loop scheduling system and method to solve the problems that the prior art cannot adapt to real-time working condition changes, lacks dynamic closed-loop scheduling mechanism, energy optimization scheduling is difficult, execution adjustment is lagging, and response speed is not uniform.

[0005] In a first aspect, the embodiments of the present application provide a multi-period and multi-medium energy prediction closed-loop scheduling system, comprising:

[0006] A data acquisition and processing module is configured to continuously acquire energy data of multi-energy equipment and process effective energy data corresponding to a plurality of scheduling periods;

[0007] A back-end service module is configured to generate a dynamic energy fluctuation prediction curve according to the effective energy data of the historical scheduling period, and construct an optimization scheduling model according to the effective energy data of the historical scheduling period and the dynamic energy fluctuation prediction curve;

[0008] The front-end operation module is used to generate optimized scheduling instructions based on the optimized scheduling model and the effective energy data of the current scheduling period, and send them to the corresponding energy equipment for execution.

[0009] The data acquisition and processing module is further configured to feed back the device execution parameters and instruction execution status of the multi-energy devices to the back-end service module; the back-end service module is further configured to generate scheduling evaluation results for each energy device based on the device execution parameters and instruction execution status.

[0010] Furthermore, the data acquisition and processing module includes at least a data acquisition unit and a data processing unit;

[0011] The data acquisition unit is connected to multiple energy devices and is used to continuously collect energy data from these devices; the energy devices include at least energy generating devices, energy storage devices, and energy consuming devices in the production system.

[0012] The data processing unit is used to perform preprocessing operations on the energy data and obtain the effective energy data; the preprocessing operations include at least: data cleaning, outlier detection, and missing value imputation.

[0013] Furthermore, the backend service module includes: an energy forecasting unit.

[0014] The energy prediction unit is used for:

[0015] Based on the effective energy data of the historical scheduling cycle, key operating conditions and non-key operating conditions are screened, and an energy change fluctuation function is constructed based on the operating condition screening results.

[0016] Based on the energy change fluctuation function and the effective energy data of the current scheduling cycle, the real-time operating condition distribution result is identified.

[0017] The real-time operating condition distribution results are compared with the planned operating conditions. Based on the comparison results, the planned operating conditions are corrected, and the corrected operating condition distribution information is obtained.

[0018] Based on the corrected operating condition distribution information and the preset energy fluctuation experience value, the imbalance of different energy media during the period of each operating condition is calculated, and a dynamic energy fluctuation prediction curve for the current scheduling cycle is generated based on the imbalance.

[0019] Furthermore, the backend service module also includes: a rules engine unit.

[0020] The rule engine unit is used to configure preset logical rules and output alternative scheduling strategies when the optimized scheduling model fails to solve the problem.

[0021] Furthermore, the backend service module also includes: an algorithm optimization unit.

[0022] The optimization algorithm unit is used for:

[0023] The optimization scheduling model is constructed with the goal of achieving the lowest overall economic cost, balanced energy efficiency, and best environmental friendliness in multi-time and multi-media scheduling. The constraints of the optimization scheduling model are set according to the safety thresholds of each energy device and the enterprise's energy scheduling rules.

[0024] Based on the optimized scheduling model, the effective energy data of the current scheduling period, and the dynamic energy fluctuation prediction curve, the optimal scheduling strategy for each energy device is solved.

[0025] When the solution is successful, an optimized scheduling instruction corresponding to each energy device is generated according to the optimal scheduling strategy; otherwise, an optimized scheduling instruction corresponding to each energy device is generated according to the alternative scheduling strategy output by the rule engine unit.

[0026] Furthermore, the backend service module also includes: an evaluation rule unit.

[0027] The evaluation rule unit specifically includes:

[0028] The tracking and evaluation subunit is used to track and evaluate the closed-loop execution of the optimized scheduling instruction based on the equipment execution parameters and instruction execution status fed back by each energy device, and generate a first scheduling evaluation result.

[0029] The retrospective analysis subunit is used to periodically retrospectively analyze the operating status, economic benefits, environmental benefits, and energy benefits of each energy device before and after scheduling optimization, and generate a second scheduling evaluation result.

[0030] The query and statistics subunit is used to query and statistically analyze the optimized scheduling instructions, the optimal or alternative scheduling strategies executed by each energy device, and the historical execution status of each energy device, and generate a third scheduling evaluation result.

[0031] Furthermore, the front-end operation module includes:

[0032] The model configuration unit is used to configure the model parameters of the optimized scheduling model based on the parameter information input by the user.

[0033] The optimization instruction unit is used to respond to user triggers, combine the effective energy data of the current scheduling cycle, call the optimization scheduling model and perform calculations and solutions; and generate optimization scheduling instructions corresponding to each energy device based on the model solution results.

[0034] The instruction issuing unit is used to issue the optimized scheduling instruction to the corresponding energy equipment and execute it in response to user triggering;

[0035] The evaluation index unit is used to convert the first scheduling evaluation result, the second scheduling evaluation result, and the third scheduling evaluation result generated by the evaluation rule unit into evaluation index charts and display them visually on the display interface.

[0036] Secondly, embodiments of the present invention provide a closed-loop scheduling method based on the multi-time period multi-media energy prediction closed-loop scheduling system described in one of the first aspects above, comprising:

[0037] Continuously collect energy data from multiple energy devices and process it to obtain effective energy data corresponding to multiple scheduling cycles;

[0038] Based on the effective energy data of historical scheduling cycles, a dynamic energy fluctuation prediction curve is generated; based on the effective energy data of the historical scheduling cycles and the dynamic energy fluctuation prediction curve, an optimized scheduling model is constructed.

[0039] Based on the optimized scheduling model and the effective energy data of the current scheduling period, an optimized scheduling instruction is generated and issued to the corresponding energy equipment for execution.

[0040] After execution, the device execution parameters and command execution status of multiple energy devices are collected, and the scheduling evaluation results of each energy device are generated based on the device execution parameters and command execution status.

[0041] Furthermore, the dynamic energy fluctuation curve for the current scheduling period is generated, specifically including:

[0042] Based on the effective energy data of the historical scheduling cycle, key operating conditions and non-key operating conditions are screened, and an energy change fluctuation function is constructed based on the operating condition screening results.

[0043] Based on the energy change fluctuation function and the effective energy data of the current scheduling cycle, the real-time operating condition distribution results are identified.

[0044] The real-time operating condition distribution results are compared with the planned operating conditions. Based on the comparison results, the planned operating conditions are corrected, and the corrected operating condition distribution information is obtained.

[0045] Based on the corrected operating condition distribution information and the preset energy fluctuation experience value, the imbalance of different energy media during the period of each operating condition is calculated, and a dynamic energy fluctuation prediction curve for the current scheduling cycle is generated based on the imbalance.

[0046] Further, the step of generating optimized scheduling instructions based on the optimized scheduling model and the effective energy data of the current scheduling period includes:

[0047] The optimization scheduling model is constructed with the goal of achieving the lowest overall economic cost, balanced energy efficiency, and best environmental friendliness in multi-time and multi-media scheduling. The constraints of the optimization scheduling model are set according to the safety thresholds of each energy device and the enterprise's energy scheduling rules.

[0048] Based on the optimized scheduling model, the effective energy data of the current scheduling period, and the dynamic energy fluctuation prediction curve, the optimal scheduling strategy for each energy device is solved.

[0049] When the solution is successful, an optimized scheduling instruction corresponding to each energy device is generated according to the optimal scheduling strategy; otherwise, an optimized scheduling instruction corresponding to each energy device is generated according to the pre-configured alternative scheduling strategy.

[0050] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0051] First, unlike existing technologies that cannot adapt to real-time changes in operating conditions, this invention continuously collects and processes energy data from multiple energy sources, using operating condition information as an important basis for energy prediction, and constructs a dynamic energy fluctuation prediction curve. This curve is applicable to various operating scenarios, improves the accuracy of energy prediction, and provides a reliable data foundation for building an optimized scheduling model.

[0052] Secondly, unlike related technologies that lack a dynamic closed-loop scheduling mechanism, resulting in difficulties in energy optimization scheduling and lag in execution and adjustment, this invention achieves integrated closed-loop control of minute-level dynamic energy scheduling commands and equipment collaborative operations by constructing an optimized scheduling model. This enables multi-time period and multi-media closed-loop feedback of "data acquisition-prediction-optimization-execution-evaluation," involving a wider range of media, adapting to more scenarios, and resulting in a more complete overall architecture for closed-loop scheduling. This solves the energy configuration problem in scenarios where complex models lead to no algorithm results, improving economic efficiency, energy-saving efficiency, and environmental benefits, thereby enhancing the overall scheduling efficiency and operational economy of multi-energy systems.

[0053] In this invention, the above-described technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of this invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of this invention can be realized and obtained from what is particularly pointed out in the description and drawings. Attached Figure Description

[0054] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0055] Figure 1This is a schematic diagram of the main modules of the multi-time period multi-media energy prediction closed-loop scheduling system according to an embodiment of the present invention;

[0056] Figure 2 This is a flowchart of the multi-time period, multi-media energy prediction closed-loop scheduling method according to an embodiment of the present invention. Detailed Implementation

[0057] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0058] A specific embodiment of the present invention discloses a multi-time period, multi-medium energy prediction closed-loop scheduling system, such as... Figure 1 As shown, it includes: a data acquisition and processing module, a backend service module, and a frontend operation module;

[0059] The data acquisition and processing module is used to continuously acquire energy data from multiple energy devices and process it to obtain effective energy data corresponding to multiple scheduling cycles.

[0060] The backend service module is used to generate a dynamic energy fluctuation prediction curve based on the effective energy data of the historical scheduling period; and to construct an optimized scheduling model based on the effective energy data and the dynamic energy fluctuation prediction curve of the historical scheduling period.

[0061] The front-end operation module is used to generate optimized scheduling instructions based on the optimized scheduling model and the effective energy data of the current scheduling period, and send them to the corresponding energy equipment for execution.

[0062] The data acquisition and processing module is further configured to feed back the device execution parameters and instruction execution status of the multi-energy devices to the back-end service module; the back-end service module is further configured to generate scheduling evaluation results for each energy device based on the device execution parameters and instruction execution status.

[0063] During implementation, firstly, the data acquisition and processing module acquires energy data from multiple energy devices and sends the pre-processed valid energy data to subsequent modules. Secondly, the backend service module constructs models and algorithms for energy prediction, optimized scheduling, and scheduling evaluation. Thirdly, the frontend operation module configures the models, outputs minute-level optimized scheduling commands based on user triggers, and executes them. During command execution, the scheduling system converts the optimized scheduling commands into a specific string format, which is then distributed to the local controllers of each energy device via the optimized control system of the energy devices through semaphore mapping technology. Finally, the execution status of the commands by multiple energy devices is fed back to the backend service module to evaluate the results of the closed-loop energy prediction scheduling.

[0064] The multi-energy device in this embodiment of the invention is used to convert, supply or consume energy media during the production process. The energy device includes, but is not limited to, energy generating equipment, energy storage equipment, energy consuming equipment and other equipment in the production system; specifically, it may include gas equipment, steam equipment, power generation and transmission and distribution equipment, compressed air equipment and technical gas equipment.

[0065] Among them, energy generating equipment refers to equipment that converts other forms of energy into the required energy through process media, such as blast furnaces that produce blast furnace gas through the blast furnace smelting process; energy storage equipment refers to equipment used to buffer and store energy, such as dry or wet gas holders used to store gas; energy consuming equipment refers to equipment that consumes energy during the production process, such as steel rolling heating furnaces and boilers, which all require gas to provide a heat source; other equipment in the production system can refer to all kinds of metallurgical main process devices and auxiliary facilities other than the above-mentioned equipment, such as steelmaking converters, continuous casting machines, rolling mills, etc., which also involve energy consumption, recovery, or conversion while producing the main products.

[0066] Meanwhile, the energy data directly acquired through the data acquisition and processing module has the same dimensions as the effective energy data obtained after preprocessing. This data is required for energy forecasting and closed-loop scheduling. Specific types include, but are not limited to, historical and real-time scheduling cycle energy production and consumption data, future scheduling cycle production plans, logistics information, abnormal operating condition information, and enterprise energy scheduling rules and equipment safety thresholds. Among these, enterprise energy scheduling rules and equipment safety thresholds are the operational boundary conditions and safety constraints that must be followed in scheduling decisions. They can be used to construct constraints for optimizing scheduling models. Specific content includes the permissible safe operating pressure of gas and steam pipelines, the safe position and lifting rate of gas holders, the technically specified calorific value range of mixed gas, the safe pressure and rate of change of steam accumulators, the maximum and minimum safe loads of each production equipment, the safe output load of generator sets, relevant indicators of purchased electricity and the plant's power grid, and the safe pressure, flow rate, and purity requirements of auxiliary gases such as compressed air, nitrogen, and oxygen.

[0067] Equipment execution parameters refer to the measurable data that energy equipment actually generates during and after executing optimized scheduling instructions, reflecting its operating status and effectiveness. Instruction execution status refers to the status assessment result regarding the degree and quality of instruction completion, obtained by comparing and analyzing the equipment execution parameters with the expected targets in the optimized scheduling instructions. Taking a generator set as an example, equipment execution parameters refer to the load adjustment status and energy input status such as gas of the generator set; instruction execution status refers to the data of the generator set after executing the instruction, such as power generation and instruction execution rate.

[0068] Thus, the energy forecasting closed-loop scheduling system completes the energy closed-loop scheduling of "data acquisition-forecasting-optimization-execution-evaluation", realizes dynamic optimization and efficient utilization of multiple energy media in multiple time periods, and can quickly adjust the scheduling strategy to ensure accurate matching of energy supply and demand.

[0069] Preferably, the data acquisition and processing module includes at least a data acquisition unit and a data processing unit; the data acquisition unit is connected to multiple energy devices and is used to continuously acquire energy data from the multiple energy devices; for example, the data acquisition unit obtains data related to energy dispatch from the field production system through data acquisition equipment and devices such as 5G network terminals; the data processing unit is used to perform preprocessing operations on the energy data and obtain the effective energy data; the preprocessing operations include at least: data cleaning, outlier detection, and missing value imputation; thereby ensuring the integrity and validity of the data.

[0070] Preferably, the backend service module includes: an energy prediction unit, a rule engine unit, an optimization algorithm unit, and an evaluation rule unit.

[0071] The energy prediction unit is used to: filter key operating conditions and non-key operating conditions based on the effective energy data of the historical scheduling cycle, and construct an energy change fluctuation function based on the operating condition screening results; identify the real-time operating condition distribution results based on the energy change fluctuation function and the effective energy data of the current scheduling cycle; compare the real-time operating condition distribution results with the planned operating conditions, correct the planned operating conditions based on the comparison results, and obtain the corrected operating condition distribution information; calculate the imbalance of different energy media during the occurrence period of each operating condition based on the corrected operating condition distribution information and the preset energy fluctuation experience value, and generate a dynamic energy fluctuation prediction curve for the current scheduling cycle based on the imbalance.

[0072] In some implementations, the energy prediction unit can be used to obtain a dynamic energy fluctuation prediction curve by following steps such as operating condition screening, operating condition identification, operating condition tracking, and energy prediction, wherein:

[0073] In the operating condition screening stage, important and non-important operating conditions are screened and classified according to the magnitude of energy fluctuations. In the operating condition identification stage, the fluctuation function of the change in different operating conditions is constructed based on the operating condition screening results, and the feature identification of the change in energy medium fluctuation under the current operating condition is performed to obtain the real-time operating condition distribution results. In the operating condition tracking stage, the real-time operating condition distribution results are compared with the planned operating conditions to obtain the corrected operating condition distribution information. In the energy prediction stage, the corrected operating condition distribution information and the preset energy fluctuation experience value are combined to match different operating conditions to the corresponding time periods in chronological order, calculate the imbalance of different energy media during the time periods of each operating condition, and generate the dynamic energy fluctuation prediction curve for the current scheduling cycle. The time periods of each operating condition include the normal operating condition period defined by the production plan, maintenance shutdown, and other operating condition periods.

[0074] In some implementations, the workflow of each stage of the energy prediction unit is as follows:

[0075] First, in the operating condition screening stage, based on the collected production and maintenance plan data and energy production and consumption data, the changes in the energy medium fluctuation under each operating condition are judged: when the change in the energy medium fluctuation is not stable, the current operating condition is classified into the important operating condition set; otherwise, the current operating condition is classified into the normal operating condition set, that is, the non-important operating condition set.

[0076] Energy fluctuations exhibit different patterns under different operating conditions. Under normal operating conditions, energy fluctuations are relatively stable; however, the distribution of important operating conditions has a significant impact on energy fluctuations. Therefore, during the operating condition screening stage, operating conditions are screened according to the magnitude of the impact of energy fluctuations. The purpose is to identify non-normal operating conditions that require special attention, i.e., important operating conditions, and to set energy change fluctuation curves for energy changes under all operating conditions.

[0077] In implementation, the selection of important operating conditions relies on key parameters, which are determined based on collected production and maintenance plans and energy production and consumption data. Production and maintenance plan data can be used to determine the time period during which equipment operates under a specific condition. Then, by combining this with energy production and consumption data to extract the energy medium fluctuation during that time period, different operating conditions can be selected and distinguished. Furthermore, various operating condition types can be categorized to ultimately obtain a set of important operating conditions. Common operating conditions in This indicates the k-th critical operating condition of the j-th device for the i-th energy medium. This represents the k-th normal operating condition of the j-th device for the i-th energy medium.

[0078] Secondly, the operating condition identification stage mainly includes two parts: setting the energy medium change fluctuation curve under different operating conditions and identifying the energy change fluctuation curve. A clustering algorithm is used to identify the characteristics of energy medium fluctuation under each operating condition, and the energy change fluctuation curve for each operating condition is extracted. Based on the operating condition screening results, the energy change fluctuation curve with zero change corresponding to each normal operating condition is set as the energy fluctuation constant. An energy change fluctuation function is constructed based on the energy change fluctuation curves corresponding to each important operating condition. The energy change fluctuation curve is obtained based on the effective energy data of the current scheduling cycle collected in real time, and this current curve is compared with the energy change fluctuation curves under each operating condition. The operating condition cluster with the closest target distance is selected as the current operating condition type identification result, i.e., the real-time operating condition distribution result.

[0079] In implementation, for setting the energy change fluctuation curve, historical energy data is read, and a clustering algorithm is used to identify the characteristics of energy medium changes under multiple operating conditions, obtaining the energy change fluctuation curve for each operating condition. It can be understood that the energy change fluctuation curve is the change based on the constant value of the conventional operating condition. Then, based on the screening results of the aforementioned conventional and important operating conditions, the energy change fluctuation function for important operating conditions is constructed, denoted as... At the same time, the energy fluctuations corresponding to normal operating conditions are set as constants, denoted as... That is, the change is 0; where, Let f(j) represent the energy change fluctuation function of the j-th device for the k-th key operating condition of the i-th energy medium; This represents the energy fluctuation constant of the j-th device under the k-th normal operating condition for the i-th energy medium; This indicates that the energy fluctuation of the j-th device for the i-th energy medium is stable at the same reference constant under normal operating conditions.

[0080] For the identification of operating condition energy curves, the identification results of the operating condition type can be used in the subsequent operating condition tracking stage. The current energy change fluctuation curve is obtained by collecting the current energy data in real time, and the curve is compared with the multi-operating condition energy change fluctuation curve obtained by the aforementioned clustering method and the similarity is calculated. The smaller the distance, the higher the similarity. Thus, the operating condition cluster with the closest target distance is selected as the identified operating condition type, which is the real-time operating condition distribution result.

[0081] Secondly, during the operating condition tracking phase, discriminant variables and conditions are determined based on the collected equipment operating data, and a set of discriminant variables for the corresponding operating condition is obtained. Based on the set of discriminant variables and conditions, the real-time collected current energy data is judged to obtain the current operating condition type judgment result. Since the actual operating conditions on the production site are dynamically changing, in order to obtain more accurate operating condition information, it is necessary to identify changes in operating conditions based on the current production situation and adjust the operating condition information in the production plan in real time.

[0082] Therefore, the operating condition tracking stage can adjust and correct the operating condition information generated based on production and maintenance plans in real time, and directly identify the energy change curve to determine the operating condition type. Specifically, based on the equipment operation data in the energy database, and according to process or expert knowledge, the discrimination variables and discrimination conditions of the energy equipment are determined. Then, the discrimination results and the energy curve identification results are combined to determine the actual operating condition of each piece of equipment at the current moment.

[0083] When using a discriminant variable for judgment, the discriminant variable can be set as κ, and the set of m corresponding working conditions can be denoted as {K1,...,K}. m Meanwhile, the set to which the discriminant variables for the corresponding working conditions belong is denoted as {Ω1,...,Ω}. m This determines the current operating condition K, and based on the real-time collected effective energy data of the current scheduling cycle, the discrimination variables, and the discrimination conditions, the current operating condition type is determined. The specific judgment formula is as follows:

[0084]

[0085] Next, the consistency between the operating condition type discrimination result and the operating condition type identification result is compared: if they are consistent, the current operating condition is corrected based on the operating condition type identification result, and the corrected operating condition distribution information is determined; otherwise, the corrected operating condition distribution information is determined according to the pre-set conflict resolution logic rules. That is, the aforementioned energy change fluctuation function is called to make a real-time judgment on the operating condition of the current scheduling cycle. If the judgment result is consistent with the judgment result obtained by the discriminant variable method, the operating condition is corrected; otherwise, the final operating condition type needs to be determined according to the user's pre-set custom rule logic. For example, when a discriminant variable or condition for a certain specific operating condition is missing, the identification result of the energy change fluctuation curve is used.

[0086] Preferably, correcting the current working condition based on the working condition type identification result further includes: if it is identified that the current working condition has changed to the first working condition but the planned working condition is not the first working condition, then the time difference Δt between the current working condition and the planned working condition is calculated, and the first working condition and its subsequent working conditions are advanced by Δt; if it is identified that the current working condition has not changed to the first working condition but the planned working condition is the first working condition, then the time difference Δt between the current working condition and the planned working condition is calculated, and the first working condition and its subsequent working conditions are delayed by Δt.

[0087] Finally, in the energy forecasting stage, the prediction focuses on the changes in energy production and consumption, rather than directly predicting the actual energy production and consumption. The dynamic energy fluctuation forecast curve, as an important reference for energy dispatching methods, can be constructed as follows:

[0088] Firstly, based on the operating condition distribution information, the combined operating condition information of multiple time periods within the production scheduling cycle is sorted in chronological order, with each two adjacent time points defined as a time period. This allows all operating conditions to be divided into multiple time nodes {t1, t2, ..., t...} in chronological order. m}, so that each time period {t l ,t l+1 Each item contains several key operating conditions and routine operating conditions for different energy equipment.

[0089] Secondly, for each time period {t} l ,t l+1 Calculate the energy change fluctuation function for different media i. The specific formula is as follows:

[0090]

[0091]

[0092] Among them, {t l ,t l+1} represents multiple time periods obtained by sorting based on working condition distribution information; This represents the prediction function for the fluctuation curve of the change in the j-th device with respect to the i-th medium; Let X represent the energy change fluctuation function of the j-th device for the k-th key operating condition of the i-th energy medium; X represents the current operating condition type. This represents a set of important operating conditions; This represents the set of normal operating conditions.

[0093] Third, by integrating and calculating the energy change fluctuation function and energy fluctuation constant corresponding to each time period, an overall dynamic energy fluctuation prediction curve can be constructed. The specific formula is as follows:

[0094]

[0095] F i (t), t=[t1,t m (5)

[0096] Among them, F i This represents the energy change fluctuation function of medium i obtained by summarizing m-1 time periods; This represents the energy change fluctuation function of medium i during the time period [t1,t2]. The function representing the fluctuation of energy change in medium i during the time interval [t2, t3]; representing [t] m-1 ,t m The energy change fluctuation function of medium i during time period; F i (t) represents the overall dynamic energy fluctuation prediction curve of medium i obtained by splicing and integrating; [t1,t] m ] represents t1 to t m The overall time period.

[0097] Furthermore, to directly obtain the prediction results of the energy fluctuation curve, adjustments can be made while ensuring the aforementioned approach remains unchanged for ease of calculation. Specifically, first, the energy fluctuation constants under the set of normal operating conditions are screened and summed to obtain a fluctuation benchmark value for energy medium i under normal operating conditions, i.e. Subsequently, based on the energy fluctuation baseline, the energy change fluctuation functions corresponding to the key operating conditions appearing in the Gantt chart for all equipment are accumulated to the baseline value. The above yields the energy change prediction function F over the entire time period. i (t). That is, the aforementioned time period division and splicing process of the fluctuation curves of various energy changes are eliminated, thus improving the calculation efficiency.

[0098] Therefore, this energy prediction unit realizes multi-time period and multi-medium energy prediction, and has the function of analyzing the fluctuation trend of energy media and the imbalance of multiple energy media in various operating conditions. It is also the basis for formulating dynamic energy optimization strategies. It not only considers the energy fluctuation under different operating conditions, making the prediction results more accurate and reliable, but also can dynamically adjust the energy dispatch strategy through real-time identification and tracking, thereby improving energy utilization efficiency and system operation stability.

[0099] The rule engine unit is used to: configure preset logical rules, and output alternative scheduling strategies when the optimized scheduling model fails to solve the problem.

[0100] Specifically, the rule engine unit is designed to use pre-defined rules for energy allocation when the optimization scheduling model is too complex for the algorithm to obtain calculation results. In other words, the rule engine module can output alternative energy scheduling solutions. Based on pre-defined industrial practice rules, such as the energy priority principle for key processes and equipment safety threshold constraints, this rule engine unit can quickly output safe and feasible energy allocation solutions as alternative scheduling strategies, thereby effectively avoiding scheduling interruptions. Thus, through an "algorithm-driven, rule-backup" model, the continuity of energy system operation is ensured while also considering the safety and basic economics of industrial scenarios.

[0101] The optimization algorithm unit is used to: construct the optimized scheduling model with the optimization objectives of minimizing the overall economic cost of multi-time period and multi-media scheduling, achieving energy efficiency balance, and maximizing environmental friendliness; set constraints on the optimized scheduling model based on the safety thresholds of each energy device and the enterprise's energy scheduling rules; and solve for the optimal scheduling strategy corresponding to each energy device based on the optimized scheduling model, the effective energy data of the current scheduling period, and the dynamic energy fluctuation prediction curve; wherein, when the solution is successful, an optimized scheduling instruction corresponding to each energy device is generated based on the optimal scheduling strategy; otherwise, an optimized scheduling instruction corresponding to each energy device is generated based on the alternative scheduling strategies output by the rule engine unit.

[0102] In some implementations, this optimization algorithm unit integrates an optimization algorithm model, a constraint configuration system, an algorithm execution engine, and result testing functions. This module supports user-defined settings and has built-in multiple solution algorithms and solvers, making it suitable for a wide range of scenarios. Its core function is to achieve coordinated optimization scheduling of energy media and equipment load.

[0103] In terms of model construction, this unit can construct corresponding objective functions and constraints based on actual scheduling needs, with the optimization objectives of minimizing the overall economic cost of multi-time period and multi-media scheduling, achieving energy efficiency balance, and maximizing environmental friendliness. It can also set priority rules for energy and equipment. Of course, this invention does not limit the specific form of the optimization objective. The optimization objective can also include other optimization objectives that make the overall scheduling more economical, energy-saving, and environmentally friendly, thereby achieving comprehensive optimization of the economy, energy saving, and environmental protection of multi-time period and multi-media overall scheduling.

[0104] The objective function can include, but is not limited to, cost target models, environmental protection target models, and energy-saving target models. For example, based on inputs of effective energy data and dynamic energy fluctuation prediction curves, the objective function can be set to minimize energy costs and operation and maintenance costs to construct a cost target model, reduce carbon emissions and achieve energy efficiency balance to construct an environmental protection target model, and improve the overall energy utilization efficiency to construct an energy-saving target model. The constraint functions can include, but are not limited to, constraints on equipment change rate, medium balance, storage equipment capacity, equipment energy consumption, calorific value upper and lower limits, variable non-negativity, equipment efficiency coefficients, and equipment operation penalty coefficients. Then, the optimization scheduling model is optimized using pre-built algorithms and solvers to obtain the optimal solution for energy medium and equipment load allocation, and the output results are tested.

[0105] It should be noted that the improvement of this invention lies in the closed-loop scheduling system jointly implemented by the energy prediction unit and the optimization algorithm unit, that is, in realizing closed-loop scheduling based on multi-time period and multi-energy medium coordination and optimization. The specific formulas and construction process of the objective function, constraints and solver can be referred to the existing technology, and will not be elaborated here.

[0106] The evaluation rule unit specifically includes the following sub-units:

[0107] The tracking and evaluation subunit is used to track and evaluate the closed-loop execution of the optimized scheduling instruction based on the equipment execution parameters and instruction execution status fed back by each energy device, and generate a first scheduling evaluation result.

[0108] The retrospective analysis subunit is used to periodically retrospectively analyze the operating status, economic benefits, environmental benefits, and energy benefits of each energy device before and after scheduling optimization, and generate a second scheduling evaluation result.

[0109] The query and statistics subunit is used to query and statistically analyze the optimized scheduling instructions, the optimal or alternative scheduling strategies executed by each energy device, and the historical execution status of each energy device, and generate a third scheduling evaluation result.

[0110] During implementation, the evaluation rule unit has functions such as strategy evaluation, periodic review, and comprehensive statistics. The strategy evaluation function can evaluate individual recommended strategy instructions, track the issuance of instructions and the execution of production operations, and track and evaluate the scheduling closed loop. The periodic review function can analyze the energy consumption difference, storage units, power generation load, and economic benefits before and after scheduling optimization, evaluate the scheduling situation, and identify gaps to improve the overall scheduling level. It also provides review tools to analyze scheduling effects, execution effects, and economic benefits, and can identify abnormal problems and provide potential tapping methods. The comprehensive statistics function can be used to query and statistically analyze scheduling strategies, issued instructions, and instruction execution.

[0111] Preferably, the front-end operation module includes:

[0112] The model configuration unit is used to configure the model parameters of the optimized scheduling model based on the parameter information input by the user.

[0113] The optimization instruction unit is used to respond to user triggers, combine the effective energy data of the current scheduling cycle, call the optimization scheduling model and perform calculations and solutions; and generate optimization scheduling instructions corresponding to each energy device based on the model solution results.

[0114] The instruction issuing unit is used to issue the optimized scheduling instruction to the corresponding energy equipment and execute it in response to user triggering;

[0115] The evaluation index unit is used to convert the first scheduling evaluation result, the second scheduling evaluation result, and the third scheduling evaluation result generated by the evaluation rule unit into evaluation index charts and display them visually on the display interface.

[0116] In some implementations, the model configuration unit can be used to configure operating parameters, establish the solution objective and judgment conditions of the optimization scheduling model, etc. For example, users can use a visual display interface to set information such as scheduling time intervals, objective function components, energy medium-related parameters, and scheduling equipment-related parameters. The optimization instruction unit, after model configuration, can calculate the optimized optimal solution based on the model and algorithm rules preset by the backend service module and user-triggered model invocation, thereby generating optimized scheduling instructions for each energy device. These instructions can be presented in tabular and textual form through a visual display interface. Simultaneously, the instruction issuance unit responds to user triggers and, using string-to-semaphore conversion technology and the DCS system, issues optimized scheduling instructions to the corresponding energy devices for execution. The evaluation index unit converts the evaluation results into evaluation index charts through a visual display interface.

[0117] For example, evaluation indicator charts include, but are not limited to, economic cost curves, energy efficiency curves, storage unit reserve curves, environmental benefit curves, strategy triggering status, instruction execution status, instruction issuance status, and economic benefits. Simultaneously, the visualization interface can also display the processing data of various modules and units within the scheduling system; visualization content includes, but is not limited to, production Gantt charts, operating condition tracking, energy storage unit reserve prediction, abnormal event tracking, scheduling instruction output, scheduling instruction issuance, execution status, evaluation status, model pipeline pressure prediction display, dynamic monitoring charts for energy closed-loop scheduling, real-time event alerts, production plans, energy plans, maintenance plans, energy production and consumption curves, and model configuration status, making data transmission more intuitive and efficient.

[0118] Therefore, the embodiments of the present invention, on the one hand, by continuously collecting and processing energy data from multiple energy media, and using operating condition information as an important basis for energy prediction, construct a dynamic energy fluctuation prediction curve, which is applicable to various operating scenarios, improves the accuracy of energy prediction, and provides a reliable data foundation for building an optimized scheduling model; on the other hand, by constructing an optimized scheduling model, it realizes the integrated closed-loop control of minute-level dynamic energy scheduling commands and equipment collaborative operation, achieving multi-time period and multi-media closed-loop feedback of "data collection-prediction-optimization-execution-evaluation", involving a wider range of media, adapting to more scenarios, and making the overall architecture of closed-loop scheduling more complete; thus, it solves the energy configuration and scheduling problem in scenarios where the algorithm has no results due to model complexity, improves economic efficiency, energy saving efficiency, and environmental protection efficiency, and further improves the overall scheduling efficiency and operational economy of multiple energy media.

[0119] It is understood that the above embodiments are for ease of understanding and simplification only, and should not be construed as limiting the present invention. The present invention does not specifically limit the architecture, algorithm model, etc. of the closed-loop scheduling system. The specific implementation of the closed-loop scheduling system of the present invention is not limited to the specific forms described in the specification. Without departing from the core idea of ​​the present invention, the scheduling driving mechanism of the system can be replaced with other equivalent logical units, the evaluation system can be further expanded or its evaluation indicators can be adjusted, and the types of energy media scheduled can also be increased according to actual needs. In addition, the names of each functional module in the system can be adjusted according to the implementation scenario, and its core algorithm and solver can also be replaced with other applicable algorithms and solving tools known to those skilled in the art.

[0120] In another embodiment of the present invention, a closed-loop scheduling method for a multi-time period, multi-media energy prediction closed-loop scheduling system based on the foregoing embodiments is proposed, such as... Figure 2 As shown, the steps S1 to S4 are as follows:

[0121] Step S1: Continuously collect energy data from multiple energy devices and process it to obtain effective energy data corresponding to multiple scheduling cycles.

[0122] Step S2: Generate a dynamic energy fluctuation prediction curve based on the effective energy data of the historical scheduling cycle; construct an optimized scheduling model based on the effective energy data of the historical scheduling cycle and the dynamic energy fluctuation prediction curve.

[0123] Step S3: Based on the optimized scheduling model and the effective energy data of the current scheduling period, generate optimized scheduling instructions and issue them to the corresponding energy equipment for execution.

[0124] Step S4: After execution is completed, collect the device execution parameters and instruction execution status of the multi-energy devices, and generate the scheduling evaluation results of each energy device based on the device execution parameters and instruction execution status.

[0125] In practice, energy forecasting for the current scheduling cycle also includes: screening key and non-key operating conditions based on the effective energy data of the historical scheduling cycles, and constructing an energy change fluctuation function based on the screening results; identifying real-time operating condition distribution results based on the energy change fluctuation function and the effective energy data of the current scheduling cycle; comparing the real-time operating condition distribution results with the planned operating conditions, correcting the planned operating conditions based on the comparison results, and obtaining corrected operating condition distribution information; calculating the imbalance of different energy media during the occurrence period of each operating condition based on the corrected operating condition distribution information and preset energy fluctuation experience values, and generating a dynamic energy fluctuation prediction curve for the current scheduling cycle based on the imbalance.

[0126] Preferably, generating optimized scheduling instructions specifically includes: constructing the optimized scheduling model with the optimization objectives of minimizing the overall economic cost, balancing energy efficiency, and achieving optimal environmental friendliness across multiple time periods and media, to achieve comprehensive optimization of the economy, energy conservation, and environmental protection of the overall multi-time period and multi-media scheduling; setting constraints on the optimized scheduling model based on the safety thresholds of each energy device and the enterprise's energy scheduling rules; solving for the optimal scheduling strategy corresponding to each energy device based on the optimized scheduling model, the effective energy data of the current scheduling cycle, and the dynamic energy fluctuation prediction curve; wherein, when the solution is successful, generating optimized scheduling instructions corresponding to each energy device according to the optimal scheduling strategy; otherwise, generating optimized scheduling instructions corresponding to each energy device according to pre-configured alternative scheduling strategies. The above system and method embodiments are based on the same principle, and their related aspects can be mutually referenced, achieving the same technical effects. For specific implementation processes, please refer to the foregoing embodiments, which will not be repeated here.

[0127] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0128] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A multi-time-period, multi-medium energy prediction closed-loop scheduling system, characterized in that, include: The data acquisition and processing module is used to continuously acquire energy data from multiple energy devices and process it to obtain effective energy data corresponding to multiple scheduling cycles. The backend service module is used to generate a dynamic energy fluctuation prediction curve based on the effective energy data of the historical scheduling period; and to construct an optimized scheduling model based on the effective energy data and the dynamic energy fluctuation prediction curve of the historical scheduling period. The front-end operation module is used to generate optimized scheduling instructions based on the optimized scheduling model and the effective energy data of the current scheduling period, and send them to the corresponding energy equipment for execution. The data acquisition and processing module is further configured to feed back the device execution parameters and instruction execution status of the multi-energy devices to the back-end service module; the back-end service module is further configured to generate scheduling evaluation results for each energy device based on the device execution parameters and instruction execution status.

2. The closed-loop scheduling system according to claim 1, characterized in that, The data acquisition and processing module includes at least a data acquisition unit and a data processing unit; The data acquisition unit is connected to multiple energy devices and is used to continuously collect energy data from these devices; the energy devices include at least energy generating devices, energy storage devices, and energy consuming devices in the production system. The data processing unit is used to preprocess the energy data and obtain the effective energy data. The preprocessing operations include at least: data cleaning, outlier detection, and missing value imputation.

3. The closed-loop scheduling system according to claim 2, characterized in that, The backend service module includes: an energy forecasting unit. The energy prediction unit is used for: Based on the effective energy data of the historical scheduling cycle, key operating conditions and non-key operating conditions are screened, and an energy change fluctuation function is constructed based on the operating condition screening results. Based on the energy change fluctuation function and the effective energy data of the current scheduling cycle, the real-time operating condition distribution result is identified. The real-time operating condition distribution results are compared with the planned operating conditions. Based on the comparison results, the planned operating conditions are corrected, and the corrected operating condition distribution information is obtained. Based on the corrected operating condition distribution information and the preset energy fluctuation experience value, the imbalance of different energy media during the period of each operating condition is calculated, and a dynamic energy fluctuation prediction curve for the current scheduling cycle is generated based on the imbalance.

4. The closed-loop scheduling system according to claim 3, characterized in that, The backend service module also includes: a rules engine unit. The rule engine unit is used to configure preset logical rules and output alternative scheduling strategies when the optimized scheduling model fails to solve the problem.

5. The closed-loop scheduling system according to claim 4, characterized in that, The backend service module also includes: an optimization algorithm unit. The optimization algorithm unit is used for: The optimization scheduling model is constructed with the goal of achieving the lowest overall economic cost, balanced energy efficiency, and best environmental friendliness in multi-time and multi-media scheduling. The constraints of the optimization scheduling model are set according to the safety thresholds of each energy device and the enterprise's energy scheduling rules. Based on the optimized scheduling model, the effective energy data of the current scheduling period, and the dynamic energy fluctuation prediction curve, the optimal scheduling strategy for each energy device is solved. When the solution is successful, an optimized scheduling instruction corresponding to each energy device is generated according to the optimal scheduling strategy; otherwise, an optimized scheduling instruction corresponding to each energy device is generated according to the alternative scheduling strategy output by the rule engine unit.

6. The closed-loop scheduling system according to claim 5, characterized in that, The backend service module also includes: an evaluation rule unit. The evaluation rule unit specifically includes: The tracking and evaluation subunit is used to track and evaluate the closed-loop execution of the optimized scheduling instruction based on the equipment execution parameters and instruction execution status fed back by each energy device, and generate a first scheduling evaluation result. The retrospective analysis subunit is used to periodically retrospectively analyze the operating status, economic benefits, environmental benefits, and energy benefits of each energy device before and after scheduling optimization, and generate a second scheduling evaluation result. The query and statistics subunit is used to query and statistically analyze the optimized scheduling instructions, the optimal or alternative scheduling strategies executed by each energy device, and the historical execution status of each energy device, and generate a third scheduling evaluation result.

7. The closed-loop scheduling system according to claim 6, characterized in that, The front-end operation module includes: The model configuration unit is used to configure the model parameters of the optimized scheduling model based on the parameter information input by the user. The optimization instruction unit is used to respond to user triggers, combine the effective energy data of the current scheduling cycle, call the optimization scheduling model and perform calculations and solutions; and generate optimization scheduling instructions corresponding to each energy device based on the model solution results. The instruction issuing unit is used to issue the optimized scheduling instruction to the corresponding energy equipment and execute it in response to user triggering; The evaluation index unit is used to convert the first scheduling evaluation result, the second scheduling evaluation result, and the third scheduling evaluation result generated by the evaluation rule unit into evaluation index charts and display them visually on the display interface.

8. A closed-loop scheduling method based on the multi-time period multi-medium energy prediction closed-loop scheduling system according to any one of claims 1-7, characterized in that, include: Continuously collect energy data from multiple energy devices and process it to obtain effective energy data corresponding to multiple scheduling cycles; Based on the effective energy data of historical scheduling cycles, a dynamic energy fluctuation prediction curve is generated; based on the effective energy data of the historical scheduling cycles and the dynamic energy fluctuation prediction curve, an optimized scheduling model is constructed. Based on the optimized scheduling model and the effective energy data of the current scheduling period, an optimized scheduling instruction is generated and issued to the corresponding energy equipment for execution. After execution, the device execution parameters and command execution status of multiple energy devices are collected, and the scheduling evaluation results of each energy device are generated based on the device execution parameters and command execution status.

9. The closed-loop scheduling method according to claim 8, characterized in that, The method further includes: generating a dynamic energy fluctuation curve for the current scheduling period, specifically including: Based on the effective energy data of the historical scheduling cycle, key operating conditions and non-key operating conditions are screened, and an energy change fluctuation function is constructed based on the operating condition screening results. Based on the energy change fluctuation function and the effective energy data of the current scheduling cycle, the real-time operating condition distribution results are identified. The real-time operating condition distribution results are compared with the planned operating conditions. Based on the comparison results, the planned operating conditions are corrected, and the corrected operating condition distribution information is obtained. Based on the corrected operating condition distribution information and the preset energy fluctuation experience value, the imbalance of different energy media during the period of each operating condition is calculated, and a dynamic energy fluctuation prediction curve for the current scheduling cycle is generated based on the imbalance.

10. The closed-loop scheduling method according to claim 9, characterized in that, The step of generating optimized scheduling instructions based on the optimized scheduling model and the effective energy data of the current scheduling period includes: The optimization scheduling model is constructed with the goal of achieving the lowest overall economic cost, balanced energy efficiency, and best environmental friendliness in multi-time and multi-media scheduling. The constraints of the optimization scheduling model are set according to the safety thresholds of each energy device and the enterprise's energy scheduling rules. Based on the optimized scheduling model, the effective energy data of the current scheduling period, and the dynamic energy fluctuation prediction curve, the optimal scheduling strategy for each energy device is solved. When the solution is successful, an optimized scheduling instruction corresponding to each energy device is generated according to the optimal scheduling strategy; otherwise, an optimized scheduling instruction corresponding to each energy device is generated according to the pre-configured alternative scheduling strategy.

Images