A methanol multi-mode combined motion state resource scheduling method, device, equipment and medium

Abstract

This invention discloses a method, apparatus, equipment, and medium for dynamic resource scheduling of methanol multimodal transport. The method includes: generating a current network state vector based on acquired methanol multimodal transport basic data and real-time methanol multimodal transport data; determining a predicted time-domain demand sequence based on the methanol multimodal transport basic data; acquiring a pre-constructed objective optimization function and at least one objective constraint; solving the objective optimization function based on the predicted time-domain demand sequence, using the current network state vector as the starting point, to obtain a predicted time-domain optimal scheduling parameter sequence that satisfies each objective constraint; any predicted time-domain optimal scheduling parameter in the predicted time-domain optimal scheduling sequence includes production adjustment, reserve release, channel flow, and transportation mode assignment; and generating and issuing resource scheduling instructions based on the predicted time-domain optimal scheduling parameter sequence.

Description

Technical Field

[0001] This invention relates to the field of intelligent scheduling technology, and in particular to a method, apparatus, equipment and medium for dynamic resource scheduling of methanol multimodal transport. Background Technology

[0002] In the field of energy material dispatching and supply chain management, various methods and systems have been developed both domestically and internationally. However, existing technologies still have significant limitations in dealing with the dynamic coordination of multimodal transport, cross-regional dispatching of west-to-east energy transfer, and coupled dispatching for emergency response to extreme events.

[0003] Existing dynamic resource scheduling methods for methanol multimodal transport mainly include: a scheduling decision-making model based on human experience, which relies on the personal experience of dispatchers and their judgment of current market information, resulting in slow response speed and low decision-making efficiency; and a scheduling optimization method based on a single mode of transport, which typically focuses on internal optimization of a single mode of transport such as pipeline, railway, or highway, such as pipeline batch optimization and railway wagon scheduling. However, ensuring the domestic supply of methanol is a typical multimodal transport problem, and optimization of a single mode cannot solve the coordination and connection problems of different modes in terms of capacity, cost, and time.

[0004] Therefore, there is an urgent need to propose a resource scheduling method for methanol multimodal transport that can dynamically adjust the methanol supply based on real-time status, in order to solve the methanol supply problem caused by unforeseen events in the dual-source scenario of west-to-east methanol transmission and eastern imports, and to achieve precise optimization of methanol resource scheduling. Summary of the Invention

[0005] This invention provides a methanol multimodal dynamic resource scheduling method, device, equipment, and medium to solve the methanol supply problem caused by unforeseen events in the dual-source scenario of west-to-east methanol transmission and eastern imports, so as to achieve precise optimization of methanol resource scheduling.

[0006] According to one aspect of the present invention, a dynamic resource scheduling method for methanol multimodal transport is provided, the method comprising: Acquire basic data and real-time data of methanol multi-transport, and generate the current network state vector at the current moment based on the basic data and real-time data of methanol multi-transport. Based on the aforementioned methanol multimodal transport data, a predicted time-domain demand sequence is determined; Obtain a pre-constructed objective optimization function and at least one objective constraint; Based on the methanol multimodal transport basic data and the methanol multimodal transport real-time data, and based on the predicted time-domain demand sequence, the objective optimization function is solved using the current network state vector as the starting point to obtain the predicted time-domain optimal scheduling parameter sequence that satisfies each of the objective constraints. Any predicted time-domain optimal scheduling parameter in the predicted time-domain optimal scheduling sequence includes production adjustment amount, reserve release amount, channel flow and transportation mode assignment. Based on the predicted time-domain optimal scheduling parameter sequence, resource scheduling instructions are generated and issued.

[0007] According to another aspect of the present invention, a methanol multimodal dynamic resource scheduling device is provided, the device comprising: The current state vector generation module is used to acquire basic data and real-time data of methanol multi-transport, and generate the current network state vector at the current moment based on the basic data and real-time data of methanol multi-transport. The demand sequence construction module is used to determine the predicted time-domain demand sequence based on the methanol multimodal transport basic data. The function acquisition module is used to acquire a pre-built target optimization function and at least one target constraint. The optimal scheduling parameter prediction module is used to solve the objective optimization function based on the methanol multimodal transport basic data and the methanol multimodal transport real-time data, using the predicted time-domain demand sequence and the current network state vector as the starting point for solving the function, to obtain the predicted time-domain optimal scheduling parameter sequence that satisfies each of the objective constraints; any predicted time-domain optimal scheduling parameter in the predicted time-domain optimal scheduling sequence includes production adjustment amount, reserve release amount, channel flow and transportation mode assignment. The scheduling instruction issuance module is used to generate and issue resource scheduling instructions based on the predicted time-domain optimal scheduling parameter sequence.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the methanol multimodal dynamic resource scheduling method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the methanol multimodal dynamic resource scheduling method according to any embodiment of the present invention.

[0010] The technical solution of this invention generates a current network state vector based on basic and real-time data of methanol multimodal transport. Based on the basic data, it determines a predicted time-domain demand sequence, obtains a pre-constructed target optimization function and at least one target constraint, and solves the target optimization function using the current network state vector as the starting point, based on the predicted time-domain demand sequence. This yields a predicted time-domain optimal scheduling parameter sequence that satisfies each target constraint. Based on this optimal scheduling parameter sequence, it generates and issues resource scheduling instructions. This solution addresses methanol supply issues caused by unforeseen events in scenarios involving both westward methanol transmission and eastern imports, achieving precise optimization of methanol resource scheduling methods.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart of a methanol multimodal dynamic resource scheduling method provided in an embodiment of the present invention; Figure 2 A flowchart of a methanol multimodal dynamic resource scheduling method provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a methanol multimodal dynamic resource scheduling device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the methanol multimodal dynamic resource scheduling method of this invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Figure 1 This is a flowchart of a methanol multimodal transport dynamic resource scheduling method provided by an embodiment of the present invention. This embodiment is applicable to the reasonable and accurate optimization of methanol multimodal transport dynamic resource scheduling in the context of west-to-east methanol transport. This method can be executed by a methanol multimodal transport dynamic resource scheduling device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes: S110. Obtain basic data and real-time data of methanol multi-transport, and generate the current network state vector at the current moment based on the basic data and real-time data of methanol multi-transport.

[0017] S120. Based on the basic data of methanol multimodal transport, determine the predicted time-domain demand sequence.

[0018] S130. Obtain the pre-constructed objective optimization function and at least one objective constraint.

[0019] S140. Based on the basic data and real-time data of methanol multimodal transport, and based on the predicted time-domain demand sequence, the objective optimization function is solved with the current network state vector as the starting point to obtain the predicted time-domain optimal scheduling parameter sequence that satisfies each objective constraint. Any predicted time-domain optimal scheduling parameter in the predicted time-domain optimal scheduling sequence includes production adjustment amount, reserve release amount, channel flow and transportation mode assignment.

[0020] S150. Generate and issue resource scheduling instructions based on the predicted optimal scheduling parameter sequence in the time domain.

[0021] The construction method for methanol multimodal transport basic data is as follows: acquire methanol collection node data and methanol collection channel data, and construct a methanol multimodal transport supply chain basic network based on the methanol collection node data and methanol collection channel data, and use the methanol multimodal transport supply chain basic network as the methanol multimodal transport basic data.

[0022] The methanol data collection nodes include node types and node attributes. Node types include major methanol production areas in western China, import ports, strategic reserves, consumption cities, and intermodal transport hubs. Node objects of different node types are constructed. Node attributes can include node identifier, geographic coordinates, and node type. Production nodes also include capacity limits, reserve nodes include storage capacity limits and safety storage capacity, and consumption nodes include annual / monthly baseline demand and demand priority.

[0023] The methanol collection channel data can include channel type and attribute information. The channel type can be pipeline, railway, inland waterway, highway and coastal shipping, etc.; the attribute type can include channel identifier, origin / end point node, transportation time, designed capacity, benchmark utilization rate, unit transportation cost and maximum allowable utilization rate, etc.

[0024] Based on the methanol collection node data, node objects of the methanol multimodal transport supply chain basic network are constructed and node attributes are assigned to the node objects. Based on the methanol collection channel data, node edges of the methanol multimodal transport supply chain basic network are constructed and edge attributes are assigned to the node edges, thereby generating a methanol multimodal transport supply chain basic network containing node objects and node edges.

[0025] Real-time data for methanol multimodal transport can specifically include methanol production capacity data, import data, transport capacity data, and market data. Specific acquisition methods include: obtaining real-time production capacity data such as actual capacity utilization rates in various production areas from the national methanol production capacity monitoring platform; connecting to the port dispatch system to obtain import data such as forecast arrival volumes, actual arrival volumes, and port operation status; connecting to the national pipeline network and railway freight system to obtain transport capacity data such as real-time pipeline throughput, railway carriage utilization rates, and hub congestion status; and connecting to key consumer markets to obtain market data such as real-time inventory, spot prices, and temporary demand fluctuations.

[0026] The current network state vector at the current moment is generated based on the basic data and real-time data of methanol multi-transport, including: if a real-time interruption event is detected based on the real-time data of methanol multi-transport, or a custom interruption event initiated by the target user is received, the current network state vector at the current moment is generated based on the basic data and real-time data of methanol multi-transport.

[0027] Specifically, real-time data on methanol multimodal transport is polled. If an interruption event rule is matched, an interruption event is initiated. For example, indicators such as port operation status, pipeline transport volume, and railway capacity can be continuously monitored and verified. A real-time interruption event is triggered when preset trigger conditions are met. These trigger conditions can be: the import port operation status is closed, the arrival volume is 0, the actual pipeline transport volume is less than 50% of the designed capacity, or the railway hub congestion duration is greater than 24 hours.

[0028] In addition to the real-time interruption events mentioned above, target users can also define their own interruption events. Specifically, target users can configure interruption event parameters and scheduling preference parameters in the visual configuration interface. Interruption event parameters can include interruption type (e.g., port closure, pipeline failure, railway interruption), interruption start time, expected duration, affected nodes, affected channels, and impact severity (e.g., port import capacity reduced to 0). Scheduling preference parameters can include the setting of objective function weight parameters, prediction time-domain period N, decision period, and convergence accuracy.

[0029] The current network state vector x(0) is generated based on the basic data and real-time data of methanol multimodal transport. The current network state vector x(0) includes the total reserve inventory of each reserve node, the in-transit flow of each transport channel, the capacity utilization rate of each production node, and the total reserve inventory of each node at the current moment. The composition of the current network state vector is as follows: in, Indicates the current time (initial time). Node reserve inventory at each reserve node; Indicates the current time On-transit traffic volume for each transport corridor; Indicates the current time Capacity utilization rate of each production node; Indicates the current time Total reserve inventory at each reserve node.

[0030] After generating a snapshot of the current network state vector at the current moment, the data is locked and used as the initial input parameters for subsequent function solving. Based on the interruption parameters of the aforementioned real-time interruption event or a custom interruption event, constraint update parameters are pre-determined and stored. For example, if an import port A experiences an interruption, the import channel capacity of import port A is... If port operations are disrupted, the system will automatically increase the production capacity of the western production area, as well as the pipeline and railway transport capacity. The constraint update parameters will be stored for later use in subsequent model iterations.

[0031] Based on methanol multimodal transport data, a predicted time-domain demand sequence is determined. In one optional embodiment, determining the predicted time-domain demand sequence based on methanol multimodal transport data includes: determining the predicted basic demand of demand nodes based on the monthly average demand of demand nodes in the methanol multimodal transport data and a preset seasonal fluctuation coefficient; and generating a predicted time-domain demand sequence for each demand node within the predicted time domain based on the predicted basic demand of demand nodes and a preset demand impact coefficient.

[0032] For example, the forecasting basis demand for demand node d is determined as follows: in, This represents the average monthly demand for demand node d. This represents the seasonal fluctuation coefficient at time t, which can be preset by relevant technical personnel.

[0033] Predicted time-domain demand sequence for each demand node d The generation method is as follows: in, This is the demand impact coefficient, which represents the impact of the interruption on the demand at node d. For example, the demand impact coefficient for nodes around the import port can be set to 0.2, while the others can be set to 0.

[0034] By integrating the current network state vector, the predicted time-domain demand sequence, and the constraint update parameters, a constraint condition and objective optimization function are constructed. The objective constraints include: capacity constraints, safety stock constraints, supply guarantee constraints, transportation time delay constraints, and intermodal transport conversion constraints.

[0035] Based on the node inventory dynamic model, capacity constraints, safety stock constraints, and supply guarantee constraints are constructed; the node inventory dynamic equations are as follows: in, This represents the real-time inventory of node n at time t; This represents the total flow into node n at time t; This represents the total flow out of node n at time t; This represents the real-time inventory of node n at time t+1.

[0036] The capacity constraints are as follows: in, This represents the maximum theoretical capacity of node n; This represents the capacity utilization rate of node n at time t.

[0037] The safety stock constraints are as follows: in, This represents the minimum safety reserve inventory, approximately 50% of the total warehouse inventory.

[0038] The supply guarantee constraints are as follows: The transportation time delay constraints are as follows: in, The transit time for transport channel e is used to accurately depict the long-distance delay in the west-to-east transport of alcohol. express The amount of methanol received or delivered at the destination of transport channel e at any given time; This represents the flow rate or shipment volume of methanol originating from the starting point e of the transportation channel at time t.

[0039] The constraints for intermodal transport conversion are as follows: in, This represents the methanol flow rate at time t during the mode of transport transition at the intermodal transport hub. This indicates the maximum transshipment capacity of a multimodal transport hub node, which is specifically determined by physical conditions such as the hub's loading and unloading equipment, yard capacity, and operational efficiency. This indicates the actual dwell or waiting time of methanol at the intermodal transport hub node; This represents the fixed time delay required for a transshipment hub node to complete a mode of transport switch.

[0040] Specifically, the objective optimization function is expressed as follows: in, To optimize the function by minimizing the cumulative stockout; To optimize the function to minimize scheduling cost; Penalties are imposed to maintain resilience.

[0041] in, , and The preset weight parameters are: k represents the current decision time, N represents the number of future cycles covered by a single optimization, and D represents the set of consumer nodes. This represents the predicted demand of consumer node d at time t. Let E represent the actual available supply at consumer node d at time t, and let E represent the set of transportation channels. This represents the unit transportation cost of channel e at time t. This represents the actual transport flow of channel e at time t. and To preset the penalty coefficient, This represents the sum of all warehouse inventories at time t. This indicates the minimum safety reserve inventory. This represents the utilization rate of the critical channel at time t. This indicates the maximum allowable utilization rate of the channel.

[0042] in, , and The preset weighting parameters can be determined in advance by relevant technical personnel, such as in emergency situations. Larger coefficient values, for example , , .

[0043] The large-scale hybrid programming solver is invoked to solve the objective optimization function based on the aforementioned predicted time-domain demand sequence N and the current network state vector, thereby obtaining the predicted time-domain optimal scheduling parameter sequence that satisfies all objective constraints. .

[0044] in, .in, This represents the production adjustment amount of node n at time t; This represents the amount of reserves released at time t; This represents the channel flow of transport channel e at time t; This indicates the path assignment method at time t.

[0045] Extracting the optimal parameters for the current decision period k solely from the predicted optimal scheduling parameter sequence in the time domain This is converted into resource scheduling instructions. Each scheduling instruction includes an instruction identifier (instruction ID), a node object, an execution action, an effective time, and other parameters. Production scheduling instructions include: instruction ID, production node object, capacity action, effective time, and capacity increment. For example, a production scheduling instruction could be: "Instruction ID: PROD-20260417-01, Production Node Object: Area A, Capacity Action: Increase capacity utilization to 100%, Effective Time: Immediately, Expected Increment: 25,000 tons / month". The reserve dispatch instruction includes: instruction ID, reserve warehouse object, release action, release rate, and release route; for example, the reserve dispatch instruction can be "Instruction ID: RESV-20260417-01, reserve node object: strategic reserve warehouse B, release action: release methanol to consumer market C, release rate: 300,000 tons / month, release route: short-distance transport to consumer market B via highway". Transportation dispatch instructions include: instruction ID, channel object, transport volume action, and effective time; for example, a transportation dispatch instruction can be "Instruction ID: TRANS-20260417-01, Channel object: Transportation pipeline D, Transport volume action: Increase the transport volume from 80,000 tons / month to full load 125,000 tons / month, Effective time: Immediately". Route scheduling instructions include: instruction ID, production area or hub object, adjustment action, and adjustment amount; for example, a route scheduling instruction can be "Instruction ID: PATH-20260417-01, production area or hub object: production area E, adjustment action: change the methanol flowing to region C1 from the original road to distribution at B1 to rail from port D1 to inland waterway to B2, adjustment amount: 50,000 tons / month". Resource scheduling instructions can be issued, specifically through relevant APIs (Application Programming Interfaces) to the national pipeline scheduling system, railway freight system, and reserve management platform.

[0046] After the resource scheduling instruction at time k is issued and executed, it waits for the next decision cycle Δt. At time k+1, the actual network state vector after execution is obtained: The above real-time network state vector and predicted state vector Comparisons are made to generate feedback corrections. The time window is rolled forward by one step, with k+1 as the new starting point, and the time domain prediction is performed from... Scroll to ,by Repeat the above steps for the new initial state to begin the next round of rolling optimization. By continuously correcting the prediction deviations in the early stages through rolling optimization, the uncertainty in the evolution of the interruption event can be addressed.

[0047] A visual dashboard can display the execution status of resource scheduling, the utilization rate of key transportation channels, changes in stockout gaps at various consumption areas, and strategic reserve inventory depletion curves in real time. After an interruption event ends, a scheduling review report can be automatically generated, comparing and analyzing the improvements of the generated dynamic scheduling plan compared to static or manual scheduling plans in terms of reducing stockouts, lowering scheduling costs, and shortening recovery time. This provides important reference for subsequent parameter adjustments such as model weight optimization.

[0048] The technical solution of this invention generates a current network state vector based on basic and real-time data of methanol multimodal transport. Based on the basic data, it determines a predicted time-domain demand sequence, obtains a pre-constructed target optimization function and at least one target constraint, and solves the target optimization function using the current network state vector as the starting point, based on the predicted time-domain demand sequence. This yields a predicted time-domain optimal scheduling parameter sequence that satisfies each target constraint. Based on this optimal scheduling parameter sequence, it generates and issues resource scheduling instructions. This solution addresses methanol supply issues caused by unforeseen events in scenarios involving both westward methanol transmission and eastern imports, achieving precise optimization of methanol resource scheduling methods.

[0049] The aforementioned technical solution represents a leap in domestic methanol multimodal transport supply scheduling, moving from experience-driven to data-model-driven approaches, from static contingency plan execution to dynamic rolling optimization, and from single-objective scheduling to comprehensive multi-objective scheduling encompassing supply, cost, and resilience. By constructing a rolling time-domain scheduling framework based on model predictive control, it can accurately respond to emergencies and dynamically coordinate increased production in western China, reserve releases, and capacity allocation across multimodal transport channels. Its built-in multi-objective optimization function intelligently balances scheduling costs and long-term resilience while prioritizing supply security (minimizing shortages). Through a closed-loop mechanism of interruption scenario awareness, rolling optimization, instruction generation, and status feedback, it provides highly automated and intelligent emergency decision-making for energy security, significantly improving decision-making efficiency and scheduling accuracy during crises, achieving optimal supply assurance at minimal cost.

[0050] To further explain the technical effects of the above-mentioned technical solutions, a detailed description is provided below with reference to specific embodiments. The following embodiments are for illustrative purposes only and do not constitute a limitation on the scope of protection. An example is the optimized decision-making process for dynamically coordinating the eastward transport of methanol from the west with the release of reserves under a scenario of import disruption in the eastern region. Under normal circumstances, the total supply is 1.13 million tons / month.

[0051] Set up emergency scenario S1: Port A, a major import port in the east, experiences disruption due to force majeure. At time 1 (Day 1), a port closure notification is received, and emergency dispatch mode is activated. The user sets the prediction time domain N = 30 days, the decision period Δt = 1 day, and the weight parameters of the objective optimization function are set to... , , .

[0052] exist At time (Day 1), the current network status x(0) is: all production areas in the west are in normal production, other ports in the east are importing normally, and all reserve warehouses are at full capacity of 3 million tons. Day 1 rolling optimization result: It is predicted that there will be a monthly supply gap of 400,000 tons in the next 30 days. After optimization, the scheduling instructions for the first day are generated as follows: 1. Immediately release the strategic reserves near provinces B and C, with a total release rate of 300,000 tons / month, focusing on ensuring the market in provinces D and E; 2. Issue a pre-instruction to the A transportation pipeline to increase the transport volume to 125,000 tons / month from the next day to operate at full capacity; 3. Issue a production scheduling instruction to the F production area to gradually increase the capacity utilization rate to 100% from the next day.

[0053] Day 10 Rolling Optimization Results: After 10 days of operation, the network status has been updated. Pipeline A is operating at full capacity, and methanol from increased production in the west has begun to arrive, but there is still a market gap in provinces E and J. Based on the current low pipeline utilization rate (due to full capacity) and gradually decreasing reserve inventory, new dispatch instructions were generated on day 10: 1. Fine-tune the reserve release rate from 300,000 tons / month to 280,000 tons / month to extend the reserve usage period; 2. Add a new railway dispatch instruction, activating the surplus capacity of railways B and C to prioritize the transfer of methanol from provinces G and H to the market in province J, with expected arrival in 10 days; 3. Increase short-distance road transport subsidies for central markets such as provinces M and N, guiding some of the westward methanol-to-eastward railway freight to be unloaded at hub A and distributed to provinces along the Yangtze River via inland waterway shipping, alleviating pressure on the railway hub.

[0054] Day 60 Rolling Optimization Results: Assuming the disruption continues and imports have not yet recovered, the production capacity of Western A has reached 100%, and railway capacity enhancement measures have fully taken effect. The system monitors that the inventory in provinces J and E has recovered to a safe level. The optimization algorithm determines that continuing to release reserves at a rate of 300,000 tons / month will lead to premature depletion of reserves, which is not conducive to coping with future uncertainties. Therefore, the instructions on day 60 are as follows: 1. The release rate of strategic reserves is significantly reduced to 50,000 tons / month, only to balance local short-term fluctuations; 2. All west-to-east methanol transmission channels are maintained at full or high capacity; 3. Instructions are issued to coastal receiving terminals to prepare to receive a small amount of spot methanol purchased at high prices from other international markets as a supplement.

[0055] To evaluate the effectiveness of the scheduling system of this invention, it was compared with a static contingency plan. The static contingency plan was set as follows: upon the occurrence of an interruption, 300,000 tons / month of reserves would be released immediately, continuously for 3 months, while the Lanzhou-Zhengzhou-Changsha pipeline operated at full capacity. The results showed that the dynamic scheduling method of this invention reduced the cumulative shortage by nearly 49% compared to the static contingency plan, from 350,000 tons to 10,000 tons / month. More importantly, while ensuring better supply assurance, the dynamic scheduling scheme used strategic reserve resources more economically, ultimately maintaining 450,000 tons more in reserve inventory than the static contingency plan, demonstrating higher resilience. Through rolling optimization, after real-time sensing of the effects of increased production in the west and improved railway transport capacity, the reserve release rate was dynamically reduced, avoiding unnecessary resource consumption. The overall scheduling cost was also lower, reflecting a better balance between economy and security.

[0056] Compared to existing scheduling methods based on human experience or static plans, the core advantages of this invention lie in its dynamic adaptability, global coordination, goal-oriented approach, and automated decision-making. Existing scheduling methods cannot adjust strategies in real time according to evolving situations, while this invention, by introducing a model predictive control framework, achieves rolling updates and closed-loop corrections of scheduling schemes, exhibiting extremely strong dynamic adaptability. Existing scheduling methods struggle to comprehensively consider the coordination of pipelines, railways, and highways along the West-to-East methanol transmission artery. Existing scheduling often neglects long-term resilience during emergencies, while this invention, through multi-objective optimization, achieves an intelligent balance between short-term supply assurance and long-term resilience maintenance.

[0057] Figure 2 This is a schematic flowchart illustrating a methanol multimodal dynamic resource scheduling method according to an embodiment of the present invention. Based on the above embodiments, this embodiment provides a preferred example. Figure 2 As shown, the method includes the following steps: S210. Obtain basic data and real-time data of methanol multimodal transport.

[0058] S220. If a real-time interruption event is detected based on the real-time data of the methanol multi-unit transportation system, or a custom interruption event initiated by the target user is received, generate the current network state vector at the current moment based on the basic data of the methanol multi-unit transportation system and the real-time data of the methanol multi-unit transportation system.

[0059] S230. Based on the monthly average demand of demand nodes in the methanol multimodal transport basic data, and based on the preset seasonal fluctuation coefficient, determine the predicted basic demand of demand nodes.

[0060] S240. Based on the predicted basic demand of the demand nodes and the preset demand influence coefficient, generate the predicted time domain demand sequence for each demand node in the prediction time domain.

[0061] S250. Obtain the pre-built target optimization function and at least one target constraint; the target constraints include: capacity constraint, safety stock constraint, supply guarantee constraint, transportation time delay constraint, and intermodal conversion constraint.

[0062] S260. Based on the basic data and real-time data of methanol multimodal transport, and based on the predicted time-domain demand sequence, the objective optimization function is solved with the current network state vector as the starting point to obtain the predicted time-domain optimal scheduling parameter sequence that satisfies each objective constraint. Any predicted time-domain optimal scheduling parameter in the predicted time-domain optimal scheduling sequence includes production adjustment amount, reserve release amount, channel flow and transportation mode assignment.

[0063] S270. Generate and issue resource scheduling instructions based on the predicted optimal scheduling parameter sequence in the time domain.

[0064] Figure 3 This is a schematic diagram of a methanol multimodal transport dynamic resource scheduling device provided in an embodiment of the present invention. The methanol multimodal transport dynamic resource scheduling device provided in this embodiment of the present invention is applicable to the reasonable and accurate optimization of methanol multimodal transport dynamic resource scheduling in the context of west-to-east methanol transportation. This methanol multimodal transport dynamic resource scheduling device can be implemented in hardware and / or software, such as... Figure 3 As shown, the device includes: a current state vector generation module 301, a demand sequence construction module 302, a function acquisition module 303, an optimal scheduling parameter prediction module 304, and a scheduling instruction issuance module 305. Among them, The current state vector generation module 301 is used to acquire basic data and real-time data of methanol multi-transport, and generate the current network state vector at the current moment based on the basic data and real-time data of methanol multi-transport. The demand sequence construction module 302 is used to determine the predicted time-domain demand sequence based on the methanol multimodal transport basic data. The function acquisition module 303 is used to acquire a pre-built target optimization function and at least one target constraint condition; The optimal scheduling parameter prediction module 304 is used to solve the objective optimization function based on the methanol multimodal transport basic data and the methanol multimodal transport real-time data, using the current network state vector as the starting point, based on the predicted time-domain demand sequence, to obtain the predicted time-domain optimal scheduling parameter sequence that satisfies each of the objective constraints; any predicted time-domain optimal scheduling parameter in the predicted time-domain optimal scheduling sequence includes production adjustment amount, reserve release amount, channel flow and transportation mode assignment. The scheduling instruction issuing module 305 is used to generate and issue resource scheduling instructions based on the predicted time-domain optimal scheduling parameter sequence.

[0065] The technical solution of this invention generates a current network state vector based on basic and real-time data of methanol multimodal transport. Based on the basic data, it determines a predicted time-domain demand sequence, obtains a pre-constructed target optimization function and at least one target constraint, and solves the target optimization function using the current network state vector as the starting point, based on the predicted time-domain demand sequence. This yields a predicted time-domain optimal scheduling parameter sequence that satisfies each target constraint. Based on this optimal scheduling parameter sequence, it generates and issues resource scheduling instructions. This solution addresses methanol supply issues caused by unforeseen events in scenarios involving both westward methanol transmission and eastern imports, achieving precise optimization of methanol resource scheduling methods.

[0066] Optionally, the current state vector generation module 301 is specifically used for: If a real-time interruption event is detected based on the real-time data of the methanol multi-transport system, or if a custom interruption event initiated by the target user is received, a current network state vector is generated based on the basic data of the methanol multi-transport system and the real-time data of the methanol multi-transport system.

[0067] Optionally, the demand sequence construction module 302 is specifically used for: Based on the monthly average demand of the demand nodes in the methanol multimodal transport basic data, and based on the preset seasonal fluctuation coefficient, the predicted basic demand of the demand nodes is determined. Based on the predicted basic demand of the demand nodes, and using a preset demand influence coefficient, a predicted time-domain demand sequence for each demand node within the predicted time domain is generated.

[0068] Optionally, the objective optimization function can be expressed in the following form: in, , and The preset weight parameters are: k represents the current decision time, N represents the number of future cycles covered by a single optimization, and D represents the set of consumer nodes. This represents the predicted demand of consumer node d at time t. Let E represent the actual available supply at consumer node d at time t, and let E represent the set of transportation channels. This represents the unit transportation cost of channel e at time t. This represents the actual transport flow of channel e at time t. and To preset the penalty coefficient, This represents the sum of all warehouse inventories at time t. This indicates the minimum safety reserve inventory. This represents the utilization rate of the critical channel at time t. This indicates the maximum allowable utilization rate of the channel.

[0069] Optionally, the construction method of the methanol multimodal transport basic data includes the following: Acquire methanol collection node data and methanol collection channel data, and construct a methanol multimodal transport supply chain basic network based on the methanol collection node data and methanol collection channel data, and use the methanol multimodal transport supply chain basic network as the basic data for methanol multimodal transport.

[0070] Optionally, the current network state vector includes the node reserve inventory of each reserve node at the current time, the in-transit traffic of each transportation channel, the capacity utilization rate of each production node, and the total reserve inventory of each node.

[0071] Optionally, the target constraints include: capacity constraints, safety stock constraints, supply guarantee constraints, transportation time delay constraints, and intermodal transport conversion constraints.

[0072] The methanol multimodal dynamic resource scheduling device provided in this embodiment of the invention can execute the methanol multimodal dynamic resource scheduling method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0073] Figure 4A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0074] like Figure 4 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded from storage unit 48 into the RAM 43. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0075] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0076] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 executes the various methods and processes described above, such as the methanol multimodal dynamic resource scheduling method.

[0077] In some embodiments, the methanol multimodal transport dynamic resource scheduling method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the methanol multimodal transport dynamic resource scheduling method described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to execute the methanol multimodal transport dynamic resource scheduling method by any other suitable means (e.g., by means of firmware).

[0078] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0079] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0080] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0082] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0083] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0084] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0085] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A dynamic resource scheduling method for methanol multimodal transport, characterized in that, include: Acquire basic data and real-time data of methanol multi-transport, and generate the current network state vector at the current moment based on the basic data and real-time data of methanol multi-transport. Based on the aforementioned methanol multimodal transport data, a predicted time-domain demand sequence is determined; Obtain a pre-constructed objective optimization function and at least one objective constraint; Based on the methanol multimodal transport basic data and the methanol multimodal transport real-time data, and based on the predicted time-domain demand sequence, the objective optimization function is solved using the current network state vector as the starting point to obtain the predicted time-domain optimal scheduling parameter sequence that satisfies each of the objective constraints. Any predicted time-domain optimal scheduling parameter in the predicted time-domain optimal scheduling sequence includes production adjustment amount, reserve release amount, channel flow and transportation mode assignment. Based on the predicted time-domain optimal scheduling parameter sequence, resource scheduling instructions are generated and issued.

2. The method according to claim 1, characterized in that, The step of generating the current network state vector at the current moment based on the methanol multimodal transport basic data and methanol multimodal transport real-time data includes: If a real-time interruption event is detected based on the real-time data of the methanol multi-transport system, or if a custom interruption event initiated by the target user is received, a current network state vector is generated based on the basic data of the methanol multi-transport system and the real-time data of the methanol multi-transport system.

3. The method according to claim 1, characterized in that, The step of determining the predicted time-domain demand sequence based on the methanol multimodal transport data includes: Based on the monthly average demand of the demand nodes in the methanol multimodal transport basic data, and based on the preset seasonal fluctuation coefficient, the predicted basic demand of the demand nodes is determined. Based on the predicted basic demand of the demand nodes, and using a preset demand influence coefficient, a predicted time-domain demand sequence for each demand node within the predicted time domain is generated.

4. The method according to claim 1, characterized in that, The objective optimization function is expressed in the following form: in, , and The preset weight parameters are: k represents the current decision time, N represents the number of future cycles covered by a single optimization, and D represents the set of consumer nodes. This represents the predicted demand of consumer node d at time t. Let E represent the actual available supply at consumer node d at time t, and let E represent the set of transportation channels. This represents the unit transportation cost of channel e at time t. This represents the actual transport flow of channel e at time t. and To preset the penalty coefficient, This represents the sum of all warehouse inventories at time t. Indicates the minimum safety reserve inventory. This represents the utilization rate of the critical channel at time t. This indicates the maximum allowable utilization rate of the channel.

5. The method according to claim 2, characterized in that, The construction method of the basic data for methanol multimodal transport is as follows, including: Acquire methanol collection node data and methanol collection channel data, and construct a methanol multimodal transport supply chain basic network based on the methanol collection node data and methanol collection channel data, and use the methanol multimodal transport supply chain basic network as the basic data for methanol multimodal transport.

6. The method according to claim 1, characterized in that, The current network state vector includes the node reserve inventory of each reserve node at the current moment, the in-transit traffic of each transportation channel, the capacity utilization rate of each production node, and the total reserve inventory of each node.

7. The method according to claim 1, characterized in that, The target constraints include: capacity constraints, safety stock constraints, supply guarantee constraints, transportation time delay constraints, and intermodal transport conversion constraints.

8. A methanol multimodal dynamic resource scheduling device, characterized in that, include: The current state vector generation module is used to acquire basic data and real-time data of methanol multi-transport, and generate the current network state vector at the current moment based on the basic data and real-time data of methanol multi-transport. The demand sequence construction module is used to determine the predicted time-domain demand sequence based on the methanol multimodal transport basic data. The function acquisition module is used to acquire a pre-built target optimization function and at least one target constraint. The optimal scheduling parameter prediction module is used to solve the objective optimization function based on the methanol multimodal transport basic data and the methanol multimodal transport real-time data, using the predicted time-domain demand sequence and the current network state vector as the starting point for solving the function, to obtain the predicted time-domain optimal scheduling parameter sequence that satisfies each of the objective constraints; any predicted time-domain optimal scheduling parameter in the predicted time-domain optimal scheduling sequence includes production adjustment amount, reserve release amount, channel flow and transportation mode assignment. The scheduling instruction issuance module is used to generate and issue resource scheduling instructions based on the predicted time-domain optimal scheduling parameter sequence.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the methanol multimodal dynamic resource scheduling method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the methanol multimodal dynamic resource scheduling method according to any one of claims 1-7.

Images