Systems and methods for resource optimization based on dual-flow multimodal transport

Abstract

Systems and techniques for optimizing hub resources and maximizing hub throughput based on Two-Stream Resource Optimization (DSRO). In an implementation, a first unit flow from a customer arriving at the hub to be loaded onto a departing train is represented as a consolidated flow, and a second unit flow arriving at the hub via an arriving train to be unloaded and delivered to a customer is represented as a split flow. A spatiotemporal network is generated for each of the consolidated and split flows and included in the DSRO model. Each stage of the flow is represented as a node in the corresponding spatiotemporal network in the DSRO model, which also models the resource interdependencies between the flows. Operation scheduling based on the DSRO model optimizes the resources during the planning period to ensure they are fairly allocated to both flows, thereby maximizing unit throughput during operation.

Description

Technical Field

[0001] This disclosure generally relates to resource optimization systems, and more specifically to systems and devices for use with resources based on a dual-stream resource optimization management hub (hub). Background Technology

[0002] Transportation operations are a pillar of progress because they allow goods and people to be moved where they are needed. Transportation operations encompass movement via ships, airplanes, trucks, rail, and more. Typically, goods are loaded into containers / trailers and then transferred to vehicles for transport to their destination. However, the complexity of transportation systems cannot be overstated, as they involve the intricate synchronization of vast amounts of resources to move goods from origin to destination.

[0003] Multimodal transport hub facilities (IHFs) may include hub facilities where goods received from customers are placed on trains and transported to their respective destinations, and / or trains carrying goods are received and unloaded for eventual customer pickup. Specifically, an IHF is characterized in that units (e.g., containers / trailers carrying goods) can be configured to be transported via different modes of transport (e.g., rail, truck, ship, aircraft, etc.). Typically, in the operation of an IHF, units (e.g., containers / trailers carrying goods) can be transported from a customer's location (e.g., on a truck trailer) to the IHF, where the unit can be processed and loaded (e.g., using various resources of the IHF) onto a train whose destination may be the destination IHF. Upon arrival at the destination IHF, the unit can be unloaded from the train and processed for delivery to the destination customer. On the other side of the IHF's operation, units (e.g., containers / trailers carrying goods) can reach the IHF (e.g., via trains carrying these units). Upon arrival, these units can be unloaded from the train and processed (e.g., using various IHF resources) for delivery to customers. In this way, IHF resources can be used to process thousands or even millions of units arriving from customers and / or traveling to the IHF via train.

[0004] In some cases, the same IHF resources can be used to process units arriving from customers to be loaded onto trains, and units arriving via trains to be unloaded for delivery to customers. For example, parking space within the IHF can be used to park units arriving from customers and units unloaded from trains. In this case, parking space is considered a shared resource because it can be used by units arriving via trains or from customers. Furthermore, units arriving from customers can compete with units arriving via trains for this shared parking space, as parking space is a limited resource. In another example, a tractor can be used to load units onto trains (e.g., to load units arriving from customers onto trains), but can also be used to unload units arriving via trains. These tractors can also be shared resources, and their use can be cooperative, as a tractor used to load units arriving from customers onto trains can subsequently be used to unload units from trains near that tractor. In this case, the use of tractors can be cooperative.

[0005] Similarly, before a unit leaves the IHF, a wide variety of IHF resources can be used to process units arriving from customers and units arriving via train, and the use of these IHF resources can be cooperative or competitive. Therefore, in some operations, using some IHF resources to process units arriving from customers and units arriving via train can be complementary, while in other cases, using some IHF resources to process units arriving from customers can compete with units arriving via train for the same IHF resources.

[0006] However, given the competition and / or collaboration of IHF resources during IHF operations, IHF productivity and resource levels during operations can be driven by factors such as cell volume (e.g., the number of cells arriving at the IHF), dwell time per cell (e.g., the time a cell spends within the IHF), replenishment cycles of various IHF resources, interdependencies between various IHF resources, and / or many other factors. Synchronizing or optimizing the use of various IHF resources and maximizing IHF throughput, considering these factors, is an extremely challenging task. It may require balancing and coordinating resources, replenishing resources, optimizing underlying processes, controlling control flow, etc., especially considering the constantly evolving operating conditions of the IHF over time. For example, in some cases, cell traffic and cell dwell time entering the IHF may be so uneven or unbalanced that it may be necessary to introduce external sources to replenish certain IHF resources. However, identifying such situations is a significant challenge, given the wide variation in replenishment cycles of resources involved in IHF operations (ranging from hours to weeks) and considering cell traffic and cell dwell time entering the IHF.

[0007] Current IHF management systems are not robust enough to handle IHF resource optimization or maximize IHF throughput during IHF operations because they typically lack the capability to analyze factors such as cell volume, cell dwell time, replenishment cycles of various IHF resources, interdependencies between various IHF resources, and all other factors that may affect IHF productivity and resource levels during IHF operations. Furthermore, these current systems lack the ability to simulate or provide insights into IHF congestion, maximum possible throughput, shortages and bottlenecking IHF resources, and remaining resources. Summary of the Invention

[0008] This disclosure provides a system, method, and computer-readable storage medium for managing hub resources based on dual-stream resource optimization, achieving technical advantages.

[0009] This disclosure provides a system that can be integrated into practical applications with meaningful constraints, as a system having the functionality to optimize resource utilization within a hub (e.g., a train yard, multimodal transport yard, etc.) and maximize hub throughput based on dual-flow resource optimization. In an embodiment, the functionality for optimizing resource utilization within a hub and maximizing hub throughput based on dual-flow resource optimization may include the ability to represent a flow of first units (e.g., units arriving at the hub from a customer to be loaded onto a departing train) through the hub as an integrated flow including multiple integration stages, and a flow of second units (e.g., units arriving at the hub via an arriving train to be unloaded and delivered to a customer) through the hub as a split flow including multiple split stages. In an embodiment, a spatiotemporal network can be generated for each of the integrated and split flows as part of a dual-flow resource optimization (DSRO) model, wherein each stage of the flow is represented as a node in the corresponding spatiotemporal network. In this way, the DSRO model of the implementation scheme may be able to pair phases (e.g., nodes) that compete for and complement each other for hub resources, and can apply constraints along with current resource levels, the amount of ordered resources en route to the hub, future resource delivery, etc., to optimize the use of hub resources and ensure that resources are allocated fairly to the two flows, thereby maximizing unit flow during operation.

[0010] In the implementation plan, it is anticipated that the number of units flowing along the integration flow and the split flow during the planning period of the spatiotemporal network, as well as the corresponding dwell time, can be fed through the DSRO model to generate an optimized operation schedule. This schedule is configured to maximize the hub's throughput during the planning period by optimizing the use of hub resources for the integration flow and the split flow within the planning timeframe and / or identifying changes that can be applied to ensure the implementation of the optimized operation schedule (e.g., resource replenishment, changes in train arrival times, etc.).

[0011] In this way, the techniques described herein can provide advantageous results that allow the system to capture unit flows and dwell times through a hub during the planning period and generate operational schedules that can achieve the maximum unit flow through train facilities based on current resource levels and resource replenishment cycles (e.g., providing indications of additional resources that can be added). In certain implementations, the techniques described herein can identify time slots where resources are likely to be sufficient and time slots where resources are likely to be scarce during the DRSO model planning period, and enable operators to replenish or relocate resources to optimize resource use.

[0012] Therefore, it will be understood that the technical solutions provided herein, which are lacking in conventional systems, are not merely simple applications of manual processes to a computerized environment, but include the functionality to implement technical processes to replace or supplement current manual solutions or solutions that do not exist for managing devices in a hub. In doing so, this disclosure goes far beyond simply applying manual processes to a computer. Therefore, the claims herein necessarily provide a technical solution to overcome the technical problem.

[0013] One object of this disclosure is to provide a method for optimizing hub resources based on dual-flow resource optimization. Another object of this disclosure is to provide a system for optimizing hub resources based on dual-flow resource optimization, and a computer-based tool for optimizing hub resources based on dual-flow resource optimization. These and other objects are provided by this disclosure, including at least the following embodiments.

[0014] In one particular implementation, a method for optimizing hub resources based on dual-flow resource management is provided. The method includes representing a first unit flow through the hub as an integrated flow comprising multiple integration phases. In this implementation, units flowing along the integrated flow are integrated into one or more departing trains based at least in part on the destination of each unit flowing along the integrated flow. The method also includes representing a second unit flow through the hub as a split flow comprising multiple split phases. In this implementation, units flowing along the split flow are split from one or more arriving trains based at least in part on the destination of each unit flowing along the split flow. The method further includes acquiring first data associated with the first group of units flowing along the integrated flow within a planning timeframe. In this implementation, the first data includes dwell time associated with each unit in the first group of units, indicating the duration of each unit's stay within the hub, and a forecast of the number of units in the first group of units using a first prediction model. The method also includes acquiring second data associated with the second group of units flowing along the split flow within a planning timeframe. In the implementation scheme, the second data includes the number of units in the second group of units, and a prediction of dwell time associated with each unit in the second group of units, indicating the duration of each unit's stay within the hub, using a second prediction model. The method also includes: generating an optimized operation schedule based on the first and second data using a dual-flow optimization model, the optimized operation schedule being configured to optimize at least one resource of the hub for both consolidation and splitting flows within a planning timeframe; and generating a signal indicating one or more actions to be performed based on the optimized operation schedule.

[0015] In another embodiment, a system for optimizing hub resources based on dual-flow resources is provided. The hub management system includes at least one processor and a memory operatively coupled to the at least one processor and storing processor-readable code configured to perform operations when executed by the at least one processor. The operations include representing a first unit flow through the hub as an integration flow comprising multiple integration stages. In one embodiment, units flowing along the integration flow are integrated into one or more departing trains based at least in part on the destination of each unit flowing along the integration flow. The operations also include representing a second unit flow through the hub as a split flow comprising multiple split stages. In one embodiment, units flowing along the split flow are split from one or more arriving trains based at least in part on the destination of each unit flowing along the split flow. The operations also include acquiring first data associated with the first group of units flowing along the integration flow within a planning timeframe. In one embodiment, the first data includes a dwell time associated with each unit in the first group of units, indicating the duration of each unit's stay within the hub, and a prediction of the number of units in the first group of units using a first prediction model. The operations also include acquiring second data associated with the second group of units flowing along the split flow within a planning timeframe. In the implementation scheme, the second data includes the number of units in the second group of units, and a prediction of dwell time associated with each unit in the second group of units, indicating the duration of each unit's stay within the hub, using a second prediction model. The operation also includes: generating an optimized operation schedule based on the first and second data using a dual-flow optimization model, the optimized operation schedule being configured to optimize at least one resource of the hub for both consolidation and splitting flows within a planning timeframe; and generating a signal indicating one or more actions to be performed based on the optimized operation schedule.

[0016] In another embodiment, a computer-based tool is provided for optimizing hub resources based on dual-flow resource management. The computer-based tool includes a non-transitory computer-readable medium storing computer code thereon, which, when executed by a processor, causes a computing device to perform operations. The operations include representing a first unit flow through the hub as an integration flow comprising multiple integration stages. In this embodiment, units flowing along the integration flow are integrated into one or more departing trains based at least in part on the destination of each unit flowing along the integration flow. The operations also include representing a second unit flow through the hub as a split flow comprising multiple split stages. In this embodiment, units flowing along the split flow are split from one or more arriving trains based at least in part on the destination of each unit flowing along the split flow. The operations also include acquiring first data associated with the first group of units flowing along the integration flow within a planning timeframe. In this embodiment, the first data includes a dwell time associated with each unit in the first group of units, indicating the duration of each unit's stay within the hub, and a prediction of the number of units in the first group of units using a first prediction model. The operations also include acquiring second data associated with the second group of units flowing along the split flow within a planning timeframe. In the implementation scheme, the second data includes the number of units in the second group of units, and a prediction of dwell time associated with each unit in the second group of units, indicating the duration of each unit's stay within the hub, using a second prediction model. The operation also includes: generating an optimized operation schedule based on the first and second data using a dual-flow optimization model, the optimized operation schedule being configured to optimize at least one resource of the hub for both consolidation and splitting flows within a planning timeframe; and generating a signal indicating one or more actions to be performed based on the optimized operation schedule.

[0017] The features and technical advantages of this disclosure have been broadly outlined above to facilitate a better understanding of the subsequent detailed description. Additional features and advantages of this disclosure that constitute the subject matter of the claims will be described below. Those skilled in the art will understand that the disclosed concepts and specific embodiments can be readily utilized as the basis for modifying or designing other structures for achieving the same purpose as this disclosure. Those skilled in the art will also recognize that such equivalent constructions do not depart from the spirit and scope of this disclosure as set forth in the appended claims. Novel features considered characteristic of this disclosure, whether in terms of their organization or method of operation, along with further purposes and advantages, will be better understood from the following description when considered in conjunction with the accompanying drawings. However, it should be clearly understood that each drawing is provided for illustrative and descriptive purposes only and is not intended to be a definition of limitation of this disclosure. Attached Figure Description

[0018] To gain a more complete understanding of this disclosure, reference is now made to the following description in conjunction with the accompanying drawings, wherein: Figure 1 This is a block diagram of an exemplary system configured with the capabilities and functions of a dual-stream resource optimization management hub, according to an implementation of this disclosure.

[0019] Figure 2 This is a block diagram illustrating an embodiment of a dual-stream resource optimization (DSRO) system configured with the capability and functionality to maximize throughput through the hub based on resources of a dual-stream resource optimization management hub, according to an implementation of the present disclosure.

[0020] Figure 3 This is a block diagram illustrating an example configuration of the integrated flow and split flow according to an implementation of this disclosure.

[0021] Figure 4A A block diagram of an exemplary spatiotemporal network representing an integrated flow during the planning period, according to an embodiment of this disclosure, is shown.

[0022] Figure 4B A block diagram of an exemplary spatiotemporal network representing split streams during the planning period, according to an embodiment of this disclosure, is shown.

[0023] Figure 5 A representation of a DSRO model configured to represent an integrated flow, a split flow, and resource interdependencies between the two flows, according to an embodiment of this disclosure, is shown.

[0024] Figure 6 A high-level flowchart illustrating the system operation for providing functions for a dual-stream resource optimization management hub, according to an embodiment of this disclosure, is shown.

[0025] It should be understood that the accompanying drawings are not necessarily drawn to scale, and the disclosed embodiments are sometimes illustrated schematically and in partial views. In some cases, details that are not essential for understanding the disclosed methods and apparatus or that make other details imperceptible may have been omitted. Of course, it should be understood that this disclosure is not limited to the specific embodiments illustrated herein. Detailed Implementation

[0026] The disclosure presented in the following written description and its various features and advantageous details will be explained more fully with reference to the non-limiting embodiments included in the accompanying drawings and as detailed in the specification. Descriptions of well-known components have been omitted to avoid unnecessarily obscuring the key features described herein. The embodiments used in the following description are intended to facilitate an understanding of how the present disclosure can be implemented and practiced. This disclosure will be interpreted by those skilled in the art as meaning that any suitable combination of the following functions or exemplary embodiments can be combined to achieve the claimed subject matter. This disclosure includes a representative number of species falling within the scope of a genus, or structural features common to members of that genus, enabling those skilled in the art to identify members of that genus. Therefore, these embodiments should not be construed as limiting the scope of the claims.

[0027] Those skilled in the art will understand that any system claims presented herein cover all elements and limitations disclosed therein, and therefore each system claim is required to be considered as a whole. Any reasonably foreseeable items functionally related to the claims are also relevant. Having fully understood the disclosure and claims of this application, the examiner has searched for prior art disclosed in patents and other publications (i.e., non-patent documents). Therefore, as demonstrated by the grant of this patent, the prior art fails to disclose or teach the elements and limitations set forth in the claims as supported by the specification and drawings, thus rendering the proposed claims patentable under the applicable laws and rules of this jurisdiction.

[0028] Various embodiments of this disclosure relate to systems and techniques for providing functionality for managing hub resources based on dual-flow resource optimization (DSRO). In these embodiments, the functionality for optimizing resource usage within a hub and maximizing hub throughput based on DSRO may include the ability to represent a first unit flow (e.g., a unit arriving at the hub from a customer to be loaded onto a departing train) as an integrated flow comprising multiple integration stages, and a second unit flow (e.g., a unit arriving at the hub via an arriving train to be unloaded and delivered to a customer) as a split flow comprising multiple split stages. In these embodiments, a spatiotemporal network can be generated for each of the integrated and split flows as part of a DSRO model, wherein each stage of the flow is represented as a node in the corresponding spatiotemporal network. In this way, the DSRO model of the embodiments may be able to pair stages (e.g., nodes) that compete for and complement each other's hub resources, and constraints can be applied along with current resource levels, the amount of ordered resources en route to the hub, future resource deliveries, etc., to optimize hub resource usage and ensure that resources are allocated fairly to both flows, thereby maximizing unit flow during operation.

[0029] In the implementation plan, the number of units expected to flow along the consolidation and splitting flows during the planning period of the spatiotemporal network, along with their corresponding dwell times, can be fed through the DSRO model to generate an optimized operation schedule configured to maximize the throughput of the train depot during the planning period by: optimizing the use of hub resources for the consolidation and splitting flows within the planning period timeframe and / or identifying changes (e.g., resource replenishment, changes in train arrival times, etc.) that ensure the implementation of the optimized operation schedule.

[0030] It is important to note that the following description focuses on the operation of hubs (e.g., multimodal transport hub facilities (IHFs)), where goods received from customers at the hub are placed on trains and transported to their respective destinations using the hub's resources, and / or trains carrying goods are received and unloaded using the hub's resources for final pickup by customers. However, the techniques described herein are applicable to any application where resources can be used across different operations, and where resource usage can be shared (e.g., collaborative or competitive), allowing optimized resource usage to generate better throughput for the system.

[0031] Figure 1 This is a block diagram of an exemplary system 100 configured with the capabilities and functions for a dual-stream resource optimization management hub, according to an implementation of this disclosure. (See diagram for example.) Figure 1 As shown, system 100 may include user terminal 130, hub 140, network 145, and DSRO system 160. These components, and their individual parts, may work together to provide the functionality discussed herein.

[0032] It should be noted that the functional blocks and components of system 100 according to embodiments of this disclosure may be implemented using processors, electronic devices, hardware devices, electronic components, logic circuits, memory, software code, firmware code, etc., or any combination thereof. For example, one or more functional blocks, or a portion thereof, may be implemented as discrete gate or transistor logic, discrete hardware components, or combinations thereof configured to provide logic for performing the functions described herein. Additionally or alternatively, when implemented in software, one or more functional blocks, or a portion thereof, may include code segments operable on a processor to provide logic for performing the functions described herein.

[0033] It should also be noted that the various components of system 100 are exemplified as individual and independent components. However, it will be understood that each of the exemplified components can be implemented as a single component (e.g., a single application, server module, etc.), can be a functional component of a single component, or the functionality of these various components can be distributed across multiple devices / components. In such an implementation, the functionality of each corresponding component can be aggregated from the functionality of multiple modules residing in one or more devices.

[0034] It should be further noted that each of the described functions in the different functional blocks of the system 100 described herein is provided for illustrative purposes only and not in a restrictive manner. For example, the functions provided by the different functional blocks may be combined into a single component or may be provided via computing resources set up in a cloud-based environment accessible through a network (such as one of the networks 145).

[0035] Hub 140 can refer to a hub (e.g., IHF, etc.) in which units (e.g., containers / trailers carrying goods) are processed as part of unit transportation. For example, units transported to another destination can be loaded onto a suitable outgoing train, and units arriving on the train can be unloaded from the train for delivery to customers. In particular, hub 140 can be functionally described by describing the complex operation of hub 140 as including two distinct flows. Units flowing along the first flow (e.g., the inbound flow) can be received from various customers through gate 141 and can ultimately be loaded onto a suitable outgoing train. For example, customers can deliver individual units (e.g., unit 142) at hub 140. Individual units can be transported by customers using various chassis (e.g., trucks) that carry the units and can enter hub 140 through gate 141. The arriving first-flow units can go to different destinations and can be delivered at hub 140 at various times of day or night. As part of the first-line process, the first-line units arriving at hub 140 can be unloaded from trucks (or from whatever chassis transported them to hub 140) (e.g., using a crane) and can be parked or stored in parking spaces (e.g., parking area 150). The first-line units can eventually be loaded onto departing trains to be taken to their destination.

[0036] For example, unit 142 may currently be delivered to hub 140 by a customer and is destined for a first destination. In this case, as part of the first flow, unit 142 may enter hub 140 and be parked in a parking space within parking area 150. Currently, parking spaces 151 and 152 may be available, so unit 142 may be assigned to one of these parking spaces. In the same embodiment, unit 143 may have previously been delivered to hub 140 by a customer (e.g., the same customer or a different customer) and is destined for a destination (e.g., the first destination or a different destination). In this embodiment, train 148 may be heading towards the first destination. In this case, unit 142, as part of the first flow, may eventually be loaded onto train 148. As can be seen, train 148 may currently have space 153 available for receiving unit 142. When the destination of unit 143 is the first destination, unit 143 may also be loaded onto train 148 as part of the first flow. As part of the first-line system, unit 142 (and unit 143 when the destination is the first destination) can eventually be loaded onto train 148 and leave hub 140 when train 148 departs for the first destination. In this way, the first-line system can operate to receive various units from various customers and integrate them into departing trains based on the units' destinations for transport to their respective destinations.

[0037] Units flowing along the second flow (e.g., inbound flow) can reach hub 140 via arriving trains carrying the second flow units (e.g., train 148 on railway 156), and can eventually be unloaded from the arriving trains for delivery to customers (e.g., for customer pickup). For example, units 144 and 146 may originate from a single point of origin and can reach hub 140 via train 148 on railway 156 carrying these units, as well as many other units in some embodiments. The second flow units arriving at hub 140 can be consigned to different and / or individual customers. For example, units 144 and 146 can be consigned to one or more customers. After arriving via train 148, the second flow units can be unloaded from train 148 (e.g., using a crane) and can be placed or parked (e.g., using various chassis vehicles) in parking spaces (e.g., parking area 150). For example, unit 144 can be unloaded from train 148 and can be parked in the parking area of ​​parking space 144. Unit 146 can also be unloaded from train 148 and can be parked in an available parking space (e.g., parking space 151 or 152). The unloaded second-stream unit can eventually be picked up by the corresponding customer and can exit (leave) hub 140. In this way, the second stream can operate to receive trains carrying various units, break down trains into various units, and make units available for delivery to the corresponding customers.

[0038] In implementation schemes, processing units along the first and second flows may involve the use of a wide variety of resources to consolidate units from customers into departing trains and / or break down arriving trains into units for delivery to customers. These resources may include hub personnel (tractor drivers, crane operators, etc.), parking spaces, chassis, tractors, cranes, rails, railcars, locomotives, etc. These resources may be used to facilitate the holding and / or movement of units through the operation of the hub. For example, parking area 150 may be used to park units while they await loading onto departing trains or await pickup by customers. Chassis 152 (e.g., including tractors, trucks, forklifts, etc.) and operators of chassis 152 may be used to move units within hub 140, such as moving unloaded units from arriving trains to parking area 150 as needed, and / or moving units from parking space 152 to departing trains. Crane 153 can be used to load units onto a departing train (e.g., unloading units from chassis 152 and loading units onto the departing train), and / or unload units from an arriving train (e.g., unloading units from the arriving train and loading units onto chassis 152). Rail vehicle 151 can be used to transport units in the train. For example, the train can consist of one or more rail vehicles, and units can be loaded onto the rail vehicles for transport. The arriving train may include one or more rail vehicles with units that can be processed by the second stream, while the departing train may include one or more rail vehicles with units that may have already been processed by the first stream. Rail vehicles 151 can be assembled together to form a train. Locomotive 154 may include an engine that can be used to power the train. Other resources 155 may include other resources not explicitly mentioned herein but configured to allow or facilitate the processing of units through the first and / or second streams.

[0039] In the implementation scheme, the first and second flows may compete for hub resources in some cases, while in others they may complement each other in terms of resource usage. Furthermore, resource usage may be related to the number of units being processed by hub 140 (e.g., processed via the first and / or second flows), as processing more units may mean increased resource usage. Additionally, the throughput of hub 140 (e.g., the rate at which units are processed over time) may depend on the efficiency of resource usage, the number of units being processed, and the dwell time of units within hub 140.

[0040] User terminal 130 may include mobile devices, smartphones, tablet computing devices, personal computing devices, laptop computing devices, desktop computing devices, vehicle computer systems, personal digital assistants (PDAs), smartwatches, other types of wired and / or wireless computing devices, or any part thereof. In embodiments, user terminal 130 may provide a user interface that can be configured to provide an interface (e.g., a graphical user interface (GUI)) constructed to facilitate operator interaction with system 100, for example via network 145, to perform and utilize features provided by server 110. In embodiments, the operator may be able, for example, through the functionality of user terminal 130, to provide configuration parameters that can be used by system 100 to provide functionality for managing the operation of hub 140 according to embodiments of this disclosure. In embodiments, user terminal 130 may be configured to communicate with other components of system 100.

[0041] In the implementation scheme, network 145 facilitates communication between various components of system 100 (e.g., hub 140, DSRO system 160, and / or user terminal 130). Network 145 may include wired networks, wireless communication networks, cellular networks, cable transmission systems, local area networks (LANs), wireless local area networks (WLANs), metropolitan area networks (MANs), wide area networks (WANs), the Internet, public switched telephone networks (PSTNs), etc.

[0042] The DSRO system 160 can be configured to provide the primary functionality of system 100 to manage the resources of hub 140 based on dual-flow resource optimization, thereby maximizing throughput through hub 140 according to embodiments of this disclosure. In embodiments, the DSRO system 160 can be configured to facilitate the synchronization of the first and second flows to maximize the throughput of hub 140 and optimize resource utilization of hub 140. Specifically, the DSRO system 160 can be configured to represent the first and second flows as a time-extended network (e.g., a DSRO model) to model the unit flow and dwell time through the hub during the planning period and apply the DSRO model to achieve maximum unit flow through hub 140. The DSRO model can identify resource-sufficient time slots and time slots where hub 140 may face resource deficits or shortages during the planning period, enabling operators to supplement or relocate resources to mitigate or avoid shortages.

[0043] Figure 2 This is a block diagram illustrating an embodiment of a DSRO system 160 configured with the capability and functionality to maximize throughput through a dual-flow resource optimization management hub, according to an implementation of this disclosure. Figure 2As shown, the DSRO system 160 can be implemented in a server (e.g., server 110). In an implementation, the functions of server 110 that facilitate the operation of the DSRO system 160 can be provided by the coordinated operation of various components of server 110, as will be described in more detail below.

[0044] It should be noted that, although Figure 2 Server 110 is shown as a single server, but it will be understood that server 110 (and its individual functional blocks) can be implemented as a standalone device and / or can be distributed across multiple devices having their own processing resources, the aggregation of which can be configured to perform operations according to this disclosure. Furthermore, those skilled in the art will recognize that, although Figure 2 The components of server 110 are exemplified as single and independent blocks, but each of the various components of server 110 can be a single component (e.g., a single application, server module, etc.), a functional component of the same component, or the functionality can be distributed across multiple devices / components. In such an implementation, the functionality of each corresponding component can be aggregated from the functionality of multiple modules residing in one or more devices. Furthermore, the specific functionality described for a particular component of server 110 can actually be part of different components of server 110; therefore, the description of a specific functionality for a particular component of server 110 is for illustrative purposes and is not intended to be limiting in any way.

[0045] like Figure 2 As shown, server 110 includes processor 111, memory 112, time-extended network 120, parking area optimization system 121, parking classification system 122, chassis vehicle optimization system 123, dynamic chassis vehicle pool system 124, diffusion system 125, cross-area relocation system 126, tractor optimization system 127, ramp planning system 128, full resource optimization manager 129, and database 114.

[0046] Processor 111 may include a processor, microprocessor, controller, microcontroller, multiple microprocessors, application-specific integrated circuit (ASIC), application-specific standard product (ASSP), or any combination thereof, and may be configured to execute instructions to perform operations according to the disclosure herein. In some embodiments, implementation of processor 111 may include code segments (e.g., software, firmware, and / or hardware logic) executable in hardware (such as a processor) to perform the tasks and functions described herein. In other embodiments, processor 111 may be implemented as a combination of hardware and software. Processor 111 may be communicatively coupled to memory 112.

[0047] Memory 112 may include one or more semiconductor memory devices, read-only memory (ROM) devices, random access memory (RAM) devices, one or more hard disk drive (HDD) devices, flash memory devices, solid-state drives (SSDs), erasable ROM (EROM), optical disc ROM (CD-ROM), optical discs, other devices configured to store data in a persistent or non-persistent state, network storage, cloud storage, local storage, or combinations of different memory devices. Memory 112 may include a processor-readable medium configured to store one or more instruction sets (e.g., software, firmware, etc.) that, when executed by a processor (e.g., one or more processors of processor 111), perform the tasks and functions described herein.

[0048] The memory 112 can also be configured to facilitate storage operations. For example, the memory 112 may include a database 114 for storing various information related to the operation of the system 100. For example, the database 114 may store configuration information related to the operation of the DSRO system 160. In embodiments, the database 114 may store information related to various models used during the operation of the DSRO system 160. The database 114 is illustrated as being integrated into the memory 112, but in some embodiments, the database 114 may be provided as a separate storage module or as a cloud-based storage module. Additionally or alternatively, the database 114 may be a single database or a distributed database implemented on multiple database modules.

[0049] As mentioned above, the synchronous processing of units along the first and second flows within a hub is a complex process and can be affected by various factors. For example, in some cases, the unit throughput and dwell time through the hub may be so uneven or unbalanced that current resources (e.g., current resource inventory) may not be able to effectively handle the unit throughput without replenishment. However, in other cases, replenishing resources may not be straightforward, as replenishment cycles for different resources may differ and may not be executed within an acceptable timeframe. For instance, in some cases, the number of second-flow units requiring chassis may exceed the number of chassis currently available within the hub, necessitating replenishment from external sources. However, the lead time for obtaining additional chassis may require several days of effort, and operators may need to request these additional chassis in advance. The replenishment cycle for rail vehicles can be much longer, as rail vehicles may have to be acquired from other locations on the rail network or may have to be ordered from lessors. The replenishment cycle for tractors may require several days to several weeks of effort.

[0050] Locomotive replenishment cycles can range from days to weeks, as locomotives may need to be released from the workshop or moved from other locations. Parking space replenishment cycles are even longer, as additional parking space cannot be created immediately and can require costly and time-consuming efforts. In some cases, if the hub is surrounded by land, adding new parking space may be impossible. Alternatively, some hardened parking space can be converted into storage areas. Crane replenishment cycles (or upgrading existing cranes to increase lifting capacity) can include years of effort and can be capital-intensive, subject in some cases to regulatory oversight and permitting. Tractor replenishment cycles can also range from days to weeks. Operator replenishment cycles can also be substantial, as staff may need to be recruited to expand the current staff roster and may require onboarding and training.

[0051] Given the extensive replenishment cycles of various resources within the hub, the interdependencies of these resources (e.g., how resources compete and / or cooperate at different stages of the flow), and the variability in the number of units and their dwell time within the hub, optimally planning and allocating all resources involved in the first and second unit flows to efficiently execute hub operations is practically impossible to do manually. However, the DSRO system implemented according to this embodiment provides a solution.

[0052] In one implementation, the DSRO system 160 can be configured to represent a first unit flow (e.g., an inbound flow where units can be received from individual customers and can be integrated into departing trains by destination) as an integrated flow 115 comprising multiple stages. In another implementation, each stage of the integrated flow 115 can represent a different operation or event that can be performed or occur to facilitate the flow of the first flow units through the hub. In yet another implementation, the DSRO system 160 can be configured to represent a second unit flow (e.g., an inbound flow where arriving trains can be split by unloading units from arriving trains and units can be used for delivery to customers) as a split flow 117 comprising multiple stages. In yet another implementation, each stage of the split flow 117 can represent a different operation or event that can be performed or occur to facilitate the flow of the second flow units through the hub.

[0053] As mentioned above, the hub's resources can be shared between the integration flow 115 and the split flow 117 (e.g., in collaborative or competitive interactions). In an implementation scheme, as will be discussed in more detail below, the DSRO system 160 can generate a spatiotemporal network for the DSRO model based on the representations (e.g., stages) of the integration flow 115 and the split flow 117. The configuration of the integration flow 115 and the split flow 117, and their interactions in terms of shared resource usage, will now be referred to... Figure 3 Let's have a discussion.

[0054] Figure 3 This is a block diagram illustrating an example configuration of the integrated flow and split flow according to an implementation of this disclosure. For example... Figure 3 As shown, the integration flow 115 can be configured to include multiple phases, namely, in-gated (IG) phase 310, assignment (AS) phase 311, ramping (RM) phase 313, release (RL) phase 314, and departure (TD) phase 315. The split flow 115 can be configured to include multiple phases, namely, arrival (TA) phase 320, strip track placement (ST-PU) phase 321, de-ramping (DR) phase 322, unit park and notification (PN) phase 323, and out-gated (OG) phase 324.

[0055] Regarding integration flow 115, each stage of integration flow 115 can represent an event or operation that can be performed or occur to facilitate the flow of units along integration flow 115. At IG stage 310, a unit can be received into the hub or enter the hub. For example, at IG stage 310, a unit can enter the hub from a customer, and the destination of the unit can be a specific destination. The resources involved at IG stage 310 can include chassis vehicles, as the entering unit can be transported to the hub using a chassis vehicle. In this case, the chassis vehicle can be considered a resource of the hub and an addition to the resources of the hub, and IG stage 310 can be considered a chassis vehicle supplier of resources for hub 140.

[0056] At AS stage 311, the unit can be assigned to a parking space to be placed there while awaiting processing by the next stage. In this case, the operator can assign the unit to a specific parking space. The operator's allocation of parking spaces can be based on available parking spaces, and in some embodiments, it can be based on the DSRO function used to optimize parking operations within the hub. At 312, the unit can be placed in the assigned parking space. It should be noted that in this exemplary representation 315 of the integration flow, the event of placing the unit in the assigned parking space may not be represented as stage 315 of the integration flow. However, in some embodiments, placing the unit in the assigned parking space can be represented as stage 315 of the integration flow. Resources involved at AS stage 311, such as when the unit can be placed in the parking space, may include the parking space and the crane. For example, as Figure 3As shown, AS phase 311 uses parking space for parking units, and units can be placed into the parking space using a crane. In some embodiments, the parking space that can be allocated to units during AS phase 311 may be located inside the hub, beside the track, or outside the hub.

[0057] At RM phase 313, the unit can be loaded from its current parking space onto a rail vehicle. In embodiments, the unit can be assigned to a rail vehicle of a departing train, such as based on the unit's destination and / or expected delivery time, such as based on the scheduled train lineup. In a particular embodiment, RM phase 313 can operate to consolidate units with the same destination (or with destinations within a specific route) into a single train based on their destinations. In this case, operations at RM phase 313 can be affected by resources including cranes, tractors, rail vehicles, parking areas, and chassis. For example, as... Figure 3 As shown, during RM phase 313, rail vehicles that can be assigned to units can be retrieved and positioned on production rails with loading capacity. The train can then be loaded by using a crane to load the units onto the rail vehicles of the departing train. Regarding units, during the RM phase, the unit can be removed from the parking space, towed by a tractor to its assigned rail vehicle, and can be loaded onto the rail vehicle using a crane. If the unit is a container mounted on a chassis, loading the unit onto the rail vehicle can free up the chassis (e.g., make the chassis available for use). Furthermore, as... Figure 3 As shown, removing a unit from the parking space frees up that parking space to be used for parking another unit. In this way, the resources involved at RM stage 313 may include parking space, cranes, tractors, rail vehicles and / or chassis vehicles.

[0058] At RL phase 314, the train can be assembled, loaded, and released for departure from the hub. Resources involved at RL phase 314 may include tracks, railcars, and locomotives. For example, RL phase 314 may release tracks (e.g., off-spot tracks to which the train is assigned) to make them available, but production tracks may be used to leave the hub, as well as railcars (e.g., those assigned to the train) and locomotives (e.g., one or more locomotives used to move the train). At TD phase 315, the train departs the hub. TD phase 314 may release production tracks, but railcars and locomotives belonging to the departing train may be used.

[0059] Regarding split flow 117, each stage of split flow 117 can represent an event or operation that can be performed or occur to facilitate the flow of units along split flow 117. At TA stage 320, an arriving train arrives at a hub. This arriving train may include a rail vehicle carrying a unit. Regarding a unit, the unit may be carried by the rail vehicle of the arriving train. In embodiments, the resources involved in TA stage 320 may include offsite tracks and non-production tracks (e.g., on which the arriving train arrives).

[0060] At stage 321 of ST-PU, arriving trains can be spotted and placed on the production track. For example... Figure 3 As shown, the resources involved in ST-PU phase 321 may include production tracks used to place trains, locomotives used to power trains to enter the production tracks, and rail vehicles as part of the arriving trains. In particular, locomotive(s) used to transport the arriving trains to the hub can now be released from split stream 117 because the trains have arrived at the hub and the locomotives are no longer used in split stream 117.

[0061] At DR stage 322, units in the railcar arriving at the train can be unloaded from the arriving train. In embodiments, unloading (e.g., removing) units from the arriving train can include unloading units to be placed in a parking space. In embodiments, unloading units from the arriving train can include unloading units from the arriving train using a crane, using a tractor to tow the units to their assigned parking space, and the parking space where the units can be assigned. DR stage 322 can also involve placing the unloaded units (containers) using a chassis vehicle, and the railcar becoming available after the units are unloaded from the railcar.

[0062] At PN stage 323, the unit is placed in the assigned parking space, and the customer is notified that the unit is available for pickup. PN stage 323 may involve using the parking space while the unit awaits pickup; however, the parking space can be released once the customer has picked up the unit. In some cases, the unit may be placed on a chassis vehicle, and a crane may be used to lift the unit from the parking space for loading onto a truck (i.e., hoisting) for delivery to the customer. At OG stage 324, the customer can pick up the unit from the parking space, and the unit can leave the hub.

[0063] like Figure 3As shown, the interaction between the consolidation flow 115 and the split flow 117 regarding the use of hub resources can be cooperative or competitive. For example, while units are waiting to be loaded (e.g., processed via RM stage 313), parking space can be used to park units processed via AS stage 312 of the consolidation flow 115. However, parking space can also be used to park units processed via DR stage 322 of the split flow 117 (e.g., units unloaded from arriving trains, while these units are waiting to be picked up by customers (e.g., processed via PN stage 323)). In this way, the consolidation flow 115 and the split flow 117 can compete for the use of parking space within the hub.

[0064] In another embodiment, during RM phase 313, the consolidation flow 115 may compete with the split flow 117 during DR phase 322 for tractor units, cranes, and chassis, as both phases may use tractor units, cranes, and chassis for operations. In this way, consolidation flow 115 and split flow 117 can compete for the use of tractor units, cranes, and chassis within the hub. In another embodiment, the consolidation flow may only require chassis when units are stacked and need to be loaded onto chassis for loading. However, it should be noted that once the loading operation is complete (e.g., once RM phase 313 is completed) and the departing train departs (e.g., at TD phase 315), the production track can be released by consolidation flow 115, which can be used to reach the train via the split flow 117 (e.g., at ST-PU phase 321). In this way, consolidation flow 115 and split flow 117 can complement each other in their use of the production track. Table 1 below provides examples of... Figure 3 The representation illustrates an example of resource interdependencies between the integrated flow 115 and the split flow 117.

[0065]

[0066] Table 1: Resource interdependencies between consolidation streams and split streams Return to reference Figure 2The DSRO system 160 can be configured to maximize hub throughput (e.g., rate of flow through hub processing units) by generating one or more spatiotemporal networks 120 to represent consolidation flow 115 and split flow 117, and configuring the DSRO model to use one or more spatiotemporal networks 120 during the planning period to optimize the use of hub resources supporting unit flows during the planning period, thereby maximizing throughput during the planning period. In an implementation, the DSRO model can generate an optimized operational schedule based on the one or more spatiotemporal networks 120, which includes one or more of the following: determined unit flows through one or more stages of each spatiotemporal network (e.g., consolidation flow and / or split flow spatiotemporal networks) at each time increment of the planning period; indications of resource shortages or surpluses at one or more stages of each spatiotemporal network at each time increment of the planning period; and / or indications or recommendations at each time increment of the planning period to perform resource replenishment at one or more stages of each spatiotemporal network to ensure the optimized operational schedule is met. The result is a powerful overview of unit throughput and resource consumption during the planning period, enabling operators to determine not only the expected unit throughput through the hub during the planning period, but also the rate of resource consumption, in an optimized manner (e.g., as optimized by the DSRO model) and methodology, to ensure optimal resource utilization and thus ensure maximum throughput through the hub.

[0067] In the implementation, the DSRO system 160 can generate one or more spatiotemporal networks 120 using the stages of the integrated flow 115 and the split flow 117. Specifically, the DSRO system 160 can define the nodes of the spatiotemporal network as representing the stages of the corresponding flow, and define the edges between nodes as representing capacity. The time increment can be variable and configurable, and can be represented, for example, a specific time range, such as hours, multi-hour blocks, shifts, etc. The time dimension of the spatiotemporal network facilitates the determination of connections between nodes, and the flow between nodes can be constrained to occur only under reasonable operating conditions. The time increment can be variable and configurable, and can be represented, for example, a specific time range, such as hours, multi-hour blocks, shifts, etc. For example, if a customer might be able to de-gate (e.g., in reference...) Figure 3 Before the OG stage 324 described, if a heaped cell requires more than one time increment (e.g., more than one time slot of the spatiotemporal network) to be retrieved from the heap, then the edge between the PN stage and the OG stage of the spatiotemporal network can be constrained to be a value other than nonzero for that cell.

[0068] As described above, the DSRO system 160 can use the phases of the integrated stream 115 to generate a spatiotemporal network and the phases of the split stream 117 to generate a spatiotemporal network. Figure 4AA block diagram of an exemplary spatiotemporal network 400 representing an integrated flow during the planning period, according to an embodiment of this disclosure, is shown. Figure 4B A block diagram of an exemplary spatiotemporal network 450 representing split streams during the planning period, according to an embodiment of this disclosure, is shown.

[0069] like Figure 4A As shown, the spatiotemporal network 400 can be generated using the phases of the integrated flow 115 and extended over a planning period, which can be from T0 to T... n The process operates in time increments. At each time increment, a unit can be processed by the represented integration flow, and therefore, each time increment can provide a snapshot of the integration flow at the corresponding time during the planning period. In the implementation, each node of the spatiotemporal network 400 can represent an event or operation of the integration flow 115 (e.g., as referenced). Figure 3 As described, the edges of the spatiotemporal network 400 can represent interactions between events or operations.

[0070] In the implementation scheme, as units flow along the integrated flow during the planning period, the flow can be represented by the spatiotemporal network 400 or captured as the unit flow between consecutive phases of the integrated flow within each time increment. Figure 4A In the specific embodiments illustrated, units can flow into the IG stage of the integration flow at T0, T1, and T2 (e.g., different units may be brought into the hub to be processed and integrated into the departing train), and can also be at T... n-1 The unit leaves the integrated flow (e.g., it may leave the hub in a departing train). In the implementation, the number of units entering the integrated flow at different time increments can be different. For example, the number of units entering the IG stage of the integrated flow at T2 can be greater than the number of units entering the IG stage of the integrated flow at T1, as indicated by the larger arrow.

[0071] like Figure 4B As shown, the spatiotemporal network 450 can be generated using the phases of split stream 117 and extended over a planning period, which can be from T0 to T... n The process operates in time increments. At each time increment, a unit can be processed by the represented split stream, and thus, each time increment can provide a snapshot of the split stream at the corresponding time during the planning period. In the implementation, each node of the spatiotemporal network 450 can represent an event or operation of the split stream 117 (e.g., as referenced). Figure 3 As described, the edges of the spatiotemporal network 450 can represent interactions between events or operations.

[0072] In the implementation scheme, as cells flow along the split flow during the planning period, the flow can be represented or captured by the spatiotemporal network 450 as cell flow between consecutive phases of the split flow within each time increment. Figure 4B In the specific embodiments illustrated, the unit can reach a hub (e.g., in an arriving train) and can enter the split flow at the TA stage at T0. The train can be split and the unit processed, and the unit can be processed in different amounts at T2, T3, T4, T5. n-1 and T n The exit from the splitting process can be handled (e.g., picked up by the customer). For example, in T n-1 The number of cells exiting the OG phase at T3 can be greater than the number of cells exiting the OG phase at T3, as indicated by the larger arrow.

[0073] Return to reference Figure 2 It is important to note that at this stage, some solutions are proposed as static and constrained optimization models because these models represent one flow or another, but not both, mathematically over a single time increment. In contrast, the DSRO model of the implementation can model multiple (e.g., two) flows and can evaluate the interaction between both continuous and discontinuous flows. By modeling the two flows of the hub operation, the DSRO system 160 can facilitate the maximum unit flow through them during the planning period while tracking resource availability, replenishment and consumption, and capacity constraints.

[0074] In the implementation scheme, the DSRO system 160 can be configured to include two spatiotemporal networks (e.g., spatiotemporal network 400 and spatiotemporal network 450) in the DSRO model, thereby modeling both the integrated flow and the split flow together. Although the flows may appear to operate independently, there are resource interdependencies between the two flows that cause them to intertwine at each stage of the flow. The DSRO model of the implementation scheme can not only model the two flows but also their resource interdependencies, and this configuration can be used to optimize the resource utilization of the two flows, thereby maximizing throughput during the planning period. Figure 5 A representation of a DSRO model configured to represent an integrated flow, a split flow, and resource interdependencies between the two flows, according to an embodiment of this disclosure, is shown.

[0075] like Figure 5As shown, the DSRO model can be configured to stack an integrated flow spatiotemporal network and a split flow spatiotemporal network, while preserving their resource interdependencies as a link between the two spatiotemporal networks. Specifically, stacking the integrated flow spatiotemporal network and the split flow spatiotemporal network can include aligning the two spatiotemporal networks with respect to time increments within the planning period. In this way, the DSRO model can consider and account for the impact of resource availability at any time increment within the planning period in representation 500, in order to optimize resource utilization between the two flows. Although, as an example, Figure 5 A link is drawn between the RM and DR in the flow, but several other stages in the two flows can also interact with each other.

[0076] In particular, as a non-limiting embodiment, the DSRO model addresses the resource interdependencies between the TD phase of the integration stream and the TA phase of the split stream (e.g., as described above regarding...). Figure 3 The resource interdependencies between the RM phase of the integration flow and the DR phase of the split flow (as described above) (e.g., regarding chassis vehicle utilization, as mentioned above) Figure 3 As described above), and the resource interdependencies between the AS phase of the integration flow and the PN phase of the split flow (e.g., regarding parking space utilization, as mentioned above regarding...). Figure 3 Modeling is performed as described.

[0077] Return to reference Figure 2 The DSRO system 160 can be configured to apply the generated DSRO model to the time-extended network 120 to optimize resource usage for consolidation and splitting flows during the planning period, thereby maximizing the hub's throughput during the planning period. To this end, DSRO 160 can include multiple optimization systems. Specifically, the full resource optimization manager 129 can be configured to generate an optimized runtime schedule based on the DSRO model, which can be implemented during the planning period to maximize unit throughput through the hub.

[0078] In the implementation, the full resource optimization manager 129 can be configured to, based on the DSRO model, determine the optimal operational schedule that maximizes throughput through the hub during the planning period, considering resource availability (e.g., resource inventory), resource replenishment cycle, resource cost, and the operational impact of insufficient resource supply for all resources involved in the consolidation and splitting flows. In the implementation, the full resource optimization manager 129 can be configured to additionally consider unit quantity (e.g., the number of units expected to flow along the consolidation and splitting flows during the planning period, such as at each time increment of the planning period) and unit dwell time (e.g., the expected dwell time of units flowing along the consolidation and splitting flows during the planning period) to determine the optimal operational schedule that maximizes throughput through the hub during the planning period.

[0079] Specifically, the validity of the DSRO model analysis may depend on obtaining data related to the expected number of units entering the hub along the two flows and the respective dwell times of these units within the hub. Regarding the integrated flow, the number of units that can enter the integrated flow (e.g., at each time increment of the planning period) may be unknown because it can depend on customer demand, which can vary significantly and may be seasonal, periodic, or even consistent. However, for the efficient operation of the hub, it may be necessary to pre-allocate sufficient resources to process these units in a timely manner, or it may be necessary to refuse customers or limit how many units a customer can have access to enter the hub. Nevertheless, the dwell times of units processed through the integrated flow are known because these units can be configured with a "target time" (e.g., the date / time on which the unit should be delivered at its destination), and the length of time a unit may spend within the hub can be calculated based on the target time. In some implementations, the hub operator can set the dwell time for each unit entering the integrated flow within the planning period because the hub operator knows the scheduled trains running during the planning period. This allows train operators to assign arriving units to the appropriate trains and set the dwell times of the units in this way.

[0080] Regarding split flows, the number of units that can enter a split flow (e.g., at each time increment of the planning period) may be known, but the dwell time of units processed through a split flow may be unknown. For example, arriving trains may be scheduled to arrive at a hub, and the number of units carried by these trains may be known. If a train is not assembled at the unit's origin, but is scheduled to start, assemble, and arrive within the planning period, the number of units carried by that train can be determined using historical averages. On the other hand, once a unit arrives at the hub and enters a split flow, it may depend on the customer picking it up from the hub. The dwell time of the unit is determined by the customer, and therefore may be unknown for the DSRO system 160.

[0081] In the implementation, the DSRO system 160 may be configured with: an entry volume model configured to predict the number of unknown units that can enter the consolidation flow (e.g., at each time increment of the planning period); and / or an entry unit dwell time prediction model configured to predict the unknown dwell time of units processed through the split flow (e.g., at each time increment of the planning period). The entry volume model can predict the number of units to enter the gate within a specific time range, categorized by shipper, unit size, destination, and service level. In the implementation, this prediction may include unit volume in time increments (e.g., hourly, daily, etc.). In the implementation, the full resource optimization manager 129 may, at the start of the optimization run, retrieve the current inventory levels in each hub area (parking area, railcars, locomotives, track occupancy, etc.) and may combine them with the entry volume prediction over time.

[0082] In the implementation, the inbound unit dwell time prediction model can be configured to use a large set of details associated with each unit and can predict the individual dwell time for each unit. In the implementation, the full resource optimization manager 129 can categorize the predicted dwell duration into a fixed set of intervals (e.g., ranges) and can map these ranges to parking zone categories during the zone allocation process.

[0083] The full resource optimization manager 129 can generate an optimized operation schedule based on the DSRO model, unit quantity data, dwell time data, resource availability, resource replenishment cycle, resource cost, and the operational impact of insufficient resource supply. This optimized operation schedule can be configured to handle the maximum number of units passing through the hub within the planning period based on the provided data and constraints. In one implementation, generating the optimized operation schedule may include: optimally allocating available resources between consolidation flows and split flows, and identifying possible changes to generate the optimized operation schedule. For example, the optimized operation schedule may include indications that changes to train timetables should be implemented to achieve the operation schedule. In another embodiment, the optimized operation schedule may include indications that additional resources may be needed at specific time increments within the planning period, and / or at specific stages of consolidation flows or split flows, to achieve the operation schedule.

[0084] In the implementation, optimized operation scheduling may include an indication of the number of units processed at each time increment of the planning period by integrating and splitting the flow. For example, optimized operation scheduling may include an indication of the number of units entering, allocating, loading, unloading, parking, and notifying customers, as well as exiting the gate, at each time increment of the planning period. In the implementation, based on the determination that a particular resource may be fully consumed at a certain time increment, optimized operation scheduling may include an indication of how many additional units can be processed based on the additional units obtained.

[0085] In the implementation, the optimized run schedule during the planning period can be dynamically adjusted by the DSRO system 160. For example, at a specific time increment, the number of units arriving during this specific time increment (e.g., units arriving at the IG state of the consolidation stream and / or units arriving at the TA stage of the split stream) can be known because units can be processed at the hub and can be counted as arriving units. In this case, the DSRO model can determine whether the predicted number of units during the specific time increment (e.g., according to the optimized run schedule) can differ from the actual number of units during the specific time increment (e.g., according to the units arriving at the hub during the time increment). In response to determining that there is a difference between the predicted number of units during the specific time increment and the actual number of units during the specific time increment, the DSRO model (e.g., the DSRO model used by the Total Resource Optimizer 129) can apply or take into account this difference to modify, refine, or regenerate the optimized run schedule based on the actual number of units within that time increment. In this case, the modified optimized run schedule can include the optimized run schedule for the remaining time increments of the planning period.

[0086] This modified optimized runtime schedule can represent a more granular prediction of unit quantity and resource utilization because it can take into account the actual resource consumption during a specific time increment, which may differ from the predicted time consumption during that specific time increment (e.g., it could be a lower unit quantity, which represents less resource consumption than predicted; or it could be a higher unit quantity, which represents more resource consumption than predicted).

[0087] In some implementations, the planning period can be dynamically adjusted based on events. For example, a train may arrive at the hub later than scheduled. In this case, the DSRO model 160 can adjust the planning period based on the train's actual arrival at the hub. In some implementations, the planning period can be dynamically adjusted based on one or more factors, including user preferences.

[0088] In some implementations, the DSRO system 160 can restrict train arrival and departure times, allowing the full resource optimization manager 129 to disregard operation scheduling that requires changes to the arrival or departure times of restricted trains. In this case, the full resource optimization manager 129 can generate an optimized operation schedule for the planning period based on fixed train arrival and departure times. In other implementations, the DSRO system 160 can allow changes to train arrival and departure times, allowing the full resource optimization manager 129 to consider operation scheduling that requires changes to the arrival or departure times of restricted trains. In this case, the full resource optimization manager 129 can generate an optimized operation schedule for the planning period that may require changes to train arrival or departure times (e.g., potentially delaying or advancing arrival times).

[0089] In the implementation scheme, the DSRO system 160 may include various post-optimization systems that can be configured to provide further optimization of hub operations. These post-optimization systems can be run to define, refine, or otherwise determine operations in an optimized manner, which can provide further optimization of optimized operation scheduling or facilitate the implementation of optimized operation scheduling.

[0090] In the implementation, the parking area optimization system 121 can be configured to maximize the throughput of the hub's parking spaces by allocating units to parking spaces based on expected unit dwell times. For example, the parking area optimization system 121 can be configured to maximize the throughput of the hub's parking spaces by ensuring that short-dwell units are allocated to easily accessible parking spaces, medium-dwell units are allocated to parking spaces with slightly less accessibility, and so on, based on the hub's zones, etc. In the implementation, the parking area optimization system 121 can consider the interaction between the integrated flow spatiotemporal network and the split flow spatiotemporal network, as well as the unit quantity and dwell composition of each flow, when optimally allocating parking spaces. In the implementation, constraints related to other critical resources of the hub can be part of the operation of the parking area optimization system 121 and can act as guardrails to keep the final recommendations from the parking area optimization system 121 valid and optimal.

[0091] In the implementation, the parking classification system 122 can be configured to classify parking areas into different categories based on their proximity to the tracks and access conditions. These categories can be used by the DSRO system 160 to allocate units to these spaces based on unit dwell time. For example, some parking areas, due to their location relative to the tracks, can be closer to the production tracks and may be more suitable for higher throughput (e.g., more turnarounds). Tractors can travel shorter distances, and parking areas adjacent to the production tracks are thus configured to provide easier access conditions for tractor drivers. The DSRO system 160 can allocate units with short dwell times to these track-side parking areas, resulting in more turnarounds. The DSRO system 160 can assess parking space availability and unit flows along with the possible dwell times from both flows, and can allocate units to appropriate parking spaces throughout the planning period. Similarly, parking areas farther from those active tracks may require resources such as tractors and drivers to move units further, and these movements can be kept to a minimum to reduce the demand on these resources.

[0092] In the implementation scheme, the chassis optimization system 123 can be configured to maximize hub throughput by optimally allocating chassis vehicles to customers while taking replenishment cycle time into account. For example, the chassis optimization system 123 can be configured to use integrated flow spatiotemporal networks and split flow spatiotemporal networks to maximize the flow of units along these flows during the planning period, while managing chassis vehicle inventory, future replenishment, and loading-unloading event synchronization.

[0093] In the implementation scheme, the dynamic chassis pool system 124 can be configured to aggregate chassis vehicle resources from multiple pools and facilitate better unit flow through the facility. The dynamic chassis pool system 124 is capable of responding to changes and can attempt to negotiate or exchange chassis vehicles between pools within one time increment of the planning period, and replenish them within another time increment, without causing a shortage of operators in any chassis pool.

[0094] In the implementation, the diffusion system 125 can be configured to allocate parking spaces closer to the integration flow units to which trains might be assigned. In this way, the travel distance between the parking space and the departing train can be minimized, thereby minimizing the time required for train marshalling and departure. The function of the diffusion system 125 is to facilitate faster loading processes by dispersing or alleviating the movement of tractor cars within the hub. Specifically, the diffusion system 125 can allocate parking spaces to individual units as a post-optimization activity (e.g., after the DSRO system 160 optimizes resources and operations) to distribute units across the hub's parking spaces.

[0095] In the implementation, the cross-zone relocation system 126 can be configured to identify movements between two different hub zones (excluding tracks) to expedite loading operations or address parking space deficits. The cross-zone relocation system 126 can function to determine if an initial zone allocation might be performed based on the prevailing parking space inventory level and is not optimal, and can reverse that movement to get closer to the optimal solution. This may require additional tractor movements, but the time required to finally load the train can be reduced.

[0096] In the implementation, the tractor optimization system 127 can be configured to pair unloading and loading activities associated with arriving and departing trains, respectively, to match tractor movements aimed at loading and unloading, thereby minimizing unproductive movements. In this way, the functionality of the tractor optimization system 127 can be used to maximize the utilization of tractors executing work orders, and their movements in both directions can be productive. For example, a tractor can unload a unit from an arriving train (e.g., unload the unit) and, based on the recommendations of the tractor optimization system 127, tow or move the unit to an assigned parking location, and then the tractor can proceed to the parking space to pick up the unit to be loaded onto the departing train. The locations of the two parking spaces make the tractor movements productive in both directions. In fact, the functionality of the tractor optimization system 127 can operate to recommend loading-unloading or unloading-loading, making the tractor movements in both directions as productive as possible.

[0097] In the implementation scheme, the ramp planning system 128 can be configured to optimally schedule inbound and outbound trains to maximize resource utilization and improve train punctuality. The ramp planning system 128 can utilize traditional scheduling components such as events, tasks, and resources when scheduling trains. For example, the ramp planning system 128 can generate track-train assignments for the length of the planning period by considering resource availability during intermediate time intervals and exploring the resource requirements of different train sequences. The ramp planning system 128 can evaluate different sequences of inbound-outbound trains and the required intermediate settings before selecting the optimal train sequence for each production track.

[0098] Figure 6 A high-level flowchart 600 is shown, illustrating an embodiment of this disclosure, configured to provide functionality for optimizing hub resource management based on dual-flow resources. For example, Figure 6 The functionality illustrated in the example blocks shown can be derived from the implementation according to this document. Figure 1 The system 100 executes the method. In an embodiment, the operation of method 600 can be stored as instructions that, when executed by one or more processors, cause the one or more processors to perform the operation of method 600.

[0099] At block 602, the first unit flow through the hub is represented as an integrated flow comprising multiple integration stages. In an implementation, units flowing along the integrated flow are integrated into one or more departing trains based at least in part on the destination of each unit flowing along the integrated flow. In an implementation, the DSRO system (e.g., as...) Figure 2 and Figure 3The DSRO system 160 illustrated herein can be used to represent a first unit flow through a hub as an integrated flow comprising multiple integration stages. In an implementation, the DSRO system can be configured as described above with reference to DSRO system 160 and as... Figures 1-5 The operations and functions illustrated herein are used to represent the first unit flow through the hub as an integrated flow comprising multiple integration stages.

[0100] At block 604, the second unit flow through the hub is represented as a split flow comprising multiple splitting stages. In an implementation, units flowing along the split flow are split upon arrival at a train from one or more trains. In an implementation, the DSRO system (e.g., as...) Figure 2 and Figure 3 The DSRO system 160 illustrated herein can be used to represent a second unit flow through a hub as a split flow comprising multiple split stages. In an implementation, the DSRO system can be configured as described above with reference to DSRO system 160 and as... Figures 1-5 The operations and functions illustrated herein are used to represent the second unit flow through the hub as a split flow comprising multiple split stages.

[0101] At block 606, first data associated with the first group of cells flowing along the integration flow within the planning timeframe is acquired. In an implementation, the first data may include dwell time associated with each cell in the first group, indicating the duration of each cell's stay within the hub, and a prediction of the number of cells in the first group using a first prediction model. In an implementation, the full resource optimization manager (e.g., as...) Figure 3 The full resource optimization manager 129 illustrated herein can be used to acquire first data associated with a first set of cells flowing along the integration flow within the planning timeframe. In an implementation, the full resource optimization manager can be configured according to the description above with reference to full resource optimization manager 129 and as described above... Figures 1-5 The operations and functions illustrated herein are performed to obtain first data associated with the first set of units flowing along the integration flow within the planning timeframe.

[0102] At block 608, second data associated with the second group of cells flowing along the split flow within the planning timeframe is acquired. In an implementation, the second data may include the number of cells in the second group, and a prediction of dwell time associated with each cell in the second group, indicating the duration of each cell's stay within the hub, using a second prediction model. In an implementation, the full resource optimization manager (e.g., such as...) Figure 3The full resource optimization manager 129 illustrated herein can be used to acquire second data associated with a second set of cells flowing along the split flow within the planning timeframe. In an implementation, the full resource optimization manager can be configured according to the description above with reference to full resource optimization manager 129 and as described above... Figures 1-5 The operations and functions illustrated herein are performed to obtain second data associated with the second group of units flowing along the split flow within the planning timeframe.

[0103] At block 610, based on the first and second data, an optimized runtime schedule is generated using a dual-stream optimization model. This optimized runtime schedule is configured to optimize at least one resource of the hub for both the consolidation and splitting streams within the planning timeframe. In the implementation, a full resource optimization manager (e.g., such as...) Figure 3 The full resource optimization manager 129 illustrated herein can be used to generate an optimized runtime schedule based on first and second data using a dual-stream optimization model. This optimized runtime schedule is configured to optimize at least one resource of the hub for both the consolidation and splitting streams within a planning timeframe. In an implementation, the full resource optimization manager can be configured according to the description above with reference to full resource optimization manager 129 and as described above. Figures 1-5 The operations and functions illustrated herein are performed to generate an optimized runtime schedule based on first and second data using a dual-stream optimization model. This optimized runtime schedule is configured to optimize at least one resource of the hub for both the integrated and split streams within the planning timeframe.

[0104] At block 612, a signal is generated indicating one or more actions to be performed based on the optimized runtime schedule. In the implementation, the full resource optimization manager (e.g., ...) Figure 3 The full resource optimization manager 129 illustrated herein can be used to generate signals indicating one or more actions to be performed based on optimized runtime scheduling. In an implementation, the full resource optimization manager can be configured according to the description above with reference to full resource optimization manager 129 and as described above. Figures 1-5 The operations and functions illustrated herein are used to generate signals indicating one or more actions to be performed based on optimized runtime scheduling.

[0105] Those skilled in the art will readily understand that the advantages and objectives described above would be impossible without the assembly of the system of the present invention and the specific combinations of the computer hardware described herein with other structural components and mechanisms. Furthermore, the algorithms, methods, and processes disclosed herein improve upon any general-purpose computer or processor disclosed in this specification and the accompanying drawings, transforming it into a special-purpose computer programmed to execute the disclosed algorithms, methods, and processes to achieve the aforementioned functions, advantages, and objectives. It will be further understood that those skilled in the art will recognize that various programming tools can be used to generate and implement the features and operations described above. Moreover, the specific selection of one or more programming tools may depend on the specific objectives and constraints imposed on the chosen implementation to achieve the concepts set forth herein and in the appended claims.

[0106] The descriptions in this patent document should not be construed as implying that any particular element, step, or function may be a fundamental or critical element that must be included within the scope of the claims. Furthermore, unless the exact words “means for” or “step for” are explicitly used in a particular claim, followed by a participle phrase identifying the function, no claim is intended to invoke 35 USC § 112(f) with respect to any appended claim or claim element. The use of terms such as (but not limited to) “mechanism,” “module,” “device,” “unit,” “component,” “element,” “building block,” “device,” “machine,” “system,” “processor,” “processing device,” or “controller” within the claims can be understood and is intended to refer to structures known to a person skilled in the art, as further modified or enhanced by the features of the claims themselves, and is not intended to invoke 35 USC § 112(f). In view of this paragraph, even under the broadest reasonable interpretation, the claims are not intended to invoke 35 USC § 112(f) without the specific language described above.

[0107] This disclosure may be embodied in other specific forms without departing from its spirit or essential characteristics. For example, each new structure described herein may be modified to accommodate specific local changes or requirements while retaining their basic configuration or structural relationships with each other, or performing the same or similar functions described herein. Therefore, this embodiment should be considered illustrative rather than restrictive in all respects. The scope of this disclosure is thus established by the appended claims. Therefore, all variations falling within the meaning and scope of the equivalents of the claims are intended to be included therein. Furthermore, the elements of the claims are not well-known, conventional, or routine. Rather, the claims address unconventional inventive concepts described in the specification.

[0108] Those skilled in the art will further recognize that the various exemplary logic blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been described above generally according to their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the system as a whole. Those skilled in the art can implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure. Those skilled in the art will also readily recognize that the order or combination of components, methods, or interactions described herein are merely embodiments, and that components, methods, or interactions of various embodiments of this disclosure can be combined or performed in ways other than those illustrated and described herein.

[0109] Figures 1-6 The functional blocks and modules described herein may include processors, electronic devices, hardware devices, electronic components, logic circuits, memory, software code, firmware code, etc., or any combination thereof. Consistent with the foregoing, the various exemplary logic blocks, modules, and circuits described in connection with this disclosure may be implemented or performed using general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration.

[0110] The steps of the methods or algorithms described in conjunction with the disclosure herein can be embodied directly in hardware, in a software module executed by a processor, or a combination of both. The software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, allowing the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal, base station, sensor, or any other communication device. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0111] In one or more exemplary designs, the described functionality can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functionality can be stored or transmitted thereon as one or more instructions or code. Computer-readable media includes computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one place to another. A computer-readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. By way of example and not limitation, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Furthermore, a connection can be appropriately referred to as a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL), then coaxial cable, fiber optic cable, twisted pair, or DSL is included in the definition of medium. As used herein, disks and discs include compact discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0112] Although the present disclosure and its advantages have been described in detail, it should be understood that various changes, substitutions, and modifications may be made herein without departing from the spirit and scope of the disclosure as defined by the appended claims. Furthermore, the scope of this application is not intended to be limited to specific embodiments of the processes, machines, manufactures, compositions of matter, apparatuses, methods, and steps described in the specification. As will be readily apparent to those skilled in the art from the disclosure, processes, machines, manufactures, compositions of matter, apparatuses, methods, or steps that are currently existing or to be developed in the future and perform substantially the same function or achieve substantially the same result as the corresponding embodiments described herein can be utilized according to the present disclosure. Therefore, the appended claims are intended to include such processes, machines, manufactures, compositions of matter, apparatuses, methods, or steps within their scope.

Claims

1. A method for optimizing the utilization of resources in a hub, comprising: The first unit flow through the hub is represented as an integrated flow comprising multiple integration stages, wherein units flowing along the integrated flow are integrated into one or more departing trains based at least in part on the destination of each unit flowing along the integrated flow. The second unit flow through the hub is represented as a split flow comprising multiple splitting stages, wherein the units flowing along the split flow are split at least in part based on the destination of each unit flowing along the split flow from one or more trains arriving at the train. Acquire first data associated with a first group of units flowing along the integration flow within the planning period, wherein the first data includes: a dwell time associated with each unit in the first group of units, indicating the duration of each unit's stay within the hub, and a prediction of the number of units in the first group of units using a first prediction model; Acquire second data associated with a second group of units flowing along the split flow within the planning period, wherein the second data includes: the number of units in the second group of units, and a prediction of the duration of stay associated with each unit in the second group of units, indicating the duration of stay of each unit within the hub, using a second prediction model; Based on the first data and the second data, an optimized operational schedule is generated using a dual-stream optimization model. This optimized operational schedule is configured to optimize at least one resource of the hub for both the integrated flow and the split flow within the planning period. Generate signals indicating one or more actions to be performed based on the optimized runtime schedule.

2. The method of claim 1, wherein the optimized operation scheduling of at least one resource of the hub, configured to optimize the consolidation flow and the split flow for the planning period timeframe, is configured to: maximize the throughput of units processed by the hub within the planning period timeframe.

3. The method according to claim 1, further comprising: A first spatiotemporal network is generated based on the integration flow, wherein each node of the first spatiotemporal network represents a corresponding stage in the plurality of integration stages, and the edge between two nodes of the first spatiotemporal network represents the capacity between the two nodes of the first spatiotemporal network.

4. The method according to claim 3, further comprising: A second spatiotemporal network is generated based on the split flow, wherein each node of the second spatiotemporal network represents a corresponding stage in the plurality of split stages, and the edge between two nodes of the second spatiotemporal network represents the capacity between the two nodes of the second spatiotemporal network.

5. The method according to claim 1, wherein generating the optimized runtime schedule comprises: The at least one resource of the hub is optimally allocated between the integrated flow and the split flow; as well as Identify one or more changes used to implement the optimized runtime scheduling.

6. The method of claim 5, wherein the signal indicating the one or more actions to be performed based on the optimized operation schedule includes an indication to implement the one or more changes.

7. The method of claim 5, wherein the one or more modifications include one or more of the following: To execute the instructions to modify the train timetable in order to achieve the optimized operation scheduling; and Additional resources need to be added at specific time increments within the planning period to implement the instructions for optimized operation scheduling.

8. The method of claim 1, wherein the optimized operation scheduling includes one or more of the following: An indication of the number of units processed through each of the plurality of integration phases at each time increment within the planning period; and An indication of the number of units processed through each of the plurality of split phases at each time increment within the planning period.

9. The method of claim 1, wherein the at least one resource of the hub comprises one or more of the following: The integration flow and the split flow contend for one or more resources during at least one integration phase and at least one split phase of the plurality of integration phases; and The integration flow and the split flow are one or more resources that complement each other during at least one integration phase and at least one split phase of the plurality of integration phases.

10. The method of claim 1, wherein a first set of integration stages of the plurality of integration stages provides resources during the integration flow, a second set of integration stages of the plurality of integration stages consumes resources during the integration flow, a first set of split stages of the plurality of integration stages provides resources during the split flow, and the second set of split stages of the plurality of integration stages consumes resources during the split flow.

11. A system configured to optimize the utilization of resources in a hub, comprising: At least one processor; as well as A memory operably coupled to the at least one processor and storing processor-readable code, which, when executed by the at least one processor, is configured to perform operations including: The first unit flow through the hub is represented as an integrated flow comprising multiple integration stages, wherein units flowing along the integrated flow are integrated into one or more departing trains based at least in part on the destination of each unit flowing along the integrated flow. The second unit flow through the hub is represented as a split flow comprising multiple splitting stages, wherein the units flowing along the split flow are split at least in part based on the destination of each unit flowing along the split flow from one or more trains arriving at the train. Acquire first data associated with a first group of units flowing along the integration flow within the planning period, wherein the first data includes: a dwell time associated with each unit in the first group of units, indicating the duration of each unit's stay within the hub, and a prediction of the number of units in the first group of units using a first prediction model; Acquire second data associated with a second group of units flowing along the split flow within the planning period, wherein the second data includes: the number of units in the second group of units, and a prediction of the duration of stay associated with each unit in the second group of units, indicating the duration of stay of each unit within the hub, using a second prediction model; Based on the first data and the second data, an optimized operational schedule is generated using a dual-stream optimization model. This optimized operational schedule is configured to optimize at least one resource of the hub for both the integrated flow and the split flow within the planning period. Generate signals indicating one or more actions to be performed based on the optimized runtime schedule.

12. The system of claim 11, wherein the optimized operation scheduling of at least one resource of the hub, configured to optimize the consolidation flow and the split flow for the planning period timeframe, is configured to: maximize the throughput of units processed by the hub within the planning period timeframe.

13. The system of claim 11, wherein the operation further comprises: A first spatiotemporal network is generated based on the integration flow, wherein each node of the first spatiotemporal network represents a corresponding stage in the plurality of integration stages, and the edge between two nodes of the first spatiotemporal network represents the capacity between the two nodes of the first spatiotemporal network.

14. The system of claim 13, wherein the operation further comprises: A second spatiotemporal network is generated based on the split flow, wherein each node of the second spatiotemporal network represents a corresponding stage in the plurality of split stages, and the edge between two nodes of the second spatiotemporal network represents the capacity between the two nodes of the second spatiotemporal network.

15. The system of claim 11, wherein generating the optimized runtime schedule comprises: The at least one resource of the hub is optimally allocated between the integrated flow and the split flow; as well as Identify one or more changes used to implement the optimized runtime scheduling.

16. The system of claim 15, wherein the signal indicating the one or more actions to be performed based on the optimized operation schedule includes an indication to implement the one or more changes.

17. The system of claim 5, wherein the one or more modifications include one or more of the following: To execute the instructions to modify the train timetable in order to achieve the optimized operation scheduling; and Additional resources need to be added at specific time increments within the planning period to implement the instructions for optimized operation scheduling.

18. The system of claim 11, wherein the optimized operation scheduling includes one or more of the following: An indication of the number of units processed through each of the plurality of integration phases at each time increment within the planning period; and An indication of the number of units processed through each of the plurality of split phases at each time increment within the planning period.

19. The system of claim 11, wherein the at least one resource of the hub comprises one or more of the following: The integration flow and the split flow contend for one or more resources during at least one integration phase and at least one split phase of the plurality of integration phases; and The integration flow and the split flow are one or more resources that complement each other during at least one integration phase and at least one split phase of the plurality of integration phases.

20. A computer-based tool for optimizing the utilization of resources in a hub, the computer-based tool comprising a non-transitory computer-readable medium having computer code stored thereon, the computer code, when executed by a processor, causing a computing device to perform operations including: The first unit flow through the hub is represented as an integrated flow comprising multiple integration stages, wherein, The units flowing along the integrated flow are integrated into one or more departure trains based at least in part on the destination of each unit flowing along the integrated flow; The second unit flow through the hub is represented as a split flow comprising multiple splitting stages, wherein the units flowing along the split flow are split at least in part based on the destination of each unit flowing along the split flow from one or more trains arriving at the train. Acquire first data associated with a first group of units flowing along the integration flow within the planning period, wherein the first data includes: a dwell time associated with each unit in the first group of units, indicating the duration of each unit's stay within the hub, and a prediction of the number of units in the first group of units using a first prediction model; Acquire second data associated with a second group of units flowing along the split flow within the planning period, wherein the second data includes: the number of units in the second group of units, and a prediction of the duration of stay associated with each unit in the second group of units, indicating the duration of stay of each unit within the hub, using a second prediction model; Based on the first data and the second data, an optimized operational schedule is generated using a dual-stream optimization model. This optimized operational schedule is configured to optimize at least one resource of the hub for both the integrated flow and the split flow within the planning period. Generate signals indicating one or more actions to be performed based on the optimized runtime schedule.

Images