Transshipment strategy: enrich your TOS with new efficient Transshipment stacking strategies
Revolutionizing Container Transshipment: Optimize Your Operations with DMSLOG.Ai’s AI-Driven Solutions. Experience the Future of Port Efficiency Today!
Your terminal today
Your Smart Port tomorrowTrusted by industry-leading innovators
Join the 1000+ terminals committed to fighting climate change
DMSLOG.Ai proposes a TOS agnostic solution with simplified API integration to plan transshipment containers stacking in the yard and pre-stowage at vessel discharging time.
Ai is a new topic in the port industry and it can be a huge innovation plan for terminal operators.
DMSLOG.Ai solutions are already used on a daily basis around the world, which raises every uncertainty about the deployment, integration and results.
Those interfaces help the operator trust the AI, measure its savings, and monitor its resource utilization – with the help of live digital twins simulations.
356t CO2
-10%
Historical insight
Yard efficiency analytics
Revolutionize terminal operations with yard view insights
This interface provides an interactive satellite view of the terminal, allowing operators to click for detailed information on blocks, bays, and containers. It integrates key performance data and offers a historical timeline feature for tracking operational changes.
Ship load optimization
Enhance vessel handling with ship view features
Focused on optimizing vessel load distribution and container movement prediction, this interface delivers detailed bay insights and supports both automatic and manual resource allocation.
It facilitates efficient workload and crane management, bolstered by scenario analysis for improved planning.
Optimized distribution
Resource flexibility
AI-enhanced vessel loading sequence prediction
Manual vessel load sequencing was time-consuming and prone to inefficiency, often leading to non-compliant container placements and unnecessary yard reshuffles.
Time-labor reduction
Reshuffle minimization
Designing the load sequence for a vessel at a container terminal is a highly labor-intensive task. It involves ensuring that containers are placed on the vessel in compliance with specific vessel constraints. Simultaneously, efforts are made to prevent unproductive moves in the yard, known as reshuffles.
The forecasting method is employed to predict the sequence in which containers will be loaded during unloading from the initial vessel for transshipment.
AI-assisted workload forecasting for yard blocks
Before AI, estimating yard block workloads was a guessing game, resulting in planning inaccuracies and inefficient container storage and retrieval.
Planning precision
Task management
The transhipment stacking strategy considers the anticipated workload within a designated block during a set timeframe, involving tasks such as storing or retrieving containers.
The importance of workload estimation lies in its ability to predict task distribution over time and blocks, facilitating efficient workload management.
However, the precise workload is uncertain during the planning phase. To address this uncertainty, machine learning techniques are employed to predict the workload accurately.
AI block allocation system
Without AI, container allocation to yard blocks was suboptimal, leading to increased transport distances and underutilized space and resources.
Distance reduction
Space maximization
Block allocation powered by AI refers to the use of Artificial Intelligence algorithms and techniques to optimize the allocation of containers to a block in port operations.
AI-powered block allocation systems consider various factors such as information about the vessel, berth information, yard layout, container inventory levels, and container characteristics.
The dynamic allocation of yard blocks improves overall workload distribution efficiency and reduces congestion around the terminal yard blocks.
Using this data, the AI determines the optimal block allocation that minimizes the distance required to transport containers and maximizes the use of available space and resources.
AI-optimized pre-stowage strategy development
Traditional methods of pre-stowage planning often compromised vessel stability and slot utilization, lacking the precision needed to meet safety standards effectively.
Stability enhancement
Safety assurance
An AI-powered optimization system for pre-stowage employs advanced algorithms to create an optimal stowage plan. It takes into account different constraints, including container size and type, as well as ship stability considerations.
The pre-stowage model is computed when the general plan for vessel is received and updated if necessary regarding the state of the yard
The model for pre-stowage guarantees an efficient and optimized arrangement of containers into the vessel, ensuring both ship stability, maximum slot utilizationand minimizing re-stowage while meeting the safety requirements.
AI-guided container positioning strategy
Prior to AI integration, assigning containers to optimal positions within a block was challenging, leading to inefficient ASC coordination and prolonged dwell times.
Positioning streamlining
ASC coordination
The AI system conducts an evaluation of different elements when a block is chosen, including TOS-related filters/segregations and predicted dwell time, in order to suggest the best position for each container.
The block allocation and position allocation models are computationally efficient and compatible with real-time data delivery (within a minute).
The proposed stacking strategy also takes into account efficient coordination between ASCs engaged in containers handling activities within the given block.
AI in predicting external truck traffic
Before employing AI, predicting external truck flows was imprecise, causing frequent bottlenecks and congestion around the terminal yard blocks.
Congestion reduction
Yard planning
The goal in this AI is the forecasting of external truck movements and traffic patterns coming to a container terminal.
This prediction is achieved by analyzing various information such as external truck visit historical data, vehicles booking system historical data, traffic information inside the terminal, weather conditions, and road infrastructure.
These predictions enable better and dynamic yard block planning, improving overall workload distribution efficiency over blocks and reducing congestion around the terminal yard blocks.
Predictive models are developed to estimate truck flow and anticipate potential bottlenecks or delays in areas surrounding the terminal yard blocks. The modeling process can also incorporate geolocation information within the yard, during the construction of predictive features.
AI-enabled dwell time estimation
The inability to accurately predict container dwell times in the terminal previously led to inefficient use of mixed-purpose yard blocks and operational delays.
Yard efficiency
Delay reduction
Dwell time is the period that a container spends within a container terminal in one or more terminal stacks. It is a crucial factor influencing the efficiency and overall performance of maritime logistics operations.
Dwell time predictions are used to estimate the workload distribution over mixed-purpose yard blocks.
The container dwell time predictions, vessel load sequences and workload per yard block benefit from incorporating some or all of the following data as predictive features:
- Container Cycle Data
- Gate Transaction Data
- Manifest Data
- Customs Clearance data
- TOS Rules and related data
- Equipment Availability
- General Stowage Plan
⚖️ Get compliant with your local and international CO2 regulations.
Intergovernmental Panel on Climate Change, United Nations Climate Change, Organisation for Economic
Co-operation and Development, UN Environment Programme, The European Council, USA Department of Energy…
📈 Our Transshipment performance & ROI
DMSLOG.Ai already has good experience with AI-powered stacking strategies and we can estimate a reasonable range for the expected results.
-0%
Unproductive moves
-0%
Vessel turnaround time
$0K
Minimum direct saved
0t
CO2 direct saved
The terminal subscribes to the Transshipment – and pays monthly based on its volume of containers.
By integrating these TOS-related filters and AI-generated parameters, our solution ensures a comprehensive and efficient approach to container stacking and pre-stowage planning.
Besides, transporters benefit from advanced features that allow them to reduce their waiting time in lines, facilitate their combined operations and rotate on the terminal more quickly.
* Prices not contractual: depending on your volume, contract duration, options, specific requirements.
The proof of concept is available as soon as the beta version is released, and already allows the terminal to check the accuracy of DMSLOG.Ai recommendations.
For any project deployment, we support you in the following steps.
5 star expertise on the latest tech
Design, Simulation, Analysis
DMS ensures that the configuration of your Ai solution meets your expectations, respects your policies and internal rules, and corresponds to your objectives.
Helpdesk and user support
We are at your disposal for technical assistance 7 days a week, to help you in all your steps.
Project management, implementation and training
Whether you have an IT team or not, available or not, we provide engineers and project managers to ensure the proper deployment of your Ai solution.
Our local IT partners.
From the web hosting of your Ai solution, to the training of your users, DMSLOG.Ai works with local partners and integrators, in all regions of the world.
Our Transshipment container stacking and container pre-stowage planning is available in…
[gtranslate]
This deployment process is done in 3 main steps.
Phase 1 – Dual Operation:
Initially, you’ll continue operating your current Vehicle Booking System (VBS) while we deploy our new system. This phase ensures there is no disruption in your terminal’s operations. Our team will work closely with yours to set up the new VBS in parallel, focusing on integrating it seamlessly with your existing infrastructure.
Phase 2 – Hybrid Testing:
In this phase, both the old and new VBS will be operational concurrently. This ‘hybrid system’ allows us to conduct real-world testing of the new VBS with a select group of carriers. It’s a crucial step to ensure the new system functions as intended and to identify and resolve any potential issues. This phase also provides an opportunity for your staff and carriers to familiarize themselves with the new system without fully depending on it.
Phase 3 – Full Transition and Closure:
Once the new VBS is thoroughly tested and validated, we’ll transition all transporter activities to it. During this phase, the old VBS will be phased out. We ensure a smooth transition where all transporters are now using the new system effectively. Following the successful implementation, the old VBS will be closed. However, we will securely store all historical data from the old system to ensure that no critical information is lost and can be accessed if needed.
This phase marks the completion of the transition to the new, more efficient VBS, aligning with your terminal’s operational needs and future growth of your Smart Port.
Yes, a CMS is integrated into our Vehicle Booking System.
This detailed breakdown provides an in-depth look at how the CMS module integrated into the VBS enhances communication and operational efficiency between the terminal and the carriers community.
For Terminal Managers – Automatic Updates:
- The following automatic features simplifies terminal operations and ensures timely information dissemination.
For Carriers – Community Space Features:
- Vessel Information Access: Enabling carriers to view detailed vessel information, including Estimated Time of Arrival (ETA) and Estimated Time of Departure (ETD).
- Container Tracking: Offering carriers the ability to track containers at each step, similar to an Amazon order tracking system, including status updates within the vessel and terminal (or on the way to the terminal, when the truck TMS is connected to the VBS via API).
- Financial Information and Transactions: Providing information on Last Free Day, storage guarantees, payments due, and fees, sourced directly from the Terminal Operating System (TOS). Carriers can conveniently pay these charges using various payment methods like Credit Card, Visa, Mastercard, GooglePay, and ApplePay.
- Truck Turnaround Time Estimations: Availability of a chart displaying estimated Truck Turnaround Times for the current and upcoming days, aiding carriers in planning and logistics.
Public and Private Access
- Access Control: Allowing for tailored information sharing based on the terminal’s and carriers’ needs.
Yes, our VBS can work without the Ai layers – even if the best logistics optimizations come from the Ai features.
Contact us for more details, it will be a pleasure to deploy our Vehicle Booking System on your terminal.
However, a Vehicle Booking System with Ai Integration has several benefits:
- Advanced Logistics Optimization: Utilizing AI algorithms, the system offers superior logistics management, optimizing container handling and vehicle scheduling.
- Predictive Analytics: AI capabilities enable predictive modeling for better forecasting and decision-making.
- Enhanced Efficiency: The AI layer streamlines operations, reducing wait times and improving turnaround.
- Data-Driven Insights: AI tools provide valuable insights for continuous improvement and strategic planning.
without any longer project deployment (they both need 4 to 6 month).
At DMSLOG.Ai, we understand the diverse needs of modern smart ports. Whether you choose our AI-enhanced Vehicle Booking System or opt for the non-AI version, we ensure top-quality service and performance. The AI-integrated system is ideal for terminals seeking cutting-edge logistics optimization and data-driven decision-making, aligning with the trending demands for AI in Smart Ports.
However, for those preferring a simpler, quicker-to-deploy solution, our non-AI VBS still offers robust functionality and efficiency.
Contact us for a tailored deployment plan that best fits your terminal’s unique requirements.
