Mobile Resources
Workers, vehicles, tools and materials must be assigned efficiently to geographically distributed interventions.
OMASCED-SABIA
Project
Multi-objective and Adaptive Optimization of Field Services in Dynamic Environments with Advanced Systems Based on Artificial Intelligence.
PID2025-172989OB-I00
ABOUT THE PROJECT
What is OMASCED-SABIA?
OMASCED-SABIA is a research project focused on developing advanced methods for the planning, scheduling and dynamic rescheduling of Field Service operations.
Field Services involve the deployment of mobile workers, technical teams, tools and materials to geographically distributed locations in order to carry out installation, maintenance, repair, inspection or assistance activities.
These operations are highly dynamic. Travel times, resource availability, customer requirements, workforce conditions and unexpected events can change continuously, requiring decisions to be revised in real time.
OMASCED-SABIA addresses this challenge by combining Operations Research, multi-objective optimization, metaheuristics, Artificial Intelligence and real-time data within an advanced Decision Support System.
The project aims to improve not only operational and economic performance, but also customer satisfaction, worker well-being and environmental sustainability.
RESEARCH CHALLENGE
A Complex and Dynamic Decision Problem
Planning Field Services requires coordinating multiple interdependent decisions under uncertainty and changing operating conditions.
Dynamic Conditions
New service requests, delays, cancellations and unexpected events can require schedules to be continuously updated.
Multiple Objectives
Economic efficiency must be balanced with service quality, workforce conditions and environmental performance.
Real-time Data
Heterogeneous data from operational systems, workers, customers and external sources must support rapid decision-making.
OBJECTIVES
Overall Objective
To develop new multi-objective mathematical models, advanced algorithms based on metaheuristics and Deep Reinforcement Learning, and an advanced Decision Support System integrating these models with heterogeneous real-time data.
The resulting system will support the dynamic and sustainable planning, scheduling and rescheduling of Field Service operations, improving economic, social and environmental efficiency.
SPECIFIC OBJECTIVES
From Conceptual Modelling to Validation
Conceptual Framework
Develop a conceptual framework for the planning and scheduling of Field Services in dynamic environments.
Processes and Information Flows
Analyse the main planning processes, decision levels, actors and information flows involved in Field Service operations.
Data Sources
Identify and structure the heterogeneous data required to support intelligent and adaptive decision-making.
State of the Art
Analyse existing scientific approaches, methods and technologies for Field Service planning and scheduling.
Multi-objective Models
Develop mathematical models capable of representing multiple operational, social and environmental objectives.
OR + AI Algorithms
Design advanced solution methods combining Operations Research, metaheuristics and Artificial Intelligence.
Decision Support System
Define and implement the architecture of an advanced Decision Support System integrating models, algorithms and real-time information.
Experimental Validation
Evaluate the proposed models and algorithms through computational experiments and representative Field Service scenarios.
Project Coordination
Ensure the scientific, technical and organizational coordination required for the successful development of the project.
Dissemination and Transfer
Disseminate scientific results and facilitate their transfer to research communities, companies and society.
METHODOLOGICAL APPROACH
Operations Research, AI, Data and DSS
OMASCED-SABIA integrates complementary research areas to address the complexity of dynamic Field Service planning and scheduling.
Operations Research
Mathematical modelling and optimization techniques for representing and solving complex planning and scheduling problems.
Artificial Intelligence
Metaheuristics and Deep Reinforcement Learning methods for adaptive decision-making in dynamic environments.
Real-time Data
Integration of heterogeneous operational and contextual information to support data-driven planning and rescheduling.
Decision Support System
A software environment integrating data, optimization models and intelligent algorithms to support operational decisions.
MULTI-OBJECTIVE PERSPECTIVE
Four Dimensions of Performance
The project goes beyond traditional cost and productivity objectives by considering four complementary dimensions.
Economic Efficiency
Reduce operational costs, travel, idle time and inefficient use of resources.
Customer Satisfaction
Improve response times, punctuality, reliability and overall service quality.
Worker Well-being
Consider workload balance, occupational conditions and the social dimension of operational decisions.
Environmental Impact
Reduce unnecessary travel, energy consumption and the environmental footprint of Field Service operations.
APPLICATION AREAS
Field Services Across Multiple Sectors
The methods developed within OMASCED-SABIA are intended to be applicable to a wide range of sectors in which mobile teams provide geographically distributed services.
Energy and Utilities
Telecommunications
Home Healthcare
Industrial Maintenance
Transport and Logistics
NEXT
Explore the Work Plan
Discover how the project is structured through eight Work Packages covering conceptual modelling, data, optimization, Artificial Intelligence, software development, validation and dissemination.