Agent-Based Simulation Framework for Optimization of Deliveries in a Parcel Distribution System

Simulation is becoming more and more powerful in management, especially strategic one. In the paper, we introduce a novel framework for combining two modelling techniques: agent-based models (ABM) and Multi-resolution modelling (MRM). Both of these methods are well known and wide practical usage. Simulation is a commonly known and recognized business decision making support method. However, their use in a single environment, and in addition reinforcement learning, provides additional opportunities for a variety of (in terms of conditions) test scenarios, shortening decision verification time, obtaining synthetic simulation data for further research and optimization for uncharacteristic conditions. The implementation of such methods allows companies to adaptively track changing in market conditions as well as to anticipate environmental changes. Moreover, machine learning algorithms (clustering and classification) for software agents will improve the scope and dynamics of the simulation models and technology. By using the approach, it is possible to analyze many business strategies (e.g. what would happen if shipments were delivered twice a day).