Skip to Main content Skip to Navigation

Simulations multi-agent pour les villes intelligentes : une architecture multi-environnement temporelle, spatiale et organisationnelle. Apports pour l’anticipation

Abstract : The multiagent simulation is a promising approach for smart city design and planning. In this context, we focus on the example of recharging electric vehicles on public charging points. This example illustrates a problem of managing limited and shared resources in time and space. Rolland May defines three main dimensions that should be integrated by the system: the space, the organisation and the time. In multi-agent simulations, the spatial dimension and the social dimension are the subject of numerous proposals in the literature. In opposite, time remains subject to very few studies and consideration. In addition, if a lot of research deals with spatial and organisational consideration in the agent's reasoning, the time consideration, as a system dynamic, is often overlooked.This highlights two aspects to which we want to contribute:- the need for interaction support to exchange spatial, social and temporal information;- the need for reasoning that takes this exchanged spatial, temporal and organisational information into account.Thought this thesis, our first objective aim at making the multiagent simulation paradigm evolve in order to consider time as a new medium of interaction, in the same way as the spatial environment or the organisational environment. For that purpose, we draw on existing approaches that are commonly used for modelling the space and organisations. Our model is called Agent-Group-Environment-Time (AGRET). It is an extension of the generic organisational model AGR and its variant AGRE.The originality of our approach is that it integrates the temporal dimension as an environment, in the same way as the spatial environment and the social environment. This time environment is used to support the exchange and the storage of time information. It complements the simulation scheduler which manages the simulation activation cycle. The implementation of this new interaction environment brings new possibilities. One of these possibilities is the use of temporal, spatial and social information, perceived through the environments, to optimise the agent's reasoning. In this context, we choose to focus on anticipatory reasoning which is particularly interesting in the context of the smart city. This anticipatory reasoning increases the realism of the simulation by showing a cognitive capacity that is specific to humans. It also improves the agent's decision mechanism by choosing a more relevant behaviour that takes into account the agent's temporal, spatial and social activation context. This anticipatory reasoning is based on information about the past, the present and the future, which the agent perceives through the temporal environment. The inclusion of future information in the anticipative reasoning is an original feature of this approach. This functionality is made possible by the temporal environment, which allows storing and perceiving information on the temporal dimension.To summarise, our contributions are both about time. Our first contribution is about the representation of time as an environment. In the multi-agent level, we propose an interaction support for the exchange and storage of information on space, time and organisation. Our second contribution is about temporal reasoning. We propose an anticipative reasoning based on the perception of spatial, temporal and social environments. In particular, we exploit the visibility of the future dimension of time that is allowed by the temporal environment. In the example of electric vehicles recharge, the integration of our approaches allows, at the collective level, the optimisation of the recharge distribution in space and time. We show this through an implementation on a multi-agent simulation model called SkuadCityModel. More generally, at the level of the smart city, the implementation of our contributions allows the optimisation of resource management in space and time.
Complete list of metadatas

Cited literature [145 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Monday, October 26, 2020 - 8:03:06 AM
Last modification on : Tuesday, October 27, 2020 - 3:30:13 AM


Version validated by the jury (STAR)


  • HAL Id : tel-02977776, version 1


Tahina Vololona Eulalie Ralitera. Simulations multi-agent pour les villes intelligentes : une architecture multi-environnement temporelle, spatiale et organisationnelle. Apports pour l’anticipation. Système multi-agents [cs.MA]. Université de la Réunion, 2020. Français. ⟨NNT : 2020LARE0017⟩. ⟨tel-02977776⟩



Record views


Files downloads