Engineering collective intelligence at the edge with aggregate processes

Casadei, Roberto; Viroli, Mirko; Audrito, Giorgio; Pianini, Danilo; Damiani, Ferruccio

doi:10.1016/j.engappai.2020.104081

Cited by 48 publications

(65 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, Alchemist represents a first choice as it ships already with a module providing ScaFi support. Moreover, Alchemist is solid and flexible: in the literature, it has been used extensively to simulate multi-agent and aggregate computing systems, in scenarios including crowd simulation [8], drone swarms [34], edge computing [51], and people rescue [36].…”

Section: Case Studymentioning

confidence: 99%

“…The idea of aggregate programming is to write programs talking about global behavior (fields) and let these drive the local activity of every device in the system. Aggregate programming is embodied by concrete aggregate programming languages [7], such as ScaFi [33,34], a Domain-Specific Language (DSL) embedded in Scala as well as a toolchain for aggregate system development and simulation [35]. ScaFi is used for the examples in this paper and for the experimental evaluation of Section 4.…”

mentioning

confidence: 99%

“…Additionally, ScaFi also represents an agile framework for testing experimental language features (cf. aggregate processes [34]-referenced in Section 5.1). Hence, among the existing languages for aggregate programming, we believe ScaFi is the one better fitting rich scenarios like those addressed in this paper.…”

mentioning

confidence: 99%

“…A full account of research about aggregate programming, field calculi, and ScaFi is beyond the scope of this article; the interested reader can refer to [7,34].…”

mentioning

confidence: 99%

See 3 more Smart Citations

A Programming Approach to Collective Autonomy

Casadei

Aguzzi

Viroli

2021

JSAN

Self Cite

View full text Add to dashboard Cite

Research and technology developments on autonomous agents and autonomic computing promote a vision of artificial systems that are able to resiliently manage themselves and autonomously deal with issues at runtime in dynamic environments. Indeed, autonomy can be leveraged to unburden humans from mundane tasks (cf. driving and autonomous vehicles), from the risk of operating in unknown or perilous environments (cf. rescue scenarios), or to support timely decision-making in complex settings (cf. data-centre operations). Beyond the results that individual autonomous agents can carry out, a further opportunity lies in the collaboration of multiple agents or robots. Emerging macro-paradigms provide an approach to programming whole collectives towards global goals. Aggregate computing is one such paradigm, formally grounded in a calculus of computational fields enabling functional composition of collective behaviours that could be proved, under certain technical conditions, to be self-stabilising. In this work, we address the concept of collective autonomy, i.e., the form of autonomy that applies at the level of a group of individuals. As a contribution, we define an agent control architecture for aggregate multi-agent systems, discuss how the aggregate computing framework relates to both individual and collective autonomy, and show how it can be used to program collective autonomous behaviour. We exemplify the concepts through a simulated case study, and outline a research roadmap towards reliable aggregate autonomy.

show abstract

Section: Case Studymentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

“…A full account of research about aggregate programming, field calculi, and ScaFi is beyond the scope of this article; the interested reader can refer to [7,34].…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Programming Approach to Collective Autonomy

Casadei

Aguzzi

Viroli

2021

JSAN

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another way is to add smartness using artificial intelligence (AI), data analytics, and ML to allow functions to adapt to changes in the environment and intelligently manage the system. For example, using collective intelligence can offer more cost-effectiveness for iIFCs [145].…”

Section: Cost Effectivenessmentioning

confidence: 99%

Applications of Integrated IoT-Fog-Cloud Systems to Smart Cities: A Survey

et al. 2021

View full text Add to dashboard Cite

Several cities have recently moved towards becoming smart cities for better services and quality of life for residents and visitors, with: optimized resource utilization; increased environmental protection; enhanced infrastructure operations and maintenance; and strong safety and security measures. Smart cities depend on deploying current and new technologies and different optimization methods to enhance services and performance in their different sectors. Some of the technologies assisting smart city applications are the Internet of Things (IoT), fog computing, and cloud computing. Integrating these three to serve one system (we will refer to it as integrated IoT-fog-cloud system (iIFC)) creates an advanced platform to develop and operate various types of smart city applications. This platform will allow applications to use the best features from the IoT devices, fog nodes, and cloud services to deliver best capabilities and performance. Utilizing this powerful platform will provide many opportunities for enhancing and optimizing applications in energy, transportation, healthcare, and other areas. In this paper we survey various applications of iIFCs for smart cities. We identify different common issues associated with utilizing iIFCs for smart city applications. These issues arise due to the characteristics of iIFCs on the one side and the requirements of different smart city applications on the other. In addition, we outline the main requirements to effectively utilize iIFCs for smart city applications. These requirements are related to optimization, networking, and security.

show abstract