Abstract:In peer-to-peer (P2P) overlay networks, a group of n (≥2) peer processes have to cooperate with each other. Each peer sends messages to every peer and receives messages from every peer in a group. In group communications, each message sent by a peer is required to be causally delivered to every peer. Most of the protocols designed to ensure causal message order are designed for networks with a plain architecture. These protocols can be adapted to use in free scale and hierarchical topologies; however, the amount of control information is O(n), where n is the number of peers in the system. Some protocols are designed for a free scale or hierarchical networks, but in general they force the whole system to accomplish the same order viewed by a super peer. In this paper, we present a protocol that is specifically designed to work with a free scale peer-to-peer network. By using the information about the network's architecture and by representing message dependencies on a bit level, the proposed protocol ensures causal message ordering without enforcing super peers order. The designed protocol is simulated and compared with the Immediate Dependency Relation and the Dependency Sequences protocols to show its lower overhead.

No abstract

Emerging applications based on vehicular ad-hoc networks (VANETs) are focused on offering new services to intelligent transportation systems (ITSs), such as traffic safety and management. For such kind of services, there are intrinsic spatial and temporal dependencies in the communication among mobile and fixed components. However, the characteristics of VANETs, which include a rapidly changing topology and the lack of global temporal references, make it difficult to satisfy such communication constraints. Commonly, the communication protocols for VANETs assume high coupled communication links; nevertheless, for most ITSs, the entities to whom such information will be useful are determined at run time by the spatial and temporal context. In this paper, a causal position-based indirect communication protocol is proposed, which allows road side units (RSUs) to disseminate messages with an uncoupled communication. The proposed solution uses the vehicles as opportunistic carriers, leveraging the bounded movement in a specific geographical region to exchange data among RSUs even with unknown recipients. To preserve the coherence of the exchange of messages, they are ordered by establishing their causal dependencies without the requirement of global references or synchronized physical clocks. Furthermore, the proposed protocol leverages message redundancy to recover some lost messages during the transmission. It is analytically demonstrated that the protocol is scalable since the size of the control information depends only on the number of RSUs rather than on the total number of entities in the system. INDEX TERMS Position-based causal diffusion, causal ordering, vehicular networks.