MONSOON: A Coevolutionary Multiobjective Adaptation Framework for Dynamic Wireless Sensor Networks

Abstract

Wireless sensor applications (WSNs) are often required to simultaneously satisfy conflicting operational objectives (e.g., latency and power consumption). Based on an observation that various biological systems have developed the mechanisms to overcome this issue, this paper proposes a biologically-inspired adaptation mechanism, called MON-SOON. MONSOON is designed to support data collection applications, event detection applications and hybrid applications. Each application is implemented as a decentralized group of software agents, analogous to a bee colony (application) consisting of bees (agents). Agents collect sensor data and/or detect an event (a significant change in sensor reading) on individual nodes, and carry sensor data to base stations. They perform these data collection and event detection functionalities by sensing their surrounding environment conditions and adaptively invoking biologicallyinspired behaviors such as pheromone emission, reproduction and migration. Each agent has its own behavior policy, as a gene, which defines how to invoke its behaviors. MONSOON allows agents to evolve their behavior policies (genes) and adapt their operations to given objectives. Simulation results show that MONSOON allows agents (WSN applications) to simultaneously satisfy conflicting objectives by adapting to dynamics of physical operational environments and network environments (e.g., sensor readings and node/link failures) through evolution.

Collaborative signal and information processing in wireless sensor networks: A review

“…Several authors, such as Sin et al [35], Boonma, and Suzuki in [36] and [37] have proposed agent-oriented frameworks for the WSN, which are based on biologically-inspired approaches. The agent operates automatically with their behavior policies as a gene and aggregates other agents to reduce communication and gives high priority to nodes that have enough energy to communicate.…”

“…A Co-evolutionary Multi objective Adaptation Framework for Dynamic Wireless Sensor Networks (MONSOON) [37] is designed to support data-collective applications, event-detection applications and hybrid applications. Each application is implemented as a decentralized group of software agents, analogous to a bee colony (application) consisting of bees (agents).…”

Constraint-based self-adaptation of wireless sensor networks

“…In the literature, we find several works [14], [3], [7], [4], [5] dealing with the adaptation of WSNs with similar motivation as our approach. However, many of them [14], [3], [7] focus in how to realize this adaptation over the network instead to search for a suitable configuration of the whole system as we propose.…”

“…Nevertheless, they only pay attention to QoS dimension instead to provide a mechanism to optimize the network regarding the context changes and other dimensions. Finally, in [4] and [5] the authors try to deal with the adaptation taking into account conflicting objectives. However, they use a biological adaptation mechanism to reconfigure the system regarding only the latency, cost and success rate.…”

Configuring multi-objective evolutionary algorithms for design-space exploration of wireless sensor networks

“…The paper defines a weighted linear fitness function for a specific WSN design and tries to maximize this linear function by use of a GA. In [3], a bee colony inspired evolutionary algorithm is used for run-time optimization. The elite selection is done in the sink node and genetic operations, including crossover and mutation are done in each sensor node.…”