Dynamic Power Management for Sensor Node in WSN Using Average Reward MDP.
Somayeh KianpishehNasrollah Moghaddam CharkariPublished in: WASA (2009)
Keyphrases
- average reward
- sensor nodes
- energy efficiency
- power management
- wireless sensor networks
- energy consumption
- markov decision processes
- sensor networks
- optimal policy
- discounted reward
- energy saving
- long run
- energy efficient
- semi markov decision processes
- policy iteration
- base station
- reinforcement learning
- resource constrained
- sensor data
- data transmission
- state and action spaces
- model free
- resource limitations
- total reward
- routing protocol
- data aggregation
- finite state
- power consumption
- multi hop
- routing algorithm
- action space
- wireless sensor nodes
- data center
- cluster head
- markov chain
- node selection
- dynamic programming
- data collection
- sink node
- topology control
- partially observable
- markov decision process
- state space
- body sensor networks
- infinite horizon
- markov decision problems
- partially observable markov decision processes
- sufficient conditions
- multi agent