Predictive Energy Management for Wireless Sensor Nodes

• Author / Creator

  Rodway, James E A

• A wireless sensor network is a tool that can collect data, aiding in answering a number of different questions in research and industrial environments. When deployed in remote locations, it is often beneficial to use of energy harvesting technologies, allowing sensor nodes to replenish energy while in the field. This permits longer deployment times while keeping node size small. In order to make the best use of harvested energy, controllers can be used to adapt node activities to available energy. In this thesis, energy forecasts based on measurements of atmospheric pressure are created and included as inputs to fuzzy controllers. These controllers are applied to simulated sensor nodes and used to control node activity levels for effective use of available energy. They were tuned using differential evolution and simulated using measured meteorological data. The results were examined in terms of the networks overall activity level and the usage of reserve energy. With respect to the solar energy forecasts, a number of applied methods were able to achieve error levels comparable to other methods where more variables were included. The tuned fuzzy controllers represented an improvement over both the uncontrolled and human-created cases.

• Subjects / Keywords

  • Solar Energy Forecast
  • Energy Management
  • Wireless Sensor Networks
  • Fuzzy Controller Tuning

• Graduation date

  Fall 2017

• Type of Item

  Thesis

• Degree

  Doctor of Philosophy

• DOI

  https://doi.org/10.7939/R3PN8XV5F

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.