Solar energy prediction for constrained IoT nodes based on public weather forecasts

Solar power is important for many scenarios of the Internet of Things (IoT). Resource-constrained devices depend on limited energy budgets to operate without degrading performance. Predicting solar energy is necessary for an efficient management and utilization of resources. While machine learning is already used to predict solar power for larger power plants, we examine how different machine learning methods can be used in a constrained sensor setting, based on easily available public weather data. The conducted evaluation resorts to commercial IoT hardware, demonstrating the feasibility of the proposed solution in a real deployment. Our results show that predicting solar energy is possible even with limited access to data, progressively improving as the system runs.

[1]  Peng Wang,et al.  Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines , 2011, IEEE Transactions on Industry Applications.

[2]  Mani B. Srivastava,et al.  Power management in energy harvesting sensor networks , 2007, TECS.

[3]  John Krogstie,et al.  A Measurement-Driven Approach to Understand Urban Greenhouse Gas Emissions in Nordic Cities , 2016, NIK.

[4]  Robert Brzoza-Woch,et al.  Predictive power consumption adaptation for future generation embedded devices powered by energy harvesting sources , 2015, Microprocess. Microsystems.

[5]  Johan Driesen,et al.  Predetermined static configurations of a partially shaded photovoltaic module , 2017 .

[6]  Anis Sakly,et al.  Comparison between conventional methods and GA approach for maximum power point tracking of shaded solar PV generators , 2013 .

[7]  Mani B. Srivastava,et al.  Harvesting aware power management for sensor networks , 2006, 2006 43rd ACM/IEEE Design Automation Conference.

[8]  Kuan-Chieh Wang,et al.  QoS-Aware Power Management for Energy Harvesting Wireless Sensor Network Utilizing Reinforcement Learning , 2009, 2009 International Conference on Computational Science and Engineering.

[9]  Albert Hiesl,et al.  East to west – The optimal tilt angle and orientation of photovoltaic panels from an electricity system perspective , 2015 .

[10]  Boris Bellalta,et al.  Adapting sampling interval of sensor networks using on-line reinforcement learning , 2016, 2016 IEEE 3rd World Forum on Internet of Things (WF-IoT).

[11]  Chao-Ming Huang,et al.  A Weather-Based Hybrid Method for 1-Day Ahead Hourly Forecasting of PV Power Output , 2014, IEEE Transactions on Sustainable Energy.

[12]  Hongseok Yoo,et al.  Dynamic Duty-Cycle Scheduling Schemes for Energy-Harvesting Wireless Sensor Networks , 2012, IEEE Communications Letters.

[13]  Lakshmish Ramaswamy,et al.  Data Quality and Energy Management Tradeoffs in Sensor Service Clouds , 2015, 2015 IEEE International Congress on Big Data.

[14]  Purushottam Kulkarni,et al.  Energy Harvesting Sensor Nodes: Survey and Implications , 2011, IEEE Communications Surveys & Tutorials.

[15]  Luca Benini,et al.  Adaptive Power Management for Environmentally Powered Systems , 2010, IEEE Transactions on Computers.

[16]  Marcelo G. Molina,et al.  Dynamic model of lithium polymer battery – Load resistor method for electric parameters identification , 2015 .

[17]  Arnab Raha,et al.  Powering the Internet of Things , 2014, 2014 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED).

[18]  Sue Ellen Haupt,et al.  Big Data and Machine Learning for Applied Weather Forecasts: Forecasting Solar Power for Utility Operations , 2015, 2015 IEEE Symposium Series on Computational Intelligence.

[19]  M. Ashry,et al.  Electrical Characteristic Measurement of the Fabricated CdSe / P-Si Heterojunction Solar Cell under Radiation Effect , 2012 .

[20]  Amit Kumar Yadav,et al.  Solar radiation prediction using Artificial Neural Network techniques: A review , 2014 .

[21]  Frank Alexander Kraemer,et al.  Energy Consumption Estimation for Energy-Aware, Adaptive Sensing Applications , 2017, MSPN.

[22]  Ian Witten,et al.  Data Mining , 2000 .

[23]  H. Vincent Poor,et al.  Three-Party Energy Management With Distributed Energy Resources in Smart Grid , 2014, IEEE Transactions on Industrial Electronics.

[24]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .