Solar Tracking for Optimizing Conversion Efficiency Using ANN

  • Neeraj Kumar Singh
  • Shilpa S. Badge
  • Gangadharayya F. Salimath
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 695)


In order to maximize the amount of radiation collected by a solar PV panel, the tracker must follow the sun throughout the day. The tracking mechanism of sun required electric motors, light sensors, gearbox, and electronic control to accurately focus at the sun at all times which make the tracking system complex. Also to get maximum power from solar PV panel, MPPT technique must be implemented to the system. This paper deals with new approach for solar tracking and MPPT using single neural network control scheme aiming to reduce overall cost and complexity without nixing efficiency of solar photovoltaic system. The simulation model is done in the MATLAB Simulink for system analysis.


Artificial neural network (ANN) Tracking reference neural network control (TRNNC) Maximum power point tracking (MPPT) 


  1. 1.
    Renewable Energy World Editors (12 Nov 2014) Residential Solar Energy Storage Market Could Approach 1 GW by 2018.
  2. 2.
    Kumar, N.M., Singh, A.K., Reddy, K.V.K.: Fossil fuel to solar power: a sustainable technical design for street lighting in Fugar City, Nigeria. Procedia Comput. Sci. 93, 956–966 (2016)Google Scholar
  3. 3.
    Cota, O.D., Kumar, N.M.: Solar energy: a solution for street lighting and water pumping in rural areas of Nigeria. In: Proceedings of International Conference on Modelling, Simulation and Control (ICMSC-2015), vol. 2, pp. 1073–1077.
  4. 4.
    Kumar, N.M., Dinniyah, F.S.: Impact of tilted PV generators on the performance ratios and energy yields of 10 kWp grid connected PV plant at Jakarta and Jayapura regions of Indonesia. In: Proceedings of 1st International Conference in Recent Advances in Mechanical Engineering (ICRAME-2017), pp. 73–75. Kingston Engineering College, Vellore, India (2017)Google Scholar
  5. 5.
    Kumar, N.M., Kumar, M.R., Rejoice, P.R., Mathew, M.: Performance analysis of 100 kWp grid connected Si-poly photovoltaic system using PVsyst simulation tool. Energy Procedia 117, 180–189 (2017). Scholar
  6. 6.
    Kumar, N.M., Reddy, P.R.K., Praveen, K.: Optimal energy performance and comparison of open rack and roof mount mono c-Si photovoltaic systems. Energy Procedia 117, 136–144 (2017). Scholar
  7. 7.
    Kumar, N.M., Reddy, P.R.K., Sunny, K.A., Navothana, B.: Annual energy prediction of roof mount PV system with crystalline silicon and thin film modules. In: Special Section on: Current Research Topics in Power, Nuclear and Fuel Energy, SP-CRTPNFE 2016, International Conference on Recent Trends in Engineering, Science and Technology, Hyderabad, India, vol. 1, no. 3, pp. 24–31 (2016)Google Scholar
  8. 8.
    Kumar, N.M., Navothna, B., Minz, M.: Performance comparison of building integrated multi-wattage photovoltaic generators mounted vertically and horizontally. In: Proceeding of 2017 IEEE International Conference on Smart Technology for Smart Nation (SmartTechCon), 17th–19th August 2017. REVA University, Bangalore, India (2017)Google Scholar
  9. 9.
    Kumar, N.M., Das, P., Krishna, P.R.: Estimation of grid feed in electricity from roof integrated Si-amorph PV system based on orientation, tilt and available roof surface area. In: Proceedings of 2017 IEEE International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), 6th & 7th July 2017, Kerala, India (2017)Google Scholar
  10. 10.
    Franke, W.T., Kürtz, C., Fuchs, F.W.: Analysis of control strategies for a 3 phase 4 wire topology for transformerless solar inverters. In: Proceedings of IEEE International Symposium Industrial Electronics, Bari, pp. 658–663 (2010)Google Scholar
  11. 11.
    Lorenzo, E., Araujo, G., Cuevas, A., Egido, M., Miñano, J., Zilles, R.: Solar Electricity: Engineering of Photovoltaic Systems. Progensa, Sevilla, Spain (1994)Google Scholar
  12. 12.
    Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the marquardt algorithm. IEEE Trans. Neural Netw. 5(6), 989–993 (1994)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Neeraj Kumar Singh
    • 1
  • Shilpa S. Badge
    • 2
  • Gangadharayya F. Salimath
    • 3
  1. 1.Department of Electrical EngineeringPES College of EngineeringAurangabadIndia
  2. 2.Department of Electronics and Telecommunication EngineeringHi-Tech Institute of TechnologyAurangabadIndia
  3. 3.Department of Electrical EngineeringShreeyash College of Engineering and TechnologyAurangabadIndia

Personalised recommendations