District Energy Optimization Based on MLP Simulation

Energy optimization is a substantial procedure for building management systems, especially for huge energy demand buildings, like factories, public transport facilities, etc. The aim of this paper is to present a simulation based decision support that models the energy balance and suggests the optimal energy-related actions based on specified optimization criteria. The energy modelling consists of the facilities energy demand and Renewable energy generation forecasting. A neural network is exploited to simulate the load of the district, while physical models are deployed to simulate wind power and Photo-voltaic energy power using weather data. Subsequently, the energy optimization is achieved through a multi-layer perceptron. Finally, the proposed tool is evaluated against real-life data from a Port, while the experimental results show the efficiency of the proposed system.

[1]  Dereje Shiferaw,et al.  Short-Term Wind Power Forecasting Using Artificial Neural Networks for Resource Scheduling in Microgrids , 2016 .

[2]  A. Mellit,et al.  A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy , 2010 .

[3]  Soukaina Barhmi,et al.  Hourly wind speed forecasting based on Support Vector Machine and Artificial Neural Networks , 2019, IAES International Journal of Artificial Intelligence (IJ-AI).

[4]  Yang Hu,et al.  An Improved Forecasting Method for Photovoltaic Power Based on Adaptive BP Neural Network with a Scrolling Time Window , 2017 .

[5]  S. Krinidis,et al.  A HYBRID PHYSICAL/STATISTICAL DAY-AHEAD DIRECT PV FORECASTING ENGINE , 2021, The 12th Mediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion (MEDPOWER 2020).

[6]  Edwin K. P. Chong,et al.  Employing ARIMA models to improve wind power forecasts: A case study in ERCOT , 2016, 2016 North American Power Symposium (NAPS).

[7]  S. Karsoliya,et al.  Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture , 2012 .

[8]  Clifford W. Hansen,et al.  Pvlib Python: a Python Package for Modeling Solar Energy Systems , 2018, J. Open Source Softw..

[9]  V. Bǎdescu.  New formulae to evaluate the atmospheric layers of precipitable water and gases, applicable in solar radiation computing models , 1988 .

[10]  Daming Xu,et al.  Optimal sizing of standalone hybrid wind/PV power systems using genetic algorithms , 2005, Canadian Conference on Electrical and Computer Engineering, 2005..

[11]  Christian Koch,et al.  Building information modelling based building energy modelling: A review , 2019, Applied Energy.

[12]  H. A. Babri,et al.  General approximation theorem on feedforward networks , 1997, Proceedings of ICICS, 1997 International Conference on Information, Communications and Signal Processing. Theme: Trends in Information Systems Engineering and Wireless Multimedia Communications (Cat..

[13]  Christos-Nikolaos Anagnostopoulos,et al.  Data Based Stock Portfolio Construction Using Computational Intelligence , 2017, INSCI Workshops.

[14]  Juan C. Vasquez,et al.  Mixed-Integer-Linear-Programming-Based Energy Management System for Hybrid PV-Wind-Battery Microgrids: Modeling, Design, and Experimental Verification , 2017, IEEE Transactions on Power Electronics.

[15]  Thomas A. Adams,et al.  Modeling and Simulation of Energy Systems: A Review , 2018, Processes.

[16]  Erich Hau,et al.  Wind Turbines: Fundamentals, Technologies, Application, Economics , 1999 .

[17]  A. Betz.  Wind-energie und ihre ausnutzung durch windmühlen , 1926 .

[18]  S. Bayne,et al.  A Comparative Forecasting Analysis of ARIMA Model vs Random Forest Algorithm for A Case Study of Small-Scale Industrial Load , 2019 .

[19]  Daniel L. Marino,et al.  Deep neural networks for energy load forecasting , 2017, 2017 IEEE 26th International Symposium on Industrial Electronics (ISIE).

[20]  Ping-Huan Kuo,et al.  A High Precision Artificial Neural Networks Model for Short-Term Energy Load Forecasting , 2018 .

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