Machine Learning Platform for Profiling and Forecasting at Microgrid Level

Abstract

The shift towards distributed generation and microgrids has renewed the interest in forecasting algorithms and methods, which need to take into account the advances in information, metering and control technologies in order to address the challenges of forecasting problems. Technologies such as machine learning have been proven useful for short-term electricity load forecasting, especially for microgrids, as they can also take into account several types of historical data and can adapt to changes often encountered in small-scale systems and on a short time scale. In this paper, we present a flexible and easily customized modular toolbox, called Divinus, for electricity use profiling and forecasting in microgrids. Divinus may support a variety of machine learning algorithms for forecasting and profiling that can be used independently or combined. For demonstration purposes, we have implemented Self-Organizing Maps for profiling and k-Neighbors for forecasting. The testing of the platform was based on electricity consumption data of the Euripus campus of the National and Kapodistrian University of Athens in Evia, Greece, from January 2010 till March 2018. The tests that have been carried out so far show that the platform can be easily customized and the algorithms examined yield high accuracy and acceptable mean errors for the case of a university campus energy profile.

Reconfiguration and Analysis of PV Array based on Particle Swarm Optimization of Solar Plant

“…A genetic algorithm (GA) has been in use for solar systems for reconfiguration under partial shading conditions. With the help of the GA, a great amount of power from the PV array has been generated [17] but this method also has drawbacks, including bad convergence, large computational steps, and requiring wide search space. In [16] the impact of stochastic PV generation on the dynamic stability of grid-connected PV systems is described using a probabilistic small-signal analysis approach.…”

Using the time varying Kalman filter for prediction of Covid-19 cases in Latvia and Greece

“…On the other hand, intelligent Decision Support Systems (i-DSS), equipped with artificial intelligence (AI) algorithm play an increasingly important role in the automated monitoring, control and operation of various systems [8] and enable the modeling, forecasting and optimization of processes and systems. Such an i-DSS has been developed [4] as a modular and scalable platform to make hourly forecasts at an electrical microgrid level, using and combining various types of historical and real-time data. Its architecture enables implementation, testing, combination and comparison of a number of forecasting and clustering algorithms in order to obtain the optimum forecast for the problem studied.…”

“…The technology required to develop such a platform, collect data, model them and offer decision support already exists in a variety of forms. An exhaustive literature review on the topic is beyond the scope of this work, however decision support platforms with IoT powered big data analytics and forecasting tools have already been designed to address other needs [4][5][6][7][8][9] and in this work we propose that they are redesigned to address the CoVID-19 related objective.…”

Health Monitoring and Fault Detection in Photovoltaic Systems in Central Greece Using Artificial Neural Networks

“…The multiple forms of machine learning (ML) are prominent in these techniques. ML may be broadly defined as the practice of using algorithms to parse data, learn from them, and then make a determination or prediction thereof [8]. Neural networks (NN) and statistical methods are the most frequent tool categories, applied in fault detection in the area of photovoltaic energy systems.…”