Big Data Techniques For Supporting Accurate Predictions of Energy Production From Renewable Sources

Abstract

Predicting the output power of renewable energy production plants distributed on a wide territory is a really valuable goal, both for marketing and energy management purposes. Vi-POC (Virtual Power Operating Center) project aims at designing and implementing a prototype which is able to achieve this goal. Due to the heterogeneity and the high volume of data, it is necessary to exploit suitable Big Data analysis techniques in order to perform a quick and secure access to data that cannot be obtained with traditional approaches for data management. In this paper, we describe Vi-POC -a distributed system for storing huge amounts of data, gathered from energy production plants and weather prediction services. We use HBase over Hadoop framework on a cluster of commodity servers in order to provide a system that can be used as a basis for running machine learning algorithms. Indeed, we perform one-day ahead forecast of PV energy production based on Artificial Neural Networks in two learning settings, that is, structured and nonstructured output prediction. Preliminary experimental results confirm the validity of the approach, also when compared with a baseline approach.

Accurate Demand Forecasting: A Flexible and Balanced Electric Power Production Big Data Virtualization Based on Photovoltaic Power Plant

“…In today's business environment, such data require real-time-based analysis, as the old data often do not reflect current situations. There are some research papers that deal with big data for PV operation and maintenance [23][24][25][26], PV-battery operation optimization [27,28], and image processing [29,30], processes that usually generate a huge volume of data. The key role of [24] is to provide an idea for the infrastructure that manages the big data generated from PV systems.…”

Comparative Analysis of Selected Open-Source Solutions for Traffic Balancing in Server Infrastructures Providing WWW Service

“…For this task, unsupervised data clustering and frequent pattern search analysis in energy time series and Bayesian network forecasting were used to forecast energy consumption. In contrast, a distributed Vi-POC system was proposed in [18] to store massive amounts of data collected from energy production plants and weather forecasting services. HBase over Hadoop framework was used on a cluster of commodity servers in order to provide a system that can be used as a basis for running machinelearning algorithms.…”

Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump System

“…Equations (8) and (9) complete the step size update by comparing it with the ideal step size. Ideally, there will be no positive or negative correlations in successive evolutionary directions due to too short or too long steps.…”

“…Esen et al used adaptive neurofuzzy inference system and artificial neural network to predict the performance of ground source heat pump system, which proved that adaptive neuro-fuzzy system has good applicability in quantitative modeling of ground source heat pump system [7]. Ceci et al used machine learning algorithms and big data technology to predict the output power of renewable energy production systems, and realized one-day forecast for photovoltaic energy systems [8]. Zhuang et al adopted a datamining based method to accurately predict the heat transfer performance of ground heat exchangers in ground-source heat pump coupling systems with support vector machine and M5 model tree technology [9].…”