Data Analysis for Solar Energy Generation in a University Microgrid

Abstract

This paper presents a data acquisition process for solar energy generation and then analyzes the dynamics of its data stream, mainly employing open software solutions such as Python, MySQL, and R. For the sequence of hourly power generations during the period from January 2016 to March 2017, a variety of queries are issued to obtain the number of valid reports as well as the average, maximum, and total amount of electricity generation in 7 solar panels. The query result on all-time, monthly, and daily basis has found that the panel-by panel difference is not so significant in a university-scale microgrid, the maximum gap being 7.1% even in the exceptional case. In addition, for the time series of daily energy generations, we develop a neural network-based trace and prediction model. Due to the time lagging effect in forecasting, the average prediction error for the next hours or days reaches 27.6%. The data stream is still being accumulated and the accuracy will be enhanced by more intensive machine learning.

A survey of big data and machine learning

“…Whereas, the unstructured data is in unknown form/structure, and as the size of this data is huge, it poses several challenges in terms of its processing for extracting value out of it. Semi-structured data can contain both structured and unstructured forms of data [18].…”

“…Industries which uses large amounts of data have recognized the value of big data and ML. By working with big data and ML organizations can work efficiently and can gain advantage over competitors [18]. The applications of big data and ML are presented in the following subsections.…”

Asset management and maintenance: a smart grid perspective

“…The information provided covers not only interval energy usage, but also status, events and alarms. Even utilities in regions with a central MDMS deployment (e.g., a single MDMS implementation for the entire regulatory jurisdiction such as a state, province or country that provides a common data repository, bill determinant calculations and customer usage presentment for all utilities and customers in the jurisdiction) have benefited from the operational visibility and efficiencies achieved from their own smart metering infrastructure data [18]. One such benefit is the ability to monitor and act on health and tamper information reported by smart meters.…”

Analysing Tuberculosis Trends in South Asia

“…The parameters considered for analysis were namely (1) average (2) maximum and (3) total amount of electricity generated on daily and monthly basis. Prediction was performed after analysis using ANN model [10].…”