Forecasting Solar Home System Customers’ Electricity Usage with a 3D Convolutional Neural Network to Improve Energy Access

Abstract

Off-grid technologies, such as solar home systems (SHS), offer the opportunity to alleviate global energy poverty, providing a cost-effective alternative to an electricity grid connection. However, there is a paucity of high-quality SHS electricity usage data and thus a limited understanding of consumers’ past and future usage patterns. This study addresses this gap by providing a rare large-scale analysis of real-time energy consumption data for SHS customers (n = 63,299) in Rwanda. Our results show that 70% of SHS users’ electricity usage decreased a year after their SHS was installed. This paper is novel in its application of a three-dimensional convolutional neural network (CNN) architecture for electricity load forecasting using time series data. It also marks the first time a CNN was used to predict SHS customers’ electricity consumption. The model forecasts individual households’ usage 24 h and seven days ahead, as well as an average week across the next three months. The last scenario derived the best performance with a mean squared error of 0.369. SHS companies could use these predictions to offer a tailored service to customers, including providing feedback information on their likely future usage and expenditure. The CNN could also aid load balancing for SHS based microgrids.

Holistic Evaluation of Demand Response Events in Real Pilot Sites: From Baseline Calculation to Evaluation of Key Performance Indicators

“…As the training progresses, accuracy improves steadily, reaching 40% to 60% and loss is reduced (around 0.5 to 1.5) in mid-epochs of 6-15. In the later epochs (15)(16)(17)(18)(19)(20), accuracy continues to increase reaching 60% to 80%, while loss further decreases, leveling off in the range of 0.3 to 1.0. [21].For the Cypriot pilot site, we had at our disposal data points of 15 min of granularity for a total of 566 days, resulting in 54,336 energy consumption data points as historical data.…”

“…On the other hand, in [16] a method of calculating the baseline is presented based on clustering nonindustrial consumers according to the size and demand estimation. A three-dimensional convolutional neural network (CNN) is used in [17] for electricity load forecasting using time series data. As is shown, various methods are used in the literature for calculating the baseline.…”

A Machine Learning Frontier for Predicting LCOE of Photovoltaic System Economics

“…[3,4] To address these escalating energy needs, solar energy presents a viable solution, offering the potential to profoundly improve the lives of communities worldwide. [5][6][7] Photovoltaic (PV) systems, which convert sunlight directly into electricity, are a means to harness the sun's renewable, sustainable, and low-carbon energy source. [8] These systems often achieve high efficiency in their conversion process.…”

A Machine Learning Framework for Predicting the LCOE of PV Systems using Demographic, Energy and Policy Data

“…In fact, most of the world's energy is consumed by China (6,875 B kWh), the US (3,989 B kWh) and India (1,229 B kWh) [3], [4]. Meeting these escalating energy needs can be achieved using solar energy, which has the potential to improve the lives of communities profoundly worldwide [5], [6]. Harnessing the Sun's renewable, sustainable and lowcarbon energy source can be achieved using photovoltaic (PV) systems, which convert sunlight into electricity and can often do so with high efficiency [7], [8].…”