The forecasting of solar energy based on Machine Learning

Solar energy, one of many types of renewable energy, is considered to be an excellent alternative to non-renewable energy sources. Its popularity is increasing rapidly, especially because fuel energy consumes and depletes finite natural resources, polluting the environment, whereas solar energy is low- cost and clean. To produce a reliable supply of energy, however, solar energy must also be consistent. The energy we derive from a photovoltaic (PV) array is dependent on changeable factors such as sunlight, positioning of the array, covered area, and status of the solar cell. Every change adds potential for the creation of error in the array. Therefore, thorough research and a protocol for fast, efficient location and correction of all kinds of errors must be an urgent priority for researchers.For this project we used machine learning (ML) with voltage and current sensors to detect, localize and classify common faults including open circuit, short circuit, and hot-spot. Using the proposed algorithm, we have improved the accuracy of fault detection, classification and localization to 100%. Further, the proposed method can execute all three tasks (detection, classification, and localization) simultaneously.

Download Full-text

Global solar radiation modeling using different machine learning and empirical models in Northeast China

10.21203/rs.3.rs-422151/v1 ◽

2021 ◽

Author(s):

Yue Jia ◽

Yongjun Su ◽

Fengchun Wang ◽

Pengcheng Li ◽

Shuyi Huo

Keyword(s):

Machine Learning ◽

Solar Radiation ◽

Solar Energy ◽

Northeast China ◽

Sunshine Duration ◽

Meteorological Data ◽

Global Solar Radiation ◽

Empirical Models ◽

Learning Models ◽

Machine Learning Models

Abstract Reliable global solar radiation (Rs) information is crucial for the design and management of solar energy systems for agricultural and industrial production. However, Rs measurements are unavailable in many regions of the world, which impedes the development and application of solar energy. To accurately estimate Rs, this study developed a novel machine learning model, called a Gaussian exponential model (GEM), for daily global Rs estimation. The GEM was compared with four other machine learning models and two empirical models to assess its applicability using daily meteorological data from 1997–2016 from four stations in Northeast China. The results showed that the GEM with complete inputs had the best performance. Machine learning models provided better estimates than empirical models when trained by the same input data. Sunshine duration was the most effective factor determining the accuracy of the machine learning models. Overall, the GEM with complete inputs had the highest accuracy and is recommended for modeling daily Rs in Northeast China.

Download Full-text

Design and analysis of an off-grid PV plant for higher utilization efficiency in the field of pharmaceutical industry considering global pandemic state .

AIUB Journal of Science and Engineering (AJSE) ◽

10.53799/ajse.v20i1.144 ◽

2021 ◽

Vol 20 (1) ◽

pp. 47-58

Author(s):

A.B.M. Khalid Hassan ◽

Kazi Firoz Ahmed

Keyword(s):

Machine Learning ◽

Solar Energy ◽

Solar Power ◽

Machine Learning Algorithms ◽

Energy Utilization ◽

Utilization Efficiency ◽

Automation System ◽

Solar Pv ◽

Data Logging ◽

Solar Energy Utilization

According to the concern of WHO the less association of people in an office may restrict the likelihood of spreading this COVID-19 infection. And it applies to all kinds of organizations. On the other hand, the pharmaceutical companies are working hard to maintain uninterrupted production of vaccine and medicines. This paper focuses on the main layer which is the power system management and its utilization through the less involvement of any individual. Automation and controlling the system remotely can be a good solution. In the design process the FDA proposed structure for the Pharmaceuticals needs to be maintained as well. One of the significant necessities is most of the energy should come from environment friendly system and in Bangladesh sunlight-based energy is the best solution right now. Solar energy utilization efficiency can be increased using the data logging system and machine learning algorithms from that archived data. In this paper, a SCADA operated Off-Grid Solar PV Automation System has been proposed to increase the utilization efficiency. To predict solar power availability over time and perform efficient energy trafficking, the automation system will analyze previous data and perform situational awareness operations for uninterrupted solar power generation. The proposed automation system has been designed focusing on pharmaceutical manufacturing utilities. A comprehensive analysis of the proposed automation system for pharmaceuticals industry applications has also been presented in this paper. The continuous monitoring system for this Off-Grid Solar PV power generating unit preserves multiple data entries, which increases with time and subjected to energy trafficking. And this energy trafficking based on machine learning increases the overall solar energy utilization efficiency.

Download Full-text

Recommendation and Prediction of Solar energy consumption for smart homes using machine learning algorithms

10.1109/aimv53313.2021.9670909 ◽

2021 ◽

Author(s):

Anish Dhage ◽

Apoorv Kakade ◽

Gautam Nahar ◽

Mayuresh Pingale ◽

Sheetal Sonawane ◽

...

Keyword(s):

Machine Learning ◽

Energy Consumption ◽

Solar Energy ◽

Learning Algorithms ◽

Smart Homes ◽

Machine Learning Algorithms

Download Full-text

Predictive Modeling for Rooftop Solar Energy Throughput: A Machine Learning-Based Optimization for Building Energy Demand Scheduling

Journal of Energy Resources Technology ◽

10.1115/1.4050844 ◽

2021 ◽

pp. 1-15

Author(s):

Mahdi Houchati ◽

Monem H. Beitelmal ◽

Marwan Khraisheh

Keyword(s):

Machine Learning ◽

Solar Energy ◽

Energy Demand ◽

Alternative Energy ◽

Average Power ◽

Building Energy ◽

Prediction Algorithm ◽

Support Vector ◽

Solar Photovoltaic ◽

Photovoltaic Array

Abstract The intermittent and fluctuating nature of solar energy is the biggest challenge facing its widespread utilization. Implementing onsite photovoltaic systems as alternative energy sources have established the need for reliable forecasting procedures to improve scheduling and demand management. This paper presents a solar energy prediction algorithm to optimize the available solar energy resource and manage the demand-side accordingly. The algorithm utilizes Support Vector Regression (SVR), a machine learning technique, validated using 1-year energy consumption data collected from an office building instrumented as an experimental testbed facility. Power meters and temperature sensors collect the building's internal climate and energy data, while a solar photovoltaic array and a weather station provide the external relevant data. The forecasting method uses the average power output of k-similar days as an added input to the SVR model to enhance its performance. The day-ahead prediction results show that this additional input contributes to higher forecasting efficiency, especially in the hot climate regions, where sunny weather conditions prevail throughout the year. The photovoltaic output prediction accuracy for the sunny days is above 90%, which offers possibilities for optimized scheduling and leading to smart building energy management. Finally, this paper also proposes a setpoint optimization algorithm for the building Air Conditioning system to minimize the difference between the building energy load and the generated solar photovoltaic power. Using 24 °C as the upper setpoint temperature limit reduces the energy demand (consumption) by up to 29% and the associated reduction in CO2 emissions.

Download Full-text