Journal of Renewable Energy and Smart Grid Technology

Artificial Neural Network Estimation of Daily Net Radiation Using Meteorological Data in Thailand

Chutimon Phoemwong — 2025-01-24

Net radiation is the difference between downward and upward radiation, considering both shortwave and longwave radiation. The net radiation controls the water cycle, plant photosynthesis, the earth’s climate changes, and the energy balance. In this paper, the Artificial Neural Network (ANN) model is developed for estimating daily net radiation from meteorological data that are based on maximum air temperature, minimum air temperature, daily relative humidity, and daily solar radiation. Net radiation and meteorological data collected for 7 years (2017-2023) from Chiang Mai meteorological station (CM: 18.77°N, 98.96°E), Ubon Ratchathani meteorological station (UB: 15.24°N, 105.02°E), Nakhon Pathom meteorological station (NP: 14.01°N, 99.96°E), and Songkhla meteorological station (SK: 7.41°N, 100.62°E) were used to train and test the model. The discrepancy between the net radiation estimated by the ANN and the measured net radiation was presented in terms of determination coefficient (R2), relative root mean square error (RMSE), and relative mean bias error (MBE). The model showed 0.98, 14.48%, and -2.17%, respectively. The result shows that the artificial neural network model is an accurate and easy option for estimating surface net radiation.

Energy Conservation in Palm Oil Mill by Installing Inverters for Motors

Kanitpong Chitsopon — 2025-03-14

Thailand is the third largest palm oil producer, accounting for 3.9% of global palm oil production, approximately 84.6%. Energy Efficiency Plan 2018 (EEP2018) aims to reduce energy consumption (Energy intensity) by 30% in 2037. This study investigates the conversational energy of palm oil mills (POM) by installing motor inverters to save energy and reduce the cost of electricity. The experiment was an energy consumption estimate pre- and post-installation of a motor inverter for Thongmongkol Palm Oil Industry Co., Ltd. That analysis used energy consumption and a payback period. The result was that Thongmongkol Palm Oil Industry Co., Ltd. used energy consumption of 4,923.09-6,364.54 MWh. The factory can generate energy for approximately 99% of the factory and purchases from the Electricity Generating Authority of Thailand (EGAT) approximately 1%. These are several motors of 229 units, a Power of 2,785.44 kW, and a horsepower of 3,742.97 HP. Station 4 is the primary process of the oil palm mill. Installing the motor inverter decreases the electricity power consumption by 10.43%. It can save energy costs of 51,091.35 Baht/year. Specific energy consumption (SEC) of 0.013 MWh/ton from 0.015-0.20 MWh/ton. It reduced SEC by 13.33-35.00%. The payback period for installing the motor inverter is 3.16 years.

Energy Development Assessment of Biomass Power Plant with Rice Husk Fuel Source in Thailand: Analysis of the Performance, LCOE and Carbon Emissions Reduction

Prachuab Peerapong — 2025-03-18

This study was conducted from the technical and financial from two rice husk power plants in Thailand. A proposed rice husk power plants use Rankine cycle power plant as a combustion configuration for electricity generation. The simulation in this research uses the System Advisor Model (SAM) to study the plant performance and financial analysis. This research investigates by using input technical plant data, and the financial variable assumptions. The results in this research can be concluded that the LCOE (the Levelized cost of electricity) of the electricity generation from the rice husk power plants at 6.62-6.63 ¢/kWh. The potentials of CO2 reduction of rice husk plants in this study are 38,319 tons/year for plant A, and 53,923 tons/year for plant B. These results can be used as a useful tool for developing strategic plans for biomass power plants in Thailand.

Selecting the Best Regression Model for Wind Power Prediction and Management for VPP

Subhajit Roy — 2025-05-21

Modern power systems increasingly rely on renewable energy, making effective prediction and management strategies essential, particularly for wind power, known for its variability and intermittency. This study delves into the application of machine learning models to predict wind power generation and optimize power management within virtual power plants (VPPs). It emphasizes key processes such as data preprocessing, feature engineering, and the use of advanced algorithms like Lasso Regression, Support Vector Machine (SVM) Regression, Adaptive Boosting (ADA Boost), and Random Forest Regression. The analysis focuses on critical meteorological and operational factors—wind speed, Low Voltage (LV) Active Power, and wind direction—that significantly impact wind energy output. The study addresses common data challenges, including missing values and feature scaling, to enhance model accuracy and reliability. By developing predictive models, the research enables efficient resource allocation, dynamic energy dispatch, and robust management strategies for VPPs. Through machine learning, the study proposes innovative solutions to improve grid stability, enhance renewable energy utilization, and promote sustainable energy systems. These insights pave the way for resilient and efficient integration of wind energy into modern power infrastructures.

Scientific Mapping of Renewable Energy in Rural Areas: A Bibliometric Analysis

Rogen A. Cagorol — 2025-06-19

This bibliometric study examines the research landscape on renewable energy in rural areas, analyzing publication trends, key contributors, thematic clusters, and emerging research directions from 1979-2025. Utilizing the Scopus database, VOSviewer, and R software's Bibliometrix package, this paper applies the PRISMA methodology to analyze 3,332 peer-reviewed publications. Findings revealed a consistent annual growth in research and considerable academic influence. India dominates global contributions, followed by China, the United States, and European countries, with institutions like the Indian Institute of Technology, North China Electric Power University, and Tsinghua University playing leading roles. Thematic analysis points to three dominant research clusters: climate change and biomass, rural energy access and electrification, and solar power and hybrid systems, evidencing an interdisciplinary effort with visions of technology, economics, and policy. New research areas such as hybrid renewable energy systems, digital infrastructure, and decentralized energy alternatives speak to increased interest in scalable and sustainable options for rural communities. Collaboration networks exhibit established research centers, but there are opportunities for further interdisciplinary and cross-border collaboration development, especially in developing countries. These results strongly impact policymakers, academics, and the industry in demanding a joined-up approach toward deepening rural electrification and boosting global energy transition objectives.

Bio-Based Composite from Sunflower Stalks for Building Wall Panels

Warangkana Nimcharoen — 2025-06-19

Burning sunflower stalks after harvesting could pose a significant environmental risk due to particulate matter 2.5 pollution. The use of low-cost recycled materials in building products is on trend. The objective of this study was to investigate a bio-composite made from sunflower stalks and sunflower bark using various ratios of natural latex as a binder and to compare the effects of hot ovens and hot compression. Three bio-composite-to-binder ratios of 1:4, 1:5, and 1:6 were compared. The physical, mechanical, thermal, and acoustic properties of the bio-composite were determined. The test box was used to evaluate the thermal performance of bio-composites. The bio-composites had a density similar to flat-pressed particleboards. The moisture content varied from 6.01 to 14.20%, with only the 1:5 and 1:6 sunflower stalk bio-composites by hot compression having a moisture content higher than 13%. Thickness swelling ranged from 5.63% to 12.03%. All composites had a fire resistance that passed the UL94HB standard, classified as at least flame retardant. As natural latex increases, the water absorption of sunflower stalks decreases while at the same time increasing fire resistance. The thermal conductivity coefficient ranged between 0.117 and 0.161 W/mK. The hot-compressed 1:6 sunflower bark bio-composite exhibited a room temperature profile that was similar to that of the MDF board. The hot compression method revealed better results in density, water absorption, flexural strength, and flexural modulus than the hot oven method.

Predicting the Temperature Increase Trend of a Generator Using RNN, GRU, and LSTM Algorithms at Nam Ngum 1 Hydropower Plant in Laos

Bounpone Thansouphanh — 2025-06-20

Synchronous generators are integral to the operation of hydropower plants. Stator faults, including short circuits, open circuits, and inter-turn faults, can cause severe performance issues and even catastrophic failures if not identified and mitigated promptly. Traditional generator monitoring methods such as periodic inspections and time-based maintenance often fail to detect subtle or evolving faults. This study proposes an advanced predictive maintenance approach utilizing deep learning techniques to monitor generator health at Nam Ngum-1 (NNG-1) Hydropower Plant in the Lao People’s Democratic Republic (PDR). Accurate temperature forecasting is vital for predictive maintenance, as excessive heat can lead to performance degradation and costly downtime. Using time-series data from the plant’s supervisory control and data acquisition (SCADA) system, including parameters such as power output, voltage, current, and cooling system temperatures, this research evaluates the models’ ability to capture temporal dependencies critical for precise trend prediction. Among the models tested, the results demonstrate that LSTM, with one hidden layer, achieved the highest accuracy based on MSE, RMSE, MAE, and R-squared, outperforming GRU, which had an R-squared of 98.60%, and RNN, which achieved 97.04%. When implemented with two hidden layers, LSTM maintained its superior performance with an R-squared of 98.34%, compared to GRU's 97.93% and RNN's 92.68%. These results demonstrate LSTM's exceptional capability in capturing both short- and long-term temperature dependencies, making it particularly suitable for predictive maintenance applications. The model's high accuracy in temperature forecasting enables early fault detection, helping to prevent performance degradation and reduce costly downtime in hydropower operations.