Journal of Renewable Energy and Smart Grid Technology

Sliding Window-Based Deep Learning Approach for Solar Power Forecasting in Malaysia Utility-Scale PV Systems

Thu, 04 Dec 2025 00:00:00 +0700

Accurate forecasting of solar power in utility-scale photovoltaic (USPV) systems is critical for grid stability but remains challenging due to meteorological variability and the large spatial scale of these systems. However, the choice of sliding window size in time-series forecasting remains underexplored. This study introduces a deep learning-based forecasting framework that systematically evaluates
the impact of sliding window size on forecasting accuracy using multivariate time-series data. The data collected from a 25 MWac USPV system in Malaysia between August 2022 and April 2023, comprises 5-minute interval measurements of solar irradiance, module temperature and solar power output. Multiple deep learning (DL) models, namely LSTM, CNN and GRU across window sizes ranging from 12 to 288 steps and forecasting horizons of 1 to 12 hours were investigated. Results show that a 144-step window consistently improves accuracy over conventional one-step input methods, with LSTM outperforming other models by achieving up to 23.1% RMSE reduction, 30.7% MAE reduction and a 8.6% increase in R² at 60 minutes forecasting horizon. This work emphasizes the importance of window size selection in optimizing forecasting accuracy for USPV systems and supporting renewable energy grid integration. By improving forecasting capabilities, this research is expected to provide critical insights to enhance renewable energy integration into the grid system.

Optimal Sizing of Stand-Alone Photovoltaic Systems using Meerkat Optimization Algorithm: A Cost-Based Performance Assessment

Wed, 17 Dec 2025 00:00:00 +0700

Stand-Alone Photovoltaic (SAPV) systems play a vital role in providing clean and reliable electricity for remote and off-grid communities where grid expansion is economically or technically unfeasible. Their economic feasibility and technical reliability, however, depend strongly on accurate component sizing and system configuration, which require advanced optimization techniques. In this study, the Meerkat Optimization Algorithm (MOA) is applied to optimize two SAPV configurations. System 1 integrates a photovoltaic array, battery storage, and a hybrid inverter, while System 2 consists of a photovoltaic array, battery storage, a solar inverter, and a charge controller. The optimization focuses on minimizing Life Cycle Cost (LCC) and Levelized Cost of Energy (LCOE), which are widely recognized as reliable indicators of long-term cost-effectiveness and financial viability. To validate the performance of MOA, its results are benchmarked against three well-established metaheuristic algorithms: Particle Swarm Optimization (PSO), Firefly Algorithm (FA), and Slime Mould Algorithm (SMA). Simulation results show that System 1 consistently achieves lower LCC and LCOE compared to System 2, primarily due to its reduced component count and simplified integration. Moreover, MOA demonstrates enhanced optimization performance by converging more rapidly and delivering more stable solutions across multiple independent runs. In contrast, PSO, FA, and SMA exhibit slower convergence and greater variability in outcomes. Importantly, the performance differences are statistically meaningful, as MOA achieved consistently lower mean values and smaller standard deviations. These findings highlight MOA as an effective and reliable optimization tool for SAPV systems and provide practical insights to support sustainable rural electrification planning.

Optimized Power Quality in Grid Systems Using PV-Based UPFC and Advanced ANN Control Approach

Wed, 24 Dec 2025 00:00:00 +0700

Nowadays, grid power losses and Power Quality (PQ) issues are inducing various problems in power systems, which need to be addressed and rectified for attaining enhanced and smooth functioning. These PQ issues are generated as a result of differing values between generated and load power, which further produces fluctuations within the power supply. Hence, to overcome these limitations, an innovative control approach is proposed for attaining optimum power flow by using a Unified Power Flow Controller (UPFC). The proposed UPFC is combined with an Artificial Neural Network (ANN) controller for improving the performance efficiency of the UPFC. The ANN controller-aided UPFC rectifies the PQ issues, including sag and swell. Additionally, to provide a consistent and unlimited power supply to the DC link, a photovoltaic (PV) system is incorporated with a single-switch boost-Cuk (SSBC) converter for boosting the PV power generation process. For attaining maximum power extraction and tracking maximum power, a new Pelican Optimized Recurrent Neural Network (RNN)-based Maximum Power Point Tracking (MPPT) technique is utilized. Furthermore, to validate the proposed model, MATLAB/Simulink is utilized and the obtained results depict improved PQ with reduced losses. Therefore, the overall system attains improved power quality, thereby, enhancing the power system functioning.

Control of Bi-directional Converter for charge-discharge battery using PI With Modified PSO

Thu, 26 Feb 2026 00:00:00 +0700

Increasing demand for renewable energy integration and efficient energy storage solutions have highlighted the critical role of battery. Batteries serve as essential components in energy systems, storing excess power for various applications, and backup power solution. However, achieving control for battery is challenging due to stability of charge and discharge, changing load condition, and battery state of charge fluctuation. To ensure efficiency of battery, accurate control of bi-directional converter is required. Bi-directional Converter facilitates the power flow required for this process but controlling battery charge discharge accurately. Among the many control methods, the Proportional-Integral (PI) controller is widely used for regulating the charge-discharge operation. However, selecting optimal PI parameters is non-trivial and greatly affects systems performance. This study proposes an enhanced control strategy for a bidirectional converter using PI controller optimized by a modified Particle swarm optimization (PSO) algorithm. The proposed method incorporates a dynamic re-randomized mechanism to overcome premature convergence in a standard PSO, improving its ability to escape local minima. Additionally, a penalty function is applied to restrict the search within a defined stable range for the controller gains. The performance of the system is evaluated based on the Integral of Time-Weighted Absolute Error (ITAE) criterion to minimize transient and steady-state errors. Simulation result using MATLAB/Simulink demonstrate that modified PSO-based PI controller significantly improves system performance-reducing overshoot, enchanting settling time, and maintaining stability under different operation modes (charge and discharge). This method offers a practical and efficient solution for optimizing converter control in battery-based energy storage systems.

Techno-Economic Feasibility of Pico-Hydropower in Southeast Asia: An Analysis of LCOE and Carbon Emission Reduction

Izzatie Akmal Zulkarnain, Mohd Farriz Basar, Kamaruzzaman Sopian — Thu, 26 Feb 2026 00:00:00 +0700

This study evaluates the techno-economic feasibility and carbon reduction potential of pico-hydropower in Southeast Asia, focusing on six representative countries: Indonesia, Malaysia, the Philippines, Vietnam, Laos, and Myanmar. Using a Levelized Cost of Electricity (LCOE) framework, the analysis demonstrates that pico-hydro systems can deliver electricity at costs between 0.04 and 0.11 USD/kWh, significantly lower than diesel-based mini-grids (0.25-0.60 USD/kWh) and comparable to solar PV. Sensitivity analysis indicates that discount rate and capacity factor are the most influential variables affecting LCOE, while capital expenditure plays a moderate role. Environmental assessment shows that a typical 5 kW pico-hydro system operating at a 60% capacity factor can displace 23-27tCO₂ annually if replacing diesel generation. At scale, deployment of 10,000 such systems across Southeast Asia could avoid more than 250,000tCO₂ annually, contributing to member states’ Nationally Determined Contributions under the Paris Agreement. Despite these advantages, barriers to widespread adoption include hydrological variability, financing constraints, inadequate policy frameworks, and limited technical capacity at the community level. Opportunities lie in hybridization with solar PV, carbon finance revenues, and integration into rural development strategies. The findings underscore pico-hydro’s role as an underutilized but highly promising option for decentralized electrification and climate mitigation in Southeast Asia. Policy support, concessional financing, and capacity-building are essential to unlock its full potential and ensure long-term sustainability. Overall, this study highlights the strategic role of pico-hydro in advancing affordable, low-carbon energy transitions for rural Southeast Asia and offers evidence for its inclusion in regional renewable energy planning.