Rooftop solar photovoltaic (PV) systems operate under weather conditions that differ significantly from Standard Test Conditions (STC), particularly in tropical regions. This study examines the impact of climatic factors on rooftop PV power generation in the Kurunegala district of Sri Lanka using measured power output and meteorological data. Three grid-connected PV systems with a capacity of 5 kW were monitored over six months, with hourly power output and inverter temperature recorded during the daytime. Corresponding weather data, including solar irradiance, ambient temperature, relative humidity, and cloud cover, were used in this research to identify their impact on power generation. In addition, monthly power generation data over 30 months were analyzed to assess seasonal trends. The results confirm that solar irradiance is the primary driver of PV power generation, while ambient temperature, inverter temperature, and relative humidity have notable secondary effects. Several deep learning and conventional machine learning techniques were applied to develop power prediction models based on the corresponding weather conditions. In addition to individual training, the models were trained using ensemble techniques of bagging, boosting, stacking, and voting. A comparative assessment of the model performance shows that ensemble learning approaches outperform individual machine learning techniques for limited, high-quality datasets. The CatBoost model that was trained using the ensemble technique of boosting achieved the highest predictive accuracy, with the highest coefficient of determination (R2 = 0.94) and the lowest Mean Squared Error (MSE = 0.09). The developed models effectively capture diurnal and short-term variations, demonstrating strong potential for reliable rooftop PV forecasting and grid integration in tropical climates.

[This corrects the article DOI: 10.1371/journal.pone.0344167.].

IntroductionUrban wetlands are considered an important nature-based solution to mitigate flood impacts in built-up areas like Colombo, Sri Lanka, due to rapid urbanization and intensifying rainfall events. Wetlands within the Colombo metropolitan region offer significant potential as nature-based solutions for flood mitigation; however, their hydrological functioning remains insufficiently quantified at high temporal resolution.MethodsThis study analyzes hourly water-level data from multiple locations over multiple years within the Colombo wetland system to investigate water-level dynamics, providing a comprehensive high-resolution analysis that remains limited in the existing literature. Data preprocessing included rigorous missing-value imputation using comparative statistical methods, with seasonal decomposition selected as the most consistent approach.Results and discussionTemporal variability was examined using correlation analysis, time-series and seasonal analyses, and continuous wavelet transform with Morlet wavelets, revealing a strong positive correlation between Kirimandala Street and Janakala Kendraya (r = 0.98) and a weak negative correlation between Diyasaru Park and Thalangama Lake (r = −0.14); time-series analysis indicated increasing trends at seven locations, no significant trends at Janakala Kendraya and Kaduwela, and a decreasing trend at Ewerihena; seasonal analysis showed a clear weekly periodicity across all locations. The wavelet results reveal dominant event-driven variability at longer time scales, reflecting cumulative rainfall effects, wetland storage, and delayed drainage processes, while short-period oscillations were comparatively weak and sporadic. Spatial heterogeneity in responses highlights the influence of wetland connectivity and surrounding urbanization on flood regulation capacity. The findings demonstrate that Colombo’s wetlands play a critical role in moderating flood dynamics and underscore the importance of conserving and integrating wetland systems into urban flood management strategies.

Wind power is becoming a cornerstone of renewable energy, providing a sustainable solution for electricity generation worldwide. Accurate prediction models are essential for maximizing energy output, ensuring grid stability, and seamlessly integrating renewable energy into power systems. This research focus on the Musalpetti Wind Power (Pvt) Ltd wind farm in Kalpitiya, Sri Lanka, for developing the wind power generation models. The total generated power is the dependent variable, while the average wind speed (m/s) and average ambient temperature (oC) are the independent variables. By employing advanced predictive modelling techniques tailored to local climate conditions and turbine specifications, the study aims to perform accurate wind power prediction with R-2 = 0.940. The findings demonstrate the potential of these refined models to enhance operational efficiency and support Sri Lanka's renewable energy ambitions. Ultimately, this study highlights the importance of localized approaches in optimizing wind energy production and driving the global shift towards sustainable energy solutions.

In this study, a machine learning-based predictive model was developed for the Musa petti Wind Farm in Sri Lanka to address the need for localized forecasting solutions. Using data on wind speed, air temperature, nacelle position, and actual power, lagged features were generated to capture temporal dependencies. Among 24 evaluated models, the ensemble bagging approach achieved the best performance, with R2 values of 0.89 at 0 min and 0.75 at 60 min. Shapley Additive exPlanations (SHAP) analysis revealed that while wind speed is the primary driver for short-term predictions, air temperature and nacelle position become more influential at longer forecasting horizons. These findings underscore the reliability of short-term predictions and the potential benefits of integrating hybrid AI and probabilistic models for extended forecasts. Our work contributes a robust and explainable framework to support Sri Lanka’s renewable energy transition, and future research will focus on real-time deployment and uncertainty quantification.

This paper presents the application of regression trees as a versatile alternative to other machine learning and statistical modelling techniques to forecast the power generation at five renewable power plants: one large hydropower plant, two mini hydropower plants, and two wind farms in Sri Lanka. The prediction models for each power station were developed by varying the depth of the regression tree. The regression tree model with the lowest depth that forecasts the output (power) in terms of all the predictor variables was selected for each power station and the accuracy of the models was evaluated by means of the Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R2). According to the degree of the above performance indicators, i.e. very low values of MAE, MAPE, and RMSE supplemented by R2 of 0.95 or more, the regression tree method proved to be a convenient forecasting technique to predict the power generation at both hydro and wind power plants. Further, it could be found that a good correlation between the input and output variables paves the way for a smaller depth in the regression tree. Moreover, regression trees presented here could accurately identify the relationship between the power generated and the most influential weather factors, without being affected by potential outliers or missing values while managing collinearity too. Extension of this study would enable to generalize the prediction of renewable power generation based on the regression tree method, leading towards minimizing the use of fossil fuel.

Passive UHF RFID transponders are usually employed with balanced antennas optimized to match the complex conjugate of the chip impedance. Since the degree of impedance matching between the antenna and the chip determines the system performance, it is essential to validate the performance of the transponder through prototype measurements. In this paper, the design of a chip -based passive UHF RFID sensor transponder antenna and the measurement of its impedance is presented. Simulations were carried out in ANSYS High Frequency Structure Simulator (HFSS) and the input impedance of the antenna was matched with the conjugate impedance of the commercial RFID chip, Farsens Rocky100. A prototype of the antenna was fabricated and its input impedance was measured using image theory. The simulated and measured results are in good agreement, thus validating the antenna's performance. The S-11 < - 10 dB bandwidth of the antenna covers the entire UHF frequency band. Accordingly, the proposed antenna can be operated in any region within the aforementioned frequency band for RFID applications.

In this paper, a miniaturized printed log-periodic dipole array (PLPDA) with a bandwidth of 1.3 – 6.0 GHz is presented. The miniaturization is achieved through m-segment fractal geometry. The m-segment PLPDA antennas presented in the paper has achieved a 24.32% width reduction when compared to the conventional PLPDA. Due to the low fabrication complexity of the m-segment fractal, and also due to the minimal effect it has on the bandwidth and gain performance of the antenna, this technique is an ideal choice for LPDA miniaturization.

The demand of multi-functional antennas with achievable performance from a single device is increasing dramatically. At the same, quad-band rectangular patch antennas are essential for numerous mm-wave applications. This study aims to use a binary-coded GA to enhance the multi-functionality of a microstrip antenna for mm-wave wireless communication. The patch surface was optimized by gridding it into 6 × 6 tiny rectangular cells and assigning conducting and non-conducting features to them. The proposed method has iteratively modeled the antenna using a Ansys HFSS and MATLAB. The reference antenna model and optimized antenna were presented and compared. The optimized antenna has resonated at 28.3, 38.1, 46.6, and 60.0 GHz center frequency. The antenna realized a peak broadside directivity of 7.8 dB, 8.8 dB, 7.3 dB, and 7.1dB with total operating bandwidth of 11.5 GHz, respectively. The simulation results of the optimized antenna were compared with references and the proposed antenna outperform in all four distinct frequencies.

Antennas with multifunctional capabilities integrated into a single device that demonstrates a high performance are in demand, and microstrip antennas with quadband coverage are very useful for a wide range of mm-wave applications. Antennas and propagation at mm-wave frequencies, on the other hand, poses several challenges which can be overcome by applying performance enhancement techniques to meet design objectives. This article presents the use of a binary-coded genetic algorithm for developing an improved quadband mm-wave microstrip patch antenna. The patch shape was optimized by dividing a conducting surface into 6 × 6 tiny rectangular blocks. The algorithm generated the solution space by introducing conducting and nonconducting features for each radiating cell on the patch surface and then greedily searched for the best-fitted individual based on the cost function. With the combination of High-Frequency Structure Simulator (HFSS) and MATLAB, candidate antennas were iteratively modeled by applying the suggested algorithm. The optimized antenna resonated at four frequencies centered at 28.3 GHz, 38.1 GHz, 46.6 GHz, and 60.0 GHz. The antenna realized a peak broadside directivity of 7.8 dB, 8.8 dB, 7.3 dB, and 7.1 dB, respectively, with a total operating bandwidth of 11.5 GHz. The research findings were compared with related works presented in the literature and found that the optimized antenna outperformed them in terms of bandwidth, directivity, and efficiency.

Currently, the inspection and verification of vehicle-related information are done by police inspectors using camera-based systems or manually.Though integrating video technology is more advantageous than manual operation, they do not perform accurately due to bad weather or driving styles.This paper presents the design of a compact, durable, battery-free, UHF RFID tag with enough memory to carry necessary information for automatic identification of traffic law enforcement applications.The vehicle owner can also be alerted when the tag is detected due to the visual indication facility.This tag's novel feature includes adapting a modified T-match structure to match the highly capacitive impedance of the chosen RFID sensor chip, i.e., Farsens Rocky100.In contrast to existing designs, the proposed tag contains no extra lumped components that necessitate an external impedance matching circuit.Instead, the input impedance was matched using an advanced T-match topology and by optimizing the antenna's geometrical features.Simulations were done in Ansys HFSS (High-Frequency Structure Simulator) whereas the dimensions of all the printed elements were fine-tuned using parametric optimization.The tag was fabricated on a low-cost FR4 substrate and measured.The tag with an overall size of 110 × 25 × 2.4 mm 3 can be detected by a conventional UHF RFID reader within a range of about 0.2 m-1 m.Due to the loop configuration, the tag exhibits a confined detection range while operating well within short ranges.

This paper presents the design of a battery-free chip-based UHF RFID sensor tag appropriate for temperature measurement inside a poultry egg incubator. The tag employs an EM4325 UHF RFID sensor chip that has a built-in temperature sensor. The antenna was connected to the chip via an internal impedance-matching circuitry and they were etched on an FR4 substrate. Tuning the antenna configuration to match the impedance of the chip and miniaturization of the tag size were performed using parametric optimization. Simulations were performed in ANSYS High-Frequency Structure Simulator (HFSS). The RFID tag, with a compact size of 75 × 20 × 1.6 mm 3 , performs well in terms of impedance matching, bandwidth, and radiation efficiency. Further, the proposed UHF RFID sensor tag demonstrates both far-field and near-field characteristics due to the antenna's dipole topology and loop structure respectively.

The necessity for multi-functional antennas with achievable performance from a single device is increasing dramatically.At the same, dual-band rectangular microstrip antennas are essential for a varieties of applications in mm-wave communication.This study aims to use a genetic algorithm to enhance the operating bandwidth of a dualband mm-wave microstrip antenna for wireless communication with binary-coded scheme.The patch surface was optimized by gridding it into 10X10 tiny rectangular blocks and designing them as non-conducting and conducting features to them.The proposed method has iteratively modeled the antenna using a Ansys HFSS and MATLAB to identify best fitted antenna.The optimized antenna has resonated at 39.1 GHz center frequency with 7.6 dB peak gain with 1.6 GHz bandwidth and at 50.2 GHz center frequency with 7.3 dB peak gain and 3.3 GHz bandwidth.The antenna's total efficiency is 71.4 % at 39.1 GHz and 92.8 % at 50.2 GHz.

This paper presents the design of a novel fabric-based multi-band microstrip antenna in mm-wave frequencies for wearable applications. The reference patch antenna was etched on a flexible polytetrafluoroethylene (PTFE) fabric substrate with an overall dimension of 18 mm × 18 mm × 0.6 mm and optimized the patch geometry using a binary-coded genetic algorithm. The algorithm iteratively creates a new shape of the path surface, evaluates the cost function, and returns the best-fitted geometry based on the formulated fitness function. The free space and on-body simulation of the best-fitted antenna performance parameter was investigated and analyzed. In free space, the proposed antenna is resonant at five distinct frequencies: 27.8 GHz, 30.3 GHz, 40.1 GHz, 47.2 GHz, and 56.7 GHz. The antenna achieves a wide bandwidth of 0.69, 2.32, 2.22, 1.76, and 8.11 GHz and an improved broadside directivity of 10.3, 8.5, 7.8, 9.6, and 8.9 dB in free space, respectively. For on-body analysis, the antenna was simulated using a three-layer human body phantom model at three distinct distances. The gain and radiation efficiency were significantly reduced when the antenna was close to the phantom model and gradually enhanced as the gap increased. Moreover, the antenna performances were evaluated and compared by using four additional fabric substrates. Because of its excellent on-body performance with flexible textile-based substrates, the optimized antenna is a suitable candidate for multi-band body-centric communications.

This paper presents the development of a wind power forecasting model based on gene expression programming (GEP) for one of the major wind farms in Sri Lanka, Pawan Danavi. With the ever-increasing demand for renewable power generation, Sri Lanka has started harnessing electricity from wind power. Though the initial establishment cost of wind farms is high, the analyses clearly showcased the economic sustainability of wind power generation in long term. In this context, forecasting the wind power generation at Sri Lankan wind farms is important in many ways. However, limited research has been carried out in Sri Lanka to predict the wind power generation against the changing climate. Therefore, to overcome this research gap, a model was developed to forecast wind power generation against two climatic factors, viz. on-site wind speed and ambient temperature. The results showcased the robustness and accuracy of the proposed GEP-based forecasting model (with R2 = 0.92, index of agreement = 0.98, and RMSE = 259 kW). Moreover, the results of the study were compared against three different forecasting models and found comparable in terms of the model accuracy. The GEP-based model is advantageous over machine learning techniques due to its capability in deriving a mathematical expression. As an acceptable relationship was found between wind power generation and climatic factors, the proposed model facilitates the future projection of wind power generations with forecasted climatic factors. Though the application of GEP in the field of wind power generation is reported in a few research publications, this is the first research in which GEP is employed to model the power generation with respect to weather indices. The proposed prediction model is advantageous than machine learning models as the relationship between the wind power and the weather indices can be expressed.

This paper presents the development of wind energy prediction models for the Nala Danavi wind farm in Sri Lanka by using machine learning and statistical techniques. Wind speed and ambient temperature were used as the input variables in modeling while the daily wind energy production was the output variable. Correlation between the wind energy and each weather index was investigated using the Pearson's and Spearman's correlation coefficients and it was found that daily wind energy output is positively correlated with both daily averaged input variables. Statistical prediction models of Multiple Linear Regression (MLR) and Power Regression (PR) and the machine learning techniques of Support Vector Regression (SVR), Gaussian Process Regression (GPR), Feed Forward Backpropagation Neural Network (FFBPNN), Cascade-Forward Backpropagation Neural Network (CFBPNN) and Recurrent Neural Network (RNN) were developed. The accuracy of the prediction models was measured in terms of the coefficient of determination, Bias, Percent Root mean square error (RMSE)Bias, and Nash-Sutcliffe Efficiency (NSE). Results of the performance evaluation indicated that all the models are highly accurate while the FFBPNN-based model demonstrates outstanding performance with very low error. Such prediction models are highly important for a country like Sri Lanka whose power generation mainly depends on imported coal followed by hydropower and expanding the on-shore and off-shore wind farms gradually in many potential locations scattered over the country.

This paper presents a low-profile, wideband antenna that can operate in four millimeter-wave frequency bands for 5G communication. The proposed antenna has composite geometry with extended blocks from a simple rectangular patch. Here the full ground plane is used to avoid the radiation losses by back lobes and to enhance the antenna performance. The proposed radiating element covers the wideband from 23.812 GHz to 48.253 GHz enclosing operating frequencies k band (26 GHz-F1) and Ka-band (28 GHz-F2, 32 GHz-F3, and 39 GHz-F4). The gains achieved in the designed single element antenna are 5.46 dBi, 5.6 dBi, 6.48 dBi, and 5.56 dBi respectively. Whereas the total efficiencies are 95.33%, 97.23%, 97.75%, and 97.9% for the respective operating frequencies. The proposed antenna is analyzed for Multiple Input Multiple Output (MIMO) communication, providing the isolation value greater than 20 dB. The diversity gain, Envelope Correlation Coefficient, and isolation are all well within their respective limits making the proposed antenna suitable for MIMO communications. Here, to check the versatility of the antenna design different configurations such as 2 × 2, 1 × 2, and port positionings are simulated. Furthermore, the designed single element and MIMO antenna is placed on the vehicle and the far-field results are analyzed.

This research introduces machine learning models using the Gaussian Process Regression (GPR) depicting the association between paddy yield and weather in Sri Lanka. All major regions in the island with most contribution to the total paddy production were considered in this research. The climatic factors of rainfall, relative humidity, minimum temperature, maximum temperature, average wind speed, evaporation, and sunshine hours were considered as input (independent) variables, while the paddy yield was the output (dependent) variable. The collinearity within each pair of independent and dependent variables was determined using Spearman’s and Pearson’s correlation coefficients. Data sets corresponding to the two main annual paddy cultivation seasons since 2009 were trained in MATLAB to develop crop-weather models. The most appropriate Kernel function was chosen from among four types of Kernels viz. Rational Quadratic, Exponential, Squared Exponential, and Matern 5/2 based on their degree of coherence in modeling. This approach exploits the full potential of GPR in developing highly accurate crop-weather models. The performance of the crop-weather models was measured by the Correlation Coefficient, Mean Absolute Percentage Error, Mean Squared Error, Root Mean Squared Error Ratio, Nash Number and the BIAS. All the GPR-based models proposed in this paper are highly accurate in terms of the aforementioned evaluation metrics. Accordingly, when the climatic data are known or projected, the paddy yield and thereby the harvest of Sri Lanka can be predicted precisely by using the proposed crop-weather models.

Multi-band microstrip patch antennas are convenient for mm-wave wireless applications due to their low profile, less weight, and planar structure. This paper investigates patch geometry optimization of a single microstrip antenna by employing a binary coded genetic algorithm to attain triple band frequency operation for wireless network application. The algorithm iteratively creates new models of patch surface, evaluates the fitness function of each individual ranking them and generates the next set of offsprings. Finally, the fittest individual antenna model is returned. Genetically engineered antenna was simulated in ANSYS HFSS software and compared with the non-optimized reference antenna with the same dimensions. The optimized antenna operates at three frequency bands centered at 28 GHz, 40 GHz, and 47 GHz whereas the reference antenna operates only at 28 GHz with a directivity of 6.8 dB. Further, the test result exhibits broadside radiation patterns with peak directivities of 7.7 dB, 12.1 dB, and 8.2 dB respectively. The covered impedance bandwidths when S11$ \leq $-10 dB are 1.8 %, 5.5 % and 0.85 % respectively.

The demand for high data rates, combined with the exponential growth of mobile data trafficking, and has prompted the use of millimeter-wave (mm-wave) spectrum for 5G mobile communication. So, for constructive assessment, this study employed various research publications, institutional reports, and other materials given at the conference. This survey article investigates the features of the mm-wave propagation channel and highlights the main challenges, solutions, and benefits associated with their utilization, as well as an analysis of their performance. The researchers observed that by reducing the difficulties and significant losses with various strategies, mm-wave cellular communication may extend up to 200m in a single cell and densification is essential for vast area coverage. The article also examines the right technical implementation approach, as well as the economic benefits and existing and predicted market situation of mm-wave cellular communication from the operator’s perspective. The outcome will be useful information for any operator or stakeholder in mm-wave communication.