Maximizing solar power generation through conventional and digital MPPT techniques: a comparative analysis.

A substantial level of significance has been placed on renewable energy systems, especially photovoltaic (PV) systems, given the urgent global apprehensions regarding climate change and the need to cut carbon emissions. One of the main concerns in the field of PV is the ability to track power effectively over a range of factors. In the context of solar power extraction, this research paper performs a thorough comparative examination of ten controllers, including both conventional maximum power point tracking (MPPT) controllers and artificial intelligence (AI) controllers. Various factors, such as voltage, current, power, weather dependence, cost, complexity, response time, periodic tuning, stability, partial shading, and accuracy, are all intended to be evaluated by the study. It is aimed to provide insight into how well each controller performs in various circumstances by carefully examining these broad parameters. The main goal is to identify and recommend the best controller based on their performance. It is notified that, conventional techniques like INC, P&O, INC-PSO, P&O-PSO, achieved accuracies of 94.3, 97.6, 98.4, 99.6 respectively while AI based techniques Fuzzy-PSO, ANN, ANFIS, ANN-PSO, PSO, and FLC achieved accuracies of 98.6, 98, 98.6, 98.8, 98.2, 98 respectively. The results of this study add significantly to our knowledge of the applicability and effectiveness of both AI and traditional MPPT controllers, which will help the solar industry make well-informed choices when implementing solar energy systems.

Managing the low carbon transition pathways through solid waste electricity.

The potential of solid waste as an energy source is clear, owing to its wide availability and renewable properties, which provide a critical answer for energy security. This can be especially effective in reducing the environmental impact of fossil fuels. Countries that rely heavily on coal should examine alternatives such as electricity from solid waste to provide a constant energy supply while also contributing to atmospheric restoration. In this regards, Low Emissions Analysis Platform (LEAP) is used for simulation the entire energy system in Pakistan and forecasted its capital cost and future CO2 emissions in relation to the use of renewable and fossil fuel resources under the different growth rates of solid waste projects like 20%, 30% and 40% for the study period 2023-2053. The results revealed that, 1402.97 TWh units of energy are generated to meet the total energy demand of 1193.93 TWh until 2053. The share of solid waste based electricity in total energy mix is increasing from a mere 0.81% in 2023 to around 9.44% by 2053 under the 20% growth rate, which then increase to 39.67% by 2053 under the 30% growth rate and further increases to 78.33% by 2053 under the 40% growth rate. It is suggested that 40% growth rate for solid waste based electricity projects is suitable for Pakistan until 2053 because under this condition, renewable sources contributes 95.2% and fossil fuels contributed 4.47% in the total energy mix of Pakistan. Hence, CO2 emissions are reduced from 148.26 million metric tons to 35.46 million metric tons until 2053 but capital cost is increased from 13.23 b$ in 2023 to 363.11 b$ by 2053.

Corrigendum: Unveiling the predictive power: a comprehensive study of machine learning model for anticipating chronic kidney disease.

[This corrects the article DOI: 10.3389/frai.2023.1339988.].

Unveiling the predictive power: a comprehensive study of machine learning model for anticipating chronic kidney disease.

In today's modern era, chronic kidney disease stands as a significantly grave ailment that detrimentally impacts human life. This issue is progressively escalating in both developed and developing nations. Precise and timely identification of chronic kidney disease is imperative for the prevention and management of kidney failure. Historical methods of diagnosing chronic kidney disease have often been deemed unreliable on several fronts. To distinguish between healthy individuals and those afflicted by chronic kidney disease, dependable and effective non-invasive techniques such as machine learning models have been adopted. In our ongoing research, we employ various machine learning models, encompassing logistic regression, random forest, decision tree, k-nearest neighbor, and support vector machine utilizing four kernel functions (linear, Laplacian, Bessel, and radial basis kernels), to forecast chronic kidney disease. The dataset used constitutes records from a case-control study involving chronic kidney disease patients in district Buner, Khyber Pakhtunkhwa, Pakistan. For comparative evaluation of the models in terms of classification and accuracy, diverse performance metrics, including accuracy, Brier score, sensitivity, Youden's index, and F1 score, were computed.