Aishwary Awasthi

Urbanization’s relentless advance intensifies the quest for sustainable energy sources, with smart cities leading the shift toward sustainability. In these innovative urban landscapes, wind power is pivotal in the clean energy paradigm. Efficient wind energy utilization hinges on accurate wind power forecasting, essential for energy management and grid stability. This review explores the use of neural network models for wind power forecasting in smart cities, driven by wind power’s growing importance in urban energy strategies and the expanding role of artificial neural networks (ANNs) in wind power prediction. Wind power integration mitigates greenhouse gas emissions and enhances energy resilience in urban settings. However, wind’s inherently variable nature necessitates precise forecasting. The surge in ANN use for wind power forecasting is another key driver of this review, as ANNs excel at modelling complex relationships in data. This review highlights the synergy between wind power forecasting and neural network models, emphasizing ANNs’ vital role in enhancing the accuracy of wind power predictions in urban environments. It covers neural network fundamentals, data preprocessing, diverse neural network architectures, and their applicability in short-term and long-term wind power forecasting. It also delves into training, validation methods, performance assessment metrics, challenges, and prospects. As smart cities champion urban sustainability, neural network models for wind power forecasting are poised to revolutionize urban energy systems, making them cleaner, more efficient, and more resilient.

The evolution of smart cities has ushered in a new era of sustainable urban living, with energy management at its core. This paper offers a comprehensive review of the energy-related planning and operational models within the smart city framework, categorizing them into five primary intervention areas: generation, storage, infrastructure, facilities, and transport. The intricate relationship between smart cities and electric vehicles (EVs) is explored, emphasizing the need for robust charging infrastructures and forecasting peak loads. As the adoption of EVs surges, challenges such as power grid strain, voltage fluctuations, and power losses become more pronounced. Innovative solutions leveraging machine learning, including techniques like LSTM, DNN, and SVM, have been proposed to manage EV charging, ensuring efficiency and minimizing costs. Furthermore, the integration of EVs into smart cities is not without its challenges. Beyond the technical aspects, economic, social, and environmental challenges arise, necessitating a holistic approach for seamless integration. This review underscores the importance of a multifaceted strategy, encompassing all aspects of EV integration, to realize the vision of truly sustainable and smart urban centres.

Grid connected solar power plants are widely established in many places worldwide. Photovoltaic (PV) based grid connected solar plants are attracting recently due to improved in controlling of power converters. Single stage grid connected systems can reduce number of converters connected in power plants which resultant in reduce cost of the system. However, DC to DC converters are generally used in PV systems to enhance the operation of maximum power point for best utilization. The inverters also can be using to extract maximum power from PV systems through new controlling techniques in power electronics devises. Therefore an extraDC to DC converter is not required to make PV at its maximum power point condition. However, this technology can be used for small scale solar power plants since all PV arrays in solar power plant cannot be received same irradiance. Takagi-Sugeno-Kang (TSK) fuzzy controlleris having significant priority than proportional plus integral controllers when rapid changes are having in input. Hence, TSK based single stage controller is developed in this paper for grid connected 1MW solar plant. Generally distribution system is connected with unbalanced loads, hence these unbalanced loads will create forcefully unbalanced currents in electrical grid. Unbalanced grid currents further create many problems to other loads. Therefore, the proposed controller is designed to help making grid currents balanced during unbalanced local loads. Further, the inverter can compensate reactive power demanded by local loads to minimize reactive power supplied by grid. Extensive results are presented and evaluated through hardware-in-loop on the platform of OPAL-RT to enhance the performance of proposed controller for 1MW grid connected solar plant.

This paper reviews the integration of renewable energy systems with Industrial IoT (IIoT) through Artificial Intelligence (AI). It examines various studies focusing on the design and monitoring of solar-powered wireless sensor nodes in diverse IIoT settings, particularly outdoors. A proposed distributed network architecture, underpinned by open-source technologies, aims for efficient solar power harvesting and data acquisition on solar radiation and ambient parameters. This data aids in devising estimation techniques to predict solar panel voltage outputs, optimizing energy utilisation of solar-powered sensor nodes. The discourse extends to photovoltaic plants, emphasising continuous monitoring and fault detection for operational safety and reliability. Reviewed works advocate embedding AI and IoT for remote sensing, fault detection, and diagnosis, addressing challenges posed by undetectable faults. Furthermore, the paper explores AI’s transformative potential in the broader energy sector, impacting electricity production, distribution, energy storage, and efficiency. The synergy of AI, IIoT, and renewable energy systems is underscored as a conduit for enhancing energy management, operational transparency, and deploying cost-effective solutions for complex industrial challenges, significantly bolstering the efficiency and intelligence of industrial production and services.

Introduction: In general, sentiment evaluation has focused on text content analysis. Traditional sentiment analysis (SA) excludes document metadata and focuses on text. The lack of research in this area prevents textual material and metadata from working together to create synergies that could lead to reliable sentiment assessment solutions.Method: We exhibit the potential uses of our integrated methodology across multiple areas and prove its efficacy through testing and evaluation on a different datasets. Data preprocessed using a multiple techniques, such as “stemming, tokenization, and stop word removal”. The “term frequency-inverse document frequency (TF-IDF)”methodology is utilized for feature extraction.Result: The outcomes of our experiments reveal that our suggested method is successful in collecting sensitive sentiment such as” accuracy, recall, precision, and f1-score”. This is a promising development in the field of sentiment assessment exploration.Conclusion: In conclusion, this study proposed a novel approach, the DDO-SVM, which addresses the limitations of conventional SA by incorporating both textual and metadata features. These components integrate well, improving sentiment evaluation across measurements. SA becomes more reliable and effective in actual applications with this breakthrough.