Volume 11 | Issue 5 |

 Abstract

Abstract--Electricity theft is a widespread issue that has a detrimental impact on both power customers and utility businesses. It impairs utility companies' ability to grow economically, creates electric risks, and has an effect on consumers' high energy costs. The development of smart grids is crucial for the identification of power theft since these systems create enormous amounts of data, including information on client use, which may be used in machine learning and deep learning methods to identify electricity theft. This research offers a method for detecting theft that use deep neural networks to classify data using extensive characteristics in the time and frequency domains. We use data interpolation and synthetic data creation techniques to overcome dataset flaws including missing data and class imbalance issues. We evaluate and contrast the influence of characteristics from perform experiments using principal component analysis in both the time and frequency domains, run experiments in combined and reduced feature space, and then apply the minimum redundancy maximum relevance approach for confirming the most crucial features. By utilizing a Bayesian optimizer to optimize hyperparameters, we may increase the performance of power theft detection. We also use an adaptive moment estimation optimizer to run tests with various values of critical parameters to find the settings that produce the greatest accuracy. Finally, we demonstrate our method's competitiveness against other approaches assessed on the same dataset. On validation, we obtained 91.8% accuracy, which is the second-best on the benchmark, and 97% area under the curve (AUC), which is 1% higher than the best AUC in existing works.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Deep neural network, electricity theft, machine learning, minimum redundancy maximum relevance, principal component analysis, smart grids.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Knowledge, Common health problems

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents the withdrawal of the United Kingdom from the European Union. This is based on the withdraw agreement according to the Article 50 0f the Treaty of Lisbon with right to any member state to leave the EU. BREXIT- the process to leave the EU was instituted by a referendum held in 2016. We also summarize how private sector employment in the UK is 60% accounted for by SMEs. The British economy relies heavily on SMEs. Further, because of the exit from the Single Market, the European Union Regulations are no longer relevant to the British SMEs. Britain's decision to depart from the EU created a surge of uncertainty that recorded a 6% reduction in Foreign Direct Investment and around 2% reduction in employment in the first couple of years. At last we summarize certain policies that have been implemented to ease the risks faced by the SMEs.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

brexit, referendum, foreign direct investmenT

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper describes the sun and wind energy based in reality charging mechanism (SWCM) to generate the electricity for charging the battery packs of electrical motors (EVs). The renewable charging station consists of each the sun photovoltaic (PV) modules and a wind generator. The SWCM immensely reduce the requirement of fossil fuels to generate energy which leads to noticeably decreased CO2 and CO associated emissions. The renewable resources collectively with wind and solar has been modelled using single diode version and an analytical modelling has been finished for wind energy technology. The simulation version has been evolved in MATLAB-Simulink for the proposed SWCM. The I-V and PV trends of the sun panel were studied beneath numerous irradiance levels and outstanding parameters of wind turbine has been studied below extremely good loading (1 kW and 3 kW) conditions. There are unidirectional direct modern-day-day (DC) to DC converters are related to the PV modules and the wind turbine and 6 bidirectional DC-DC converters are associated with 10 charging elements which offers charging to the electrical vehicle. To stability the burden call for, the proposed device is hooked up to the grid through a 3 section bidirectional DC-AC (alternating contemporary-day) inverter. The received effects display that the proposed renewable charging mechanism is appropriate for EV charging therefore developing pollution loose surroundings.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Wind generator, Electromagnetic interference and Magnetic scenario.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The power generation from renewable power sources is variable in nature, and may contain unacceptable fluctuations So in current use the renewable energy is stored in the battery or super capacitors to use it later but it requires high maintenance charge So the main aim of the proposed system is to regulate the renewable power during the fluctuation to give uninterrupted power supply so here we are continuously monitoring the power generation of solar panel and simultaneously load usage these values are sent to machine learned model to classify the switching status of regulator circuit all these AI process is done in Python Platform.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Renewable power sources, Python Platform and Phasor Measurement Unit

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Sustainability in Supply Chain Management (SSCM) has emerged as a paramount concern for businesses globally, prompted by escalating environmental crises and societal pressure for ethical business practices. This research paper undertakes a comprehensive and systematic review of the extant literature on SSCM, encompassing multidisciplinary studies from the past two decades. The goal is to distil the salient themes, theoretical frameworks, methodologies, findings, and future research directions, thereby rendering a panoramic view of the field. The review reveals SSCM as a complex and nuanced arena, influenced by a multiplicity of factors including regulatory policies, technological advancements, stakeholder pressures, and organizational culture. Despite substantial progress, significant knowledge gaps persist, particularly concerning the global South and the integration of Industry 4.0 technologies. The paper concludes with recommendations for future research and practice.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Sustainability, Supply Chain Management, Systematic Literature Review, Global Context, Industry 4.0, Stakeholder Engagement, Regulatory Policies, Organizational Culture.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper proposes a wireless charging system for electric vehicles (EVs) that aims to address the limitations of traditional plug-in charging systems. The wireless charging system utilizes inductive power transfer technology to transfer energy wirelessly between the charging pad and the EV battery. The system incorporates efficient power transfer through mutual induction and a control system for safe and reliable operation. The system's key features include automatic alignment and power transfer control, fault detection, and thermal management. The study also evaluates the system's efficiency, electromagnetic compatibility, and electromagnetic interference. The proposed wireless charging system offers a convenient and safe charging solution for EVs, reducing the need for physical connection between the charger and the vehicle, and enabling efficient charging while on the go.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Mutual induction, Electric vehicles, Static wireless charging.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Stock market forecasts have always been the focus of experts in this and related fields. Over the years, many modern techniques have been used in conjunction with previously available statistical models to find better predictive techniques. Among modern technologies, machine learning and specifically artificial intelligence holds the greatest share of predictive models on the market. Compared to other techniques, deep learning techniques showed better results in modelling market movements. Some techniques have been tried and tested individually but with unsatisfactory results, these techniques include automatic feature extraction, time series prediction, recurrent neural network (RNN), etc. However, hybrid frameworks with multiple inputs and based on deep learning methods such as RNN and LSTM (Long Short-Term Memory) have not been studied much. We propose a recurrent neural network (RNN)-based framework that combines with long-short-term memory (LSTM) to predict the stock market closing price. The RNN-LSTM framework extracts features from a rich feature set and applies time series modelling to predict what will happen next. The set includes raw price data for the target index as well as foreign indices, technical indicators, exchange rates, and commodity price data, all selected by protocol and price configurations. known in the industry. Now let's come to the LSTM (Long Short-Term Memory) part, which is known for its series forecasting. LSTM is greatly helpful in time series forecasting. A correct price forecast will bring huge benefits to users of our framework/model. Successfully predicting the future price of a stock can bring substantial profits.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Long Short-Term Memory, Recurrent Neural Network (RNN), Deep Learning, Machine Learning, Artificial Intelligence.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The increasing adoption of electric vehicles (EVs) has prompted the development of efficient charging infrastructure and innovative vehicle-to-home (V2H) systems. This project presents a solar-based bi-directional electric vehicle charger that enables a V2H system, allowing the transfer of energy between the EV and the home. The proposed charger integrates solar power generation with bidirectional power flow capability, enabling the EV to not only charge from the solar panels but also supply power back to the home during peak demand or in emergency situations. The system incorporates power electronics converters and energy management strategies to ensure efficient and reliable operation. Moreover, the charger is designed to meet safety standards, providing flexibility and grid support. The Solar Based Electric vehicle Charger's efficiency, reliability, and ease of use also make it an attractive option for EV owners and operators, providing a cost-effective and convenient charging solution. As the world continues to shift towards renewable energy sources, the Solar Based Electric vehicle Charger is poised to play a crucial role in shaping the future of transportation and energy.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Bi-directional, Vehicle to home, Vehicle to grid, Converters

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

One disease at a time is the focus of many of the machine learning models for healthcare analysis currently in use. For example, one analysis is done for cancer, another for heart disease, etc. Multiple diseases cannot be predicted using the same framework by a single analysis. This study proposes a system to forecast various diseases using the Flask Application programming interface (API). The approach for examining diabetes, heart disease, kidney, liver, and cancer was proposed in this work. Numerous disease analyses were implemented using TensorFlow, the Flask API, and machine learning techniques. Python dataset is used to save the model behavior and to load the dataset file as necessary. The importance of this article analysis lies in the fact that all the contributing elements to the illness are taken into account while analyzing it, allowing for the identification of the disease's complete range of potential effects. For example, a lot of the existing techniques for analyzing diabetes took into account a few factors like age, sex, BMI, and insulin. However, in contrast to the existing model, our proposed system takes into account additional variables like the number of pregnancies, blood glucose levels, skin thickness, heart rate, and family history of diabetes. The behavior of the finished model will be captured in a Python dataset file, and the Flask API will be developed. When using this API, the disease's parameters must be sent along with the disease's name. The Flask API will call the pertinent model and then return the patient's status. The goal of this project is to look at as many diseases as we can in order to monitor patients' status and provide them warnings, when necessary, in order to lower the death rate

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning, Flask API, Convolutional Neural Network, XG-Boost

  License

Creative Commons Attribution 4.0 and The Open Definition