Emerging deregulation policies together with the distributed renewable resource had led to the restructuring of power grid operation as several interconnected self-reliant clusters. Forecasting models play a vital role to handle its inherent variability so that the safe and reliable operation of the grid can be ensured. However, the irradiance variation caused by a fast-moving cumulus cloud in the nowcasting horizon results in a fairly higher forecast error. This in turn leads to fluctuating power injections with considerable ramp rates. In a deregulated grid with weaker reactive power support, these fluctuating injections can cause severe voltage quality issues. Since the availability of the resources is uncertain in the deregulated grid, conventional decentralized control may not be sufficient to handle these voltage quality issues. Though much research is happening on these issues, the characteristics of fast-moving cumulus cloud-induced power quality issues are not well investigated. In this regard, this work investigates the voltage quality issues caused by the grid tied solar farms. Real-world data of irradiance variation under fast-moving cumulus clouds are considered for the investigation. The investigation carried out and the results demonstrated can benefit the power quality remedial measures in emerging deregulated grids.
A dynamic platform, the Internet of Things uses data, which in turn invites cybersecurity risks. In a dynamic and complicated world, many organisations are putting more of their attention into understanding cyber threats and attempting to quantify their exposure. This paper highlights and goes into great detail on standard cyber risk assessment methods while focusing on the assessment of cybersecurity threats in IoT and its vectors through a risk-based approach employing machine learning algorithms. Based on the statistical research, it can be determined that the CAQ model utilising J48 classifies at 94 percent, while the Bayesian method performs in evaluating possible risks at 82 percent. The Bayes algorithm also aids in estimating complicated risks coming from various sources, aids in comprehending how risk variables originate and connect in an IoT environment, and aids in determining what controls are necessary for quantifying and reducing them.
The rapid market integration of electric vehicles has resulted in an increase in the interest of fast charging technology. One of the major concerns associated with fast charging is safety of the operation. Fast charging involves effective communication between DC charger and battery management system through the charging control algorithm embedded in the vehicle controller unit. The development of such control strategy requires interdisciplinary cooperation between different participants. A lack of system understanding can lead to safety hazards. Here in this paper, we have developed a charging control strategy for CHAdeMO DC charger using model-based development which is a better method than conventional embedded C coding and its working is shown in a starter model of DC charger in STATEFLOW.
Cardiovascular diseases are deadly and kill millions of people around the world every year. Heart failure is one of the unfortunate consequence where the heart is unable to pump enough blood for the body. A medical checkup of these patients with attributes including creatinine phosphokinase, ejection fraction, serum creatinine and serum sodium can be used for analysis. In this paper, we have analysed this clinical data and built machine learning models that can predict the survival rate of heart failure of a person. We have used various dimensionality reduction techniques to analyse the data with the aim of reducing the dimensions of the dataset. Finally, we reduced the overfitting of data using Synthetic Minority Oversampling Technique(SMOTE) and Adaptive Synthetic(ADASYN).
The necessity of modern intensive care units (ICU) based on IoT is becoming obvious as a result of the population boom and, most notably, coronavirus disease (COVID-19). The continual monitoring of patients' vital indicators (Blood Pressure, ECG, Heart Rate, Blood Saturation, Body Temperature) is one of the most important aspects of an ICU. Existing improvements in informatics, signal processing, or engineering, which potentially reduce the pressure on ICUs, have yet to be implemented. It's possible due to a lack of user participation in research and development. This manuscript focuses on the improvement of a completely integrated system where the doctors can directly connect to patients through the Smart Portable ICU, and physicians can access the patients. Thus, the crucial boundaries of a patient to the concerned specialist at a far-off position have been resolved simply and helpfully. Thus, the specialist can attend to the patient remotely and infuse lifesaving drugs from the distant area if necessary.
Floods can be considered the most dangerous natural disaster, given their unpredictability and capacity to wipe out valuable life and property. The timely and efficient prediction of floods and flood susceptible or risk zones has been of utmost importance and can help with risk assessment, long-term management, and future preparedness. Over the years, Machine Learning (ML) has evolved as a powerful tool to build accurate flood models, inundation maps, and warning systems. This study uses the Support Vector Machine (SVM) and Random Forest (RF) algorithms and a Bagging Ensemble Model for Flood Susceptibility Mapping of Ernakulam, Kerala, India using multi-source geospatial data and the WEKA software. A total of twelve Flood Conditioning Factors (FCFs) are considered as variables, namely elevation, slope, curvature, Topographic Roughness Index (TRI), Topographic Wetness Index (TWI), Stream Power Index (SPI), rainfall, Land Use Land Cover (LULC), distance to the river, drainage density, and geology. The contribution of factors is assessed using the OneR Feature Selection method. The models are compared using the Receiver Operating Characteristics (ROC) curve and the Area Under the Curve (AUC) method. The Flood Susceptibility Map provides an opportunity for planners and authorities to flood preparation and long-term planning against flood impacts.
Handwritten script recognition has risen as a significant issue in a previous couple of years. Areas of computer vision and pattern recognition has attracted many researchers for a lot of real-time applications. Among these fields, Devanagari script recognition is a hot area for many Indian researchers due to its many applications like document reading, postal address sorting, etc. Lot of deep convolutional neural network (DCNN) models are being implemented to increase recognition accuracy. The objective of this study is to compare the performance of the proposed DCNN model by applying two image formats that are without processing (original) and with our proposed augmentation technique. The results show that the classification accuracy has increased by using the proposed technique of augmentation on a very limited training benchmark dataset of handwritten Devanagari digits proposed by Dongre and Mankar. The authors have achieved the highest classification accuracy of 98.49%.
In this day and age, online entertainment has turned into a significant stage where individuals are allowed to offer their viewpoint on any item. This can be useful for others on the off chance that they will realize other’s perspectives prior to purchasing anything. Individuals will more often than not visit the majority of the E-trade sites where item surveys are accessible. Likewise many tweets are additionally being made on twitter, a social media site, connected with various item audits. In this venture we mean to make a web application in which we can accept a fine food items as a contribution from customers and aid them by recommending or not recommending the product based on the reviews using Random Forest Classifier with 85 percent accuracy. The current systems employ recommendations based on data from single source of reviews. In our system, we plan to verify the viability of reviews across different platforms and then the product is recommended so that the customer can make an informed decision.
The best way to express emotions is through facial expressions. These facial expressions are a nonverbal way of communication. It could be quite helpful if a machine could identify or recognize these expressions and concluded about how the person is feeling at that moment. Recognizing these expressions on a real-time basis is itself a challenge. The main aim of the proposed model is to detect five different facial expressions, viz. Angry, Happy, Neutral, Sad, and Surprise. The proposed model is built using various preprocessing algorithms followed by standard architecture like Convolution Neural Networks. The model is trained to obtain the h5 file. The h5 file is then used to work in real-time, MTCNN (Multi-task Cascaded Convolutional Neural Networks) classifier is used to capture the facial features to get a better image localization. The innovative part of the system is the robustness in architecture, low latency of 0.030 seconds, FPS of 28, better accuracy of 75% on the test set, and an average weighted F- 1 score of 0.75.
Power quality monitoring and parameter estimation are essential for the proper functioning of modern power grids. Various techniques have been proposed to estimate the characteristics of power signals and to gain insight into their dynamics. Non-stationary Fourier mode decomposition (NFMD) is a new interpretable time-frequency analysis framework for non-stationary and nonlinear signals. This work investigates the prospects of NFMD in the estimation of power-system characteristics such as fundamental frequency, amplitude and presence of disturbance components. Usage of NFMD as a noise removal technique is also explored in the current work. Results show that NFMD is robust to noisy disturbances and can perform well in noisy environments. The proposed methodology can be used for real-time analysis and interpretation of large volume of data from advanced smart metering techniques such as microphasor measurement units in microgrids.
This paper proposes a hybrid structure including static VAR compensator (SVC) and conventional hybrid power quality conditioner (HPQC) in co-phase traction railway system powered by V/v transformer. The SVC plays a vital role in compensating the full required load reactive power in addition to filtering the third and fifth harmonics, while the HPQC handles the left harmonics and negative sequence current of the grid side. Moreover, to keep the grid power factor flexibly within acceptable limits, a control strategy employs two partial compensation techniques, one balanced and one unbalanced (BPCT and UPCT, respectively). The proposed arrangement not only drastically improves power quality indices (PQI) but also reduces HPQC capacity by as much as 23%. Since the hybrid structure has a lower capacity and higher performance than the conventional one, it may be a viable option for achieving power quality targets in electric rail networks.
This paper proposes a solar photovoltaic (PV) plant installation in the campus of an educational institute in Faridabad, India. The proposed PV plant is in grid connected mode. Total energy consumed in the year 2019 is analyzed. The institute is having a small scale PV installation which contributed to little more than 7% of it’s annual consumption. The area under installation can be increased by covering areas like parking and other available rooftop area. Three local solar panel manufacturers are taken for simulation and the one giving maximum output is selected. Simulation is done on PVsyst 7.2 software. The system generated 31832 MWh electric energy which can meet 85% of the electricity demand and still having nearly 31000 MWh surplus energy which can be sold to the grid. An economic analysis is done considering different costs involved in installing and operating the system. The amount invested can be recovered in nearly 7 years making the PV plant economically feasible.
Optimal signal generation and accurate on-time determination of switches are essential for the improvement of an inverter feed drive’s steady-state and transient responses. This work combines a simple classical optimal current generation process with sector segmentation of six SVPWMs to improve drive performance. An average of two adjacent states is used to get six virtual states to segment six sectors into twelve sectors. Simulation is carried out in Matlab-2021 to see the performance of the proposed system. A simulation has shown that the control method is efficient in controlling the speed dynamics and steady-state error. In addition, the ratio of harmonic power loss to total active power loss of the proposed system is less.
This study provides the investigation of underground cable fault. Fault are classified into two type such as symmetrical and unsymmetrical fault. For this fault detection range of about 1m to 2.6 km of the underground cable have been investigated. In underground cable, fault is validating through live tests as per the research knowledge. The underground cable fault are largely caused due to improper insulation, interweave, mesh and other accessories. symmetrical and unsymmetrical fault are present to detect and classify incipient fault in underground cable at the distribution voltage level. The wavelet transformer approach has been used to detect the fault location of the underground fault. This project deal with number of high voltage cable fault location technique with modeling and simulation.
Internet of things (IoT) is an advanced technology used in many networking application systems. IoT involves huge number of objects or things that generate enormous amounts of data for storage and processing. The association and control of this enormous volume of information requires original thoughts in the plan and the execution of the IoT system in order to process and improve their presentation. In a similar manner, the Software Defined Networks (SDN) is also a popular networking system and extensively used for monitoring and controlling IoT based devices. Furthermore, OpenFlow is a kind networking protocol mainly used for establishing reliable data transmission in SDNs, which transmits the messages with the help of switches and controllers. In SDN, the controller has the responsibility to coordinate the routing operations of entire network by using switches. Along these lines, to improve the system execution, data packets ought to be routed to the best path. In this paper, the Lion Optimization Algorithm (LOA) is proposed to find the best or optimal path in the data plane of SDN for routing a given packet. By selecting the optimal path between the hosts, the packet loss rate will be reduced and also response time will be improved. Execution of LOA in the SDN environment with OpenFlow Switch system is performed utilizing NS-2 Network Simulator. When compared to the conventional models, the results obtained results using the proposed LOA provide an improved performance values in terms of reduced packet loss rate, increased throughput and packet delivery ratio.
This paper analyses the impact of active and reactive power controls of VSC-HVDC on the behaviour of frequency controllers. The performance of droop and PI type frequency control strategies are investigated. The effect of feedforward and feedback active power loops are examined through bandwidth analysis. The influence of reactive power controllers on the performance is also studied. Inferences are drawn through MATLAB/SIMULINK based time domain simulations.
A multiport AC-DC microgrid system involves numerous stages of conversions. This results in an additional number of control schemes, switching losses, and system costs. This paper proposes a new energy harvesting converter topology capable of simultaneously operating as an inverter and a buck-boost converter. The appropriate selection of modes of switching and diode conduction in the suggested converter results in regulated and simultaneous power delivery to DC and AC loads. Extensive mathematical modeling and the development of a laboratory prototype validate the proposed topology. The converter can find broad scope in charging stations and microgrid applications.
In this paper, the donkey and smuggler optimization algorithm (DSOA) is enforced for the controller design of a two-degree-of-freedom PID (2DOFPID) for the study of load frequency control (LFC). An extensively implemented model of two area reheat hydro-thermal (TARHT) system is chosen for investigation and carried out the analysis for a perturbation in step load (SLP) of 10% on area-1. Controller optimization is performed subjected to the objective index of integral time square error (ITSE). However, the efficacy of 2DOFPID is evidenced with traditional controllers of PID and PID plus filter (N). An investigation is further extended to the integration of the TARHT system with the DC line to obtain performance enhancement. Sensitivity test is conducted finally to showcase the robustness of the suggested control approach.
This work considers a grid connected solar photo-voltaic system with battery to assess technical and economical performances. Real-time load demand data of two different residential consumers with identical solar capacity has been used in this study. To reduce the grid dependency, battery size is redesigned for longer run time. This work also signifies the time of switch over from grid to battery during peak hours thereby providing financial gain to consumers especially when Time of Day (ToD) tariff rates are high. This work also explains that even if the system is installed with similar solar and battery capacities but with different load pattern, the LCOE is identical for both cases, but the payback is different. The annual savings was found to be dependent on load pattern and ToD tariff.
India’s target of 500 GW of renewable energy capacity by 2030 can be achieved by increasing decentralized energy production for which, the deployment of microgrids is the best option. The design and implementation of a microgrid (MG) system with the integration of solar, wind, or/and other renewable energy sources and conventional sources makes it feasible to provide power to islands and rural areas. This paper focuses on optimizing the energy cost of an MG which includes solar photovoltaic systems, wind turbines, diesel generators, and batteries for a village in southern India. Stand-alone microgrid models with five different configurations and grid-connected microgrid models were designed and analyzed for their economic viability in the village. The system with the combination of PV, DG, WT, and Battery gives the minimum COE among the stand-alone models, whereas grid–connected system gives the least COE when compared to all stand-alone models.
