Week Ahead Electricity Power and Price Forecasting Using Improved DenseNet-121 Method

In the Smart Grid(SG)residential environment,consumers change their power consumption routine according to the price and incentives announced by the utility,which causes the prices to deviate from the initial pattern.Thereby,electricity demand and price forecasting play a significant role and can help in terms of reliability and sustainability.Due to the massive amount of data,big data analytics for forecasting becomes a hot topic in the SG domain.In this paper,the changing and non-linearity of consumer consumption pattern complex data is taken as input.To minimize the computational cost and complexity of the data,the average of the feature engineering approaches includes:Recursive Feature Eliminator(RFE),Extreme Gradient Boosting(XGboost),Random Forest(RF),and are upgraded to extract the most relevant and significant features.To this end,we have proposed the DensetNet-121 network and Support Vector Machine(SVM)ensemble with Aquila Optimizer(AO)to ensure adaptability and handle the complexity of data in the classification.Further,the AO method helps to tune the parameters of DensNet(121 layers)and SVM,which achieves less training loss,computational time,minimized overfitting problems and more training/test accuracy.Performance evaluation metrics and statistical analysis validate the proposed model results are better than the benchmark schemes.Our proposed method has achieved a minimal value of the Mean Average Percentage Error(MAPE)rate i.e.,8%by DenseNet-AO and 6%by SVM-AO and the maximum accurateness rate of 92%and 95%,respectively.

Energy Theft Identification Using Adaboost Ensembler in the Smart Grids

One of the major concerns for the utilities in the Smart Grid(SG)is electricity theft.With the implementation of smart meters,the frequency of energy usage and data collection from smart homes has increased,which makes it possible for advanced data analysis that was not previously possible.For this purpose,we have taken historical data of energy thieves and normal users.To avoid imbalance observation,biased estimates,we applied the interpolation method.Furthermore,the data unbalancing issue is resolved in this paper by Nearmiss undersampling technique and makes the data suitable for further processing.By proposing an improved version of Zeiler and Fergus Net(ZFNet)as a feature extraction approach,we had able to reduce the model’s time complexity.To minimize the overfitting issues,increase the training accuracy and reduce the training loss,we have proposed an enhanced method by merging Adaptive Boosting(AdaBoost)classifier with Coronavirus Herd Immunity Optimizer(CHIO)and Forensic based Investigation Optimizer(FBIO).In terms of low computational complexity,minimized over-fitting problems on a large quantity of data,reduced training time and training loss and increased training accuracy,our model outperforms the benchmark scheme.Our proposed algorithms Ada-CHIO andAda-FBIO,have the low MeanAverage Percentage Error(MAPE)value of error,i.e.,6.8%and 9.5%,respectively.Furthermore,due to the stability of our model our proposed algorithms Ada-CHIO and Ada-FBIO have achieved the accuracy of 93%and 90%.Statistical analysis shows that the hypothesis we proved using statistics is authentic for the proposed technique against benchmark algorithms,which also depicts the superiority of our proposed techniques.

Th-Shaped Tunable Multi-Band Antenna for Modern Wireless Applications

A compact,reconfigurable antenna supporting multiple wireless services with a minimum number of switches is found lacking in literature and the same became the focus and outcome of this work.It was achieved by designing a Th-Shaped frequency reconfigurable multi-band microstrip planar antenna,based on use of a single switch within the radiating structure of the antenna.Three frequency bands(i.e.,2007–2501 MHz,3660–3983MHz and 9341–1046 MHz)can be operated with the switch in the ON switch state.In the OFF state of the switch,the antenna operates within the 2577–3280MHz and 9379–1033MHz Bands.The proposed antenna shows an acceptable input impedance match with Voltage Standing Wave Ratio(VSWR)less than 1.2.The peak radiation efficiency of the antenna is 82%.A reasonable gain is obtained from 1.22 to 3.31 dB within the operating bands is achieved.The proposed antenna supports UniversalMobile Telecommunication System(UMTS)-1920 to 2170 MHz,Worldwide Interoperability and Microwave Access(WiMAX)/Wireless Broadband/(Long Term Evolution)LTE2500–2500 to 2690 MHz,Fifth Generation(5G)-2500/3500 MHz,Wireless Fidelity(Wi-Fi)/Bluetooth-2400 to 2480 MHz,and Satellite communication applications in X-Band-8000 to 12000 MHz.The overall planar dimension of the proposed antenna is 40×20mm2.The antennawas designed,along with the parametric study,using Electromagnetic(EM)simulation tool.The antenna prototype is fabricated for experimental validation with the simulated results.The proposed antenna is low profile,tunable,lightweight,cheap to fabricate and highly efficient and hence is deemed suitable for use in modern wireless communication electronic devices.

Impairments Approximations in Assembled mmWave and Radio Over Fiber Network

The fiber nonlinearity and phase noise(PN)are the focused impairments in the optical communication system,induced by high-capacity transmission and high laser input power.The channels include high-capacity transmissions that cannot be achieved at the end side without aliasing because of fiber nonlinearity and PN impairments.Thus,addressing of these distortions is the basic objective for the 5G mobile network.In this paper,the fiber nonlinearity and PN are investigated using the assembled methodology of millimeter-wave and radio over fiber(mmWave-RoF).The analytical model is designed in terms of outage probability for the proposed mmWave-RoF system.The performance of mmWave-RoF against fiber nonlinearity and PN is studied for input power,output power and length using peak to average power ratio(PAPR)and bit error rate(BER)measuring parameters.The simulation outcomes present that the impacts of fiber nonlinearity and PNcan be balanced for a huge capacity mmWave-RoF model applying input power carefully.

Power Scheduling with Max User Comfort in Smart Home:Performance Analysis and Tradeoffs

The smart grid has enabled users to control their home energy more effectively and efficiently.A home energy management system(HEM)is a challenging task because this requires the most effective scheduling of intelligent home appliances to save energy.Here,we presented a meta-heuristic-based HEM system that integrates the Greywolf Algorithm(GWA)and Harmony Search Algorithms(HSA).Moreover,a fusion initiated on HSA and GWA operators is used to optimize energy intake.Furthermore,many knapsacks are being utilized to ensure that peak-hour load usage for electricity customers does not surpass a certain edge.Hybridization has proven beneficial in achieving numerous objectives simultaneously,decreasing the peak-to-average ratio and power prices.Widespread MATLAB simulations are cast-off to evaluate the routine of the anticipated method,Harmony GWA(HGWA).The simulations are for a multifamily housing complex outfitted with various cool gadgets.The simulation results indicate that GWA functions better regarding cost savings than HSA.In reputes of PAR,HSA is significantly more effective than GWA.The suggested method reduces costs for single and ten-house construction by up to 2200.3 PKR,as opposed to 503.4 in GWA,398.10 in HSA and 640.3 in HGWA.The suggested approach performed better than HSA and GWA in PAR reduction.For single-family homes in HGWA,GWA and HSA,the reduction in PAR is 45.79%,21.92%and 20.54%,respectively.The hybrid approach,however,performs better than the currently used nature-inspired techniques in terms of Cost and PAR.

Cactus-Shaped Frequency Reconfigurable Antenna for Sub 10 GHz Wireless Applications

This paper presents,a novel cactus shaped frequency reconfigurable antenna for sub 10 GHz wireless applications.PIN diode is utilized as an electrical switch to achieve reconfigurability,enabling operation in four different frequency ranges.In the switch ON state mode,the antenna supports 2177-3431 and 6301-8467 MHz ranges.Alternatively,the antenna resonates within 2329-3431 and 4951-6718 MHz while in the OFF state mode.Radiation efficiency values,ranging from 68%to 84%,and gain values,ranging from 1.6 to 4 dB,in the operating frequency bands.the proposed antenna satisfy the practical requirements and expectations.The overall planner dimensions of the proposed antenna model is 40×21 mm^(2).Moreover,the measurement results from the prototype support the simulation results.Based on the frequency ranges supported by the antenna,it can be used for multiple wireless standards and services,including Worldwide interoperability and Microwave Access(WiMAX),Wireless Fidelity(Wi-Fi),Bluetooth,Long Term Evolution(LTE)and satellite communications.This increases its applicability for use in mobile terminals.

Automatic Detection of Outliers in Multi-Channel EMG Signals Using MFCC and SVM

The automatic detection of noisy channels in surface Electromyogram(sEMG)signals,at the time of recording,is very critical in making a noise-free EMG dataset.If an EMG signal contaminated by high-level noise is recorded,then it will be useless and can’t be used for any healthcare application.In this research work,a new machine learning-based paradigm is proposed to automate the detection of low-level and high-level noises occurring in different channels of high density and multi-channel sEMG signals.A modified version of mel fre-quency cepstral coefficients(mMFCC)is proposed for the extraction of features from sEMG channels along with other statistical parameters i-e complexity coef-ficient,hurst exponent,and root mean square.Several state-of-the-art classifiers such as Support Vector Machine(SVM),Ensemble Bagged Trees,Ensemble Sub-space Discriminant,and Logistic Regression are used to automatically identify an EMG channel either bad or good based on these extracted features.Comparison-based analyses of these classifiers have also been considered based on total classi-fication accuracy,prediction speed(observations/sec),and processing time.The proposed method is tested on 320 simulated EMG channels as well as 640 experi-mental EMG channels.SVM is used as our main classifier for the detection of noisy channels which gives a total classification accuracy of 99.4%for simulated EMG channels whereas accuracy of 98.9%is achieved for experimental EMG channels.