Distance protection of flexible ac transmission lines, including the thyristor-controlled series compensator (TCSC), static synchronous compensator, and static var compensator has been a very ...challenging task. This paper presents a new approach for the protection of TCSC line using a support vector machine (SVM). The proposed method uses postfault current samples for half cycle (ten samples) from the inception of the fault and firing angle as inputs to the SVM. Three SVMs are trained to provide fault classification, ground detection, and section identification, respectively, for the line using TCSC. The SVMs are trained with polynomial kernel and Gaussian kernel with different parameter values to get the most optimized classifier. The proposed method converges very fast with fewer numbers of training samples compared to neural-network and neuro-fuzzy systems which indicates fastness and accuracy of the proposed method for protection of the transmission line with TCSC
A new differential current-based fast fault detection and location scheme for multiple Photovoltaic-based dc microgrid is proposed in this paper. A multiterminal dc (MTDC) distribution network is an ...effective solution for present grid scenario, where local distribution is incorporated primarily by power electronics based dc loads. PV systems with auxiliary power sources and local loads are used for MTDC connection, especially when ac utility grid is integrated with it by voltage source converters. Pole to pole and pole to ground faults are basically considered as dc distribution network hazards. As PV is connected through dc cable, high resistive dc arc fault is also studied in present literature. The proposed PV system is considered with arc-fault circuit interrupters as backup protection and is used to detect arcing series fault. Fast acting dc switching is considered for proposed differential current-based unit protection. A discrete frame differential current solution is considered to classify the fault type by modified cumulative sum average approach. By calculating unknown dc cable resistance accurately by non-iterative Moore-Penrose pseudo inverse technique, the fault distance is calculated. TMS320C6713 DSP based test-bench is used for verification of the scheme.
15 min ahead irradiance prediction in sunny weather.
Display omitted
•A new robust Wavelet Kernel ELM is used for solar irradiation forecasting.•VMD and EMD are used to decompose the solar ...irradiation time series data samples.•To reduce the computational overhead the size of the kernel matrix is reduced.•A variable weighting factor is used for each error residual for robustness.•Solar irradiation prediction during changing weather condition is also presented.
In this paper a new hybrid method has been implemented by combining Variational Mode Decomposition (VMD) and a new low rank robust kernel based Extreme Learning Machine (RKELM) for solar irradiation forecasting. This hybrid model presents an efficient and effective short term solar irradiation prediction approach using the historical solar irradiation data. The original non-stationary time series data is decomposed into various modes using VMD approach. The proposed VMD-RMWK (VMD based reduced Morlet Wavelet Kernel extreme learning machine) method is used to predict the solar irradiation of an experimental 1 MW solar power plant in Odisha, India. Different time intervals of 15 min, 1 h and 1 day ahead in different weather conditions are considered for forecasting purpose. The VMD technique decomposes the original nonlinear irradiation into a set of Variational Mode Functions (VMFs), and the extracted VMFs are used to train the kernel based robust ELM. Comparison with empirical mode decomposition (EMD) based low rank kernel is also presented in this paper. As a new contribution to the previously performed literature survey this paper presents a more accurate solar irradiation prediction paradigm for distinctive weather conditions, and different time intervals varying from very short duration of 15 min to one day ahead. Also to improve the reliability of the KELM and to make it robust under noisy conditions and the presence of outliers in the data, a weight loss matrix has been derived using a non-parametric kernel density estimation method and incorporated in the new formulation (RKELM). A typical solar power experimental solar power station in India has been taken for detailed study showing clearly the accuracy and robustness of the proposed approach. For cross validation of the proposed model, solar irradiation data from a solar power plant located in the state of Florida has been implemented.
In this paper, an efficient new hybrid time series forecasting model combining variational mode decomposition (VMD) and Deep learning mixed Kernel ELM (MKELM) Autoencoder (AE) has been presented for ...precise prediction of wind power. It is well known that KELM-AE avoids manual tuning of weights of hidden layer nodes, and exhibits superb model generalization property, reduces execution time, and produces exact solution of output weights by generalized least squares resulting in compact storage space, etc. This is in contrast to other deep learning neural network models with nonconvex optimization problems, time consuming training process and limitations of backpropagation learning algorithms. Further the VMD parameters (α, K) are optimized to yield suitable number of intrinsic modes (IMFs) using a newly presented meta-heuristic population based Sine Cosine integrated water cycle algorithm (SCWCA) algorithm. Further the mixed kernel parameters and their associated weights are optimized using the same SCWCA to improve the performance of the Deep MKELM predictor against any outliers or noise in the data. Wind power data of three wind farms located in Sotavento Spain, Wyoming, and California, USA are applied for short-term and multi-step prediction of wind power with significant accuracy.
Display omitted
•A new Deep learning mixed kernel ELM-AE is presented for wind power prediction.•Adaptive VMD is used to select suitable IMFs as inputs to Deep MKELM Autoencoder.•MKELM-AE parameters are optimized using a novel Sine Cosine Water Cycle Algorithm.•Multi step forecasting of wind power is achieved using the Robust MKELM-AE.•High prediction accuracy is achieved using data from three wind farms.
Present study attempts to project extreme precipitation indices over 34 different meteorological subdivisions and six homogeneous regions such as Northwest, Central Northeast, Northeast, West ...Central, Peninsular India and Hilly Region during summer monsoon season in the twenty-first century. For this purpose, the Regional Climate Model version4 (RegCM4) had been run at 50 km horizontal resolution forced with the global model GFDL-ESM2 M, during reference period 1976–2005 for the model validation, and the mid- (2031–2060) and far-future (2070–2099) for projections under RCP8.5 scenario over the South Asia CORDEX domain. In this paper, model simulated precipitation has been validated against IMD, APHRODITE and NCEP/NCAR data sets. The results indicate that RegCM4 captures the important features of seasonal precipitation and various extreme indices over the study area. The RegCM4 has projected an increase in the mean seasonal precipitation by 0.56 mm/day whereas in case of GFDL model the rate is 0.39 mm/day during the far-future relative to the reference period. The heavy precipitation indices are projected to increase more frequently (0.264/decade) than the mean precipitation rate (0.01/decade) over India. The correlations between the extreme precipitation indices and the seasonal mean precipitation are found to be strong. In addition, the consecutive dry days are projected to occur more frequently (3–5 days) over West Central (Telangana, Vidarbha and Marathwada) and west Rajasthan while consecutive wet days are projected to decrease over larger parts of India during far-future. Similarly, 1 day maximum precipitation and the simple daily intensity index are projected to increase consistently from mid- to far- futures over some sub-divisions of West coast, Hilly and Northeast regions. From a spatial probability perspective, model projection indicates more frequent severe drought and flood conditions over India.
•CH4 emission was increased by 26% in rice-fish than rice alone.•N2O emission was decreased by 9% in rice-fish with common carp than rice alone.•The GWP and CEE increased by 29.5% in rice-fish with ...common carp than rice alone.•Rice+common carp in rainfed shallow lowland is economic, higher C credit compliance.•Indian major carps (mrigal rohu and catla) emit less GHGs than common carp.
Four fish species namely, Cirrhinus mrigala H. (mrigal), Labeo rohita H. (rohu), Cyprinus carpio L. (common carp) and Catla catla H. (catla) were introduced along with rice (Oryza sativa L.) cv. Varshadhan, in a rainfed shallow (0–25cm water depth) Inceptisol to evaluate the effect of fish species on methane (CH4) and nitrous oxide (N2O) emission in a rice-fish farming system. On seasonal basis, the emission of CH4 was significantly higher by 26% under rice-fish co-culture compared to rice alone. The maximum emission of CH4 (36% higher) was found under rice+common carp farming. On contrary, the emission of N2O was significantly lower by 9% under rice-fish compared to rice alone. Although the global warming potential (GWP) was highest (29.5% more) in rice+common carp, the CH4 and N2O emission from this treatment per unit of total yield (rice+fish) were at par and significantly lower, respectively, compared to rice alone. Further, it provided significantly higher yield (rice+fish) and economic benefit over rice and other rice+fish species combinations. The integration of common carp with rice in rainfed shallow lowland ecology is thus, one of the viable options for livelihood of the small and marginal farmers besides, higher carbon (C) credit compliance. However, Indian major carps, mrigal rohu and catla in order, are potentially less harmful in terms of GHGs emission in shallow rice fields besides, higher profitability and carbon credit compliance compared to rice farming alone.
•Tropical flooded rice ecosystem behaved as net C sink on annual basis.•Low land rice ecology revealed C storage potential in wet and dry seasons.•Annual cumulative net ecosystem CO2 exchange was ...negative.•Integrated annual net ecosystem CH4 exchange was positive.•Annual gross primary production was greater than ecosystem respiration.
A yearlong field study was undertaken to investigate the carbon dioxide (CO2) and methane (CH4) exchange in relation to ecosystem carbon (C) balance in tropical low land rice by employing open path eddy covariance (OPEC) system. The study was conducted on annual basis, included both wet and dry seasons crop. This is the first report from India on net ecosystem CH4 exchange (NEME) from low land flooded rice ecology through eddy covariance techniques. On annual basis the cumulative net ecosystem CO2 exchange (NEE) was −457gCm−2 and NEME was +262.62kgCH4ha−1, respectively. On the other hand, the annual gross primary production (GPP) was +1340gCm−2 and ecosystem respiration (RE) was +883gCm−2. On seasonal basis the rate of NEE was in the range of −3.29 and −2.74gCm−2 day−1, respectively and NEME was +2.80 and +4.34mgm−2h−1 in wet and dry cropping seasons, respectively. As a whole, the integrated NEE in dry and wet seasons was −355 and −341gCm−2, whereas, the integrated NEME in the two seasons was +84 and +129kgha−1, respectively. Considering the net ecosystem production (NEP or −NEE: +695gCm−2), rhizodeposition, algal biomass, root, stubble and compost added as ecosystem C input and NEME (+213kgha−1), C removal through harvest and dissolved organic C as ecosystem C output, the tropical rice acts as net C sink both seasonally and annually. Although CH4 is a source of C loss from low land flooded rice ecosystem, considering all the components of C balance on system basis, this ecology has a good potential to store considerable amount of C.
This paper proposes fast variants of the discrete S-transform (FDST) algorithm to accurately extract the time localized spectral characteristics of nonstationary signals. Novel frequency partitioning ...schemes along with band pass filtering are proposed to reduce the computational cost of S-transform significantly. A generalized window function is introduced to improve the energy concentration of the time–frequency (TF) distribution. An application of the proposed algorithms is extended for detection and classification of various nonstationary power quality (PQ) disturbances. The relevant features required for classification were extracted from the time–frequency distribution of the nonstationary power signal patterns. An automated decision tree (DT) construction algorithm was employed to select optimal set of features based on a specified optimality criterion for extraction of the decision rules. The set of decision rules thus obtained were used for identification of the PQ disturbance types. Various single as well as simultaneous power signal disturbances were considered in this paper to prove the efficiency of proposed classification scheme. A comparison of the classification accuracies with techniques proposed earlier, clearly demonstrates the improved performance. The major contributions of this manuscript are new FDST algorithms for fast and accurate time–frequency representation and an efficient classification algorithm for identifying PQ disturbances. The advantages of the classification algorithm are (i) accurate feature derivation from the TF distribution and optimum feature selection by the DT construction algorithm, (ii) robust performance at different signal-to-noise ratios, (iii) simple decision rules for classification, and (iv) recognition of simultaneous PQ events.
Display omitted
► A novel scheme for multiple Power Quality Patterns Recognition is presented. ► Fast Discrete S-Transform with frequency scaling and Band Pass filtering is used. ► Fast and Accurate Feature selection and robust performance under noise are achieved. ► A decision tree classifier is used with Fast ST features.
This paper presents a cross-differential protection scheme for power transmission systems inclusive of a STATCOM. The measurement of the energy of the prominent frequency components of the current ...signals is done using a computationally fast version of the discrete S Transform suitable for power system signal analysis. The energy thus obtained is used for cross-differential purposes. The practical implementation of the new fast discrete S-transform is performed on the TMS320C6713 digital signal processor for verification of real-time operation of the relaying scheme. The computational load of the processor to perform the transform in online mode is reduced by a cross-differential check using a cumulative difference technique. The results obtained from the extensive experimentations show the feasibility and speed of the new approach.
•Kernel Extreme Learning Machine (KELM) is used to forecast Currency Exchange rate and Trend.•A fast reduced version of KELM reduces execution time using random support vectors from the ...data.•Nonlinear time series data is first decomposed by Empirical Mode decomposition.•Accurate forecasting and trend analysis is achieved for a basket of currencies.•The currency movement trends are used to generate trading signals using KELM.
In this paper, we propose a hybrid forecasting model that combines Empirical Mode Decomposition (EMD) with fast reduced kernel Extreme Learning Machine (KELM) for day ahead foreign currency exchange rate forecasting. EMD is an efficient method for nonlinear data decomposition in such a noisy environment and the purpose is to find important components in terms of Intrinsic Mode Functions (IMFs) by which the nonlinear time series is converted into stationary time series by making the data smoother and simpler for analysis. The average IMFs decomposed from EMD (AEMD) are hybridized with fast KELM named as AEMD-KELM for producing a more accurate forecast. The experimental results using AEMD-KELM method for seven currency exchange rates like CAD/HKD, CAD/CNY, CAD/USD, CAD/BRL, CAD/JPY, EUR/USD, and GBP/USD provide superior prediction and trend analysis in comparison with EMD based ELM (EMD-ELM) approaches. Further currency exchange rate movement trends are used for generating trading signals like buy, sell or hold.