Long Short-Term Memory (LSTM) is a Recurrent Neural Network (RNN) that overcomes typical neural network constraints. Because of its ability to record temporal dependencies and solve nonlinear equations, long-term data...
Long Short-Term Memory (LSTM) is a Recurrent Neural Network (RNN) that overcomes typical neural network constraints. Because of its ability to record temporal dependencies and solve nonlinear equations, long-term data can be simply managed. LSTM is intended to alleviate the problems of RNN's vanishing gradient and exploding gradient difficulties. In this paper, we used LSTM to solve nonlinear plant equations with a gradient descent-based back propagation approach and retrieved the plant's output as well as other performance measures including Average Mean Square Error (AMSE) and Total Mean Average Error (TMAE). When the output of an LSTM is compared to that of a feed-forward Neural Network (FFNN), the LSTM outshines the FFNN. All the parameters of both models, such as iteration count and learning rate are kept constant.
A Double Internal Loop Recurrent Neural Network (DILRNN) model is proposed for Multiple Input Multiple Output (MIMO) system to obtain improved output using Gradient Descent based Back Propagation Algorithm. In the mod...
A Double Internal Loop Recurrent Neural Network (DILRNN) model is proposed for Multiple Input Multiple Output (MIMO) system to obtain improved output using Gradient Descent based Back Propagation Algorithm. In the modelling of DILRNN, three feedback loops are taken i.e., the first feedback is taken from the unit delay of the output to the hidden layer, the second feedback is taken from the previous value of hidden layer to itself and the last feedback is taken from the previous value of output to output. The weight is updated with the help of the algorithm after every iteration. The output of the proposed DILRNN model reduces error significantly vis-à-vis other Recurrent Neural Network (RNN) models for constant value of iterations and epochs. The statistical parameters such as RMSE and TMAE for the proposed model are greatly in comparison to other models and thereby enhances the accuracy of the model.
Partial shading imposes a major issue while generating power using solar photovoltaics (SPV) and consequences in the formation of hot spots and manifold peaks in the power-voltage (P-V) curve of the SPV arrays. As a r...
详细信息
Partial shading imposes a major issue while generating power using solar photovoltaics (SPV) and consequences in the formation of hot spots and manifold peaks in the power-voltage (P-V) curve of the SPV arrays. As a result, a main deforming concern arises i.e., The power loss due to mismatch in the SPV system is dependent on and directly caused by the shading pattern. Mitigation of this MPL can be assessed by selecting a proper configuration of the SPV array and optimal shading dispersion over the complete SPV array. This paper focuses on the implementation of renowned metaheuristic algorithms (MAs) to optimally disperse the shading effect for a partially shaded total-cross-tied (TCT) SPV array configuration. A partial shading effect is generated using a realistic moving cloud model by incorporating various affecting environmental parameters. Furthermore, MAs are tested for the designed moving cloud model and a comprehensive analysis is presented among the various SPV array configurations.
Several rural communities are still living with disrupted power supplies. Consequently, diesel generators are used for getting regular power supply to provide effective healthcare services. Usage of diesel generator n...
详细信息
ISBN:
(数字)9798350355048
ISBN:
(纸本)9798350355055
Several rural communities are still living with disrupted power supplies. Consequently, diesel generators are used for getting regular power supply to provide effective healthcare services. Usage of diesel generator not only have deteriorating impact on the environment, but also is an expensive alternative to grid supply. Usage of renewable energy systems with battery are becoming popular solution for feeding such kind of loads in the remote areas. In this work, an off-grid hybrid electrification system (HES) is designed which consists of Solar PV-Diesel Generator-Batteries for the regular supply of electricity to the available load of PHC, located in a remote area of Kaimur district in Bihar, India. Investigation is carried out for five different technologies of batteries Lead-acid (LA), Lithium-ion (LI), Vanadium flow (VF), Zinc bromide (ZB) and Nickel-iron (NI) which are incorporated with HES. An optimum configuration for a PHC has been designed taking all major techno-economic factors and renewable penetration into consideration. Investigation reveals that a vanadium flow-based hybrid electrification system is the most feasible solution with respect to the techno-economic perspective among all considered configurations.
This work presents a segment-based patient-independent (PI) seizure detection system using hybrid feature extraction method. The segment-based approach offers increased applicability across various seizure patients co...
详细信息
The Corona virus disease 2019 (COVID-19) pandemic has caused substantial increase in distress among people all over the world. This work aims to study depression during the COVID-19 among the educational sector and to...
详细信息
The accuracy of the solar forecasting model depends upon various factors such as attributes of the data, time horizon, time interval, length of the data, etc. This means attributes of data selection are an important f...
详细信息
The accuracy of the solar forecasting model depends upon various factors such as attributes of the data, time horizon, time interval, length of the data, etc. This means attributes of data selection are an important feature of any solar forecasting model. A lot of research has been done on solar forecasting using deep learning and machine learning approaches, providing better accuracy for a particular type of model and data. However, how to accurately apply the multi-model techniques in the data-driven approaches of the solar radiation prediction model is still a challenging issue due to the complexity of the temporal resolution, length, and attribute selection of the data. This paper proposes a multi-model technique using data-driven approaches to get an improvised solar forecasting model with respect to the attributes of data. In this research, a multi-model method based on data-driven approaches is developed for short-term solar radiation forecasting. Three years of weather data with different temporal resolutions taken from reliable online sources were used for training and testing in this work. The weather data considered various input parameters such as temperature, humidity, pressure, wind speed, and wind direction;solar radiation data is considered the model's target variable. This work is a two-stage process. In the first stage, multi-model methods are analyzed based on solar forecasts at different temporal resolutions, and best-performing models are selected. The optimization technique is applied to the best model in the second stage to obtain an improvised solar forecasting model. It is observed that the multi-model forecasts provide better accuracy in terms of R2, nRMSE, and MAE than the conventional forecasting model. In this work, the performance parameters of nRMSE = 0.34, MAE = 4.71, and R2 = 0.93 are obtained before optimization, and nRMSE = 0.25, MAE = 1.39 and R2 = 0.96 are obtained after optimization in the testing stage for an hourly dataset. Fo
In the financial sector, the sales price forecasting is a hot issue. Since the indices associated with the stock are nonlinear and are affected by various internal and external factors, they are very difficult to mode...
详细信息
Nowadays, various advanced techniques, like big data and deep learning, have been used in energy management systems for improving energy efficiency. Various research has been done on solar power generation prediction ...
详细信息
For grid-connected photovoltaic (PV) systems, accurate solar irradiance forecasting is crucial, especially in cases of intermittent environmental conditions, in order to ensure grid operation, scheduling, and grid ene...
For grid-connected photovoltaic (PV) systems, accurate solar irradiance forecasting is crucial, especially in cases of intermittent environmental conditions, in order to ensure grid operation, scheduling, and grid energy management. Solar irradiance, temperature, and other meteorological factors significantly influence PV generation and also make it intermittent in nature. Time series analysis provides an efficient way to map temporal patterns, like hourly, monthly, yearly, and seasonal variations, and within solar irradiance data. In this paper, time series forecasting of 24hourly future observations of global horizontal irradiance (GHI) is done using a multilayer perceptron (MLP) of deep learning framework. Different hyperparameters like hidden layers, hidden units of each layer, activation function, optimizer, and lag observations/steps are tuned to develop the best model that fits the GHI historical data. Further dropout regularization is used to avoid overfitting the model. The model is validated using validation data that the model has never seen before. RMSE, MSE, MAE, and NRMSE errors, aiming at minimizing forecasting errors on test data, are used to select the optimal value of hyperparameters.
暂无评论