Abstract null null The Photovoltaic generation inherits the instability due to the variability and non-availability of solar irradiation at times. Such unstable generation will cause grid management, planning, and operation issues. Researchers have proposed several classical and advanced algorithms to forecast the power generation of photovoltaic plants to avoid such unsuitability issues. Artificial Neural Networks advancement has pushed them in power forecasting, ranging from yearly to hourly prediction of power generation. These networks’ performance depends on the choice of hyperparameters, which includes the number of layers, neurons in each layer, activation function, and learning rate. In power forecasting, these parameters are selected through trial and error, which is inefficient and does not ensure the optimal selection. In this paper, we have presented the Hyperband Gated Recurrent Unit model for power, voltage, and current forecasting of the photovoltaic power plant. The model has a monthly prediction horizon with a temporal resolution of a day. We used the Hyperband technique for the optimal selection of the hyper-parameters. It is an iterative process where several configurations are tried on each trial, and only n best configurations qualify for the subsequent trial. The inputs to the model are irradiation, temperature, and wind speed, and the model's output includes current, voltage, and power. We trained our model on 11 months of data and predicated the outputs for the 12-th month. The network is tested with other variants of Recurrent Neural Networks based on several evaluation metrics. The proposed model achieved promising results with minimum error.
#1Abdul Rehman Khan(PIEAS: Pakistan Institute of Engineering and Applied Sciences)H-Index: 2
#2Ameer Tamoor Khan(PolyU: Hong Kong Polytechnic University)H-Index: 3
Last. Sunila Bakhsh(Balochistan University of Information Technology, Engineering and Management Sciences)
view all 4 authors...
In this paper, we presented an autonomous control framework for the wall following robot using an optimally configured Gated Recurrent Unit (GRU) model with the hyperband algorithm. GRU is popularly known for the time-series or sequence data, and it overcomes the vanishing gradient problem of RNN. GRU also consumes less memory and is computationally more efficient than LSTMs. The selection of hyper-parameters of the GRU model is a complex optimization problem with local minima. Usually, hyper-pa...
#1Ameer Tamoor Khan(PolyU: Hong Kong Polytechnic University)H-Index: 3
#2Shuai Li(PolyU: Hong Kong Polytechnic University)H-Index: 53
Last. Xinwei Cao(SHU: Shanghai University)H-Index: 6
view all 3 authors...
Abstract In this paper, we present a model-free tracking controller for a cooperative mobile-manipulators, which are the cornerstone for future smart homes. The mobile-manipulators are common in industries as they are flexible and mobile, and there are several control frameworks for their industrial applications. However, these control algorithms do not consider the unique complex environment of a smart home, which requires a specialized and customized control. For example, elderly care robots i...
Abstract The sites selected for solar PV facilities significantly affect the amount of electric power that can be generated over the long term. Therefore, predicting the power output of a specific PV plant is important when evaluating potential PV sites. However, whether prediction models built with data from existing PV plants can be applied to other plants for long-term power forecasting remains poorly understood. In this case, topographical and meteorological conditions, which differ among si...
The intermittency of solar energy resources has brought a big challenge for the optimization and planning of a future smart grid. To reduce the intermittency, an accurate prediction of photovoltaic (PV) power generation is very important. Therefore, this paper proposes a new forecasting method based on the recurrent neural network (RNN). At first, the entire solar power time series data is divided into inter-day data and intra-day data. Then, we apply RNN to discover the nonlinear features and i...
Abstract This study presents a hybrid numerical weather prediction model (NWP) and a Gaussian process regression (GPR) model for near surface wind speed prediction up to 72 h ahead using data partitioned on atmospheric stability class to improve model performance. NWP wind speed data from the UK meteorological office was corrected using a GPR model, where the data was subdivided using the atmospheric stability class calculated using the Pasquill-Gifford-Turner method based on observations at the...
Last. Faisal Q. Alenezi(The Public Authority for Applied Education and Training)H-Index: 2
view all 5 authors...
The use of solar photovoltaic (PV) systems as green renewable sources for electricity generation in modern power networks is steadily increasing. One of the problems with using PV units in developing countries and small companies is access to a simple model to assess the short-time output of a solar cell. For example, a robust model that is capable of analyzing cloud variations and ambient temperature (important factors impacting the PV output) to assess short-term PV output would be very helpfu...
Abstract This paper presents a fast and novel method to determine the optimal capacity of a battery and a hydrogen system for a grid-connected photovoltaic (PV) system based on the required grid dependency ( GD ) and the minimum Levelized Cost of Energy ( LCE ). The GD is calculated from the weather data at 9 locations throughout Japan during 25 years considering different sizing of PV, battery, and hydrogen system. Based on the results, the relationship between the GD and the capacities of the ...
Deep neural networks (DNN) have revolutionized the field of natural language processing (NLP). Convolutional neural network (CNN) and recurrent neural network (RNN), the two main types of DNN architectures, are widely explored to handle various NLP tasks. CNN is supposed to be good at extracting position-invariant features and RNN at modeling units in sequence. The state of the art on many NLP tasks often switches due to the battle between CNNs and RNNs. This work is the first systematic compari...
#2Kevin Jamieson(UW: University of Washington)H-Index: 21
Last. Ameet Talwalkar(CMU: Carnegie Mellon University)H-Index: 46
view all 5 authors...
Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian optimization to adaptively select configurations, we focus on speeding up random search through adaptive resource allocation and early-stopping. We formulate hyperparameter optimization as a pure-exploration nonstochastic infinite-armed bandit problem where a predefined resource like iterations, data samples, or features is allocated to randomly sampled...
