In the smart grid (SG) environment, consumers are enabled to alter electricity consumption patterns in response to electricity prices and incentives. This results in prices that may differ from the initial price pattern. Electricity price and demand forecasting play a vital role in the reliability and sustainability of SG. Forecasting using big data has become a new hot research topic as a massive amount of data is being generated and stored in the SG environment. Electricity users, having advanced knowledge of prices and demand of electricity, can manage their load efficiently. In this paper, a recurrent neural network (RNN), long short term memory (LSTM), is used for electricity price and demand forecasting using big data. Researchers are working actively to propose new models of forecasting. These models contain a single input variable as well as multiple variables. From the literature, we observed that the use of multiple variables enhances the forecasting accuracy. Hence, our proposed model uses multiple variables as input and forecasts the future values of electricity demand and price. The hyperparameters of this algorithm are tuned using the Jaya optimization algorithm to improve the forecasting ability and increase the training mechanism of the model. Parameter tuning is necessary because the performance of a forecasting model depends on the values of these parameters. Selection of inappropriate values can result in inaccurate forecasting. So, integration of an optimization method improves the forecasting accuracy with minimum user efforts. For efficient forecasting, data is preprocessed and cleaned from missing values and outliers, using the z-score method. Furthermore, data is normalized before forecasting. The forecasting accuracy of the proposed model is evaluated using the root mean square error (RMSE) and mean absolute error (MAE). For a fair comparison, the proposed forecasting model is compared with univariate LSTM and support vector machine (SVM). The values of the performance metrics depict that the proposed model has higher accuracy than SVM and univariate LSTM.

In wireless underwater sensor networks (WUSNs), network protocols for information routing are usually designed when a significant number of nodes are present in the network. Therefore, for sparse conditions, when a noticeable reduction in the number of nodes occurs, the performance of such protocols exhibits a degraded behavior pattern. To cope with routing issues when sparse conditions prevail, two routing algorithms for WUSNs are proposed in this paper. They are energy-aware scalable reliable and void-hole mitigation routing (ESRVR) and cooperative energy-aware scalable reliable and void-hole mitigation routing (Co-ESRVR). The ESRVR uses a number of strategies. Firstly, it uses two hop neighbors’ information to develop routing trajectories for information advancement, as one hop information cannot avoid a void-hole, a condition when a node is not able to find neighbors towards the sea surface, and more than two hop information is difficult to obtain when sparse conditions prevail. Secondly, when a void-hole still exists, the protocol uses a backward transmission mechanism to find other routing paths to deliver packets to the end target. Thirdly, the time by which a packet is held by a node prior to transmission is short for the nodes with low energy, depth and high count of neighbors. This reduces packets loss and avoids congestion of the channel. It also helps the nodes with no or few neighbors to hold the packet for a significant chunk of time until they find suitable neighbors, due to sea tides and currents, for further packets’ advancement. The Co-ESRVR further adds reliability to information advancement by adding routing in a cooperative fashion to ESRVR, which involves packets advancement to destination along two paths: directly from source and via a relayed path. This provides multiple paths for data advancement to the sea surface, so that if one path is badly affected by the harsh sea characteristics, others may not be. Unlike the counterpart protocol, the proposed algorithms are not dependent on a node’s geographical location or the distance from the sea surface, which increases their scalability and reduces the computational complexity. Performance analysis displays superior behavior patterns of the proposed algorithms over the counterpart in terms of the compared characteristics.

Representation and classification of Electroencephalography (EEG) brain signals are critical processes for their analysis in cognitive tasks. Particularly, extraction of discriminative features from raw EEG signals, without any pre-processing, is a challenging task. Motivated by nuclear norm, we observed that there is a significant difference between the variances of EEG signals captured from the same brain region when a subject performs different tasks. This observation lead us to use singular value decomposition for computing dominant variances of EEG signals captured from a certain brain region while performing a certain task and use them as features (nuclear features). A simple and efficient class means based minimum distance classifier (CMMDC) is enough to predict brain states. This approach results in the feature space of significantly small dimension and gives equally good classification results on clean as well as raw data. We validated the effectiveness and robustness of the technique using four datasets of different tasks: fluid intelligence clean data (FICD), fluid intelligence raw data (FIRD), memory recall task (MRT), and eyes open / eyes closed task (EOEC). For each task, we analyzed EEG signals over six (06) different brain regions with 8, 16, 20, 18, 18 and 100 electrodes. The nuclear features from frontal brain region gave the 100% prediction accuracy. The discriminant analysis of the nuclear features has been conducted using intra-class and inter-class variations. Comparisons with the state-of-the-art techniques showed the superiority of the proposed system.