Power prediction is important not only for the smooth and economic operation of a combined cycle power plant (CCPP) but also to avoid technical issues such as power outages. In this work, we propose to utilize machine learning algorithms to predict the hourly‐based electrical power generated by a CCPP. For this, the generated power is considered a function of four fundamental parameters which are relative humidity, atmospheric pressure, ambient temperature, and exhaust vacuum. The measurements of these parameters and their yielded output power are used to train and test the machine learning models. The dataset for the proposed research is gathered over a period of six years and taken from a standard and publicly available machine learning repository. The utilized machine algorithms are K‐nearest neighbors (KNN), gradient‐boosted regression tree (GBRT), linear regression (LR), artificial neural network (ANN), and deep neural network (DNN). We report state‐of‐the‐art performance where GBRT outperforms not only the utilized algorithms but also all the previous methods on the given CCPP dataset. It achieves the minimum values of root mean square error (RMSE) of 2.58 and absolute error (AE) of 1.85.

In this article, a compact four-port MIMO antenna system resonating from 4.7–5.1 GHz on −6 dB criteria is discussed. The proposed antennas are arranged in a perpendicular manner providing diversity with good isolation characteristics. The proposed antenna was fabricated and designed on a commercially available low-cost FR-4 substrate with a relative permittivity of 4.4. The total size of the antenna is 40 × 40 mm², and a minimum isolation of 25 dB was observed at most nearby resonating elements. The proposed antenna was fabricated and tested at an in-house facility, and the measured results agree well with the simulations. The MIMO antenna characteristics, such as the envelope correlation coefficient (ECC) among any two radiating elements, have been found to be less than 0.1, and the diversity gain (DG) value evaluated showed that the proposed antenna is well designed. Furthermore, the SAR analysis showed that the desired antenna system is safe for users, with a value of 0.94 W/Kg. The channel capacity (cc) was found to be 18.7 bps/Hz, approximately 2.7 times more than SISO systems. Through its robust and reliable performance and its peak gain of 2.8 dBi, the proposed compact antenna is a good candidate for future 5G devices.

The demand of 5G in modern communication era due to its high data rate, reliable connectivity and low latency is enormous. This paper presents a novel dual band antenna resonating at two distinct bands allotted for 5G services. The proposed antenna is composed of inverted L shape probes comprising a rectangular defected ground structure. The propose antenna covers 3.4–3.6 GHz and 5.4–5.6 GHz spectrum. In propose MIMO system, the efficiency ranges from 52 to 69% with peak gain of 3.1 dBi. The proposed antenna system is sufficiently isolated with minimum value of 13 dB and ECC less than 0.05 among any two radiating elements. Similarly, the channel capacity is found to be 38 and 39.5 at both resonating bands at 20 dB SNR and diversity and mean effective gains lies in acceptable range. The radiation characteristics of the proposed design shows that the proposed antenna is providing good diversity characteristics and SAR values have demonstrated to be safe for user vicinity. The proposed dual band antenna prototype is developed tested. With the measured results obtained, the MIMO system proposed can be seen as vital candidate for 5G LTE band 42 and 46 services.

A wideband circularly polarized rectangular dielectric resonator antenna (DRA) fed by a single feeding mechanism has been studied theoretically and experimentally. The purpose of the study is to determine how adding a parasitic strip next to the flat surface metallic feed would affect various far- and near-field antenna characteristics. Initially, the basic antenna design, i.e., the T-shape feed known as antenna A, produced a 4.81% impedance matching bandwidth (|S₁₁| −10 dB). Due to the narrow and undesirable results of the initial antenna design, antenna-A was updated to the antenna-B design, i.e., Yagi-Uda. The antenna-B produced a decent result (7.89% S₁₁) as compared to antenna-A but still needed the bandwidth widened, for this, a parasitic patch was introduced next to the Yagi-Uda antenna on the rectangular DRA at an optimized location to further improve the results. This arrangement produced circular polarization (CP) waves spanning a broad bandwidth of 28.21% (3.59–3.44 GHz) and a broad impedance |S₁₁| bandwidth of around 29.74% (3.71–3.62 GHz). These findings show that, in addition to producing CP, parasite patches also cause the return loss to rise by a factor of almost three times when compared to results obtained with the Yagi-Uda-shape feed alone. Computer simulation technology was used for the simulation (CST-2017). The planned antenna geometry prototype was fabricated and measured. Performance indicators show that the suggested antenna is a good fit for 5G applications. The simulated outcomes and measurements match up reasonably.

Network on Chip (NoC) is a communication framework for the Multiprocessor System on Chip (MPSoC). It is a router-based communication system. In NoC architecture, nodes of MPSoC are communicating through the network. Different routing algorithms have been developed by researchers, e.g., XY, intermittent XY, DyAD, and DyXY. The main problems in these algorithms are congestion and faults. Congestion and faults cause delay, which degrades the performance of NoC. A congestion-aware algorithm is used for the distribution of traffic over NoC and for the avoidance of congestion. In this paper, a congestion-aware routing algorithm is proposed. The algorithm works by sending congestion information in the data packet. The algorithm is implemented on a mesh NoC using FPGA. The proposed algorithm decreases latency, increases throughput, and uses less bandwidth in sharing congestion information between routers in comparison to the existing congestion-aware routing algorithms.