False Data Injection Attacks (FDIAs) present a significant threat to smart grids by manipulating measurement data, which may lead control centers to make incorrect operational decisions. Accurate and efficient detection of FDIAs is critical for ensuring reliable grid operation. Existing deep learning approaches often fail to capture both short-term local features and long-term dependencies in power grid data, and they typically show weak correlations with past and future time series information, reducing the trustworthiness of detection results. Similarly, conventional Intrusion Detection Systems (IDS) struggle to detect advanced FDIAs due to their reliance on predefined signatures and rule-based mechanisms. To overcome these limitations, we propose IG-APSO-DNN, a two-stage deep learning model for detecting FDIAs in smart grids. The first stage employs Information Gain (IG) and Adaptive Particle Swarm Optimization (APSO) for feature selection, reducing data dimensionality and improving model efficiency. The second stage uses a Deep Neural Network (DNN) to effectively capture both spatial and temporal patterns in smart grid measurements. The proposed model is evaluated on the Industrial Control System (ICS) Cyber Attack Power System Dataset, which simulates various FDIA scenarios. Results demonstrate that IG-APSO-DNN significantly outperforms traditional methods, improving key performance metrics including detection accuracy, precision, recall, and F-measure, while ensuring reliable operation of the smart grid. This study presents a robust anomaly-based IDS framework and highlights future directions, such as real-world validation, adaptive learning, exploration of novel optimization algorithms, and addressing scalability and real-time processing challenges.

Parallel power loads anomalies are processed by a fast-density peak clustering technique that capitalizes on the hybrid strengths of Canopy and K-means algorithms all within Apache Mahout’s distributed machine-learning environment. The study taps into Apache Hadoop’s robust tools for data storage and processing, including HDFS and MapReduce, to effectively manage and analyze big data challenges. The preprocessing phase utilizes Canopy clustering to expedite the initial partitioning of data points, which are subsequently refined by K-means to enhance clustering performance. Experimental results confirm that incorporating the Canopy as an initial step markedly reduces the computational effort to process the vast quantity of parallel power load abnormalities. The Canopy clustering approach, enabled by distributed machine learning through Apache Mahout, is utilized as a preprocessing step within the K-means clustering technique. The hybrid algorithm was implemented to minimise the length of time needed to address the massive scale of the detected parallel power load abnormalities. Data vectors are generated based on the time needed, sequential and parallel candidate feature data are obtained, and the data rate is combined. After classifying the time set using the canopy with the K-means algorithm and the vector representation weighted by factors, the clustering impact is assessed using purity, precision, recall, and F value. The results showed that using canopy as a preprocessing step cut the time it proceeds to deal with the significant number of power load abnormalities found in parallel using a fast density peak dataset and the time it proceeds for the k-means algorithm to run. Additionally, tests demonstrate that combining canopy and the K-means algorithm to analyze data performs consistently and dependably on the Hadoop platform and has a clustering result that offers a scalable and effective solution for power system monitoring.

This article proposes a novel Airborne Internet of Things Network (AIN) system architecture for monitoring water quality, combining existing wireless technologies with the aid of a low altitude platform (LAP) to relay data over long distances in hilly terrain. The proposed system consists of water quality sensors, smart utility network (SUN) devices, long range (LoRa) wireless devices, an LAP air balloon, and Wi-Fi devices. A measurement campaign was conducted to assess the proposed system, focusing on the communication link reliability and the LAP stability and robustness. Several constraints, such as payload limit and safe weather conditions, were also highlighted for operating the LAP with extensive and reliable coverage. On the other hand, characterizing the wireless channel has become a crucial parameter for planning and deploying Internet of Things (IoT) applications. Accordingly, this work proposes a novel hybrid machine learning (ML)-based semi-empirical path loss (PL) model for LoRa wireless communication. The results validated the proposed system’s effectiveness, unique characteristics, and capability to monitor water quality in a harsh environment. Results also revealed a significant difference in packet delivery rate (PDR) for different gateway height and spreading factor (SF) configurations. For instance, switching SF7 to SF12 increased PDR by 28.7%. Meanwhile, increasing gateway height increased PDR by 29.2% for similar SF configurations. The evaluation also revealed that none of the established PL models are suitable to represent harsh tropical environments. Finally, the proposed model achieved nearly 90% prediction accuracy for testing samples and 95% accuracy for training and overall measurement samples, vastly outperforming conventional models.

Narrowband Internet of Things (NB-IoT) is expected to lead the way in wireless access technologies and support major 5G-based Internet of Things applications in the future. Since NB-IoT has yet to be fully deployed globally, there are only limited real-world performance evaluations available, particularly in the case of outdoor performance. Therefore, this study expanded on previous studies and comprehensively evaluated the performance of NB-IoT in the real world in terms of coverage parameters, path loss (PL), packet delivery rate (PDR), and latency limits. Numerical and detailed analyses were also performed to calculate power consumption and estimate the average battery life of NB-IoT, Sigfox, and LoRaWAN in relation to the various factors affecting power consumption. These three technologies were then compared in terms of power consumption. An overall PDR of 91.76% was achieved, indicating that NB-IoT can handle high data rates with minimal signal quality. NB-IoT performance was also found to correspond with theoretical assumptions on coverage and maximum range. However, depending on signal quality, latency was found to vary greatly, resulting in critical degradation of battery life efficiency. Although this study discovered that immense power savings could be achieved by applying critical power management strategies, achieving a long battery life for NB-IoT was not simple. LoRaWAN and Sigfox technologies proved to be more battery efficient than NB-IoT. In a one packet delivery per day scenario, LoRaWAN, Sigfox, and NB-IoT were found to have average battery lives of 1608.9, 1527.6, and 344.9 days, respectively.

Statistical distribution of rain attenuation is essential for development of microwave and millimeter‐wave communication links. Therefore rain‐related statistics are very important for a commercialisation system designer. This study proposes modifications to the International Telecommunication Union (ITU‐R P.618‐10) model and an appropriate rain attenuation prediction model for tropical countries. The model was developed based on data obtained from tropical and equatorial regions. The proposed model uses rainfall rate and rain attenuation at 0.01% of the time, R 0.01 and A 0.01 , elevation angle θ and altitude of site h s , respectively, as input parameters. The proposed model showed remarkable agreement with existing rain attenuation measured data in terms of prediction errors for mean square, standard deviation and root‐mean square. The proposed rain attenuation model was used for validation by comparing the model with measured data collected from Nigeria, Kenya and Papua New Guinea, whereby the proposed model gave a percentage error below 12%.

In this paper, a new trend of Space Time Block Code-Orthogonal Frequency Division Multiplexing (STBC-OFDM) was proposed. First, introduce brief description of the conventional (STBC-OFDM) scheme. Second, introduce the efficient and low complexity scheme of a STBC-OFDM, where both encoder and decoder lay in the time domain. This scheme does not require channel knowledge either at the transmitter or receiver. The decoding algorithm is based on generalized maximum-likelihood sequence estimation. The performance of the proposed scheme was investigated over two-tap Rayleigh fading channels. The simulation results show the performance of proposed STBC-OFDM scheme definitely outperforms conventional STBC-OFDM scheme on fading channel for different Doppler frequency (fD).

The main drawback of the Multi - Carrier Code Division Multiple Access (MC - CDMA) systems is the high Peak - to - Average Power Ratio (PAPR). MC - CDMA is the best candidate for the fourth generation of mobile communications. Many works present techniques to reduce the PAPR like the Partial Transmit Sequence (PTS), Selected Mapping (SLM), Clipping and Filtering and so on, but all are either increases the system complexity or reduce the Bit Error Rate (BER) performance. In this paper, we proposed a technique that is easy to implement and enhance the BER performance at the same time. The key idea of this method is based on a phase changing transform. We have used the Inverse Fast Fourier Transform (IFFT) as a phase re - distributor which consequently will reduce the PAPR at the same time it will enhance the Walsh - Hadamard spreading code when it is not fully loaded. Simulation results show good enhancement with respect of PAPR and the BER approximately doesn't affected without increasing the complexity.

At frequencies above 10 GHz, cloud attenuation in equatorial climate is one of the components that need to be characterised for low-availability satellite links. In addition to annual and worst month cumulative cloud attenuation, the statistics of seasonal and diurnal variations are required for providing detailed insights into system design. The authors present the cloud occurrences observed during different months, seasons and cloud attenuation results obtained from Penang, Malaysia, for a period of 5 years. A comparison of the present results with the results obtained from the existing models is also presented.