In order to address the issue of insufficient task offloading decisions in vehicle networks of transportation cyber-physical systems (TCPS) because of multitasking and resource constraints, this study presents a quasi-Newton deep reinforcement learning-based two-stage online offloading (QNRLO) algorithm. Computer simulation experiments show that the approach performs exceptionally well in terms of convergence under various conditions and parameter configurations. Most of the trials are carried out in a simulated setting, and further real-world scenarios may be required to confirm the algorithm’s efficacy. This methodology initially implements batch normalization techniques to enhance the training process of the deep neural network, subsequently utilizing the quasi-Newton method for optimization to successfully approximate the ideal answer. According to the experimental results, the QNRLO algorithm’s loss function and normalized computation rate have converged after 2,000 iterations, demonstrating the algorithm’s excellent stability and dependability. The findings demonstrate that the computational load and training time can be further optimized by appropriately adjusting certain parameters without compromising convergence performance. Furthermore, the technique incorporates system transmission time allocation into the TCPS model, hence augmenting the model’s practicality. The proposed approach markedly enhances the efficiency and stability of job offloading compared to previous algorithms, effectively addressing task offloading challenges in TCPS and exhibiting considerable applicability and reliability.
3 October 2023 in Engineering Applications of Artificial Intelligence
Within the realm of e-commerce networks, it is frequently observed that certain users exhibit behavior patterns that differ substantially from the normative behaviors exhibited by the majority of users. The identification of these atypical individuals and the understanding of their behavioral patterns are of significant practical significance in maintaining order on e-commerce platforms. One such method for accomplishing this objective entails examining the behavioral tendencies of atypical users through the abstraction of e-commerce networks as heterogeneous information networks. These networks are then transformed into a bipartite graph that establishes associations between users and devices. The Self-Supervised Aberrant Detection Model (SAD) has been proposed within this theoretical framework as a means to identify and detect users who exhibit aberrant behavior. The SSADM methodology utilizes a self-supervised learning process that utilizes autoencoders to encode representations of user nodes. The proposed method aims to maximize a combined objective function for backpropagation while utilizing support vector data description to detect abnormalities in the representations of user nodes. In summary, many tests have been conducted utilizing both authentic network datasets and partially synthetic network datasets to demonstrate the efficacy and superiority of the SAD technique, specifically within the domain of an energy-efficient 5G network.
16 May 2022 in Security and Communication Networks
Recently, data integrity for multiagent-based big data environments has been challenging. This paper presents a blockchain-based Merkle DAG structure (M-DAG) for audit data integrity. M-DAG resolves the problem that arises due to the multicopy of a large data volume in a big data environment. It employed Boneh–Lynn–Shacham’s (BSL) signature to verify the integrity of identical multicopy on big data environments. The proposed M-DAG audit mechanism uses a consortium chain algorithm for decentralized traceability and audit to archive reliable data. The evaluation has been carried out for the efficiency of the data integrity audit.
The design of solid-state lighting is vital, as numerous metrics are involved in their exact positioning, and as it is utilized in various processes, ranging from intelligent buildings to the internet of things (IoT). This work aims to determine the power and delay spread from the light source to the receiver plane. The positions of the light source and receiver were used for power estimation. We focus on analog orthogonal frequency-division multiplexing (OFDM) in visible light communication (VLC) and assess the area under the curve (AUC). The proposed system was designed using modulation techniques (i.e., quadrature amplitude modulation; QAM) for visible light communication (VLC) and pulse-width modulation (PWM) for dimming sources. For the positioning and spreading of brightness, the proof-of-concept was weighted equally over the entire area. Therefore, the receiver plane was analyzed, in order to measure the power of each light-emitting diode (LED) in a given area, using the delayed mean square error (MSE). A framework was applied for the placement of LEDs, using full-width at half-maximum (FWHM) parameters with varying distances. Then, the received power was confirmed. The results show that the AUC using DRMS values for LEDs significantly increased (by ) when the number of source LEDs was changed from four to three. These results confirm that our system, associated with the simple linear lateration estimator, can achieve better energy consumption.
Mobile edge computational power faces the difficulty of balancing the energy consumption of many devices and workloads as science and technology advance. Most related research focuses on exploiting edge server computing performance to reduce mobile device energy consumption and task execution time during task processing. Existing research, however, shows that there is no adequate answer to the energy consumption balances between multi-device and multitasking. The present edge computing system model has been updated to address this energy consumption balance problem. We present a blockchain-based analytical method for the energy utilization balance optimization problem of multi-mobile devices and multitasking and an optimistic scenario on this foundation. An investigation of the corresponding approximation ratio is performed. Compared to the total energy demand optimization method and the random algorithm, many simulation studies have been carried out. Compared to the random process, the testing findings demonstrate that the suggested greedy algorithm can improve average performance by 66.59 percent in terms of energy balance. Furthermore, when the minimum transmission power of the mobile device is between five and six dBm, the greedy algorithm nearly achieves the best solution when compared to the brute force technique under the classical task topology.