Search

Summary: Web service recommendation as an emerging topic attracts increasing attention due to its important practical significance. As the number of available Web services continues to grow, users face the challenge of searching the most suitable services that meet their specific needs. Quality of service (QoS)‐based service recommendation becomes a popular approach to address this issue. However, existing QoS‐based service recommendation methods are inability to effectively capture valuable content and structural information from services. These methods often rely solely on low‐order explicit feature intersections in QoS information, do not fully utilize the high‐order implicit feature intersections, and ignore the rich semantic information existing in service descriptions and user preferences. To address this problem, this paper proposes a Web service recommendation method via combining knowledge distillation representation and DCNMIX quality prediction. This method combines content‐based and structure‐based service classification and service prediction based on multi‐dimensional service quality information. First, it builds a service relationship network using semantic features extracted from service descriptions. Second, it designs a graph neural network knowledge distillation framework. The teacher model extracts the knowledge of the graph neural network model, and the student model learns the structure‐based and feature‐based prior knowledge of the service relationship network. Then the student model is used to learn the knowledge of the teacher model, classify Web services, and obtain service representations. Finally, based on service representations and multi‐dimensional QoS information, it exploits the DCNMIX model to learn the explicit and implicit features intersections of Web services and obtain the prediction score and ranking of Web services. The experimental results on the ProgrammableWeb dataset show that the proposed method outperforms the state‐of‐the‐art baselines in terms of Recall, F1, Logloss, and AUC_ROC. [ABSTRACT FROM AUTHOR]

Summary: This study shows how GPU performance of the ADER discontinuous Galerkin method in SeisSol (an earthquake simulation software) can be further improved while preserving its original design that ensures high CPU performance. We introduce a new code generator ("ChainForge") that fuses subsequent batched matrix multiplications ("GEMMs") into a single GPU kernel, holding intermediate results in shared memory as long as necessary. The generator operates as an external module linked against SeisSol's domain specific language YATeTo and, as a result, the original SeisSol source code remains mainly unchanged. In this paper, we discuss several challenges related to automatic fusion of GPU kernels and provide solutions to them. By and large, we gain ≈$$ \approx $$60% in performance of SeisSol's wave propagation solver using Fused‐GEMMs compared to the original GPU implementation. We demonstrated this on benchmarks as well as on a real production scenario simulating the Northridge 1994 earthquake. [ABSTRACT FROM AUTHOR]

Summary: Due to the high performance of cloud computing‐based microservices, a wide range of industries and fields rely on them. In a containerized cloud, traditional resource management strategies are typically used to allocate and migrate virtual machines. A major problem for cloud service providers is resource allocation for containers, which directly affects system performance and resource consumption. In this paper, we propose a joint optimization of load balancing and resource allocation in the cloud using an optimal container management strategy. We aim to enhance scheduling efficiency and reduce costs by improving the container's schedule requested digitally by users. An improved backtracking search optimization (IBSO) algorithm is used to allocate resources between end‐users/IoT devices and the cloud under the consideration of service‐level agreements. Mechanic quantum recurrent neural networks (MQ‐RNNs) are designed to allocate, consolidate, and migrate containers in cloud environments. The various simulation measures used to validate the proposed strategy are energy consumption, number of active servers, number of interruptions, total cost, runtime, and statistical measures. [ABSTRACT FROM AUTHOR]

Architectures generation optimization has been received a lot of attention in neural architecture search (NAS) since its efficiency in generating architecture. By learning the architecture representation through unsupervised learning and constructing a latent space, the prediction process of predictors is simplified, leading to improved efficiency in architecture search. However, searching for architectures with top performance in complex and large NAS search spaces remains challenging. In this paper, an approach that combined a ranker and generative model is proposed to address this challenge through regularizing the latent space and identifying architectures with top rankings. We introduce the ranking error to gradually regulate the training of the generative model, making it easier to identify architecture representations in the latent space. Additionally, a surrogate‐assisted evolutionary search method that utilized neural network Bayesian optimization is proposed to efficiently explore promising architectures in the latent space. We demonstrate the benefits of our approach in optimizing architectures with top rankings, and our method outperforms state‐of‐the‐art techniques on various NAS benchmarks. The code is available at https://github.com/outofstyle/RAGS‐NAS. [ABSTRACT FROM AUTHOR]

Summary: This paper presents a numerical approach for the design sensitivity analysis of modal frequencies of elastic structures submerged in an unbounded heavy fluid domain. Because the feedback of sound pressure onto the fluid‐loaded structures has to be taken into account in this case, a fully coupled scheme which combines the structural finite element method (FEM) and the acoustic boundary element method (BEM) is employed in the numerical simulation. The resulting nonlinear eigenvalue problem created by the coupled finite element and boundary element (FE‐BE) method is converted into a generalized eigenvalue problem (GEP) of reduced dimension by using a contour integral method. The design sensitivity formulation for non‐repeated eigenvalues is derived based on an adjoint method which uses both the left and right eigenvectors, and a small GEP is formed to calculate the gradients of repeated eigenvalues. The Burton‐Miller formulation is employed to shift the fictitious eigenfrequencies and their derivatives, and the parameter setting which is beneficial to the filtering of fictitious eigenfrequencies is investigated. Numerical examples are given to verify the accuracy and effectiveness of the developed method. [ABSTRACT FROM AUTHOR]

Summary: This paper presents Relay node selection scheme and Deep sleep period for power management in Energy Harvesting Wireless Sensor Networks (RD‐EHWSN), a new energy‐saving scheme founded on asynchronous duty cycling. RD‐EHWSN reduces sensor node energy consumption and guarantees equilibrium energy use between sensor nodes in WSN with the energy harvesting capacity by adjusting these sensor nodes duty cycles more drastically and deeply by according to the estimated value of its residual energy on the basis of future‐presented harvested energy, and this is done through the use of a new proposed energy threshold policy. RD‐EHWSN also grips the benefit of transmitter initiated using the low power listening (LPL) technique with short preamble messages and uses a new relay node selection procedure to achieve the load balancing in WSN. We implemented RD‐EHWSN by using OMNeT++/MiXiM. For evaluation, we compared it with PS‐EHWSN, under multiple concurrent multihop traffic flows scenarios and scenarios in which nodes can harvest different energy harvesting rate. In all experiments, RD‐EHWSN significantly outperformed the PS‐EHWSN scheme; the results of simulation demonstrate that our scheme enhances the general yielding of WSN thru lessening the energy consumption and the mean latency, as well as raising the packet delivery ratio and the throughput. Moreover, RD‐EHWSN improves the WSN lifetime and ensures it operates in good condition in the case where the energy harvesting rate is lower by comparing it with the PS‐EHWSN scheme. [ABSTRACT FROM AUTHOR]

Summary: Opportunistic network (OppNet) belongs to the category of Mobile Ad‐hoc Networks (MANETs), a kind of Delay Tolerant Network (DTN), where the wireless nodes are completely mobile and the data transmission routes are dynamic. The major challenge in developing a routing model for such a network is the unpredictable nature of the movement of the nodes. In this paper, a spatiotemporal prediction model based on human mobility pattern is proposed using Bayesian posterior probability (BPPR) where several clusters are identified within the network and the day and time duration of nodes visiting those clusters are recorded. The Bayesian posterior probability is then used to determine the probability of the neighbor node visiting the destination's cluster. If the calculated probability for that node is higher than a specified threshold, the packet will be forwarded. A comparison of the results obtained on simulation is made with benchmark models—Epidemic, Prophet, HBPR, EDR, NexT, and EBC, to name a few, where it is found that on average the proposed model outperforms the other models in terms of delivery probability, hop count and number of messages dropped by around 23.89%, 24.8%, 24.4%, 37%, 11%, and 42% respectively, with varying number of nodes, TTL, message generation interval, and buffer size. Similar improvements have been observed in terms of the other two metrics. In terms of overhead ratio, the proposed model outperforms Epidemic, Prophet, HBPR, NexT, and EBC. However, as the number of nodes and TTL are varied, BPPR performs better than NexT by around 9% and 12%, respectively, in terms of average latency. [ABSTRACT FROM AUTHOR]

Summary: This paper analyzes the performance of a cooperative nonorthogonal multiple access (NOMA) in an underlay cognitive radio network aided by an energy harvesting relay. A secondary source transmits signal for two users, where a near user acts as a relay for the far user. The far user applies the selection combining (SC) approach on the signals which were relayed by the near user and received via direct path from the secondary source. We analytically derive the outage probability (OP) of each user separately, the overall system OP, and the throughput of the system. The impact of the power allocation coefficient of NOMA and energy harvesting parameters on outage is indicated. Further, the performance of the network is investigated with imperfection in successive interference cancellation (SIC), maximal ratio combining (MRC) at relay, and Nakagami‐m fading. The results derived analytically are supported by simulation in MATLAB. [ABSTRACT FROM AUTHOR]

Summary: With the continuous proliferation of sensing technology, it has become possible to utilize energy harvesting (EH)‐enabled sensor nodes for a variety of applications. However, conventional wireless sensor networks (WSNs), that is, those without EH‐enabled nodes, still have limited applicability due to their limited battery resources. Further, the utilization of EH‐enabled nodes in the network not only imposes a financial burden on the user but also limits its performance due to its dependence on environmental conditions. To address this concern, in this paper, we propose the EH‐enabled energy‐efficient routing (EHEER) technique for green communication in WSN. The predominant concern being addressed in this paper is the selection of cluster head (CH), which helps in gathering, aggregating and forwarding the data from the cluster‐based routing paradigm. We use the spotted hyena optimizer (SHO) algorithm for optimizing the fitness parameters for CH selection, namely, energy ratio, distance considerations, node density, load balancing and the network's average energy. We use EH‐enabled nodes in the network strategically so as to keep control over the costs incurred in the network. The simulation outcomes empirically prove the efficacy of the proposed work, as it effectively increases the network stability and operational period by a huge margin as compared to the existing techniques. [ABSTRACT FROM AUTHOR]

Summary: The orthogonal time frequency space (OTFS) transmission scheme was shown to outperform orthogonal frequency division multiplexing (OFDM) under the doubly dispersive channel. In this paper, the linear precoding is studied for multiple‐input and multiple‐out (MIMO) OTFS systems, in which a spatial‐Doppler domain singular value decomposition (SVD) precoding scheme is proposed. At the transmitter, the Doppler domain symbols from different spatial streams are precoded before projected onto multiple antennas for transmission. At the receiver, multipath components of the transmitted symbols in the delay‐Doppler grid are combined by using maximal ratio combining (MRC) strategy, so as to achieve the multipath diversity gain and increase the reception reliability. The achievable rate and complexity of the proposed scheme are analyzed, revealing that it can increase the achievable rate while reducing the detector complexity as well. The simulation results confirm that the SVD‐based precoding significantly enhances the error performance of the MIMO‐OTFS with MRC‐based detector. [ABSTRACT FROM AUTHOR]