Improve System Throughput Research Articles

Advanced Custom Interconnects: A Paradigm Shift in High-Performance Computing Data Transfer Efficiency

Recent advancements in high-performance computing (HPC) systems have highlighted the critical role of custom interconnects in achieving optimal system performance and efficiency. This article comprehensively analyzes modern custom interconnect architectures, focusing on their capacity to enhance data transfer speeds while maintaining power efficiency. The article examines the integration mechanisms for heterogeneous computing elements, including CPUs, GPUs, and specialized accelerators, and evaluates their impact on system-wide performance. The article explores advanced routing algorithms and coherence protocols that enable seamless communication across multiple processing elements while ensuring data consistency. The findings demonstrate that custom interconnects significantly improve system throughput and reduce latency in large-scale HPC deployments. Furthermore, the article analyzes the implications of these advancements for cloud computing, artificial intelligence, and big data analytics applications. This article contributes to the understanding of next-generation computing infrastructure by highlighting the crucial relationship between interconnect design and overall system performance while addressing the escalating demands of modern computational workloads.

Enhancing energy efficiency in MC-NOMA systems through optimized channel and power allocation

Non-orthogonal multiple access (NOMA) has quickly become popular due to its higher spectral efficiency (SE) and is crucial in extending future networks’ capacity. This paper presents an innovative approach to enhancing energy efficiency (EE) in downlink (DL) multi-carrier (MC) NOMA systems, in which a single base station (BS) supports a group of users across multiple sub-channels. A novel least user sum gain-based user assignment (LUSGUA) algorithm is proposed in this paper, which prioritizes users with the lowest channel gains for optimal sub-carrier allocation. Additionally, a novel power allocation (PA) scheme is developed across sub-carriers to further improve energy efficiency (EE), throughput, and fairness. throughput and fairness. Since the PA optimization problem (OP) is constrained and non-convex, to tackle this problem, a penalty approach (PTA) is proposed, which is then addressed by particle swarm optimization (PSO) with sequential optimization of the inter/intra-level PA. Power is allocated across sub-carriers at the inter-level using PSO, while at the intra-level, power is distributed among users via the Bisection Method (BM). Simulation results demonstrate that the proposed algorithm achieves significant enhancements in EE, with improvements ranging from 13.04% to 48.67% compared to existing resource allocation (RA) schemes techniques, while also improving system throughput, fairness, and outage percentage. These results highlight substantial advancements over traditional methods.

Cross-shard transaction optimization based on community detection in sharding blockchain systems

Blockchain systems have always faced the challenge of performance bottlenecks, and sharding technology is considered a promising mainstream on-chain scalability solution to solve this problem. Due to the complexity and high cost of the cross-shard transaction processing mechanism in the sharding blockchain system, as well as the high proportion of cross-shard transactions, it becomes challenging for the sharding blockchain system to reach the ideal theoretical performance upper limit. Therefore, this paper aims to reduce the proportion of cross-shard transactions by dividing accounts with frequent transactions into the same shard, thereby improving system throughput. This paper builds a hypergraph based on historical transaction data to represent the diverse transaction relationships between accounts, and formulates the account division problem in the blockchain as a community discovery problem on the hypergraph structure. A time-aware community detection algorithm is proposed to partition accounts by considering the sustainability of transaction relationships between accounts. This also solves the problem of community detection algorithms tending to partition into larger shards. In addition, this paper builds a local Ethereum test network and implements the proposed algorithm on a real transaction dataset. Experimental results show that this algorithm can reduce the proportion of cross-shard transactions from about 95% to about 10%. Furthermore, it shows superior performance in terms of transaction throughput and latency compared with other community detection-based account partitioning algorithms.

A novel sharding algorithm based on TOPSIS method for blockchain systems

PurposePerformance optimization algorithms based on node attributes are of great importance for sharding blockchain systems. Currently, existing studies on blockchain sharding algorithms consider only random selection sharding strategies. However, the random selection strategy does not perfectly utilize the performance of a node to break the bottleneck of blockchain performance.Design/methodology/approachThis paper proposes a blockchain sharding algorithm called TOPSIS Optimization Sharding System (TOSS), which is based on entropy weight method, relative Euclidean distance and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). It defines a multi-attribute matrix to assess node performance and applies TOPSIS for scoring nodes. Then, an algorithm based on the TOPSIS method is proposed to calculate the performance score of each data node. In addition, an entropy weighting method is introduced to obtain the weights of each attribute to balance the impact of dimensional differences of attributes on the attribute weights. Nodes are ranked by composite scores to guide partitioning.FindingsThe effectiveness of the proposed algorithm in this paper is verified by comparing it with various comparative algorithms. The experimental results show that the TOSS algorithm outperforms the comparison algorithms in terms of performance improvement for the blockchain system, and the throughput metrics are improved by about 20% in comparison.Originality/valueThis study introduces a novel approach to blockchain sharding by incorporating the entropy weight method and relative Euclidean distance TOPSIS into the sharding process. This approach allows for a more effective utilization of node performance attributes, leading to significant improvements in system throughput and overall performance, addressing the limitations of the random selection strategy commonly used in existing algorithms.

Solving blockage problem of the 5G mmWaves Wireless Communications using Jellyfish Search Optimizer

The 5G technologies are aimed to support a variety of vertically connected applications with heterogeneous devices and machines with significant improvements in terms of higher quality of service, increased network capacity and improved system throughput. However, 5G systems still face a number of challenges mentioned by researchers and organizations, and among these challenges, we highlight that millimeter wave links are very susceptible to blockage. If the line-of-sight communication path is blocked, reflexive path communication can help maintain communication. The shortest route was to take an alternate route when the first route was blocked. Among the proposed solutions to the blocking problem is an algorithm to distribute the power between different mmWave communication paths in order to overcome the masses of links under randomly distributed obstacles. The problem has been resolved with an exact method. In this article, we have optimized all the results of this exact method by applying a powerful metaheuristic technique called jellyfish search optimizer to maximize the overall capacity of the path between two nodes. The results showed that our approach procures an improvements exceed 100% over the results of the exact method.

Cross-chain mapping blockchain: scalable data management in massive IoT networks

We propose a Cross-Chain Mapping Blockchain (CCMB) for scalable data management in massive Internet of Things (IoT) networks. Specifically, CCMB aims to improve the scalability of securely storing, tracing, and transmitting IoT behavior and reputation data based on our proposed cross-mapped Behavior Chain (BChain) and Reputation Chain (RChain). To improve off-chain IoT data storage scalability, we show that our lightweight CCMB architecture efficiently utilizes available fog-cloud resources. The scalability of on-chain IoT data tracing is enhanced using our Mapping Smart Contract (MSC) and cross-chain mapping design to perform rapid Reputation-to-Behavior (R2B) traceability queries between BChain and RChain blocks. To maximize off-chain to on-chain throughput, we optimize the CCMB block settings and producers based on a general Poisson Point Process (PPP) network model. The constrained optimization problem is formulated as a Markov Decision Process (MDP), and solved using a dual-network Deep Reinforcement Learning (DRL) algorithm. Simulation results validate CCMB's scalability advantages in storage, traceability, and throughput. In specific massive IoT scenarios, CCMB can reduce the storage footprint by 50% and traceability query time by 90%, while improving system throughput by 55% compared to existing benchmarks.

Atom: An Efficient Query Serving System for Embedding-based Knowledge Graph Reasoning with Operator-level Batching

Knowledge graph reasoning (KGR) answers logical queries over a knowledge graph (KG), and embedding-based KGR (EKGR) becomes popular recently, which embeds both queries and KG entities such that the vector embeddings of a query and its answer entities are similar. Compared with traditional KGR methods based on subgraph matching, EKGR produces fewer intermediate results and is more robust to missing and noisy information in the KG. However, existing systems are inefficient for serving online EKGR queries because they can only batch queries of the same type for execution (i.e., query-level batching ) and hence have limited batching opportunities due to the heterogeneity of queries. To serve EKGR queries efficiently, we propose the Atom system with operator-level batching, which decomposes queries into operators and batches operators of the same type from different queries for execution. The insight is that the types of operators are far fewer than the types of queries, and thus different queries typically share common operators, yielding more batching opportunities. To schedule the operators, Atom adopts a hybrid policy, which improves system throughput and avoids starving rare operators. For efficiency, Atom incorporates system optimizations including two-level pipeline, opportunistic submission, pre-allocated memory buffer, and tailored GPU kernels. Experiment results show that compared with existing systems, Atom can improve query throughput by over 20x and reduce query latency by over 5x. Micro experiments suggest that the designs and optimizations are effective in improving system performance.

Adaptive and Scalable Database Management with Machine Learning Integration: A PostgreSQL Case Study

The increasing complexity of managing modern database systems, particularly in terms of optimizing query performance for large datasets, presents significant challenges that traditional methods often fail to address. This paper proposes a comprehensive framework for integrating advanced machine learning (ML) models within the architecture of a database management system (DBMS), with a specific focus on PostgreSQL. Our approach leverages a combination of supervised and unsupervised learning techniques to predict query execution times, optimize performance, and dynamically manage workloads. Unlike existing solutions that address specific optimization tasks in isolation, our framework provides a unified platform that supports real-time model inference and automatic database configuration adjustments based on workload patterns. A key contribution of our work is the integration of ML capabilities directly into the DBMS engine, enabling seamless interaction between the ML models and the query optimization process. This integration allows for the automatic retraining of models and dynamic workload management, resulting in substantial improvements in both query response times and overall system throughput. Our evaluations using the Transaction Processing Performance Council Decision Support (TPC-DS) benchmark dataset at scale factors of 100 GB, 1 TB, and 10 TB demonstrate a reduction of up to 42% in query execution times and a 74% improvement in throughput compared with traditional approaches. Additionally, we address challenges such as potential conflicts in tuning recommendations and the performance overhead associated with ML integration, providing insights for future research directions. This study is motivated by the need for autonomous tuning mechanisms to manage large-scale, heterogeneous workloads while answering key research questions, such as the following: (1) How can machine learning models be integrated into a DBMS to improve query optimization and workload management? (2) What performance improvements can be achieved through dynamic configuration tuning based on real-time workload patterns? Our results suggest that the proposed framework significantly reduces the need for manual database administration while effectively adapting to evolving workloads, offering a robust solution for modern large-scale data environments.

Serein: A parallel pipeline‐based DAG schema for consensus in blockchain

AbstractAs the core technology of blockchain, consensus mechanisms play a crucial role in ensuring the consistency and reliability of blockchain systems. In a decentralized and open system environment like blockchain, traditional consensus algorithms are often unsuitable due to their inability to tolerate arbitrary faults such as malicious node behaviour. Consequently, Byzantine fault tolerance consensus algorithms have become a focal point in blockchain systems. However, as Byzantine fault tolerance consensus algorithms have evolved, they still face significant challenges, particularly in addressing issues related to network latency and throughput. This paper proposes a parallel pipeline‐based DAG schema for consensus in blockchain, Serein. Firstly, the Serein algorithm achieves functional partitioning of nodes, enhancing their scalability. Secondly, it employs a pipeline structure, allowing each block to proceed without waiting for the previous block's result, thereby reducing block generation latency. Lastly, the Serein algorithm leverages the advantages of the DAG block structure to achieve concurrent block ordering and submission, improving system throughput. Experimental results demonstrate that the proposed Serein algorithm maintains robust performance under conditions of high transaction volume with multiple nodes, effectively enhancing consensus efficiency while ensuring Byzantine fault‐tolerant security.

User Scheduling and Path Planning for Reconfigurable Intelligent Surface Assisted MISO UAV Communication

The high mobility of unmanned aerial vehicles (UAVs) enables them to improve system throughput by establishing line-of-sight (LoS) links. Nevertheless, in urban environments, these LoS links can be disrupted by complex urban structures, leading to potential interference issues. Reconfigurable intelligent surfaces (RIS) provide an innovative approach to enhance communication performance by intelligently reflecting incident signals. Recent studies suggest that utilizing multi-antenna transmission can increase system efficiency, while single-antenna transmission may be more prone to interference. To address these challenges, this article introduces a RIS-assisted multiple-input single-output (MISO) UAV communication system. Our objective is to optimize the minimum user rate, thereby guaranteeing equitable communication for all users. Nevertheless, the non-convexity inherent in this optimization problem complicates the pursuit of a direct solution. Hence, we decompose the problem into four subproblems: user scheduling optimization, RIS phase-shift optimization, UAV trajectory optimization, and UAV transmit beamforming optimization. To obtain suboptimal solutions, we have developed an alternating iterative optimization algorithm for addressing the four subproblems. Numerical results demonstrate that our algorithm effectively boosts the minimum user rate of the entire system.

Distributed resource optimisation using the Q-learning algorithm, in device-to-device communication: A reinforcement learning paradigm

In the context of wireless systems going forward, particularly in the Beyond 5G (B5G) era, where high data rates and low latency are critical, D2D communication is a pivotal technology that has many advantages. In D2D communication, the allocation of resources plays a critical role in achieving higher throughput while ensuring interference management, improved spectrum and energy efficiency, and system fairness. Conventional resource allocation methodologies encounter challenges in dynamically changing and diverse communication environments. To deal with the dynamic and unpredictable character of channel characteristics, we utilize a distributed iterative resource allocation technique based on the reinforcement learning (RL) approach that empowers the system to learn and adapt to the wireless environment autonomously. In this paper, we formulate a distributed Q learning-based RL method as its real-time learning capabilities, reduced communication overhead, and exploration efficiency make it well-suited for adapting to dynamic D2D environments compared to other RL methods. By applying the Q-learning method, the D2D devices act as learning agents striving to maximize the cumulative rewards. Through interactions with the environment and continuous learning from feedback, these agents adapt to real-time resource allocation decisions over time. Comparing our proposed Q-learning method to the state-of-the-art RL techniques, simulation results show improvements in energy and spectrum efficiency, latency, an increase in Jain's fairness index, and improvements in overall system throughput of about 6 %–8 %. The scalability is found to be 1.69 interpreting that Q-learning exhibits a good scalability as the throughput does not abruptly decrease for an increasing number of devices.

TortoiseBFT: An asynchronous consensus algorithm for IoT system

Traditional partial synchronous Byzantine fault tolerant (BFT) protocols are confronted with new challenges when applied to large-scale networks like IoT systems, which bring about rigorous demand for the liveness and consensus efficiency of BFT protocols in asynchronous network environments. HoneyBadgerBFT is the first practical asynchronous BFT protocol, which employs a reliable broadcast protocol (RBC) to broadcast transactions and an asynchronous binary agreement protocol (ABA) to determine whether transactions should be committed. DumboBFT is a follow-up proposal that requires fewer instances of ABA and achieves higher throughput than HoneyBadgerBFT, but it does not optimize the communication overhead of HoneyBadgerBFT.In this paper, we propose TortoiseBFT, a high-performance asynchronous BFT protocol with three stages. We can significantly reduce communication overhead by determining the order of transactions first and requesting missing transactions after. Our two-phase transaction recovery mechanism enables nodes to recover missing transactions by seeking help from 2f+1 nodes. To improve the overall throughput of the system, we lower the verification overhead of threshold signatures in HoneyBadgerBFT, DumboBFT, and DispersedLedger from On3 to On2. We develop a node reputation model that selects producers with stable network conditions, which helps to reduce the number of random lotteries. Experimental results show that TortoiseBFT improves system throughput, reduces transaction delays, and minimizes communication overhead compared to HoneyBadgerBFT, DumboBFT, and DispersedLedger.

Subchannel assignment for social-assisted UAV cellular networks using dynamic hypergraph coloring

Device-to-Device (D2D) communication when used in conjugation with Unmanned Aerial Vehicle (UAV) Femtocell and unlicensed spectrum can effectively tackle the ever-increasing mobile data demands. However, D2D communication raises security and privacy concerns among users due to the absence of a centralized entity such as a base station. Therefore, exploring social connections among users becomes imperative to enable secure and trustworthy D2D communication. This paper seeks to improve the performance of a social-assisted UAV cellular network augmented by D2D communication by proposing a novel subchannel assignment technique employing hypergraph coloring. Considering the real-world scenario, we incorporate the user/UAV mobility by using dynamic hypergraph coloring for subchannel assignment instead of the static one. Our proposed technique shifts a set of cellular users from the licensed to the unlicensed band based on their social connection with other co-channel D2D users. Additionally, we assign subchannels to different users to optimize the throughput while minimizing overall interference. Our proposed technique demonstrates significant improvements in system throughput, energy efficiency, and interference efficiency compared to conventional techniques. For our proposed technique, we observed improvements of 69%, 42%, and 15% in the per user system throughput when compared with the conventional techniques (graph, hypergraph, and dynamic-hypergraph, respectively). Moreover, our technique achieves higher per user energy efficiency by 120%, 70%, and 25%, and higher per user interference efficiency by 92%, 43%, and 22%, respectively, compared to graph, hypergraph, and dynamic-hypergraph techniques.

Mobility aware blockage management of a multi-user multi-cell hybrid Li-Fi Wi-Fi system with freeform diversity receiver

In order to accommodate high data traffic, the co-deployment of heterogeneous networks like light fidelity (Li-Fi) and wireless fidelity (Wi-Fi) can offer supplementary small-cell layers of support and bring about a paradigm shift in achievable system throughput and quality of service. However, dense deployment of Li-Fi access points(APs) in an indoor arena often leads to co-channel-interference (CCI) that can be fruitfully diminished by adopting a customized optical front-end called freeform diversity receiver (FDR). With regard to multi-user association, this work judiciously imparts the motivation behind the adoption of FDR in a hybrid Li-Fi Wi-Fi network (HLWNet). Based on different mobility scenarios and blockage conditions the performance of the proposed HLWNet has been evaluated. A Li-Fi channel model with FDR and a rule-based resource allocation algorithm (RBRA) has been proposed for the purpose. Nevertheless, the network data quality of the multi-user system has been estimated in terms of packet loss, latency, and fairness index. Unlike the existing optimal resource allocation (ORA), the RBRA demonstrates superior network performance. Additionally, the execution time in the RBRA is reduced by a factor of 89 compared to the optimal resource allocation algorithm. Simulation results show a satisfactory fairness index of more than 0.85 and latency within 2.1 ms for a 10-user association inside an indoor environment of 25m2 floor area. In the absence of LOS blockage, the system throughput exhibits minimal variation, staying consistent for both methods with less than a 2% difference. However, significant improvement in average user throughput and effective system throughput has been observed compared to the existing studies. Despite line-of-sight (LOS) blockage, the proposed system with RBRA consistently maintains throughput within the range of 2.01 Gbps to 2.55 Gbps. The average user throughput, varying from 182 Mbps to 480 Mbps, is contingent upon the number of associated users, which ranges from 4 to 14.

Enhancing Data Freshness in Air-Ground Collaborative Heterogeneous Networks through Contract Theory and Generative Diffusion-Based Mobile Edge Computing.

Mobile edge computing is critical for improving the user experience of latency-sensitive and freshness-based applications. This paper provides insights into the potential of non-orthogonal multiple access (NOMA) convergence with heterogeneous air-ground collaborative networks to improve system throughput and spectral efficiency. Coordinated resource allocation between UAVs and MEC servers, especially in the NOMA framework, is addressed as a key challenge. Under the unrealistic assumption that edge nodes contribute resources indiscriminately, we introduce a two-stage incentive mechanism. The model is based on contract theory and aims at optimizing the utility of the service provider (SP) under the constraints of individual rationality (IR) and incentive compatibility (IC) of the mobile user. The block coordinate descent method is used to refine the contract design and complemented by a generative diffusion model to improve the efficiency of searching for contracts. During the deployment process, the study emphasizes the positioning of UAVs to maximize SP effectiveness. An improved differential evolutionary algorithm is introduced to optimize the positioning of UAVs. Extensive evaluation shows our approach has excellent effectiveness and robustness in deterministic and unpredictable scenarios.

Labeled graph partitioning scheme for distributed edge caching

Distributed edge caching could address latency and congestion problems in large-scale data access effectively, improving system throughput and performance. However, the lack of specialized edge caching solutions for graph data resulted in low cache hit rates and high data access latency. This limitation stemmed from existing graph partitioning schemes that overlooked the specific requirements of edge caching, such as communication overhead between edge servers, data query frequency, and query patterns. To overcome these challenges, we proposed LGPE, a labeled graph partitioning scheme for distributed edge caching based on frequent query patterns. LGPE generated frequent query patterns according to the user’s historical query subgraphs and then performed labeled graph partitioning based on the frequent pattern, ensuring that the labeled graph divided into edge servers had a high hit rate for frequent user queries while satisfying a minimum edge cut. Evaluation on real datasets from various application domains demonstrated that LGPE achieved approximately 40% higher cache hit rates compared to benchmarks like METIS and SCOTCH, and it also performed well in terms of edge cuts in special graph cases.

Exploiting Propagation Delay in Underwater Acoustic Communication Networks via Deep Reinforcement Learning.

This article proposes a novel deep-reinforcement learning-based medium access control (DL-MAC) protocol for underwater acoustic networks (UANs) where one agent node employing the proposed DL-MAC protocol coexists with other nodes employing traditional protocols, such as time division multiple access (TDMA) or q -Aloha. The DL-MAC agent learns to exploit the large propagation delays inherent in underwater acoustic communications to improve system throughput by either a synchronous or an asynchronous transmission mode. In the sync-DL-MAC protocol, the agent action space is transmission or no transmission, while in the async-DL-MAC, the agent can also vary the start time in each transmission time slot to further exploit the spatiotemporal uncertainty of the UANs. The deep Q -learning algorithm is applied to both sync-DL-MAC and async-DL-MAC agents to learn the optimal policies. A theoretical analysis and computer simulations demonstrate the performance gain obtained by both DL-MAC protocols. The async-DL-MAC protocol outperforms the sync-DL-MAC protocol significantly in sum throughput and packet success rate by adjusting the transmission start time and reducing the length of time slot.

Database Replication for Disconnected Operations with Quasi Real-Time Synchronization

Database replication is a way to improve system throughput or achieve high availability. In most cases, using an active-active replica architecture is efficient and easy to deploy. Such a system has CP properties (from the CAP theorem: Consistency, Availability and network Partition tolerance). Creating an AP (available and partition tolerant) system requires using multi-primary replication. This approach, because of many difficulties in implementation, is not widely used. However, deployment of CCDB (experiment conditions and calibration database) needs to be an AP system in two locations. This necessity became an inspiration to examine the state-of-the-art in this field and to test the available solutions. The tests performed evaluate the performance of the chosen replication tools: Bucardo and EDB Replication Server. They show that the tested tools can be successfully used for continuous synchronization of two independent database instances.

Optimisation of Buffer Allocations in Manufacturing Systems: A Study on Intra and Outbound Logistics Systems Using Finite Queueing Networks

Optimal buffer allocations can significantly improve system throughput by managing variability and disruptions in manufacturing or service operations. Organisations can minimise waiting times and bottlenecks by strategically placing buffers along the flow path, leading to a smoother and more efficient production or service delivery process. Determining the optimal size of buffers poses a challenging dilemma, as it involves balancing the cost of buffer allocation, system throughput, and waiting times at each service station. This paper presents a framework that utilises finite queueing networks for performance analysis and optimisation of topologies, specifically focusing on buffer allocations. The proposed framework incorporates a finite closed queuing network to model the intra-logistics material transfer process and a finite open queueing network to model the outbound logistics process within a manufacturing setup. The generalised expansion method (GEM) is employed to calculate network performance measures of the system, considering the blocking phenomenon. Discrete event simulation (DES) models are constructed using simulation software, integrating optimisation configurations to determine optimal buffer allocations to maximise system throughput. The findings of this study have significant implications for decision-making processes and offer opportunities to enhance the efficiency of manufacturing systems. By leveraging the proposed framework, organisations can gain valuable insights into supply chain performance, identify potential bottlenecks, and optimise buffer allocations to achieve improved operational efficiency and overall system throughput.

Scheduling of graph neural network and Markov based UAV mobile edge computing networks

With the rapid advancement of communication technology, unmanned aerial vehicles (UAVs) have gained significant attention. The incorporation of UAVs in mobile edge computing (MEC) systems has proven to be a viable method for improving system throughput and decreasing computing latency. In pursuit of enhancing the quality of service (QoS) for users, we propose a UAV-assisted MEC system. Our approach entails the utilization of a multi-agent graph convolutional deep reinforcement learning algorithm that facilitates the transmission of distributed information and computing tasks from multiple ground users to the UAV. Through individual strategy training, users are able to effectively learn collaborative strategies. Simulation results validate the efficacy of the proposed UAV-assisted MEC scheduling method, which is based on graph neural networks (GNN), in significantly enhancing system throughput.