Throughput Scaling Research Articles

Automating Data Pipelines with AI for Scalable, Real-Time Process Optimization in the Cloud

Modern data processing environments demand efficient, scalable solutions for handling massive data streams in real-time, yet traditional Extract, Transform, Load (ETL) pipelines face significant limitations in processing speed and adaptability. This article presents an AI-Enhanced Cloud Data Pipeline (AECDP) framework that combines Deep Learning-based Stream Processing (DLSP) with Adaptive Resource Management (ARM) for real-time data optimization. The framework introduces novel algorithms for stream processing, resource allocation, and quality assurance, including the Adaptive Stream Processing Algorithm (ASPA) and Anomaly Detection and Correction (ADC) system. The implementation utilizes a multi-cloud architecture with containerized microservices, enabling independent scaling and maintenance of pipeline components. Experimental results demonstrate the framework's effectiveness across various industry applications, including e-commerce, financial services, and manufacturing sectors. The system achieves consistent sub-second latency for real-time processing, linear throughput scaling, and optimal resource utilization across cloud instances. Additionally, the framework incorporates advanced security features and automated quality monitoring systems, ensuring robust and reliable data processing. The AECDP framework represents a significant advancement in data pipeline automation, providing organizations with a comprehensive solution for managing complex data processing requirements while maintaining high performance and reliability standards.

Concurrent Data Structures Made Easy

Design of an efficient thread-safe concurrent data structure is a balancing act between its implementation complexity and performance. Lock-based concurrent data structures, which are relatively easy to derive from their sequential counterparts and to prove thread-safe, suffer from poor throughput under even light multi-threaded workload. At the same time, lock-free concurrent structures allow for high throughput, but are notoriously difficult to get right and require careful reasoning to formally establish their correctness. In this work, we explore a solution to this conundrum based on a relatively old idea of batch parallelism---an approach for designing high-throughput concurrent data structures via a simple insight: efficiently processing a batch of a priori known operations in parallel is easier than optimising performance for a stream of arbitrary asynchronous requests. Alas, batch-parallel structures have not seen wide practical adoption due to (i) the inconvenience of having to structure multi-threaded programs to explicitly group operations and (ii) the lack of a systematic methodology to implement batch-parallel structures as simply as lock-based ones. We present OBatcher---a Multicore OCaml library that streamlines the design, implementation, and usage of batch-parallel structures. OBatcher solves the first challenge (how to use) by suggesting a new lightweight implicit batching design pattern that is built on top of generic asynchronous programming mechanisms. The second challenge (how to implement) is addressed by identifying a family of strategies for converting common sequential structures into the corresponding efficient batch-parallel versions, and by providing a library of functors that embody those strategies. We showcase OBatcher with a diverse set of benchmarks ranging from Red-Black and AVL trees to van Emde Boas trees, skip lists, and a thread-safe implementation of a Datalog solver. Our evaluation of all the implementations on large asynchronous workloads shows that (a) they consistently outperform the corresponding coarse-grained lock-based implementations---the only ones available in OCaml to date, and that (b) their throughput scales reasonably with the number of processors.

Analyzing imbalance of short tandem repeats for pancreatic cancer detection.

e16359 Background: Short tandem repeats (STRs), alternatively known as microsatellites, encompass repeat units of 1 to 6 base pairs (bp) in the genome and function as regulators of gene expression, impacting plasticity and complex traits. STRs are prone to hypermutation with alterations correlated to pathogenicity in multiple Mendelian and acquired disorders. STR variant classes include insertions, mobile element insertions (MEIs), deletions, and multi-allelic copy number variants (mCNVs). These can lead to repeat expansions, allelic imbalance (AI), and microsatellite instability (MSI) observed in diseases such as Huntington's disease, hereditary ataxia, and multiple cancers. In pancreatic cancer, AI and associated loss-of-heterozygosity (LOH) at tumor suppressor loci flanked by hypervariable STR regions correspond to a pathogenic phenotype with a risk of aggressive disease. Consequently, it is critical to develop accurate and robust methods to precisely identify and genotype pancreatic samples with varying specimen quality in a clinical setting to aid in diagnosis. Methods: Capillary electrophoresis (CE) and Sanger sequencing have been used to analyze STRs. The availability of newer tools such as 2nd generation short-read (NGS) and 3rd generation long-read (TGS) sequencers could allow for high throughput scaling, however, informatics challenges associated with analyzing repetitive regions remain. Here we developed amplification and enrichment methods for targeted analysis for detection by CE, NGS and TGS. Results: Amplification and enrichment strategies for detecting 17 short tandem repeat regions that play a role in pancreatic carcinogenesis were developed. Methods were optimized for detecting STR alterations in cell-free nucleic acids isolated from endoscope-guided pancreatic fine needle aspirate biopsies. Furthermore, informatics tools were developed to analyze short-read and long-read sequencing data to accurately analyze repeat regions. Conclusions: Here we compared 3 platforms (CE, NGS, and TGS) and found that CE remains the gold standard for analyzing AI/LOH with data comparable to long-read TGS, while short-read NGS is not always amenable to accurate analysis dependent on the region of interest. Additionally, we found that artifacts of amplification persist, irrespective of the 3 platforms analyzed.

Throughput scaling and thermomechanical behaviour in multiplexed fused filament fabrication

Multiplexed Fused Filament Fabrication (MF3) combines a dynamic extrusion-based toolpath with a multi-extruder-single-gantry machine tool architecture to increase printing speed without sacrificing geometric capabilities or increasing hardware complexity. This work establishes a novel capability for geometrically generalizable synthesis of MF3 toolpaths and creates a new thermal model that incorporates the unique nature of material deposition. It is shown that MF3 can increase throughput by an order of magnitude or more via the atypical and nonlinear effects of part size, infill density and extruder spacing. Further, the unusual temperature history in MF3 is found to enhance the part's mechanical properties.

Human Hepatic Spheroid Coculture Model for the Assessment of Drug-Induced Liver Injury.

Accurate evaluation of potential drug risks such as drug-induced liver injury (DILI) continues to be a challenge faced by pharmaceutical industry and regulatory agencies. Preclinical testing has served as a foundation for the evaluation of the potential risks and effectiveness of investigational new drug (IND) products in humans. However, current two-dimensional (2D) in vitro human primary hepatocyte (HPH) culture systems cannot accurately depict and simulate the rich environment and complex processes observed in vivo, while animal studies present inherited species-specific differences and low throughput scales. Thus, there is a continued demand to establish new approaches that can better characterize DILI during drug discovery and development. Among others, the three-dimensional (3D) hepatic spheroid model comprising self-aggregated primary human hepatocytes cocultured with non-parenchymal cells (NPCs) appears to be a more accurate representation of the natural hepatic microenvironment with intercellular interactions between hepatocytes, stellate cells, Kupffer cells, liver sinusoidal endothelial cells (LSECs), and other cell types. This model holds the potential to improve the ability for long-term functional and toxicological studies. Here, we provide methodological details for this human hepatic spheroid coculture model system.

Root Walker: an automated pipeline for large scale quantification of early root growth responses at high spatial and temporal resolution.

Plants are sessile organisms that constantly adapt to their changing environment. The root is exposed to numerous environmental signals ranging from nutrients and water to microbial molecular patterns. These signals can trigger distinct responses including the rapid increase or decrease of root growth. Consequently, using root growth as a readout for signal perception can help decipher which external cues are perceived by roots, and how these signals are integrated. To date, studies measuring root growth responses using large numbers of roots have been limited by a lack of high-throughput image acquisition, poor scalability of analytical methods, or low spatiotemporal resolution. Here, we developed the Root Walker pipeline, which uses automated microscopes to acquire time-series images of many roots exposed to controlled treatments with high spatiotemporal resolution, in conjunction with fast and automated image analysis software. We demonstrate the power of Root Walker by quantifying root growth rate responses at different time and throughput scales upon treatment with natural auxin and two mitogen-associated protein kinase cascade inhibitors. We find a concentration-dependent root growth response to auxin and reveal the specificity of one MAPK inhibitor. We further demonstrate the ability of Root Walker to conduct genetic screens by performing a genome-wide association study on 260 accessions in under 2 weeks, revealingknown and unknown root growth regulators. Root Walker promises to be a useful toolkit for the plant science community, allowing large-scale screening of root growth dynamics for a variety of purposes, including genetic screens for root sensing and root growth response mechanisms.

Comparative Assessment of Diagnostic Performance of Cytochrome Oxidase Multiplex PCR and 18S rRNA Nested PCR.

Malaria elimination and control require prompt and accurate diagnosis for treatment plan. Since microscopy and rapid diagnostic test (RDT) are not sensitive particularly for diagnosing low parasitemia, highly sensitive diagnostic tools are required for accurate treatment. Molecular diagnosis of malaria is commonly carried out by nested polymerase chain reaction (PCR) targeting 18S rRNA gene, while this technique involves long turnaround time and multiple steps leading to false positive results. To overcome these drawbacks, we compared highly sensitive cytochrome oxidase gene-based single-step multiplex reaction with 18S rRNA nested PCR. Cytochrome oxidase (cox) genes of P. falciparum (cox-III) and P. vivax (cox-I) were compared with 18S rRNA gene nested PCR and microscopy. Cox gene multiplex PCR was found to be highly specific and sensitive, enhancing the detection limit of mixed infections. Cox gene multiplex PCR showed a sensitivity of 100% and a specificity of 97%. This approach can be used as an alternative diagnostic method as it offers higher diagnostic performance and is amenable to high throughput scaling up for a larger sample size at low cost.

On Covert Communication Against Sequential Change-Point Detection

We investigate covert communication under a sequential change-point detection (SCPD) framework, where a transmitter, Alice, attempts to communicate reliably with a receiver, Bob, over an additive white Gaussian noise channel, while simultaneously ensuring covertness (low probability of detection) with respect to an adversary, Willie. Different from the binary hypothesis test based detection framework considered in prior works where Willie collects all signal samples together and makes a decision in a batch manner, we view Willie’s detection process as an SCPD process that works in a real-time manner. We establish a new criterion to evaluate the covertness of the communication between Alice and Bob, and investigate the performance of covert communication accordingly. Subject to the proposed constraint on covertness, we investigate the feasible transmit power and transmission duration under three SCPD algorithms, namely, the Shewhart test, the finite moving average chart (FMAC), and the cumulative sum (CUSUM) test, and characterize how the covert communication throughput scales with the average run length to false alarm (ARL2FA) of Willie’s detector as the ARL2FA increases without bound. Our theoretical results can be viewed as upper bounds on the covert communication throughput that can be achieved, and we show that compared with the case where Willie performs the CUSUM test, Alice and Bob achieve a higher covert communication throughput if Willie performs the Shewhart test or the FMAC.

A Real-Time, Distributed, Directional TDMA MAC Protocol for QoS-Aware Communication in Multi-Hop Wireless Networks

Time division multiple access (TDMA) based medium access control (MAC) schemes are widely used for communication among directional nodes since they can provide a conflict-free transmission schedule. However, the existing directional TDMA schemes introduce significant overhead and delay, and cannot adapt in real-time to topology changes in a directional multi-hop network. These schemes also incur considerable overhead and delay in order to support the QoS (quality of service) traffic. In this paper, a novel, real-time, distributed, directional TDMA scheme is presented for directional multi-hop wireless networks. This scheme adapts to the topology changes and/or flow requirements in real-time , and facilitates QoS-aware communication with no notification overhead . In the proposed scheme, the 1-hop neighborhood of every node is divided into fully connected 1-hop neighborhoods , which allows the node to intelligently serve multiple routes without requiring a globally converged scheduling solution. This feature allows the use of a low-complexity rank-based mechanism to obtain a distributed, real-time transmission schedule for a directional multi-hop network. The following new features are also added in the proposed scheme: ( ${i}$ ) REQ period which reduces slot wastage, ( ii ) throughput scaling which ensures fairness and helps in congestion management, and ( iii ) piggyback reservation period which increases the spatial reuse and adapts to the dynamic requirements of multiple flows in real-time. The control-period overhead in our scheme is low and linearly changes with the number of nodes in a fully connected 1-hop neighborhood, instead of the total number of nodes in the entire network. Simulation results and comparisons with other recent, distributed TDMA-based schemes show that our scheme provides a higher throughput with very low control overhead for both static and mobile network topologies.

Parallelizing Shared File I/O Operations of NVM File System for Manycore Servers

NOVA, a state-of-the-art non-volatile memory (NVM) file system, has limited performance due to its coarse-grained per-file lock when multiple threads perform I/Os to a shared file in a manycore environment. For instance, a writer lock blocks other threads attempting to access the same file, although they access different regions of a file. When multiple threads reading the same file share a cache line containing a reader counter, performance can be significantly degraded due to cache consistency protocol as we increase the number of readers. This paper proposes a fine-grained segment-based range lock (SRL) that divides a file into multiple segments and manages a lock variable dynamically for each segment. Consequently, write operations can be parallelized without blocking unless there is a conflict in accessing the same range in a file. Moreover, SRL maintains a reader counter per segment that allows multiple reader threads to perform read operations without causing a performance bottleneck. We evaluated an SRL-based NOVA on an Intel Optane DC persistent memory (PM) manycore server. The benchmarking results showed that the average write throughput of the SRL-based NOVA is $3\times $ higher than the original NOVA, and the average read throughput scales linearly, while the original NOVA does not scale.

Mobility-Assisted Covert Communication Over Wireless Ad Hoc Networks

We study the effect of node mobility on the throughput scaling of the covert communication over a wireless adhoc network. It is assumed that $n$ mobile nodes want to communicate each other in a unit disk while keeping the presence of the communication secret from each of $\Theta (n^{s})$ non-colluding wardens ( $s>0$ ). The wardens can be mobile or fixed. Our results show that the node mobility greatly improves the throughput scaling, compared to the case of fixed node location. In particular, for $s\leq 1$ , the aggregate throughput scaling, i.e., the maximally achievable throughput scaling of the total network when each source-destination pair communicates with the same rate, is shown to be arbitrarily close to linear in $n$ when the number of channel uses $l$ that each warden uses to judge the presence of communication is not too large compared to $n$ . More specifically, the aggregate throughput scaling is arbitrarily close to linear when $s\leq 1$ and $l=O(n^{(\alpha -2)(1-s)})$ , where ${\alpha \geq 2}$ denotes the path loss exponent. For the achievability, we modify the two-hop based scheme by Grossglauser and Tse (2002), which was proposed for a wireless ad hoc network without a covertness constraint, by introducing a preservation region around each warden in which the senders are not allowed to transmit and by carefully analyzing the effect of covertness constraint on the transmit power and the resultant transmission rates. This scheme is shown to be optimal for $0 under an assumption that each node outside preservation regions around wardens uses the same transmit power.

Throughput Scaling of Covert Communication Over Wireless Adhoc Networks

We consider the problem of covert communication over wireless adhoc networks in which (roughly) $n$ legitimate nodes (LNs) and $n^{\kappa }$ for $\kappa > 0$ non-communicating warden nodes (WNs) are randomly distributed in a square of unit area. Each legitimate source wants to communicate with its intended destination node while ensuring that every WN is unable to detect the presence of the communication. In this scenario, we study the throughput scaling law. Due to the covert communication constraint, the transmit powers are necessarily limited. Under this condition, we introduce a preservation region around each WN. This region serves to prevent transmission from the LNs and to increase the transmit power of the LNs outside the preservation regions. For the achievability results, multi-hop (MH), hierarchical cooperation (HC), and hybrid HC-MH schemes are utilized with some appropriate modifications. In the proposed MH and hybrid schemes, because the preservation regions may impede communication along direct data paths, the data paths are suitably modified by taking a detour around each preservation region. To avoid the concentration of detours resulting extra relaying burdens, we distribute the detours evenly over a wide region. In the proposed HC scheme, we control the symbol power and the scheduling of distributed multiple-input multiple-output transmission. We also present upper bounds on the throughput scaling under the assumption that every active LN consumes the same average transmit power over the time period in which the WNs observe the channel outputs. For $0 , these upper bounds match with the achievable throughput scalings.

Scalable Multiway Stream Joins in Hardware

Efficient real-time analytics are an integral part of an increasing number of data management applications, such as computational targeted advertising, algorithmic trading, and Internet of Things. In this paper, we focus primarily on accelerating stream joins, which are arguably one of the most commonly used and resource-intensive operators in stream processing. We propose a scalable circular pipeline design ( $\sf{ Circular\text{-}MJ}$ Circular - MJ ) in hardware to orchestrate a multiway join while minimizing data flow disruption. In this circular design, each new tuple (given its origin stream) starts its processing from a specific join core and passes through all respective join cores in a pipeline sequence to produce the final results. We also present a novel two-stage pipeline stream join ( $\sf{ Stashed\text{-}MJ}$ Stashed - MJ ) that uses a best-effort buffering technique (referred to as stash) to maintain intermediate results. If an overwrite is detected in the stash, our design automatically resorts to recomputing intermediate results. Finally, we present a parallelized version of our multiway stream join by integrating our proposed pipelines into a parallel unidirectional flow-based architecture ( $\sf{ Parallel\text{-}MJ}$ Parallel - MJ ). Our experimental results demonstrate a linear throughput scaling with respect to the numbers of streams and processing cores.

The Use of Voltage Sensitive Dye di-4-ANEPPS and Video-Based Contractility Measurements to Assess Drug Effects on Excitation-Contraction Coupling in Human-Induced Pluripotent Stem Cell-Derived Cardiomyocytes.

Because cardiotoxicity is one of the leading causes of drug failure and attrition, the design of new protocols and technologies to assess proarrhythmic risks on cardiac cells is in continuous development by different laboratories. Current methodologies use electrical, intracellular Ca2+, or contractility assays to evaluate cardiotoxicity. Increasingly, the human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) are the in vitro tissue model used in commercial assays because it is believed to recapitulate many aspects of human cardiac physiology. In this work, we demonstrate that the combination of a contractility and voltage measurements, using video-based imaging and fluorescence microscopy, on hiPSC-CMs allows the investigation of mechanistic links between electrical and mechanical effects in an assay design that can address medium throughput scales necessary for drug screening, offering a view of the mechanisms underlying drug toxicity. To assess the accuracy of this novel technique, 10 commercially available inotropic drugs were tested (5 positive and 5 negative). Included were drugs with simple and specific mechanisms, such as nifedipine, Bay K8644, and blebbistatin, and others with a more complex action such as isoproterenol, pimobendan, digoxin, and amrinone, among others. In addition, the results provide a mechanism for the toxicity of itraconazole in a human model, a drug with reported side effects on the heart. The data demonstrate a strong negative inotropic effect because of the blockade of L-type Ca2+ channels and additional action on the cardiac myofilaments. We can conclude that the combination of contractility and action potential measurements can provide wider mechanistic knowledge of drug cardiotoxicity for preclinical assays.

Assessment on the Achievable Throughput of Multi-Band ITU-T G.652.D Fiber Transmission Systems

Fiber-optic multi-band transmission (MBT) aims at exploiting the low-loss spectral windows of single-mode fibers (SMFs) for data transport, expanding by $\sim\!11\times$ the available bandwidth of C-band line systems and by $\sim\!5\times$ C+L-band line systems’. MBT offers a high potential for cost-efficient throughput upgrades of optical networks, even in absence of available dark-fibers, as it utilizes more efficiently the existing infrastructures. This represents the main advantage compared to approaches such as multi-mode/-core fibers or spatial division multiplexing. Furthermore, the industrial trend is clear: the first commercial C $+$ L-band systems are entering the market and research has moved toward the neighboring S-band. This article discusses the potential and challenges of MBT covering the ITU-T optical bands O $\rightarrow$ L. MBT performance is assessed by addressing the generalized SNR (GSNR) including both the linear and non-linear fiber propagation effects. Non-linear fiber propagation is taken into account by computing the generated non-linear interference by using the generalized Gaussian-noise (GGN) model, which takes into account the interaction of non-linear fiber propagation with stimulated Raman scattering (SRS), and in general considers wavelength-dependent fiber parameters. For linear effects, we hypothesize typical components’ figures and discussion on components’ limitations, such as transceivers,’ amplifiers’ and filters’ are not part of this work. We focus on assessing the transmission throughput that is realistic to achieve by using feasible multi-band components without specific optimizations and implementation discussion. So, results are meant to address the potential throughput scaling by turning-on excess fiber transmission bands. As transmission fiber, we focus exclusively on the ITU-T G.652.D, since it is the most widely deployed fiber type worldwide and the mostly suitable to multi-band transmission, thanks to its ultra-wide low-loss single-mode high-dispersion spectral region. Similar analyses could be carried out for other single-mode fiber types. We estimate a total single-fiber throughput of 450 Tb/s over a distance of 50 km and 220 Tb/s over regional distances of 600 km: $\sim\!10\times$ and 8× more than C-band transmission respectively and $\sim\!2.5\times$ more than full C+L.

Prediction of leaf water potential and relative water content using terahertz radiation spectroscopy.

Increases in the frequency and severity of droughts across many regions worldwide necessitate an improved capacity to determine the water status of plants at organ, whole plant, canopy, and regional scales. Noninvasive methods have most potential for simultaneously improving basic water relations research and ground‐, flight‐, and space‐based sensing of water status, with applications in sustainability, food security, and conservation. The most frequently used methods to measure the most salient proxies of plant water status, that is, water mass per leaf area (WMA), relative water content (RWC), and leaf water potential (Ψleaf), require the excision of tissues and laboratory analysis, and have thus been limited to relatively low throughput and small study scales. Applications using electromagnetic radiation in the visible, infrared, and terahertz ranges can resolve the water status of canopies, yet heretofore have typically focused on statistical approaches to estimating RWC for leaves before and after severe dehydration, and few have predicted Ψleaf. Terahertz radiation has great promise to estimate leaf water status across the range of leaf dehydration important for the control of gas exchange and leaf survival. We demonstrate a refined method and physical model to predict WMA, RWC, and Ψleaf from terahertz transmission across a wide range of levels of dehydration for given leaves of three species, as well as across leaves of given species and across multiple species. These findings highlight the powerful potential and the outstanding challenges in applying in vivo terahertz spectrometry as a remote sensor of water status for a range of applications.

Interference-Aware Opportunistic Random Access in Dense IoT Networks

It is a challenging task to design a random access protocol that achieves the optimal throughput in multi-cell random access with decentralized transmission due to the difficulty of coordination. In this paper, we present a decentralized interference-aware opportunistic random access (IA-ORA) protocol that enables us to obtain the optimal throughput scaling in an ultra-dense multi-cell random access network with one access point (AP) and a number of users. In sharp contrast to opportunistic scheduling for cellular multiple access where users are selected by base stations, under the IA-ORA protocol, each user opportunistically transmits with a predefined physical layer (PHY) data rate in a decentralized manner if not only the desired signal power to the serving AP is sufficiently large but also the generating interference leakage power to the other APs is sufficiently small (i.e., two threshold conditions are fulfilled). As a main result, it is shown that the optimal aggregate throughput scaling (i.e., the MAC throughput of e/1 in a cell and the power gain) is achieved in a high signal-to-noise ratio regime if the number of per-cell users exceeds some level. Additionally, it is numerically demonstrated via computer simulations that under practical settings, the proposed IA-ORA protocol outperforms conventional opportunistic random access protocols in terms of aggregate throughput.

Throughput Maximization for Delay-Sensitive Random Access Communication

Future 5G cellular networks supporting delay-sensitive, low-latency communications could employ random access communication to reduce the overhead compared to scheduled access techniques used in 4G networks. We consider a wireless communication system where multiple devices transmit payloads of a given fixed size in a random access fashion over shared radio resources to a common receiver. We allow retransmissions and assume Chase combining at the receiver. The radio resources are partitioned in the time and frequency dimensions, and we determine the optimal partition granularity to maximize throughput, subject to given constraints on latency and outage. In the regime of high and low signal-to-noise ratio (SNR), we derive explicit expressions for the granularity and throughput, first using a Shannon capacity approximation and then using finite block length analysis. Numerical results show that the throughput scaling results are applicable over a range of SNRs. The proposed analytical framework can provide insights for resource allocation strategies in reliable and delay-sensitive random access systems and in specific 5G use cases for massive, short packet uplink access.

Inter-Cluster Cooperation for Wireless D2D Caching Networks

Proactive wireless caching and device to device (D2D) communication have emerged as promising techniques for enhancing users’ quality of service and network performance. In this paper, we propose a new architecture for D2D caching with inter-cluster cooperation. We study a cellular network in which users cache popular files and share them with other users either in their proximity via D2D communication or with remote users using cellular transmission. We characterize the network average delay per request from a queuing perspective. Specifically, we formulate the delay minimization problem and show that it is NP-hard. Furthermore, we prove that the delay minimization problem is equivalent to the minimization of a non-increasing monotone supermodular function subject to a uniform partition matroid constraint. A computationally efficient greedy algorithm is proposed which is proven to be locally optimal within a factor $(1 - e^{-1})\approx 0.63$ of the optimum. We analyze the average per request throughput for different caching schemes and conduct the scaling analysis for the average sum throughput. We show how throughput scaling depends on video content popularity when the number of files grows asymptotically large. Simulation results show a delay reduction of 45% to 80% compared to a D2D caching system without inter-cluster cooperation.

Analysis of Pure and Slotted ALOHA With Multi-Packet Reception and Variable Packet Size

Multiple packet reception (MPR) is becoming a viable reality for wireless random access protocols thanks to advances in the physical layer and new coding techniques. In the simplest $K$ -MPR model, a receiver can resolve up to $K\geq 1$ parallel transmissions. We extend the classical analysis of pure and slotted ALOHA to $K$ -MPR devices with arbitrary degree $K$ for fixed and variable packet size. Through a parsimonious modeling approach, we derive relatively simple analytical expressions. In this way, we gain insight and quantitative understanding on the fundamental tradeoffs between pure and slotted ALOHA and on the scaling of maximum achievable throughput with $K$ .