IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
Optimal Transmission Scheduling in Small Multimodal Underwater Networks
Get PDFWe describe a scheduling protocol for multimodal networks of relatively limited size, whose nodes encompass various underwater communication technologies. For such a case, we show that significant improvement in the network operations is possible when the transmission schedule is set to jointly utilize all communication technologies. Our solution is based on per-technology TDMA frames, whose time slots are determined optimally to maximize the overall channel utilization while preserving flow limitations and maintaining fairness in resource allocation. Our numerical simulations and experimental results \remembertext{phy}{for multimodal networks with several acoustic technologies} show that, while maintaining a fair resource allocation, our scheduling solution provides both high throughput and low packet delivery delay.pu
vrAIn: A Deep Learning Approach Tailoring Computing and Radio Resources in Virtualized RANs
Get PDFDOI: https://doi.org/10.1145/3300061.3345431The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complex dependencies between computing and radio resources make vRAN resource control particularly daunting. We present vrAIn, a dynamic resource controller for vRANs based on deep reinforcement learning. First, we use an autoencoder to project high-dimensional context data (traffic and signal quality patterns) into a latent representation. Then, we use a deep deterministic policy gradient (DDPG) algorithm based on an actor-critic neural network structure and a classifier to map (encoded) contexts into resource control decisions. We have implemented vrAIn using an open-source LTE stack over different platforms. Our results show that vrAIn successfully derives appropriate compute and radio control actions irrespective of the platform and context: (i) it provides savings in computational capacity of up to 30% over CPU-unaware methods; (ii) it improves the probability of meeting QoS targets by 25% over static allocation policies using similar CPU resources in average; (iii) upon CPU capacity shortage, it improves throughput performance by 25% over state-of-the-art schemes; and (iv) it performs close to optimal policies resulting from an offline oracle. To the best of our knowledge, this is the first work that thoroughly studies the computational behavior of vRANs, and the first approach to a model-free solution that does not need to assume any particular vRAN platform or system conditions.TRUEpu
Collaborative Wideband Signal Decoding using Non-coherent Receivers
Get PDFIn recent years we are experiencing an important growth of interest for sensing the electromagnetic spectrum and making its access more agile. Emerging initiatives use low-cost receivers in large deployments for sensing the radio spectrum or collecting air-traffic signals at large scale. One of the major drawbacks of low-cost spectrum receivers is their limited sampling rate, which does not allow to decode wideband signals. In order to circumvent the hardware limitations of single receivers, we envision a scenario where non-coherent receivers sample the signal collaboratively to cover a larger bandwidth than the one of the single receiver and then, enable the signal reconstruction and decoding in the backend. We present a methodology to enable the signal reconstruction in the backend by multiplexing in frequency a certain number of non-coherent receivers in order to cover a signal bandwidth that would not otherwise be possible using a single receiver. We propose a method that does not use the knowledge of the modulation scheme, and has been designed to be transparent to the subsequent decoding process. As such, it is equivalent to the reception of the signal by a high-end receiver. We demonstrate and evaluate our approach with two non-coherent receivers which collaboratively sample an aviation signal of almost twice the bandwidth of each receiver. The experimental results show that, using two non-coherent receivers, our method is able to reconstruct and decode correctly more than 80% of data.TRUEpu
Greener RAN operation through machine learning
No full textThe use of base station (BS) sleep modes is one of the most studied approaches for the reduction of the energy consumption of radio access networks (RANs). Many papers have shown that the potential energy saving of sleep modes is huge, provided the future behavior of the RAN traffic load is known. This paper investigates the effectiveness of sleep modes combined with machine learning (ML) approaches for traffic forecast. A portion of a RAN is considered, comprising one macro BS and a few small cell BSs. Each BS is powered by a photovoltaic (PV) panel, equipped with energy storage units, and a connection to the power grid. The PV panel and battery provide green energy, while the power grid provides brown energy. Our study examines the impacts of different prediction models on the consumed energy mix and on QoS. Numerical results show that the considered ML algorithms succeed in achieving effective trade-offs between energy consumption and QoS. Results also show that energy savings strongly depend on traffic patterns that are typical of the considered area. This implies that a widespread implementation of these energy saving strategies without the support of ML would require a careful tuning that cannot be performed autonomously and that needs continuous updates to follow traffic pattern variations. On the contrary, ML approaches provide a versatile framework for the implementation of the desired trade-off that naturally adapts the network operation to the traffic characteristics typical of each area and to its evolution.pu
Data Transmission Plan Adaptation Complementing Strategic Time-Network Selection for Connected Vehicles
Get PDFConnected vehicles can nowadays be equipped with multiple network interfaces to access the Internet via a number of networks. To achieve an efficient transmission within this environment, a strategic time-network selection for connected vehicles has been developed, which plans ahead delay-tolerant transmissions. Under perfect prediction (knowledge) of the environment, the proposed strategic time-network selection approach is shown to outperform significantly leading state-of-the-art approaches which are based either on time selection or network selection only. Under realistic environments, however, the efficiency of planning-based approaches may be severely compromised since network presence and available capacities change rapidly and in an unforeseen manner (because of changing conditions due to the uncertainty in car movement, data transmission needs and network characteristics). To address this problem, a mechanism is proposed in this paper that determines the deviation from the anticipated conditions and modifies the transmission plan accordingly. Simulation results show that the proposed adaptation mechanisms help maintain the benefits of a strategic time-network selection planning under changing conditions.pu
Why Online Services Should Pay You for Your Data? The Arguments for a Human-Centric Data Economy
Get PDFAbstract—Data, and the economy around it, are said to be driving the fourth industrial
revolution. Interestingly, the people—whose data are what moves the new economy—
have a rather passive role in it as they are left outside the direct value flow that transforms
raw data into huge monetary benefits. This is a consequence of a de facto understanding
(or, one may say, misunderstanding) between people and companies that the former
receive unpaid access to online services in exchange for the unpaid access to their
personal data. This article argues in favor of an alternative human-centric data economy
in which people will be paid whenever their data will be used by revenue-generating
products and services. We discuss the benefits of such an economy, the main challenges
for realizing it, and its feasibility in the view of existing technologies and business
practices.pu
Web Experience in Mobile Networks: Lessons from Two Million Page Visits
Get PDFMeasuring and characterizing web page performance is a challeng- ing task. When it comes to the mobile world, the highly varying technology characteristics coupled with the opaque network con- guration make it even more di cult. Aiming at reproducibility, we present a large scale empirical study of web page performance collected in eleven commercial mobile networks spanning four countries. By digging into measurement from nearly two million web browsing sessions, we shed light on the impact of di erent web protocols, browsers, and mobile technologies on the web per- formance. We nd that the impact of mobile broadband access is sizeable. For example, the median page load time using mobile broadband increases by a third compared to wired access. Mobility clearly stresses the system, with handover causing the most evi- dent performance penalties. Contrariwise, our measurements show that the adoption of HTTP/2 and QUIC has practically negligible impact. To understand the intertwining of all parameters, we adopt state-of-the-art statistical methods to identify the signi cance of di erent factors on the web performance. Our analysis con rms the importance of access technology and mobility context as well as webpage composition and browser. Our work highlights the importance of large-scale measurements. Even with our controlled setup, the complexity of the mobile web ecosystem is challenging to untangle. For this, we are releasing the dataset as open data for validation and further research.TRUEpu
NFV orchestration on intermittently available SUAV platforms: challenges and hurdles
Get PDFIn this paper, we analyze the main challenges and issues related with the orchestration of Virtualized Network Functions (VNFs) on Small Unmanned Aerial Vehicles (SUAVs). Our analysis considers a reference scenario where a number of SUAVs are deployed over a delimited geographic area and provide a mobile cloud environment that supports the deployment of functionalities using Network Functions Virtualization (NFV) technologies. The orchestration of services in this reference scenario presents different challenges, due to the constrained capacity and limited lifetime of battery-powered SUAVs, the intermittent availability of network communications, and the need to consider enhanced policies for the allocation of virtual functions to SUAVs. Finally, we perform a first exploratory evaluation of the identified challenges and issues, using a well-known and widely adopted virtualized infrastructure manager, i.e., OpenStack.TRUEpu
Resource Sharing Efficiency in Network Slicing
Get PDFThe economic sustainability of future mobile networks will largely depend on the strong specialization of its offered services. Network operators will need to provide added value to their tenants, by moving from the traditional one-size-fits-all strategy to a set of virtual end-to-end instances of a common physical infrastructure, named network slices, which are especially tailored to the requirements of each application. Implementing network slicing has significant consequences in terms of resource management: service customization entails assigning to each slice fully dedicated resources, which may also be dynamically reassigned and overbooked in order to increase the cost-efficiency of the system. In this paper, we adopt a data-driven approach to quantify the efficiency of resource sharing in future sliced networks. Building on metropolitan-scale real-world traffic measurements, we carry out an extensive parametric analysis that highlights how diverse performance guarantees, technological settings, and slice configurations impact the resource utilization at different levels of the infrastructure in presence of network slicing. Our results provide insights on the achievable efficiency of network slicing architectures, their dimensioning, and their interplay with resource management algorithms at different locations and reconfiguration timescales.pu
RL-Cache: Learning-Based Cache Admission for Content Delivery
Get PDFContent delivery networks (CDNs) distribute much of the Internet content by caching and serving the objects requested by users. A major goal of a CDN is to maximize the hit rates of its caches, thereby enabling faster content downloads to the users. Content caching involves two components: an admission algorithm to decide whether to cache an object and an eviction algorithm to decide which object to evict from the cache when it is full. In this paper, we focus on cache admission and propose a novel algorithm called RL-Cache that uses model-free reinforcement learning (RL) to decide whether or not to admit a requested object into the CDN's cache. Unlike prior approaches that use a small set of criteria for decision making, RL-Cache weights a large set of features that include the object size, recency, and frequency of access. We develop a publicly available implementation of RL-Cache and perform an evaluation using production traces for the image, video, and web traffic classes from Akamai's CDN. The evaluation shows that RL-Cache improves the hit rate in comparison with the state of the art and imposes only a modest resource overhead on the CDN servers. Further, RL-Cache is robust enough that it can be trained in one location and executed on request traces of the same or different traffic classes in other locations of the same geographic region.TRUEpu