Forecasting QoS Attributes Using LSTM Networks

White, Gary; Palade, Andrei; Clarke, Siobhán

doi:10.1109/ijcnn.2018.8489052

Cited by 41 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This means that if the LSTM unit detects an important feature from an input sequence, this feature will be carried over a long distance and used to capture long-distance dependencies. This allows them to be used for a number of forecasting applications such as traffic flow prediction [38], QoS forecasting [39], air quality prediction [40], particle matter forecasting [41] and energy load forecasting [42].…”

Section: ) Long Short Term Memory (Lstm)mentioning

confidence: 99%

“…The additional processing power available from the embedded GPUs at the edge compared to traditional IoT gateways (e.g., Raspberry Pis and Intel Galileos) allows the devices to run more complex prediction models for the QoS of services in the environment [74], [25], [39]. These predictions can be used as part of a middleware architecture to compose more reliable services even in dynamic environments.…”

Section: Deep Edgesmentioning

confidence: 99%

“…The SDE uses the backward-planning algorithm to identify the concrete services, which can be used to satisfy the request and sends this list of services to the SCEE. The QoS monitor is used to monitor these services and can forecast when a service is about to degrade in quality [39] and predict possible candidate services to switch to when this degradation happens [74], [25]. The SCEE will use these services to create a response for the request using a stigmergic service composition algorithm [76].…”

Section: Deep Edgesmentioning

confidence: 99%

See 2 more Smart Citations

Urban Intelligence With Deep Edges

White

Clarke

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the increased accuracy available from state of the art deep learning models and new embedded devices at the edge of the network capable of running and updating these models there is potential for urban intelligence at the edge of the network. The physical proximity of these edge devices will allow for intelligent reasoning one hop away from data generation. This will allow a range of modern urban reasoning applications that require reduced latency and jitter such as remote surgery, vehicle collision detection and augmented reality. The traffic flow from IoT devices to the cloud will also be reduced as with the increased accuracy from deep learning models only a subset of the data will need to be reported after a first pass analysis. However, the training time of deep learning models can be long, taking weeks on multiple desktop GPUs for large datasets. In this paper we show how transfer learning can be used to update the last layers of pre-trained models at the edge of the network, dramatically reducing the training time and allowing the model to perform new tasks without data ever having to be sent to the cloud. This will also improve the users' privacy, which is a key requirement for urban intelligence applications with the introduction of GDPR. We compare our approach to alternative IoT urban intelligence architectures such as cloud-based architectures and deep learning algorithms trained only on local data. INDEX TERMS Edge computing, transfer learning, deep learning, urban intelligence, IoT, QoS. I. INTRODUCTION Urban intelligence can provide insight into a number of the major problems being faced by our cities, such as air pollution, increased mobile communication network demand, traffic congestion and water floods, etc., through the use of data from IoT sensors and intelligent analytics on the data. This can allow for the efficient running of a smart city, making the most of the resources available. Problems in smart cities such as increased network demand and crowd congestion are set to get increasingly difficult with the UN predicting 60% of people globally will live in cities with at least half a million inhabitants by 2030 [1]. This will exacerbate the current problems in our cities, so it will be critical to mange these problems with intelligent urban reasoning algorithms and a suitable deployment architecture. IoT devices will enable access to a range of devices and information that was not available to urban authorities before. This additional information from air pollution sensors, CCTV cameras, vehicles and so on will allow the development of more advanced urban reasoning applications [2]. The associate editor coordinating the review of this manuscript and approving it for publication was Hao Ji.

show abstract

Section: ) Long Short Term Memory (Lstm)mentioning

confidence: 99%

Section: Deep Edgesmentioning

confidence: 99%

Section: Deep Edgesmentioning

confidence: 99%

See 1 more Smart Citation

Urban Intelligence With Deep Edges

White

Clarke

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…[Pedras et al 2018] propuseram um modelo de Qualidade de Experiência (QoE) para redes celulares que obteve valores de RMSE da ordem de 10%, contudo o modelo não considera que existe uma correlação temporal entre as medições, como proposto neste trabalho. [White et al 2018] empregam LSTM ou GRU para prever valores futuros de QoS em dispositivos IoT de baixa potência. Um middleware monitora o acesso de aplicações a web-services, prevê quando a QoS será degradada a ponto de não mais satisfazer um acordo de nível de serviço (SLA -Service Level Agreement).…”

Section: Trabalhos Relacionadosunclassified

Estimativa de Qualidade de Serviço em Estações Wi-Fi Utilizando Redes Neurais Recorrentes

Júnior

Moura

Nunes

et al. 2019

Anais Do XXXVII Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2019)

View full text Add to dashboard Cite

show abstract

“…They are the basis of the state of the art by a clear and significant margin for prediction in natural language [ 7 , 8 , 9 , 10 ]. They also have been successfully applied to modeling many other kinds of time series found across disciplines [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

Estimating Predictive Rate–Distortion Curves via Neural Variational Inference

Hahn

Futrell

2019

Entropy

View full text Add to dashboard Cite

The Predictive Rate–Distortion curve quantifies the trade-off between compressing information about the past of a stochastic process and predicting its future accurately. Existing estimation methods for this curve work by clustering finite sequences of observations or by utilizing analytically known causal states. Neither type of approach scales to processes such as natural languages, which have large alphabets and long dependencies, and where the causal states are not known analytically. We describe Neural Predictive Rate–Distortion (NPRD), an estimation method that scales to such processes, leveraging the universal approximation capabilities of neural networks. Taking only time series data as input, the method computes a variational bound on the Predictive Rate–Distortion curve. We validate the method on processes where Predictive Rate–Distortion is analytically known. As an application, we provide bounds on the Predictive Rate–Distortion of natural language, improving on bounds provided by clustering sequences. Based on the results, we argue that the Predictive Rate–Distortion curve is more useful than the usual notion of statistical complexity for characterizing highly complex processes such as natural language.

show abstract

Forecasting QoS Attributes Using LSTM Networks

Cited by 41 publications

References 23 publications

Urban Intelligence With Deep Edges

Urban Intelligence With Deep Edges

Estimativa de Qualidade de Serviço em Estações Wi-Fi Utilizando Redes Neurais Recorrentes

Estimating Predictive Rate–Distortion Curves via Neural Variational Inference

Contact Info

Product

Resources

About