Spelling suggestions: "subject:"andnetwork computational"" "subject:"anmnetwork computational""
1 |
In-network computation in sensor networksSappidi, Rajasekhar Reddy 22 November 2012 (has links)
Sensor networks are an important emerging class of networks that have many
applications. A sink in these networks acts as a bridge between the sensor nodes
and the end-user (which may be automated and/or part of the sink). Typically,
convergecast is performed in which all the data collected by the sensors is
relayed to the sink, which in turn presents the relevant information to the
end-user. Interestingly, some applications require the sink to relay just a
function of the data collected by the sensors. For instance, in a fire alarm
system, the sinks needs to monitor the maximum of the temperature readings of
all the sensors. For these applications, instead of performing convergecast, we
can let the intermediate nodes process the data they receive, to significantly
reduce the volume of traffic transmitted and increase the rate at which
the data is collected and processed at the sink: this is known as in-network
computation.
Most of the current literature on this novel technique focuses on asymptotic
results for large networks and for very elementary functions. In this
dissertation, we study a new class of functions for which we want to compute
explicit solutions for networks of practical size.
We consider the applications where the sink is interested in the first
M statistical moments of the data collected at a certain time.
The k-th statistical moment is
defined as the expectation of the k-th power of the data. The M=1 case represents the
elementary functions like MAX, MIN, MEAN, etc. that are commonly considered in
the literature. For this class of functions, we are interested in explicitly
computing the maximum achievable throughput including routing, scheduling and
queue management for any given network when in-network computation is allowed.
Flow models have been routinely used to solve optimal joint routing and scheduling
problems when there is no in-network computation and they are typically
tractable for relatively large networks. However, deriving such models is not
obvious when in-network computation is allowed. Considering a single rate wireless network
and the physical model of interference, we develop a discrete-time model for
the real-time network operation and perform two transformations to obtain a flow
model that keeps the essence of in-network computation. This model gives an
upper bound on the maximum achievable throughput. To show the tightness of that
upper bound, we derive a numerical lower bound by computing a feasible solution
to the discrete-time model. This lower bound turns out to be
close to the upper bound proving that the flow model is an excellent
approximation to the discrete-time model.
We then adapt the flow model to a
wired multi-rate network with asynchronous transmissions on links with different
capacities. To compute the lower bound for wired networks, we propose a
heuristic strategy involving the generation of multiple trees and effective
queue management that achieves a throughput close to the one computed by the
flow model. This cross validates the tightness of the upper bound and the
goodness of our heuristic strategy. Finally, we provide several engineering
insights on what in-network computation can achieve in both types of networks.
|
2 |
In-network computation in sensor networksSappidi, Rajasekhar Reddy 22 November 2012 (has links)
Sensor networks are an important emerging class of networks that have many
applications. A sink in these networks acts as a bridge between the sensor nodes
and the end-user (which may be automated and/or part of the sink). Typically,
convergecast is performed in which all the data collected by the sensors is
relayed to the sink, which in turn presents the relevant information to the
end-user. Interestingly, some applications require the sink to relay just a
function of the data collected by the sensors. For instance, in a fire alarm
system, the sinks needs to monitor the maximum of the temperature readings of
all the sensors. For these applications, instead of performing convergecast, we
can let the intermediate nodes process the data they receive, to significantly
reduce the volume of traffic transmitted and increase the rate at which
the data is collected and processed at the sink: this is known as in-network
computation.
Most of the current literature on this novel technique focuses on asymptotic
results for large networks and for very elementary functions. In this
dissertation, we study a new class of functions for which we want to compute
explicit solutions for networks of practical size.
We consider the applications where the sink is interested in the first
M statistical moments of the data collected at a certain time.
The k-th statistical moment is
defined as the expectation of the k-th power of the data. The M=1 case represents the
elementary functions like MAX, MIN, MEAN, etc. that are commonly considered in
the literature. For this class of functions, we are interested in explicitly
computing the maximum achievable throughput including routing, scheduling and
queue management for any given network when in-network computation is allowed.
Flow models have been routinely used to solve optimal joint routing and scheduling
problems when there is no in-network computation and they are typically
tractable for relatively large networks. However, deriving such models is not
obvious when in-network computation is allowed. Considering a single rate wireless network
and the physical model of interference, we develop a discrete-time model for
the real-time network operation and perform two transformations to obtain a flow
model that keeps the essence of in-network computation. This model gives an
upper bound on the maximum achievable throughput. To show the tightness of that
upper bound, we derive a numerical lower bound by computing a feasible solution
to the discrete-time model. This lower bound turns out to be
close to the upper bound proving that the flow model is an excellent
approximation to the discrete-time model.
We then adapt the flow model to a
wired multi-rate network with asynchronous transmissions on links with different
capacities. To compute the lower bound for wired networks, we propose a
heuristic strategy involving the generation of multiple trees and effective
queue management that achieves a throughput close to the one computed by the
flow model. This cross validates the tightness of the upper bound and the
goodness of our heuristic strategy. Finally, we provide several engineering
insights on what in-network computation can achieve in both types of networks.
|
3 |
Comparação entre controladores fuzzy e neural desenvolvidos via simulação e transferidos para ambientes reais no âmbito da robótica evolutiva / Comparison between fuzzy and neural controllers developed by simulation and transferred to real environments in the scope of evolutionary roboticsFarias, Weslley Alves 26 July 2018 (has links)
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / One of the greatest limitations of Evolutionary Robotics is when transfering controllers
evolved by simulation to real environments. This limitation is mainly caused by
model simplifications and difficulties to represent dynamic characteristics, whether from
the robot or the environment. And this results in performance degradation of the evolved
controller after the transfer, a phenomenon called reality gap. Because this problem is a
limitation for practical and complex applications of evolutionary robotics, many solutions
have been proposed since the 90s. Until now, most of the research use control strategies
based on artificial neural networks because they allow algorithms to be evolved with less
designer influence. On the other hand, fuzzy logic can also be used for the development
of controllers in the field of evolutionary robotics because it also allows emulating human
intelligence. Therefore, this dissertation investigates whether fuzzy control systems
are more robust than neural control systems, both optimized by a genetic algorithm in
simulation and later transferred to a real robot in physical environment in the task of
autonomous navigation while avoiding obstacles. The results show that in the analyzed
conditions, fuzzy controllers present better transfer characteristics, mainly considering the
smoothness of the executed trajectory, and an equivalent performance, when compared
with neural controllers. / Uma das grandes limitações da Robótica Evolutiva diz respeito à transferência de
controladores evoluídos por simulação e transferidos ao ambiente real. Tal limitação devese,
sobretudo, a simplificações de modelo e dificuldades na representação de características
dinâmicas, tanto do robô quanto do ambiente, e isso resulta na queda de desempenho do
controlador evoluído após a transferência, fenômeno denominado de reality gap. Muitas
soluções vêm sendo propostas desde a década de 90, em virtude deste problema ser uma
limitação para aplicações práticas e complexas da robótica evolutiva. Até o momento, a
maioria dos trabalhos de pesquisa desenvolvidos utiliza estratégias de controle baseadas
em redes neurais artificiais por permitirem que algoritmos possam ser evoluídos com menor
influência do projetista. Por outro lado, a lógica fuzzy também pode ser usada para o
desenvolvimento de controladores no âmbito da robótica evolutiva, pois também permite
emular a inteligência humana. Portanto, nesta dissertação é investigado se sistemas de
controle fuzzy são mais robustos que sistemas de controle neurais, ambos otimizados por
um algoritmo genético em simulação e posteriormente transferidos para um robô real em
ambiente físico na tarefa de navegação autônoma evitando obstáculos. Como resultado,
obteve-se que nas condições analisadas, os controladores fuzzy apresentaram uma melhor
transferência, com destaque para a suavidade da trajetória executada, e um desempenho
equivalente, quando comparados com controladores neurais. / São Cristóvão, SE
|
Page generated in 0.1156 seconds