Multi-objective surrogate modeling for real-time energy-efficient station grouping in IEEE 802.11ah

Tian, Le; Mehari, Michael; Santi, Sintha Soraya; Latré, Steven; Poorter, Eli De; Famaey, Jeroen

doi:10.1016/j.pmcj.2019.04.007

Cited by 11 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the model does not take the finite length of the RAW slot into account. Recently, we proposed a new RAW performance model based on supervised surrogate modeling [11], [12]. The model is trained on a limited set of labeled data samples from ns-3 simulation results, supports realistic channel conditions, including communication errors, propagation delays and capture effects.…”

Section: Related Work On Ieee 80211ah Rawmentioning

confidence: 99%

“…For training simplicity, we assume each station sends one packet per second and a small buffer size of 10 packets is used. The built model can be further used by the RAW optimization algorithms, such as TAROA [9], [10] and MoROA [11], [12], to calculate RAW performance under arbitrary data transmission intervals.…”

Section: A Training Scenariosmentioning

confidence: 99%

“…To the best of our knowledge, this is the first RAW model that supports heterogeneous stations in terms of different modulation and coding schemes (MCSs) and packet sizes. The built model can be used as an input for real-time optimization algorithms such as [9], [10], [11], [12] to get optimal RAW configurations for IEEE 802.11ah heterogeneous networks, achieving highest performance.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization-Oriented RAW Modeling of IEEE 802.11ah Heterogeneous Networks

Tian

López-Aguilera

García-Villegas

et al. 2019

IEEE Internet Things J.

Self Cite

View full text Add to dashboard Cite

The new medium access method of IEEE 802.11ah, called Restricted Access Window (RAW), divides stations into different groups, and only allows stations in the same group to access the channel simultaneously, in order to reduce collisions and thus achieve better performance (e.g., throughput). However, the existing station grouping strategies only support homogeneous scenarios where all stations use the same modulation and coding scheme (MCS) and packet size. A surrogate model is an efficient mathematical model that represents the behavior of a complex system, trained with a limited set of labeled input-output data samples. In this paper, we present a surrogate model that can accurately predict RAW performance under a given Restricted Access Window (RAW) configuration in heterogeneous networks. Different from the homogeneous scenario, heterogeneous networks are defined by a large number of parameters, leading to an enormous design space, i.e., the order of 10 17 possible data points. This is too big to achieve feasible training convergence. In this paper, we present a novel training methodology that leads to a new design space with highly reduced size, i.e., the order of 10 5 data points. The surrogate model converges when less than 6000 labeled data points are used for training, which is only a tiny portion of the whole design space. The results show that, the relative error between model prediction and simulation results is less than 0.1 for 95% of the data points, in the areas of the design space studied. Its low complexity and high precision make the proposed model a valuable tool to develop real-time RAW optimization algorithms for heterogeneous IEEE 802.11ah networks.Index Terms-IEEE 802.11ah, RAW, surrogate model, heterogeneous networks.

show abstract

Section: Related Work On Ieee 80211ah Rawmentioning

confidence: 99%