Clustered complex echo state networks for traffic forecasting with prior knowledge

Abstract

For mobile communication traffic, an accurate prediction result plays an important role in network management, capacity planning, traffic congestion control, channel equalization, etc. This paper proposes a clustered complex echo state network for mobile communication traffic forecasting with prior knowledge. In order to reflect some learning mechanisms of real world organization, various complexities such as small-world features and scale-free node degree distribution were introduced to the dynamic reservoir of original Echo State Network (ESN) and viewed as promising tools for function approximation, modeling of nonlinear dynamic systems, and chaotic time series prediction. Our further observation on the real traffic collected by China Mobile Communications Corporation (CMCC) Heilongjiang Co.Ltd., showed the property of multi-periodicities. Based on this characteristic, Fourier spectrum was chosen as the prior knowledge in this paper for generating multiple functional clusters, corresponding to the frequency components revealed in traffic series of each cell, in the dynamic reservoir of complex echo state network. Experiment results on real traffic showed that: the forecasting accuracy of proposed prior knowledge based clustered complex echo state network (PCCESN) model is superior to that of original ESN models and provides decisionmaking support for network planning and optimization of mobile network.

Echo state network‐based radio signal strength prediction for wireless communication in Northern Namibia

“…The desired output weights are the linear regression weights of the desired outputs on the harvested extended states [23]. Let be the correlation matrix of the extended reservoir states (the prime denotes transpose), and let be the cross‐correlation matrix of the states against the desired outputs.…”

Putting Opportunistic, Situational and Smart Approaches to Underlie the Data Transmission of Social Urban Sensing Applications

“…ESN have been applied to solve practical problems in various domains. With regard to forecasting by means of ESN, the following can be cited [Yu et al 2011] [Rabin et al 2013]. At this time, we cannot find any work that applies ESN in social urban sensing applications.…”

Constraint optimization for Echo State Networks applied to satellite image forecasting

“…A wider range of constraints is supported by regression methods in support vector machines [4]. For ESNs, prior knowledge has been used to determine the reservoir topology [5]. In [6], we introduced the Constrained Extreme Learning Machine (CELM) to embed and verify a wide range of constraints in order to insert prior domain knowledge in the learning process of a feedforward network.…”