Cooperative Spectrum Prediction-Driven Sensing for Energy Constrained Cognitive Radio Networks

Abstract

Spectrum prediction based sensing schemes minimize the overall energy consumption of the sensing module in cognitive radio networks (CRNs) by predicting the status of spectrum before performing actual physical sensing. But, the performance of independent or local prediction models suffer from inaccuracies. Cooperative mode of spectrum prediction is found to be suitable to overcome the issues of local prediction models. In this work, we propose a cooperative spectrum prediction-driven sensing scheme for energy constrained cognitive radio networks to reduce the energy consumption while maintaining the spectral efficiency. The proposed scheme first employs a long short term memory network technique to perform local spectrum prediction, which identifies the status of a channel before actual sensing to improve energy efficiency. Thereafter, a parallel fusion based cooperative spectrum prediction model is applied to minimize the errors induced in local prediction model. Finally, the resultant cooperative prediction model is combined with a spectrum sensing framework to perform sensing operation when the cooperative spectrum prediction results to an indeterminate state in order to enhance the spectral efficiency. Simulation results show the efficacy of the proposed scheme in terms of spectral efficiency and energy efficiency compared to similar schemes from literature.

Optimization for Prediction-Driven Cooperative Spectrum Sensing in Cognitive Radio Networks

“…If the system considers that the prediction result is accurate, this stage will end with a DM state. Otherwise it ends with an IM state [12]. Slot-wise energy spent during prediction stage for each SU is represented by e M .…”

“…As a result, energy efficiency and energy consumption during spectrum sensing become two important topics in energy-constrained CRNs. To effectively reduce energy consumption while maintaining system reliability, a joint and proactive approach that fully exploits sensing and prediction techniques is now considered to be a promising method [12], [13]. Empirical studies have shown that in real-life spectrum usage, certain patterns exist [14].…”

“…Many studies have focused on the joint predictionsensing scheme for CRNs and analyzed the performance from different perspectives. A joint prediction-sensing model was introduced in [12] that utilizes a parallel fusion-based cooperative spectrum prediction scheme to minimize errors and increase efficiency for energyconstrained CRNs. The accuracy was discussed in [12] using simulation results, while the exact analytical expressions were not given.…”

“…A joint prediction-sensing model was introduced in [12] that utilizes a parallel fusion-based cooperative spectrum prediction scheme to minimize errors and increase efficiency for energyconstrained CRNs. The accuracy was discussed in [12] using simulation results, while the exact analytical expressions were not given. A spectrum sharing model based on spectrum prediction and sensing was proposed in [13].…”

Low complexity multichannel spectrum prediction algorithm based on optimized neural network for spectrum allocation in cognitive radio internet of things

“…Currently, spectrum prediction comes as a big partner to any CR function. It accompanies the sensing process to minimize its considerable decision delays and energy consumption like in Reference 8, and to guide SUs to sense only frequency bands that are predicted to be free. It also indicates the access map for SUs, that is, cognitive resource allocation, and proactive spectrum mobility, 9 in addition to its major role in managing unlicensed users' frequency resources and sharing protocols.…”