LP-MAB: Improving the Energy Efficiency of LoRaWAN Using a Reinforcement-Learning-Based Adaptive Configuration Algorithm

Abstract

In the Internet of Things (IoT), Low-Power Wide-Area Networks (LPWANs) are designed to provide low energy consumption while maintaining a long communications’ range for End Devices (EDs). LoRa is a communication protocol that can cover a wide range with low energy consumption. To evaluate the efficiency of the LoRa Wide-Area Network (LoRaWAN), three criteria can be considered, namely, the Packet Delivery Rate (PDR), Energy Consumption (EC), and coverage area. A set of transmission parameters have to be configured to establish a communication link. These parameters can affect the data rate, noise resistance, receiver sensitivity, and EC. The Adaptive Data Rate (ADR) algorithm is a mechanism to configure the transmission parameters of EDs aiming to improve the PDR. Therefore, we introduce a new algorithm using the Multi-Armed Bandit (MAB) technique, to configure the EDs’ transmission parameters in a centralized manner on the Network Server (NS) side, while improving the EC, too. The performance of the proposed algorithm, the Low-Power Multi-Armed Bandit (LP-MAB), is evaluated through simulation results and is compared with other approaches in different scenarios. The simulation results indicate that the LP-MAB’s EC outperforms other algorithms while maintaining a relatively high PDR in various circumstances.

Machine-Learning-Assisted Transmission Power Control for LoRaWAN Considering Environments With High Signal- to -Noise Variation

“…We conducted a detailed grid search combined with fivefold cross-validation, as detailed in Table 6. This approach specifically evaluated various hyperparameters of the ANN with a Multilayer Perceptron structure as follows: architectures including configurations denoted as tuples in the hidden layers (e.g., (m,n) means that the ANN has two hidden layers with m neurons in the first layer and n neurons in the second layer [49]) with values of (5,2), (10,5), (15,7), (20,10), (10,5,2), (15,7,3), and (20,10,5); learning rates of 0.0001, 0.001, 0.01, 0.05, and 0.1; and learning rate update policies such as 'constant,' 'adaptive,' and 'invscaling.' We used the Rectified Linear Unit (RELU) as the activation function due to its proven effectiveness in regression.…”

“…Teymuri et al [20] employed reinforcement learning to find suitable transmission parameters to reach an acceptable PDR while minimizing energy consumption. They used nonstationary adversarial and stochastic algorithms to train the reinforcement learning policies with a short exploration time.…”

LoRaWAN Meets ML: A Survey on Enhancing Performance with Machine Learning

“…An algorithm called Low-Power LP-MAB (MAB) [ 179 ] was designed to configure the transmission parameters (e.g., SF) of ED in a centralized manner to improve energy consumption and PSR. The LP-MAB algorithm works on the NS side by interacting with the ED.…”

İran’da Tütün İmtiyazının İngilizlere Verilmesi Meselesi ve İranlı Kadınlar (1890- 1892)

“…28 Nitekim Nasıreddin Şah'ın üçüncü Avrupa seyahatini (1889) takiben 29 , İran'dan sürekli yeni tavizler elde etmeye çalışan İngiliz hükümeti, fırsat bilip İran'da üretilen tütünün işletme imtiyazını Şah'tan talep etti. 30 Bu işin sorumluluğu da Gerald Talbot'a verildi. Bu şahıs İngiltere Başbakanı Lord Salisbury'nin yakınlarından ve danışmanlarından biriydi.…”

“…31 8 Mart 1890 tarihinde Şah, gezisinin fahiş masraflarını karşılamak ve ayrıca rüşvet karşılığında İngilizlere tütün işletme imtiyazını vermeyi kabul etti. 32 İki taraf arasında imzalanan antlaşmaya göre, sözleşmenin süresi elli yıl idi ve bu antlaşmanın bazı önemli maddeleri şöyleydi: Birinci madde: imtiyaz sahipleri yılda 15 bin İngiliz lirasını İngilizlere verilen tütün imtiyazı büyük bir titizlikle İran halkından gizleniyordu. Çünkü merkezi hükümet, imtiyazın halktan gizlenmesi için karar almıştı.…”