Received Signal Strength Prediction Research Articles

CNN‐based received signal strength prediction: A frequency conversion scheme

AbstractTo support the design and deployment of emerging high‐frequency wireless systems in various applications such as intelligent transportation, advanced received signal strength (RSS) simulation tools for radio coverage prediction are needed. In railway transportation, the vector parabolic equation (VPE) method is a commonly used approach for radio wave propagation modelling in large guiding structures such as tunnels. However, running VPE simulations at high frequencies in such an environment is computationally expensive, as the discretization parameters are closely related to the wavelength. In this letter, the authors propose a convolutional neural network‐based model that can efficiently provide RSS prediction at high frequencies by leveraging data obtained from VPE simulations at a lower frequency as an anchor. This proposed model can significantly improve the efficiency of VPE for high‐frequency RSS predictions and has been validated against conventional VPE in various tunnel cases.

A New Vertical Handover Prediction Method for Heterogeneous Wireless Networks

Long Term Evolution (LTE) is the fourth generation (4G) cellular network technology that provides improved performance that related to data rate, coverage and capacity compared to earlier cellular systems. The addition of many small cells in a heterogeneous network configuration provides a means to enhance capacity through extreme frequency reuse. The heterogeneous environment of different network technologies can provide high data rate and enhance multimedia services, but it is challenging to provide optimized handover (HO). In this paper, a new method is proposed to select the optimal network from available networks to which a UE may be handed over to achieve better QoS performance. The aggregation of multiple criteria for calculation of overall ranking of networks is obtained by Analytical Hierarchy Process (AHP) [1] and is combined with the history of previously visited cells and regression analysis of the Layer 1 (L1) and Layer 3 (L3) filtered Received Signal Strength (RSS) data for prediction of future values. The AHP is used to calculate the weights for the system attributes and to rank the available networks based on multiple criteria Multiple Attribute Decision Making (MADM). The sequence of visited cells is used in target network selection as it reduces frequent handover. The sequence of visited cells would be modeled as a Markov Chain. To assess RSS, beside L1, L3 filtering RSS prediction and smoothing is used to predict future signal samples to hasten the process of HO. RSS forecasting is used to predict handover necessity so as to reduce the handover delay. The results show that the number of handovers is reduced by up to 50% compared to the conventional AHP. The results also show that the threshold crossing rate and average duration of fades are reduced by 47% compared with the AHP. Handover delay is also reduced by up to 40 ms due to RSS forecasting.

Received signal strength prediction model for wireless underground sensor networks using machine learning algorithms

Analysis of the Received Signal Strength (RSS) from the Wireless Underground Sensor Network (WUSN) is essential before the deployment of the sensor network. It is difficult to predict received signal strength from an underground sensor network using a theoretical model due to variations in environmental conditions. Prediction of RSS using the machine learning approach considers varying environmental conditions. In this work, we develop the RSS prediction model using machine learning concepts based on linear regression, Support Vector Machine (SVM) and random forest algorithms. The RMSE and MAE of the machine learning approach based on the SVM algorithm were found to be the least among the three techniques. It is further observed that the RSS prediction using machine learning methods produces lower RMSE than the theoretical model. Accurate estimates of RSS from a machine learning based prediction model help in deciding the node positioning in order to achieve effective communication within a WUSN.

3.5 GHz Outdoor Radio Signal Strength Prediction With Machine Learning Based on Low-Cost Geographic Features

In the fifth-generation (5G) and beyond 5G (B5G) networks, received signal strength (RSS) prediction has always been a fundamental task in network planning and optimization phases. The existing machine learning (ML)-based RSS prediction models seldom testify to the model validity with reliable drive test data in 5G networks and tend to neglect the low-cost extraction in feature contriving. This article presents an ML scheme based on the geographic feature to predict RSS. We elaborately select four features closely related to RSS from the easily acquired geographic dataset and design low-cost methods for computing them. Experiments are executed in the large-scale outdoor scenario at 3.5 GHz for a 5G network where the real RSS data are collected by the field measurement in the urban city. We adopt four state-of-the-art ML algorithms for the proposed scheme and compare the algorithm accuracy with a Stanford University interim (SUI) model, an ECC-33 model, and a ray tracing method. Experiment results show the validity of the extracted features. Besides, the proposed scheme performs well in its model accuracy and computational efficiency compared with the existing methods. Furthermore, it is promising to build a universal, accurate, and efficient ML-based RSS prediction scheme based on massive field data in 5G or B5G networks.

Multiple linear regression-based machine learning model for received signal strength prediction of multiband applications

Multiple linear regression-based machine learning model for received signal strength prediction of multiband applications

Multi-criteria vertical handoff decision algorithm for overlaid heterogeneous mobile IP networks

One of the key challenges to improving the quality of service (QoS) in integrated heterogeneous mobile Internet protocol networks is the design of an intelligent decision engine for accessing various services anywhere and at any time. The multi-criteria decision making algorithm plays a significant role in ensuring universal and seamless connection. In this study, a multi-criteria vertical handoff decision algorithm plus dwell time is developed to achieve a satisfactory quality of service using the best access network selection in an integrated wireless local area network (WLAN), a worldwide interoperability for microwave access (WiMAX), and a universal mobile telecommunications system (UMTS). Handoffs are divided into two schemes: the UMTS originating handoff (downward) and the WLAN/WiMAX originating handoff (upward/intrasystem). The initial criteria for real-time and non-real-time services are presented. The metrics that are required to trigger a handoff are the predictive received signal strength (PRSS) of neighbor networks and the received signal strength obtained from the current network. The back propagation neural network is learned for the prediction. The dwell time is used as a counter to avoid the unnecessary handoffs that may occur in the overlapping areas. The quantitative network selection is the largest merit value and is based on the available bandwidth, cost, user preference, and the criteria to eliminate inappropriate candidate networks. The importance of using the PRSS, dwell time, and merit function is evaluated. To illustrate the QoS satisfaction, the multi-criteria vertical handoff decision algorithm outperforms the single-criteria using the hysteresis and Mamdani fuzzy method.

Propagation-Model-Free Base Station Deployment for Mobile Networks: Integrating Machine Learning and Heuristic Methods

As densification is the promising trend of future mobile networks, deployment of base stations (BSs) becomes increasingly difficult due to the laborious procedures in network planning; besides, unreasonable layout may lead to poor coverage performance. Hence, this paper firstly trains a propagation-model-free received signal strength (RSS) predictor based on machine learning (ML) models, and then optimizes coverage performance of BS deployment via multi-objective heuristic methods. Specifically, many practical features that affect signal propagation like geographical types and operating parameters of BS, are fed into ML models to predict RSS in a rasterized area; then based on the trained model, a well-designed multi-objective genetic algorithm (GA) is proposed to minimize the number of deployed BSs with coverage constraint. For the practical considerations of fast convergence and output-consistence, greedy algorithm with fixed initial solution and searching direction is also carried out. Moreover, the typical scenarios of incremental deployment (the mobile operator needs to deploy more BSs on the basis of the existing deployment) and BS outage compensation (one BS fails and other BSs need to adjust their configurations to fill the coverage gap), are also investigated for practical needs. Simulations show that multi-layer perceptron outperforms other ML algorithms in terms of RSS prediction with mean absolute error (MAE) yielded to 3.78 dB; and numerical results verify the convergence and availability of the proposed algorithms, which shows 18.5% gain than the real-world deployment in terms of coverage rate.

Lightweight Workload Fingerprinting Localization Using Affinity Propagation Clustering and Gaussian Process Regression.

Fingerprinting localization approach is widely used in indoor positioning applications owing to its high reliability. However, the learning procedure of radio signals in fingerprinting is time-consuming and labor-intensive. In this paper, an affinity propagation clustering (APC)-based fingerprinting localization system with Gaussian process regression (GPR) is presented for a practical positioning system with the reduced offline workload and low online computation cost. The proposed system collects sparse received signal strength (RSS) data from the deployed Bluetooth low energy beacons and trains them with the Gaussian process model. As the signal estimation component, GPR predicts not only the mean RSS but also the variance, which indicates the uncertainty of the estimation. The predicted RSS and variance can be employed for probabilistic-based fingerprinting localization. As the clustering component, the APC minimizes the searching space of reference points on the testbed. Consequently, it also helps to reduce the localization estimation error and the computational cost of the positioning system. The proposed method is evaluated through real field deployments. Experimental results show that the proposed method can reduce the offline workload and increase localization accuracy with less computational cost. This method outperforms the existing methods owing to RSS prediction using GPR and RSS clustering using APC.

해상환경에서의 수신 신호세기 예측을 통한 포물선 궤적 비행체의 Two-Ray 전파손실 극복

섬 등의 기타 구조물이 없는 해상 환경에서 송수신기 간의 이동 궤적이 주어진다면, 해상 통신 채널 환경은 two-ray 전파모델로 깊은 페이딩이 발생하는 구간을 예측할 수 있다. 본 논문에서는 해상의 포물선 궤적 비행체에 대하여 둥근 지구 반사 모델을 통해 수신신호 세기를 예측하였다. 이를 바탕으로, 깊은 페이딩을 극복하기 위해 적용하는 시공간 다이버시티의 효과를 시뮬레이션으로 분석하였으며, 효율적인 시공간 다이버시티 적용 방안을 제시한다. 포물선 궤적 비행체의 실제 비행시험 데이터를 바탕으로, UHF 대역 수신 신호 세기 예측값과 실측값을 비교하여 수신신호 세기 예측 모델의 정확도를 보여주었다. 또한 다수의 S 대역 안테나를 통해 수신된 데이터의 프레임 오류와 수신신호 세기를 예측한 값과의 개연성을 설명하였으며 시공간 다이버시티가 적용된 효과를 보여주었다.

Development of hybrid artificial intelligent based handover decision algorithm

The possibility of seamless handover remains a mirage despite the plethora of existing handover algorithms. The underlying factor responsible for this has been traced to the Handover decision module in the Handover process. Hence, in this paper, the development of novel hybrid artificial intelligent handover decision algorithm has been developed. The developed model is made up of hybrid of Artificial Neural Network (ANN) based prediction model and Fuzzy Logic. On accessing the network, the Received Signal Strength (RSS) was acquired over a period of time to form a time series data. The data was then fed to the newly proposed k-step ahead ANN-based RSS prediction system for estimation of prediction model coefficients. The synaptic weights and adaptive coefficients of the trained ANN was then used to compute the k-step ahead ANN based RSS prediction model coefficients. The predicted RSS value was later codified as Fuzzy sets and in conjunction with other measured network parameters were fed into the Fuzzy logic controller in order to finalize handover decision process. The performance of the newly developed k-step ahead ANN based RSS prediction algorithm was evaluated using simulated and real data acquired from available mobile communication networks. Results obtained in both cases shows that the proposed algorithm is capable of predicting ahead the RSS value to about ±0.0002dB. Also, the cascaded effect of the complete handover decision module was also evaluated. Results obtained show that the newly proposed hybrid approach was able to reduce ping-pong effect associated with other handover techniques.

Vertical Handoff with Predictive Received Signal Strength in Next Generation Wireless Network

Since the last few decades, tremendous innovations and inventions have been observed in every field, but especially in wireless network technology. The prevailing demand curves and trends in this particular area of communication show the importance of real-time multimedia applications over several networks with guaranteed quality of service (QoS). The Next Generation Wireless Network (NGWN) consists of heterogeneous wireless networks that will grant high data rate and bandwidth to mobile users. The primary aim of Next Generation Wireless Network (NGWN) is to conceal heterogeneities and to achieve convergence of diverse networks to provide seamless mobility. So that mobile user can move freely between networks without losing the connection or changing the setting at any moment. When the mobile user moves between different networks, there is a requirement to handover the channel, from one network to another by considering its services, features and user preferences. Channel handover between two different networks is done with the help of vertical handoff (VHO). In a heterogeneous environment, numerous technologies co-exist with their unique characteristics. Therefore, it is very difficult to design efficient handoff decision algorithm. The poorly designed handoff algorithm tends to increase the traffic load and, thereby tend to dramatic decrease in quality of service. A mobile node equipped with multiple network interfaces will be able to access heterogeneous wireless access network. But the availability of alternatives give rise to a problem of unnecessary handoff. To avoid this, we have proposed a decision algorithm based on predictive received signal strength, hysteresis margin and dwell time to select an optimum target network. The handoff policies are designed using received signal strength (RSS), available bandwidth, service cost, user preference, type of application and network condition to reduce the number of handoffs, decision delay, probability of handoff failure and probability of unnecessary handoff. We have also made a comparative analysis of various vertical handoff decision algorithms in this paper.

A novel link switching scheme using pre-scanning and RSS prediction in visible light communication networks

Abstract Visible light communication (VLC) is gaining increasing attention and is considered as a promising technology for future wireless indoor communications. Because movable users expect a seamless connectivity experience when switching among transmitters (i.e., VLC access points) in the VLC system, fast link switching operations must be supported by the networks. This paper presents a novel hard link switching scheme for VLC networks with the use of pre-scanning and received signal strength (RSS) prediction. Our proposed scheme achieves the advantages of both conventional hard and soft link switching schemes without changing device hardware or the IEEE 802.15.7 medium access control (MAC) protocol. To help compare our proposed scheme with conventional hard and soft link switching schemes, the signal-to-interference-plus-noise ratio (SINR), the outage probability regarding the link switching situation, and the queuing models for link switching schemes are taken into account. Simulation and numerical results validate that our proposed scheme outperforms conventional hard and soft link switching schemes.

Media Independent Handover-based Competitive On-Line CAC for Seamless Mobile Wireless Networks

In Media Independent Handover (MIH), Call Admission Control (CAC) and Vertical Handoff (VH) are two important mechanisms in a Mobile Wireless Networks (MWNs) that consists of various types of wireless networks (e.g., WiMAX and WiFi) and cellular communications (e.g., 3G, 3.5G and 4G). First, an adaptive CAC is needed in base stations for achieving high network reward while guaranteeing QoS requirements. Second, an efficient vertical handoff enables mobile stations accomplishing seamless, fast, QoS-aware mobility in MWNs. In CAC, several studies have proposed the mechanisms: the static resource reservation-based, bandwidth borrow-based and Markov chain model-based approaches. They suffer from moderate performance in Grade of Service (GoS), Fractional Reward Loss (FRL) and transmission quality. In VH, it should consider both the received signal strength (RSS) and the service-class mapping between the serving and target networks. Most studies adopted the integration of a RSS-based method with hysteresis to minimize unnecessary handoffs, but high handoff dropping and low network utilization limit the contributions. This work thus proposes a MIH-based competitive on-line (COL) CAC for vertical handoff in a loosely-coupled MWN. First, in a base station (BS) the COL CAC models the resource occupancy of each wireless network in a MWN as a Markov chain model, and then forms a cost-reward CAC for maximizing network reward. Second, in MS the VH scheme adopts a predictive RSS to predict the moving trend of each mobile station to select the optimal target network. Numerical results indicate that the proposed approach outperforms other approaches in GoS, FRL and the number of vertical handoffs while yielding competitive utilization.

Cross-Layer-Based Adaptive Vertical Handoff With Predictive RSS in Heterogeneous Wireless Networks

A heterogeneous wireless network consists of various wireless networks [e.g., Worldwide Interoperability for Microwave Access (WiMAX) and Wireless Fidelity (WiFi)] and cellular communications [e.g., beyond the third generation (B3G) and the fourth generation (4G)]. Vertical handoff is an important mechanism for achieving continuous seamless transmissions in these networks. In contrast to horizontal handoff, vertical handoff considers not only the received signal strength (RSS) but also the service-class mapping between handoff-in and handoff-out networks. Most previous works have adopted the RSS-based mechanism to determine handoff thresholds, which causes a serious ping-pong effect that increases unnecessary handoff. Although integrating the RSS-based mechanism with a hysteresis method reduces the unnecessary handoff, it suffers from high dropping [i.e., high Sum of Weighted Grade of Service (SWGoS)] and low utilization. Therefore, this paper proposes a cross-layer-based adaptive vertical handoff algorithm with predictive RSS to reduce the unnecessary handoff while significantly increasing utilization and decreasing connection dropping. The proposed approach determines the optimal target network in two phases, i.e., polynomial regression RSS prediction and Markov decision process analysis. Furthermore, fast changes in bandwidth caused by vertical handoff result in inaccurate Transmission Control Protocol (TCP) congestion control and, thus, reduce the TCP goodput. The cross-layer scheme provides a TCP receiver to reply to the TCP sender with the wireless network's protocol type. By using the cross-layer information, the TCP sender can accurately predict the available bandwidth and increase the network goodput. Numerical results indicate that the proposed cross-layer-based approach outperforms the other approaches in the number of vertical handoffs and SWGoS while yielding competitive utilization. In addition, the cross-layer scheme cooperates with existing TCP algorithms to increase goodput by up to 18%.