Gradient RSSI Filter and Predictor for Wireless Network Algorithms and Protocols

Suárez, Alvaro; Elbatsh, Kholoud; Macías, Elsa M.

doi:10.5296/npa.v2i2.414

Cited by 12 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequent studies reported that it had a specific effect as an indicator for detecting the decrease in communication link reliability at an early stage, especially when targeting AGVs [17,18]. Furthermore, prediction methods for future RSSI trends have been verified through experiments and simulations [19][20][21][22]. In our proposed method, we also utilize RSSI as an indicator to understand wireless fluctuations.…”

Section: Related Workmentioning

confidence: 89%

A Machine-Learning-Based Access Point Selection Strategy for Automated Guided Vehicles in Smart Factories

Ohori,

Yamaguchi,

Itaya

et al. 2023

Sensors

View full text Add to dashboard Cite

Automated Guided Vehicles (AGVs) are becoming popular at many manufacturing facilities. To ensure mobility and flexibility, AGVs are often controlled by wireless communication, eliminating the constraints of physical cables. These AGVs require multiple Access Points (APs) to ensure uninterrupted coverage across the site. As AGVs move, they need to switch between these APs seamlessly. A primary challenge is that the communication downtime during this link-switching process must be minimal for effective AGV monitoring and control. Current AP selection strategies based on observed Received Signal Strength Indicator (RSSI) often fail in manufacturing environments due to RSSI’s inherent instability. This paper introduces a new AP selection technique for AGVs navigating these sites. Our approach harnesses the distinct movement patterns of AGVs and uses machine learning techniques to learn location-, trajectory-, and orientation-specific RSSI from the APs. Real-world factory data from our unique dataset revealed that our method extends the potential communication duration per route by 1.34 times compared to the prevalent signal strength-based switching methods commonly implemented in current drivers provided by chipset vendors or open-source Wi-Fi drivers. These results indicate that the automatic evaluation and tuning of the wireless environment using the proposed method is beneficial in reducing the time and effort required to investigate the detailed propagation paths needed to adapt AGV to existing APs.

show abstract

Section: Related Workmentioning

confidence: 89%

A Machine-Learning-Based Access Point Selection Strategy for Automated Guided Vehicles in Smart Factories

Ohori,

Yamaguchi,

Itaya

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…After that, a wireless device that was disconnected from the A j now must be connected to the A i . That process produces a forced handoff (Wang et al 2017) that has been well studied, and efficient traditional solutions exist for it (Suárez et al 2010). For that reason, it is necessary to characterize the trajectory of wireless terminals and efficiently assign the APs of the WiFi network so that the handoff is achieved efficiently.…”

Section: Algorithms For Turning On and Turning Off Aps Of Amentioning

confidence: 99%

A novel energy-saving method for campus wired and dense WiFi network applying machine learning and idle cycling techniques

Alvarado,

Suárez

2024

FACETS

Self Cite

View full text Add to dashboard Cite

University campus networks need wired (ethernet) and dense wireless fidelity networks that have devices like access points, switches, and routers that are always turned on. Consequently, they generate two important problems: the energy bill and the influence of carbon dioxide into the atmosphere. Energy savings are the solution to those problems. There are several proposals to augment the energy savings separately in ethernet and wireless fidelity, but there is no integrated method to simultaneously reduce them in both parts of the networks. Our novel method combines idle cycling and machine learning techniques to efficiently obtain energy savings in both parts of the network simultaneously. We categorize network devices into two groups: (a) those that are always turned on and (b) those that can be dynamically turned on or off based on network performance. We formulated two algorithms that decide when to turn on and off access points. We use Ward's machine learning hierarchical clustering technique to optimize the energy savings of our model in the network of the Unidades Tecnológicas de Santander (Bucaramanga, Colombia). We showed that energy savings of 21.5 kWh per day are possible. The success of the model in this context highlights its potential to achieve substantial energy savings.

show abstract

“…Received signal strength indicator is one of the most common metrics used in handover decision making [14,[33][34][35]. Through monitoring RSSI via MN, we can analyze the quality and distance for each AP in the range.…”

Section: Tracking Received Signal Strength Indicatormentioning

confidence: 99%

A smart handover prediction system based on curve fitting model for Fast Mobile IPv6 in wireless networks

Sadiq

Bakar

Ghafoor

et al. 2012

Int J Communication

View full text Add to dashboard Cite

Seamless handover process is essential in order to provide efficient communication between mobile nodes in wireless local area networks. Despite the importance of a signal strength prediction model to provide seamless handovers, it is not embedded in standard mobility management protocols. In this article, we propose a smart handover prediction system based on curve fitting model to perform the handover (CHP) algorithm. The received signal strength indicator parameter, from scanning phase, is considered as an input to the CHP in order to provide a prediction technique for a mobile node to estimate the received signal strength value for the access points in the neighborhood and to select the best candidate access point from them in an intelligent way. We implemented the proposed approach and compared it with standard protocols and linear regression-based handover prediction approach. Simulation results in complex wireless environments show that our CHP approach performs the best by predicting the received signal strength value with up to 800 ms in advance from real obtained value via scanning phase. Moreover, our CHP approach is the best in terms of layer 2 and overall handover latency, in comparison with standard protocols and linear regression approach, respectively.A. S. SADIQ ET AL. model, is responsible for detecting the potential handover and obtaining the decision to perform the handover procedure. The second layer, the network layer or layer 3 (L3) in the Open Systems Interconnection model, becomes involved in the handover process just when the MN enters the network domain of a different subnet [2]. The MN, to be able to maintain the network connectivity, requires to execute the L3 signaling in order to obtain a new Internet Protocol (IP) address. An interruption occurs when MN is going to change its place across different access routers (ARs) in the range of movement. This is known as the time required to change the wireless network link and then to return back to routability. In other words, it is identified as a handover latency mentioned in [3], which consists of several levels of delay distributed over handover process levels.The handover can be defined as the time spent changing from one point of attachment AR to another. During this time, the MN is not able to send or receive data. Thus, the connection may be interrupted, and packets may be lost or delayed because of intermediate buffers [3,4]. The Internet Engineering Task Force (IETF) developed Mobile IP (MIP) to tackle the handover latency issue by utilizing efficient mobility management. IETF has designed two versions of MIPs: Mobile IPv4[5] and Mobile IPv6 (MIPv6) [6]. MIPv6 has recently been used as a mobility protocol supported with IPv6 addressing, and its process scheme is illustrated in Figure 1. We can observe the signaling scheme of MIPv6 protocol during MN roaming process among previous AR (PAR), new AR (NAR), home agent (HA), and corresponded node (CN) (a node that communicates with an MN that is out of its own network). This mobility ...

show abstract

Gradient RSSI Filter and Predictor for Wireless Network Algorithms and Protocols

Cited by 12 publications

References 17 publications

A Machine-Learning-Based Access Point Selection Strategy for Automated Guided Vehicles in Smart Factories

A Machine-Learning-Based Access Point Selection Strategy for Automated Guided Vehicles in Smart Factories

A novel energy-saving method for campus wired and dense WiFi network applying machine learning and idle cycling techniques

A smart handover prediction system based on curve fitting model for Fast Mobile IPv6 in wireless networks

Contact Info

Product

Resources

About