Multi-agent based DRL with federated learning for data transmission in mobile sensor networks

Wireless body area network (WBAN) can collect and analyze human health signs data of various modes in real time by virtue of low-energy consumption high-precision sensing technology, and it needs to protect health sensitive data related to personal privacy in the process of data transmission. In order to solve the important problem of reliable data transmission in wireless body area network, a new strategy is proposed in this paper. From the two levels of single-hop communication and two-hop communication, the channel characteristics and node data rate in WBAN are fully considered. The reliable data transmission in wireless body area network is realized by using time slot allocation and relay strategy. The introduction of TDMA mechanism of dynamic time slot allocation improves the energy efficiency of strategy and avoids the energy consumption caused by competition, while dynamic time slot allocation satisfies the change of node flow. Time slot allocation strategy based on channel condition and data traffic, exist some nodes in the practical use of the status of the data transmission reliability not guaranteed, we use the relay for this strategy to improve its, meet the requirements of the reliability of data transmission in the network, to bring the additional energy consumption, and strategy information dynamic relay selection depend on the channel information and energy, so that improve the energy efficiency, its energy consumption is reduced. Simulation results show that our transmission strategy can significantly improve the transmission success rate and reduce packet loss, and can adjust the channel changes to improve the reliability of data transmission.

Multi-agent deep learning for simultaneous optimization for time and energy in distributed routing system

The collaboration between wireless sensor networks and the distributed robotics has prompted the making of mobile sensor networks. However, there has been a growing enthusiasm in developing mobile sensor networks, which are the favoured family of wireless sensor networks in which autonomous movement assumes a key part in implementing its application. By introducing mobility to nodes in wireless sensor networks, the capability and flexibility of mobile sensor networks can be enhanced to support multiple mansions, and to address the previously stated issues. The reduction in costs of mobile sensor networks and their expanding capacities makes mobile sensor networks conceivable and useful. Today, many types of research are focused on the making of mobile wireless sensor networks due to their favourable advantage and applications. Allowing the sensors to be mobile will boost the utilization of mobile wireless sensor networks beyond that of static wireless sensor networks. Sensors can be mounted on, or implanted in animals to monitor their movements for examinations, but they can also be deployed in unmanned airborne vehicles for surveillance or environmental mapping. Mobile wireless sensor networks and robotics play a crucial role if it integrated with static nodes to become a Mobile Robot, which can enhance the capabilities, and enables their new applications. Mobile robots provide a means of exploring and interacting with the environment in more dynamic and decentralised ways. In addition, this new system of networked sensors and robots allowed the development of fresh solutions to classical problems such as localization and navigation beyond that. This article presents an overview of mobile sensor network issues, sensor networks in robotics and the application of robotic sensor networks.

Localization problem in mobile wireless sensor networks has drawn widely attention in recent years due to the rapid advances in mobile computing and improvements of wireless communication technologies. Indeed, mobile sensor networks become a valuable asset for many applications, since sensors can be mobile or easily tethered to mobile entities such as robots, vehicles or human. Thereby, it is crucial to support mobility without compromising the quality of applications that require wireless communications. Although, numerous research activities have successfully addressed the localization problem in static networks, few studies deal with the localization issue in mobile sensor networks. In this paper, we present a survey on existing work in this area and we address the gaps for actual deployment of mobile wireless sensor networks. Following our analysis, we propose a classification of the most important algorithms and schemes that outcome from recent literature. We discuss their basic principles, characteristics and concepts. Finally, we point out open research issues, their challenges and some future directions for localization in mobile wireless sensor networks.

Improving network lifetime with mobile wireless sensor networks

The unreliability and dynamics of mobile wireless sensor networks make it hard to perform end-to-end communications. This paper presents a novel source-initiated on-demand routing mechanism for efficient data transmission in mobile wireless sensor networks. It explores the Thorup-Zwick theory to achieve source-initiated on-demand routing with time efficiency. It is able to find out shortest routing path between source and target in a network and transfer data in linear time. The algorithm is easy to be implemented and performed in resource-constrained mobile wireless sensor networks. We also evaluate the approach by analyzing its cost in detail. It can be seen that the approach is efficient to support data transmission in mobile wireless sensor networks.

An envisioned usage of sensor networks is in surveillance systems for detecting a target or monitoring a physical phenomenon in a region. Traditionally, stationary sensor networks are deployed to carry out the sensing operations. In many applications, if the monitored region is relatively large compared to the sensing range of a node, a large number of nodes are required in the region to achieve high coverage. Using mobile nodes in such situations can be an attractive alternative. Mobility of sensor nodes has been studied in sensor networks for many purposes such as power saving, data collection, and packet delivery. However, nearly all research literature for the target detection problem has focused on stationary sensor networks. This paper investigates the problem of detecting the presence/absence of a target using mobile sensor networks. It presents an analytic method to evaluate the detection latency based on a collaborative sensing approach using nodes with uncoordinated mobility. We verify the analytic model through simulations. The analytic method provides a simple way of analyzing the tradeoff between number of nodes and detection latency in a mobile sensor network. The analysis is also used to compare the performance of mobile and stationary sensor networks with respect to these measures. Results show that if the target is present at the worst possible location in a given deployment, then detection latency of mobile sensor networks is considerably less as compared to that of stationary networks with the same number of nodes.

The aim of this paper is design and develop energy efficient MANET network in wireless networks. One of the most significant and effective protocol based on low energy consumption and number of Ad-hoc is MANET as remote directing convention source nodes forward in network simulator. Less number of nodes in the network would give low energy usage or consumption as the nodes in the network exceeds or increases that will also increase the energy consumption in the network. The designed MANET system is tried with 9, 12, 15 and 18 number of nodes in a system using network simulation-2 (NS-2). Henceforth source node needs to restart over and over which brings about low energy consumption use and use, ectiveness is less and packet space is additionally less and throughput is likewise less and more start to finish delay. Arrangement of this issue in MANET convention which is advanced as the node doesn't advance when demand arrived at their first it checked there is low energy consumption (battery lifetime) and until the node energy consumption is more noteworthy than the limit. Designed MANET examinations of the energy consumption and node energy consumption by maintaining a strategic distance from the low number of nodes in a network. By contrasting energy consumption and node it demonstrates that MANET is far superior to existing framework 802.11 protocol convention based on battery lifetime, energy consumption, throughput, and power transmission. We have performed a comparison between EEM and AODV routing protocol considering different measuring parameters.

The aim of this paper is design and develop energy efficient MANET network in wireless networks. One of the most significant and effective protocol based on low energy consumption and number of Ad-hoc is MANET as remote directing convention source nodes forward in network simulator. Less number of nodes in the network would give low energy usage or consumption as the nodes in the network exceeds or increases that will also increase the energy consumption in the network. The designed MANET system is tried with 9, 12, 15 and 18 number of nodes in a system using network simulation-2 (NS-2). Henceforth source node needs to restart over and over which brings about low energy consumption use and use, ectiveness is less and packet space is additionally less and throughput is likewise less and more start to finish delay. Arrangement of this issue in MANET convention which is advanced as the node doesn't advance when demand arrived at their first it checked there is low energy consumption (battery lifetime) and until the node energy consumption is more noteworthy than the limit. Designed MANET examinations of the energy consumption and node energy consumption by maintaining a strategic distance from the low number of nodes in a network. By contrasting energy consumption and node it demonstrates that MANET is far superior to existing framework 802.11 protocol convention based on battery lifetime, energy consumption, throughput, and power transmission. We have performed a comparison between EEM and AODV routing protocol considering different measuring parameters.

The mobile wireless sensor network is a promising technology having a wide number of applications. The sensor nodes are mobile and able to communicate with each other in an ad hoc manner. Due to mobility, it outperforms the static wireless sensor network as MWSN increases the throughput, network lifetime, and reduces energy consumption. Mobile sensor network has better ability to monitor the target area than static sensor network. However, the routing protocol in mobile environment is complex in resource constraints MWSN. So, it is required to develop an energy-efficient routing protocol to improve network performance. In this paper, a robust energy-efficient cluster-based routing protocol is proposed. The energy-rich node is selected as cluster head with minimum velocity for maximum connectivity among the cluster members. Selection of reliable forwarder improves network performance. Extensive simulation study is carried out to evaluate the performance of the proposed routing protocol with respect to delay, throughput, PDR, and total energy consumption.

The recent technological advances in the field of wireless sensor networks (WSNs) have expanded the range of WSN applications. In some of these applications, sensor nodes are mobile rather than static. Also, the recent advances in personal digital assistants (PDAs) allow the existence of multiple mobile sinks to collect the sensors data. These characteristics require the design of new routing protocols to meet the existence of mobile sensors and multiple mobile sinks while taking into consideration the limited resources for sensor nodes especially the energy. In-network aggregation is one of the important techniques used to save power consumption by aggregating the data on sensor nodes before transmitting towards the sinks and hence reduce the number of transmissions required. ABRM, as previously proposed, is an aggregation based routing protocol for mobile sensor networks (MSNs) with multiple mobile sinks. This paper proposes enhanced ABRM (E-ABRM) to improve the aggregation results and reduce the routing overhead and power consumption. E-ABRM is compared to ABRM and CCBR through mathematical analysis and simulation results. The comparisons show that E-ABRM reduces aggregation error, routing overhead, and energy consumption.

Advances in the field of sensor networking, coupled with the increased level of ubiquity of wireless Internet access has given rise to the ability to support Mobile Sensor Network scenarios. The name Mobile Sensor Network refers to a group of sensor nodes that move together, collectively sensing the environment around them as their location changes. In this paper we present our sensor-to-sink all IPv6 based Mobile Sensor Networking solution that facilitates the delivery of the sensor nodes' data to any data sink connected to the Internet by forming a dynamic routing infrastructure between clusters of these networks. Our approach has the ability to utilise any available Internet connection for transmitting this data to any globally reachable location without requiring any specific alteration to the infrastructure of the access networks, whilst also ensuring that every node in a Mobile Sensor Network remains persistently reachable whenever an external connection to the Internet is available. We provide results from our experimental testbed that highlight the overall capabilities of our approach and its suitability for supporting Mobile Sensor Networking scenarios.

An important problem in mobile ad-hoc wireless sensor networks is the localization of individual nodes, i.e., each node's awareness of its position relative to the network. In this paper, we introduce a variant of this problem (directional localization) where each node must be aware of both its position and orientation relative to the network. This variant is especially relevant for the applications in which mobile nodes in a sensor network are required to move in a collaborative manner. Using global positioning systems for localization in large scale sensor networks is not cost effective and may be impractical in enclosed spaces. On the other hand, a set of pre-existing anchors with globally known positions may not always be available. To address these issues, in this work we propose an algorithm for directional node localization based on relative motion of neighboring nodes in an ad-hoc sensor network without an infrastructure of global positioning systems (GPS), anchor points, or even mobile seeds with known locations. Through simulation studies, we demonstrate that our algorithm scales well for large numbers of nodes and provides convergent localization over time, even with errors introduced by motion actuators and distance measurements. Furthermore, based on our localization algorithm, we introduce mechanisms to preserve network formation during directed mobility in mobile sensor networks. Our simulations confirm that, in a number of realistic scenarios, our algorithm provides for a mobile sensor network that is stable over time irrespective of speed, while using only constant storage per neighbor.

Data transmission is the most critical operation for mobile sensors networks in term of energy waste. Particularly in pervasive healthcare sensors network it is paramount to preserve the quality of service also by means of energy saving policies. Communication and data transmission are among the most critical operation for such devises in term of energy waste. In this paper we present a novel approach to increase battery life-span by means of shorter transmission due to data compression. On the other hand, since this latter operation has a non-neglectable energy cost, we developed a compression efficiency estimator based on the evaluation of the absolute and relative entropy. Such algorithm provides us with a fast mean for the evaluation of data compressibility. Since mobile wireless sensor networks are prone to battery discharge-related problems, such an evaluation can be used to improve the electrical efficiency of data communication. In facts the developed technique, due to its independence from the string or file length, is extremely robust both for small and big data files, as well as to evaluate whether or not to compress data before transmission. Since the proposed solution provides a quantitative analysis of the source's entropy and the related statistics, it has been implemented as a preprocessing step before transmission. A dynamic threshold defines whether or not to invoke a compression subroutine. Such a subroutine should be expected to greatly reduce the transmission length. On the other hand a data compression algorithm should be used only when the energy gain of the reduced transmission time is presumably greater than the energy used to run the compression software. In this paper we developed an automatic evaluation system in order to optimize the data transmission in mobile sensor networks, by compressing data only when this action is presumed to be energetically efficient. We tested the proposed algorithm by using the Canterbury Corpus as well as standard pictorial data as benchmark test. The implemented system has been proven to be time-inexpensive with respect to a compression algorithm. Finally the computational complexity of the proposed approach is virtually neglectable with respect to the compression and transmission routines themselves.

MSLG-RGSO: Movement score based limited grid-mobility approach using reverse Glowworm Swarm Optimization algorithm for mobile wireless sensor networks