Dynamic Computation Offloading Scheme for Drone-Based Surveillance Systems

Kim, Bongjae; Min, Hong; Heo, Junyoung; Jung, Jinman

doi:10.3390/s18092982

Cited by 28 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are remarkable research results that are based on reinforcement learning techniques for sequential stochastic decision-making in various computing research domains. For the application of deep reinforcement learning to mobile edge computing, the research contributions in [8][9][10][11] had been discussed about the optimization for their own objective functions. Even if they considered many criteria for the offloading, there are not contributions that aim at the optimal sequential decision-making for offloading decisions, i.e., whether it has to conduct offloading (i.e., centralized computing) or not (i.e., local edge computing).…”

Section: Related Work: Reinforcement Learning For Mobile Edge Computingmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Real-Time Offloading Decision-Making for Mobile Edges: Deep Reinforcement Learning Framework and Simulation Results

et al. 2020

View full text Add to dashboard Cite

This paper proposes a novel dynamic offloading decision method which is inspired by deep reinforcement learning (DRL). In order to realize real-time communications in mobile edge computing systems, an efficient task offloading algorithm is required. When the decision of actions (offloading enabled, i.e., computing in clouds or offloading disabled, i.e., computing in local edges) is made by the proposed DRL-based dynamic algorithm in each unit time, it is required to consider real-time/seamless data transmission and energy-efficiency in mobile edge devices. Therefore, our proposed dynamic offloading decision algorithm is designed for the joint optimization of delay and energy-efficient communications based on DRL framework. According to the performance evaluation via data-intensive simulations, this paper verifies that the proposed dynamic algorithm achieves desired performance. IntroductionAccording to the fact that the 5G era has been realized based on networking technology innovation, many new computing and communications paradigms are introduced such as millimeter-wave communications, hyper-dense networks, and device-to-device proximal networking [1-3]. Among them, mobile edge computing (MEC) is one of the major technologies for realizing data/computing distribution in order to improve cellular network performance [4]. Based on the benefits of MEC technologies such as data rate improvement and quality enhancement, mobile cellular users can enjoy high quality, seamless, and real-time communication networking services.Together with the MEC technologies, many networked components are also of interest such as cloud servers and connected devices/vehicles. As the number of connected devices/vehicles increases, the amount of data transmitted to the MEC is also rapidly increasing. This obviously introduces serious network limitations such as data processing performance limits, storage capacity limits, and the battery use of terminal devices. Under the consideration of these limitations and problems, the use of cloud computing server is more efficient to deal with big data (gathered from connected vehicles/devices via MEC edges) than the local computing on terminals. On the other hand, for any cases where the data cannot be handled in the cloud servers due to delay requirements and security reasons, MEC devices should be able to handle or process the data from the connected vehicles/devices. Therefore, we can observe the trade-off between cloud computing servers and MEC servers (local edge computing servers). In summary, cloud servers have more power and centralized computing benefits comparing to MEC servers, whereas, it may have limitations when we have delay requirements and security requirements/regulations. Figure 1 shows the combined architecture of local edge computing and cloud computing. As the transmission from connected vehicles/devices (i.e., data upload and download) delay goes down, it is much more suitable for real-time processing. It enables real-time data processing and transmission using high-quality ...

show abstract

Section: Related Work: Reinforcement Learning For Mobile Edge Computingmentioning

confidence: 99%

“…In mobile edge computing research, several algorithms were proposed in order to optimize their own objectives [8][9][10][11][12]. However, none of them are considering offloading decision for determining whether it has to conduct offloading or not.…”

mentioning

confidence: 99%

Adaptive Real-Time Offloading Decision-Making for Mobile Edges: Deep Reinforcement Learning Framework and Simulation Results

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Forward secrecy safeguards from potential secret-key compromises on previous sessions. Through creating a unique session key for each session initiated by a user, a single session key compromise will not impact any data other than that shared in the session secured by that specific key [10]. Reverse Secrecy ensures that an uninvolved foe who knows an adjoining subset of gathering keys can't find the previously used group keys.…”

Section: Forward and Backward Secrecymentioning

confidence: 99%

Secure Key Agreement Protocol for Multi-Drone Communication

P*,

2020

IJRTE

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAV), or Drone communication, are developing areas of research that can be used in fields of military, hospital or agriculture. Drone communication keeps up associations among drones and a ground station with a satisfactory information rate for sustaining ongoing transmissions. The communication is imparted between one another through RF. This communication is over the air and it should be encrypted. This guarantees an attacker can't comprehend the caught data. The ongoing research areas focus on efficiently encrypting the channel to make it secure and reducing the dependency on GCS for key generation. This paper proposes a key trade protocol for secure drone to drone communication. Normally in a drone communication, the communication between the Ground Control Station(GCS) and the drones are encrypted utilizing the URANUSLink protocol. The drone to drone communication occurs through the ground station which takes a lot of communication time and resources. Additionally, if an immediate drone to drone communication is built up it is significantly decoded or sets aside the need for effective and secure key generation functions. To overcome the previously mentioned issue the proposed protocol defeats the computation and storage issues by utilizing parameters like Drone ID(DID), Mission ID(MID), Timestamp and Nonce alongside hashing capacities for the key age and communication process. The proposed protocol consists of three phases: i)Registration- the new drones are assigned with DID and MID after registering with the GCS ii)Group-Key Generation- the key is generated using hash functions and iii) Communication Establishment- the keys are exchanged and verified before the communication starts. This protocol guarantees forward secrecy, reverse secrecy and insurance from attacks like eavesdropping, spoofing, replay, and physical capture attacks. AVISPA is utilized for the security examination of the protocol.

show abstract

“…The goal is to reduce the processing time of recognition and detection. A mobility-aware computation offloading decision scheme is proposed in [ 23 ]. Based on the mobility information of the moving target object and network conditions, it will offload some computation task that is related to the recognizing and tracking of a moving object to a remote control center.…”

Section: Related Workmentioning

confidence: 99%

A Design and Simulation of the Opportunistic Computation Offloading with Learning-Based Prediction for Unmanned Aerial Vehicle (UAV) Clustering Networks

Valentino

Jung

2018

Sensors

View full text Add to dashboard Cite

Drones have recently become extremely popular, especially in military and civilian applications. Examples of drone utilization include reconnaissance, surveillance, and packet delivery. As time has passed, drones’ tasks have become larger and more complex. As a result, swarms or clusters of drones are preferred, because they offer more coverage, flexibility, and reliability. However, drone systems have limited computing power and energy resources, which means that sometimes it is difficult for drones to finish their tasks on schedule. A solution to this is required so that drone clusters can complete their work faster. One possible solution is an offloading scheme between drone clusters. In this study, we propose an opportunistic computational offloading system, which allows for a drone cluster with a high intensity task to borrow computing resources opportunistically from other nearby drone clusters. We design an artificial neural network-based response time prediction module for deciding whether it is faster to finish tasks by offloading them to other drone clusters. The offloading scheme is conducted only if the predicted offloading response time is smaller than the local computing time. Through simulation results, we show that our proposed scheme can decrease the response time of drone clusters through an opportunistic offloading process.

show abstract

Dynamic Computation Offloading Scheme for Drone-Based Surveillance Systems

Cited by 28 publications

References 13 publications

Adaptive Real-Time Offloading Decision-Making for Mobile Edges: Deep Reinforcement Learning Framework and Simulation Results

Adaptive Real-Time Offloading Decision-Making for Mobile Edges: Deep Reinforcement Learning Framework and Simulation Results

Secure Key Agreement Protocol for Multi-Drone Communication

A Design and Simulation of the Opportunistic Computation Offloading with Learning-Based Prediction for Unmanned Aerial Vehicle (UAV) Clustering Networks

Contact Info

Product

Resources

About