Load Balancing Control Research Articles

Load Balancing in Distributed Cloud Computing: A Reinforcement Learning Algorithms in Heterogeneous Environment

Balancing load in cloud based is an important aspect that plays a vital role in order to achieve sharing of load between different types of resources such as virtual machines that lay on servers, storage in the form of hard drives and servers. Reinforcement learning approaches can be adopted with cloud computing to achieve quality of service factors such as minimized cost and response time, increased throughput, fault tolerance and utilization of all available resources in the network, thus increasing system performance. Reinforcement Learning based approaches result in making effective resource utilization by selecting the best suitable processor for task execution with minimum makespan. Since in the earlier related work done on sharing of load, there are limited reinforcement learning based approaches. However this paper, focuses on the importance of RL based approaches for achieving balanced load in the area of distributed cloud computing. A Reinforcement Learning framework is proposed and implemented for execution of tasks in heterogeneous environments, particularly, Least Load Balancing (LLB) and Booster Reinforcement Controller (BRC) Load Balancing. With the help of reinforcement learning approaches an optimal result is achieved for load sharing and task allocation. In this RL based framework processor workload is taken as an input. In this paper, the results of proposed RL based approaches have been evaluated for cost and makespan and are compared with existing load balancing techniques for task execution and resource utilization..

Frequency reserves and inertia in the transition to future electricity systems

AbstractThe transition towards an electricity system that is dominated by asynchronous and non-dispatchable generators, such as wind and solar power, entails challenges related to balancing the load and, thereby, keeping the grid frequency stable. Many technologies can contribute to load balancing and frequency control. This study investigates the interactions between electricity generation and frequency control in terms of investments and operation, using cost-minimizing, linear optimization modeling. The model is applied in three different geographic cases and for four future time-points, starting off with the already existing transmission and generation capacities, so as to yield insights into different systems and different stages along the energy transition. The results show that frequency control constraints in the optimization model have a weak impact on the system composition and cost, and that batteries are important for minimizing the impact. Furthermore, inertia requirements without a reserve demand show no impact on the cost or system composition. When allowing for vehicle-to-grid from battery electric vehicles, a large proportion of stationary grid battery investments is displaced, and the impact on system cost from adding frequency control constraints is removed.

Load Balancing Control Algorithm of Internet of Things Link Based on Non-Parametric Regression Model

In order to solve the problems of poor channel balance control ability and unable to effectively reduce the output bit error rate in the traditional Internet of things link load balance control methods, a new Internet of things (IoT) link load balance control algorithm based on non-parametric regression model is proposed in this paper. The transmission model of IoT link channel is constructed, and the sparse random cluster analysis method is used to extract the load characteristics of IoT link. According to the load feature extraction results, through the estimated regression function of known data features, a non-parametric regression model is constructed, and the fuzzy cyclic iterative control is used to realize the load balancing control of the Internet of things link. The experimental results show that this method has strong channel balance control ability, low output bit error rate, the maximum average link utilisation can reach 1, and the maximum output bit error rate is only 102, which improves the stability of the Internet of things.

LBABC: Distributed controller load balancing using artificial bee colony optimization in an SDN

LBABC: Distributed controller load balancing using artificial bee colony optimization in an SDN

A Novel Security Method for Exact Average Consensus

Consensus is a fundamental problem for multi-agent systems, and achieving average consensus is essential for many applications, such as load balancing and cooperative control, where all agents must reach an agreement through a communication network. However, conventional approaches require agents to disclose information to their neighbors, which is often undesirable. This paper presents a novel security method for achieving exact average consensus in a distributed manner using the Paillier cryptosystem without the involvement of a third party. To protect the privacy of an agent, we replace the agent's initial state and one of its neighbor's initial state with virtual values, which are constructed based on the Pailler cryptosystem, ensuring that attackers can only infer the virtual initial values. We rigorously prove that the privacy of an agent can be guaranteed even when all of its neighbors are untrusted.

An SDN-Based Framework for Load Balancing and Flight Control in UAV Networks

Unmanned aerial vehicles (UAVs) are gaining tremendous attention due to their flying nature. To complete the task efficiently, multi-UAV systems are a good choice as compared to a single UAV system. However, multi-UAV systems introduce issues, such as high dynamics, limited battery, and frequent changes in topology. Software control is required to solve these issues. Thus, software-defined networking (SDN) is an excellent candidate to separate control logic from forwarding elements and provide high-level programming abstractions. However, due to architectural constraints, applying SDN introduces some new challenges, including uneven load on multiple links between source and destination. This irregular load also affects UAVs’ battery consumption, necessitating an adequate solution to meet these challenges fully. This article proposes an SDN-based framework for UAV elements that monitors frequent changes in the network topology. Based on this monitoring, an algorithm is designed, which distributes traffic load evenly on different links of multi-UAV systems. UAV networks have limited resources; therefore, battery limitations are also considered, and traffic is shifted to a path where elements have more battery. Moreover, a flight control mechanism is proposed to avoid collisions due to the high dynamics of UAVs. Extensive simulation results show that the traffic load is distributed evenly on multiple links connecting different systems with less battery consumption.

A Review on Emerging Communication and Computational Technologies for Increased Use of Plug-In Electric Vehicles

The electric vehicle (EV) industry is quickly growing in the present scenario, and will have more demand in the future. A sharp increase in the sales of EVs by 160% in 2021 represents 26% of new sales in the worldwide automotive market. EVs are deemed to be the transportation of the future, as they offer significant cost savings and reduce carbon emissions. However, their interactions with the power grid, charging stations, and households require new communication and control techniques. EVs show unprecedented behavior during vehicle battery charging, and sending the charge from the vehicle’s battery back to the grid via a charging station during peak hours has an impact on the grid operation. Balancing the load during peak hours, i.e., managing the energy between the grid and vehicle, requires efficient communication protocols, standards, and computational technologies that are essential for improving the performance, efficiency, and security of vehicle-to-vehicle, vehicle-to-grid (V2G), and grid-to-vehicle (G2V) communication. Machine learning and deep learning technologies are being used to manage EV-charging station interactions, estimate the charging behavior, and to use EVs in the load balancing and stability control of smart grids. Internet of Things (IoT) technology can be used for managing EV charging stations and monitoring EV batteries. Recently, much work has been presented in the EV communication and control domain. In order to categorize these efforts in a meaningful manner and highlight their contributions to advancing EV migration, a thorough survey is required. This paper presents existing literature on emerging protocols, standards, communication technologies, and computational technologies for EVs. Frameworks, standards, architectures, and protocols proposed by various authors are discussed in the paper to serve the need of various researchers for implementing the applications in the EV domain. Security plays a vital role in EV authentication and billing activities. Hackers may exploit the hardware, such as sensors and other electronic systems and software of the EV, for various malicious activities. Various authors proposed standards and protocols for mitigating cyber-attacks on security aspects in the complex EV ecosystem.

RBAC-LBRM: An RBAC-Based Load Balancing Assisted Efficient Resource Management Framework for IoT-Edge-Fog Network

The inefficient handling of Internet of Things (IoT) network traffic may result in load-imbalance and unauthorized access, causing network performance degradation. The performance can be improved by off-loading some of the tasks to the network edge and fog layers. The existing works have discussed the issues of load balancing and access control in IoT using edge and fog environments; however, the design of an efficient resource management framework for an IoT-edge-fog environment is still under development. This work presents a role-based access control (RBAC)-based load balancing-assisted efficient resource management framework for IoT-edge-fog network named RBAC-LBRM. The overall average improvements of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">29.85, 16.82, 13.63, and 16.55%</i> have been achieved by RBAC-LBRM over other approaches w.r.t. CPU usage, memory usage, delay, and jitter metrics, respectively.

DSMLB: Dynamic switch-migration based load balancing for software-defined IoT network

The deployment of multiple controllers in Software-Defined Internet of Things (SD-IoT) networks enhance the distributed control plane scalability and reliability. With the rapid advancement of IoT, millions of smart devices generate enormous amounts of IoT traffic, causing significant challenges for the network to acquire the better Quality-of-Service (QoS) to the user. The control plane load management is crucial due to the dynamic nature of IoT networks and the heterogeneity of IoT devices in terms of flow generation rate. The load distribution among SD-IoT controllers relies on their available capacity to ensure optimal load balancing performance. The dynamic switch migration method was proposed in prior findings to handle load balancing distribution among controllers. However, the migration efficiency of conventional approaches is limited due to inefficient load balancing performance of the control plane after the migration of switch, leading to additional migration overhead on the network. Taking this into account, we propose a dynamic switch migration-based load balancing approach (DSMLB) to prevent control plane overhead and distribute traffic efficiently while considering heterogeneous IoT devices. The proposed DSMLB scheme measures the real-time load ratio to the mean load ratio of each controller by describing various load metrics and selecting the target controller by optimizing the migration efficiency with residual controller resource utilization. When choosing the candidate switches from the associated overloaded controller, DSMLB considers the migration efficiency and load balancing degree simultaneously for the fastest load reduction and enhances the load balancing performance. The simulation results show that DSMLB outperforms conventional approaches for efficient load balancing performance on a distributed control plane by reducing the controller response time up to 38.6% and migration cost about 45.5% on average. Moreover, DSMLB also improves controller load balancing rate and reduces communication overhead.

Packet-in request redirection: A load-balancing mechanism for minimizing control plane response time in SDNs

A distributed control plane is more scalable and robust in software defined networking. This paper focuses on controller load balancing using packet-in request redirection, that is, given the instantaneous state of the system, determining whether to redirect packet-in requests for each switch, such that the overall control plane response time (CPRT) is minimized. To address the above problem, we propose a framework based on Lyapunov optimization. First, we use the drift-plus-penalty algorithm to combine CPRT minimization problem with controller capacity constraints, and further derive a non-linear program, whose optimal solution is obtained with brute force using standard linearization techniques. Second, we present a greedy strategy to efficiently obtain a solution with a bounded approximation ratio. Third, we reformulate the program as a problem of maximizing a non-monotone submodular function subject to matroid constraints. We implement a controller prototype for packet-in request redirection, and conduct trace-driven simulations to validate our theoretical results. The results show that our algorithms can reduce the average CPRT by 81.6% compared to static assignment, and achieve a 3× improvement in maximum controller capacity violation ratio.

CASM: A Cost-Aware Switch Migration Strategy for Elastic Optical Inter-Datacenter Networks

In inter-datacenter elastic optical networks, multi-controller deployment is adopted to improve the stability and scalability of the control plane. As the network scale increases, the traditional multi-controller deployment scheme ignores the dynamic characteristics of traffic, resulting in unbalanced load among multiple controllers. In response to this problem, the existing switch migration mechanism is proposed to achieve balanced distribution of control loads. However, most of the existing research work does not consider the additional cost of switch migration, and the load balancing performance of the controller is not significantly improved after switch migration. In this paper, we propose a cost-aware switch migration (CASM) strategy for controller load balancing. The proposed CASM strategy first measures the controller load through multiple performance indicators that affect the controller load, and then judges whether the controller is overloaded or underloaded based on the controller’s response time to the request message, thereby improving the load balancing performance of the controller. Additionally, when selecting the switch to be migrated, the CASM selects the optimal switch for migration based on minimizing the migration cost, thereby reducing the cost of switch migration. The performance evaluation shows that CASM significantly improves load balancing performance of controllers and reduces the migration cost compared to existing solutions.

Efficient Load Balancing for Cloud Computing by Using Content Analysis

Nowadays, computer networks have grown rapidly due to the demand for information technology management and facilitation of greater functionality. The service provided based on a single machine cannot accommodate large databases. Therefore, single servers must be combined for server group services. The problem in grouping server service is that it is very hard to manage many devices which have different hardware. Cloud computing is an extensive scalable computing infrastructure that shares existing resources. It is a popular option for people and businesses for a number of reasons including cost savings and security. This paper aimed to propose an efficient technique of load balance control by using HA Proxy in cloud computing with the objective of receiving and distributing the workload to the computer server to share the processing resources. The proposed technique applied round-robin scheduling for an efficient resource management of the cloud storage systems that focused on an effective workload balancing and a dynamic replication strategy. The evaluation approach was based on the benchmark data from requests per second and failed requests. The results showed that the proposed technique could improve performance of load balancing by 1,000 request /6.31 sec in cloud computing and generate fewer false alarms

RETRACTED ARTICLE: An adaptive traffic routing approach toward load balancing and congestion control in Cloud–MANET ad hoc networks

RETRACTED ARTICLE: An adaptive traffic routing approach toward load balancing and congestion control in Cloud–MANET ad hoc networks

The Improved Nonparametric Regression Model for the IoT Link Load Balancing Control Algorithm

In order to improve the load balance control effect of the Internet of Things link, this paper combines the nonparametric regression model to improve the load balancing algorithm of the Internet of Things link. Moreover, this paper proposes a load balancing research strategy based on data plane data flow, which is aimed at improving the load balancing problem of data flow in the link. The data center network uses a multilayer fat tree topology to store information in the flow table corresponding to the switch for data flow processing and forwarding operations. In addition, this paper constructs a load balancing model for intelligent Internet of Things link and verifies the model in this paper through experimental research. The research results show that the load balancing control algorithm for Internet of Things link based on the nonparametric regression model proposed in this paper can effectively improve the internal scheduling of the Internet of Things link system and promote the load balancing effect.

Intelligent Network Traffic Control Based on Deep Reinforcement Learning

This paper studies the problems of load balancing and flow control in data center network, and analyzes several common flow control schemes in data center intelligent network and their existing problems. On this basis, the network traffic control problem is modeled with the goal of deep reinforcement learning strategy optimization, and an intelligent network traffic control method based on deep reinforcement learning is proposed. At the same time, for the flow control order problem in deep reinforcement learning algorithm, a flow scheduling priority algorithm is proposed innovatively. According to the decision output, the corresponding flow control and control are carried out, so as to realize the load balance of the network. Finally, experiments show, the network traffic bandwidth loss rate of the proposed intelligent network traffic control method is low. Under the condition of random 60 traffic density, the average bisection bandwidth obtained by the proposed intelligent network traffic control method is 4.0mbps and the control error rate is 2.25%. The intelligent network traffic control method based on deep reinforcement learning has high practicability in the practical application process, and fully meets the research requirements.

Enabling Robust DRL-Driven Networking Systems via Teacher-Student Learning

The past few years have witnessed a surge of interest towards deep reinforcement learning (DRL) in computer networks. With extraordinary ability of feature extraction, DRL has the potential to re-engineer the fundamental resource allocation problems in networking without relying on pre-programmed models or assumptions about dynamic environments. However, such black-box systems suffer from poor robustness, showing high performance variance and poor tail performance. In this work, we propose a unified Teacher-Student learning framework that harnesses rich domain knowledge to improve robustness. The domain-specific algorithms, less performant but more trustable than DRL, play the role of teachers providing advice at critical states; the student neural network is steered to maximize the expected reward as usual and mimic the teacher’s advice meanwhile. The Teacher-Student method comprises of three modules where the confidence check module locates wrong decisions and risky decisions, the reward shaping module designs a new updating function to stimulate the learning of student network, and the prioritized experience replay module to effectively utilize the advised actions. We further implement our Teacher-Student framework in existing video streaming (Pensieve), load balancing (DeepLB), and TCP congestion control (Aurora). Experimental results manifest that the proposed approach reduces the performance standard deviation of DeepLB by 37%; it improves the 90th, 95th, and 99th tail performance of Pensieve by 7.6%, 8.8%, and 10.7% respectively; and it accelerates the growth rate of Aurora by 2x at the initial stage, and achieves a more stable performance in dynamic environments.

Load balance control method of multi electromechanical transmission system based on dynamic programming

Controlling the load balance of multi electromechanical transmission system is the core and difficulty of metro vehicles. In order to effectively control the load of multi electromechanical transmission system and ensure the load balance of multi electromechanical transmission system. A load balancing control method of multi electromechanical transmission system based on dynamic programming is proposed. By designing the structure of the transmission system filter, the low DC resonant frequency of the inverter is maintained and the grid harmonics with higher order effect are suppressed. The rotor field oriented correction method based on dynamic programming can improve the torque performance of traction electric drive system, control the DC side active damping oscillation, and realize the load balance control of multi electromechanical drive system. The simulation results show that the proposed method avoids the wrong rise of multi electromechanical voltage and the saturation of regulator output caused by inaccurate magnetic field orientation, can effectively control the load of multi electromechanical transmission system, ensure the load balance of multi electromechanical transmission system, and provide an effective reference for the load balance control of multi electromechanical transmission system.

Multi-Objective Control Plane Dimensioning in Hybrid SDN/Legacy Networks

Software defined networking (SDN) is gaining the confidence of network operators, who are increasingly motivated to introduce it in their networks. However, since SDN is based on centralized control plane (decoupled from the data plane), it is incompatible with distributed control plane of legacy networks. As adopting SDN by complete overhaul of existing legacy networks is infeasible, several solutions propose to incrementally adopt SDN in legacy networks, resulting in hybrid SDN/legacy networks during the transition phase. While strategies to effectively introduce SDN switches in legacy networks have received significant attention in the literature, the same is not true for the associated SDN controller placement in hybrid SDN networks. In this paper, we introduce and formulate the multi-objective control plane dimensioning problem in hybrid SDN/legacy networks, considering network resilience, flow-setup latency and controller load balancing as objectives. We propose optimization models for both the single-objective as well as the multi-objective controller placements. We model both controller processing latency (based on queueing theory) and inter-controller network state synchronization latency (based on Steiner trees) without compromising linearity of the optimization formulations. A genetic algorithm-based heuristic is presented to efficiently deduce the approximate Pareto frontier for our problem. Extensive simulations over a large number of real networks establish the effectiveness of our approach in terms of several single-objective and multi-objective performance metrics.

Load Balancing Algorithm on the Immense Scale of Internet of Things in SDN for Smart Cities

Since the worldwide Internet of Things (IoT) in smart cities is becoming increasingly popular among consumers and the business community, network traffic management is a crucial issue for optimizing the IoT ’s performance in smart cities. Multiple controllers on a immense scale implement in Software Defined Networks (SDN) in integration with Internet of Things (IoT) as an emerging paradigm enhances the scalability, security, privacy, and flexibility of the centralized control plane for smart city applications. The distributed multiple controller implementation model in SDN-IoT cannot conform to the dramatic developments in network traffic which results in a load disparity between controllers, leading to higher packet drop rate, high response time, and other problems with network performance deterioration. This paper lays the foundation on the multiple distributed controller load balancing (MDCLB) algorithm on an immense-scale SDN-IoT for smart cities. A smart city is a residential street that uses information and communication technology (ICT) and the Internet of Things (IoT) to improve its citizens’ quality of living. Researchers then propose the algorithm on the unbalancing of the load using the multiple controllers based on the parameter CPU Utilization in centralized control plane. The experimental results analysis is performed on the emulator named as mininet and validated the results in ryu controller over dynamic load balancing based on Nash bargaining, efficient switch migration load balancing algorithm, efficiency aware load balancing algorithm, and proposed algorithm (MDCLB) algorithm are executed and analyzed based on the parameter CPU Utilization which ensures that the Utilization of CPU with load balancing is 20% better than the Utilization of CPU without load balancing.

Scalable Traffic Control Using Programmable Data Planes in a Space Information Network

The past several decades have witnessed wide deployment of space information networks (SINs). More than 8000 satellites have been launched into Earth's orbit recently. Meanwhile, the space communications requirements have grown by a factor of 10 in the last decade. The sharply increasing traffic volume puts tremendous pressure on the network traffic control in SINs. Current end-host-based schemes have to collect a massive amount of data (e.g., explicit congestion notification) to respond to one network event (e.g., topology change, network congestion), which is unacceptable in SINs due to the large end-to-end delay. Recently, with the emergence of programmable network devices, it has become possible to perform flexible control strategies as the traffic is flowing through the network (i.e., in-network traffic control). By implementing the control directly inside the network, the in-network schemes are more effective at scale and more responsive to network dynamics. Therefore, in this article, we design an in-network traffic control powered SIN architecture to enhance the network performance. In addition, we present two use cases, in-network load balance and in-network congestion control, to demonstrate the feasibility of our architecture. Extensive simulations are performed to evaluate our proposed schemes.