Load Distribution Algorithm Research Articles

Energy characteristics of multi-chiller load distribution algorithms in a large office building

This study evaluates the energy efficiency of multi-chiller systems in large office buildings, focusing on their optimization across various climate zones as defined by ASHRAE. Using EnergyPlus for simulations, the research examines five different load distribution algorithms in multi-chiller systems that range from one to ten chillers, aiming to understand their effectiveness in 15 distinct climate zones. The primary objectives of the study include identifying the energy efficiency of multi-chiller systems in each climate zone, determining the appropriate number of chillers for each zone, and evaluating the performance of the load distribution algorithms. Based on the U.S. Department of Energy’s commercial building model, the results suggest that multi-chiller systems can significantly reduce cooling energy consumption in various climates. Among the algorithms evaluated, the Sequential Uniform Part Load Ratio (SUPLR) algorithm demonstrates notable efficiency, especially in the 4A climate zone (Baltimore), where it achieves substantial energy savings. Applying the SUPLR algorithm in a multi-chiller setup with four chillers in this zone leads to an estimated 24.5 % reduction in energy usage, equivalent to 183 MW annually. The research indicates that a range of 3 to 5 chillers is typically optimal for most climate zones. In-depth analysis in the 4A climate zone highlights the importance of minimizing operation hours at low Part Load Ratios (PLR) to ensure that chillers operate at a high Coefficient of Performance (COP). This strategy underscores the potential of well-designed multi-chiller systems to reduce cooling energy demand, particularly in climates with transitional seasons. This study provides an overview of the energy-saving potential of multi-chiller systems, applicable across a variety of climatic scenarios.

Priority based energy and load aware routing algorithms for SDN enabled data center network

Nowadays, to accommodate the swift expansion of cloud computing, big data, and other emerging technologies, integrating data center networks and SDN (Software Defined Network) is suggested, which also improves the network management’s convenience and flexibility. As network devices in these data centers continue to increase at a high rate, efficient route management to handle these devices’ vast amounts of data has emerged as a significant concern. This work suggests a novel admission and routing scheme considering the importance or priorities of the network flows, path energy, and routing path load. Using the SDN paradigm in DCN (Data Center Network), we first develop a Mixed Integer Linear Programming (MILP) formulation by jointly considering flow priority, path energy, and path load. The MILP formulation can maximize the number of flows as well as minimize the energy consumption and load variance in the network, or it can make a trade-off among all three. However, due to the potentially long running time, later, we introduce two greedy methods, Priority Based Energy Minimization Algorithm (PEMA) and Priority Based Evenly Load Distribution Algorithm (PEDL), where PEMA aims to maximize the flow with less energy, and PEDL focuses on maximizing the flow with reduced load variation. Finally, the developed routing strategies are implemented, and the simulation results demonstrate the out-performance of our work compared to the existing works in terms of successful flow ratio, energy savings, and load balancing.

DCSP: A delay and cost-aware service placement and load distribution algorithm for IoT-based fog networks

The service placement problem in a fog-cloud pertains to the intricate task of ascertaining the optimal placement locations for diverse service replicas that constitute an Internet of Things (IoT) application within a distributed computing architecture. Nonetheless, due to the heterogeneous nature of fog nodes and cloud data centers, the constantly evolving nature of IoT applications, the pressing demand for real-time data processing with minimal latency, and the imperative of cost optimization, service placement remains an arduous and intricate challenge. Heuristic algorithms are widely employed to derive near-optimal solutions. The present study introduces a novel heuristic approach to service placement and load distribution in fog-cloud environments called Delay and Cost-aware Service Placement (DCSP). This approach takes into account both delay and cost and thereby enables the optimal utilization of resources, delay, and cost for delay-sensitive services. DCSP features continual adjustment of the number of service replicas based on workload and resource availability, ensuring efficient usage of fog and cloud computing resources and optimal delay for each request. The results of simulation experiments that compare various algorithms demonstrate the superiority of DCSP, which outperforms other methods in cost, average delay, and resource utilization. The experimental results not only illustrate the exceptional superiority of our method over MOHGA, MVC, and the Local method in terms of delay and utilization but also demonstrate our efforts to maintain cost at a comparable level. Our method surpasses all of them in utilization, achieving remarkable improvements ranging from 7.4 % to 49.7 %. Furthermore, it outperforms them in terms of delay, with significant enhancements ranging from 2.1 % to 19.3 %.

Parallel mutation testing for large scale systems

Mutation testing is a valuable technique for measuring the quality of test suites in terms of detecting faults. However, one of its main drawbacks is its high computational cost. For this purpose, several approaches have been recently proposed to speed-up the mutation testing process by exploiting computational resources in distributed systems. However, bottlenecks have been detected when those techniques are applied in large-scale systems. This work improves the performance of mutation testing using large-scale systems by proposing a new load distribution algorithm, and parallelising different steps of the process. To demonstrate the benefits of our approach, we report on a thorough empirical evaluation, which analyses and compares our proposal with existing solutions executed in large-scale systems. The results show that our proposal outperforms the state-of-the-art distribution algorithms up to 35% in three different scenarios, reaching a reduction of the execution time of—at best—up to 99.66%.

The study of energy filtering management process for microgrid based on the dynamic response model of vanadium redox flow battery

For the efficient application of vanadium redox flow battery (VRB) in microgrid containing the clean renewable energy and advanced coal-fired power system such as the supercritical carbon dioxide (S-CO2) Brayton cycle power plant, a feasible energy filtering optimization process is proposed in this paper. A coupled dynamic response model of VRB and an optimized load distribution algorithm are covered in the process. First, the Ustack-Ibattery-SOC curves are fitted based on the coupled calculation model of VRB. The equivalent resistance of the simplified equivalent circuit model is further calculated. The dynamic response model is refined for the fast calculation of real-time efficiencies. Second, a basic operation scheme and an optimized operation scheme based on the moving average filtering method are selected as the load distribution algorithms. An energy filtering optimization management process that includes a configuration optimization design part and a load distribution part is further constructed. Finally, a case application is carried out to verify the feasibility of the proposed energy management process. The relevant results are presented as follows. First, the combination of the experimental data and the fitted curves can be used to calculate the equivalent resistance of the dynamic response model. The maximum Ustack of 86.14 V is obtained at the SOC of 0.99 and Ibattery of 10A when charging. Second, when applying the optimized operation scheme, the time average efficiency of VRB is operating at an efficient level of 82.75%. The change frequency of load command for each equipment and its dynamic response characteristic can be well matched. Finally, compared to the case where the basic operation scheme is selected in the experimental system, the time average efficiency of VRB is increased from 69.50% to 82.13%., the time average efficiency of S-CO2 power plant is increased from 39.79% to 40.02%. The application of energy filtering optimization management process for the actual microgrid is feasible. The study can provide the operation scheme and case application for VRB energy storage system in the actual microgrid.

A tribo-dynamic based pitting evolution model of planetary gear sets: A topographical updating approach

Considering the coupling effects of the tribology and dynamics, a dynamic pitting evolution model of planetary gear sets is developed. A fast dynamic load distribution algorithm is proposed to obtain the dynamic contact load considering complex pitting topography. Then the mixed elastohydrodynamic lubrication theory is adopted to acquire the tribological parameters. Combing the dynamic load and Zaretsky's fatigue criterion, a contact fatigue model is developed to predict the pitting topography during the degradation process. An iterative algorithm framework is developed to realize the topographical updating in the dynamic pitting prediction. The effectiveness of the proposed model is demonstrated using two experimental examples. The probability distribution of the pitting location is investigated using the proposed model. It is revealed that the gamma distribution is more consistent with the pitting distribution along the involute direction than the normal distribution. Owing to the “competition mechanism” of the pitting and surface wear, the pitting center approaches the pitch point with the increase of the surface roughness. The proposed model is capable of evaluating tribo-dynamic behaviors of planetary gear sets during the life-cycle degradation process of pitting failure. Moreover, it can provide theoretical guidance for the pitting fault mechanism and model-based fault diagnosis.

An Improved Differential Evolution Whale Algorithm for Economic Load Distribution

An improved optimization algorithm combining the differential evolution algorithm and the whale algorithm is proposed for the problem of not being able to get rid of the local optimum in the economic load distribution algorithm. The algorithm adopts a nonlinear convergence strategy, a crossover strategy of differential evolution and the introduction of an elimination mechanism, which balances the global search and local exploitation ability of the algorithm and improves the accuracy of the solved optimal solution. The 13-unit and 40-unit systems are selected for economic load distribution calculation, and the experimental results show that the proposed improved algorithm is superior in distributing the economic load of the power system and can effectively reduce the economic cost.

Kinematics, dynamics, and load distribution analysis of a 4-PPPS redundantly actuated parallel manipulator

In this paper, the kinematics, dynamics, and load distribution algorithm of a 4-PPPS redundantly actuated parallel manipulator are investigated with the screw theory. For the forward kinematic analysis, we propose the major joint set, a minimum set for determining the kinematic and dynamic state of the mobile platform with six specially selected prismatic joints. The reciprocity of screws is applied for simplifying the derivation of the Jacobian matrix. The driving forces of the active joints are solved with the principle of virtual work for the non-redundant and the fully redundant actuation mode with the major joint set. For the fully redundant actuation mode, to avoid joint overload resulted from the conventional least-norm load distribution solution, to smooth the force transition, and to increase the positioning accuracy of the manipulator, a load distribution algorithm based on Lagrange optimization is proposed. These effects are achieved by means including reducing the deformations of the z-axis links and considering the sensitivity and elasticity of major joints. At last, the effectiveness of the modeling method and the proposed algorithm is verified with a case study.

Effects of Differentiated 5G Services on Computational and Radio Resource Allocation Performance

5G is poised to support new emerging service types that help in the realization of futuristic applications. These services include enhanced Mobile BroadBand (eMBB), ultra-Reliable Low Latency Communication (uRLLC), and massive Machine-Type Communication (mMTC). Even though the new services offer a variety of new use-cases to be implemented, it is still a challenge to guarantee the Quality of Service (QoS) they demand. Moreover, as considerable amount of computational resources are introduced in the evolved Radio Access Network (RAN) following the Mobile Edge Computing (MEC) concept, computational resource allocation optimization along with radio allocation becomes essential. In this paper, we examine the characteristics of the new 5G services and propose a joint computational and radio resource allocation framework that analyzes the QoS performance of each 5G service individually. The framework is developed based on per-service load characterization. Therefore, a computational load distribution algorithm is developed that balances the workloads subject to user association constraint. Further, radio resource allocation performs load-based eMBB-mMTC slicing and uRLLC puncturing. The simulation results show that the proposed solution reduces the packet loss ratio by up to 15% and increases the user data rate by up to 7% for 4G-like services. Furthermore, the effect of resource granularity in radio allocation has been identified as crucial factor for effective allocation of services with small data loads. Finally, the problem of small granularity has been solved by adapting the allocation interval.

A Scalable Virtualized Server Cluster Providing Sensor Data Storage and Web Services

With the rapid development of the Internet of Things (IoT) technology, diversified applications deploy extensive sensors to monitor objects, such as PM2.5 air quality monitoring. The sensors transmit data to the server periodically and continuously. However, a single server cannot provide efficient services for the ever-growing IoT devices and the data they generate. This study bases on the concept of symmetry of architecture and quantities in system design and explores the load balancing issue to improve performance. This study uses the Linux Virtual Server (LVS) and virtualization technology to deploy a virtual machine (VM) cluster. It consists of a front-end server, also a load balancer, to dispatch requests, and several back-end servers to provide services. These receive data from sensors and provide Web services for browsing real-time sensor data. The Hadoop Distributed File System (HDFS) and HBase are used to store the massive amount of received sensor data. Because load-balancing is critical for resource utilization, this study also proposes a new load distribution algorithm for VM-based server clusters that simultaneously provide multiple services, such as sensor services and Web service. It considers the aggregate load of all back-end servers on the same physical server that provides multiple services. It also considers the difference between physical machines and VMs. Algorithms such as those for LVS, which do not consider these factors, can cause load imbalance between physical servers. The experimental results demonstrate that the proposed system is fault tolerant, highly scalable, and offers high availability and high performance.

Балансировка нагрузки в облачных вычислениях

Cloud computing is a new Internet technology that focuses on commercial computing. Load balancing helps improve the performance of a centralized server. This paper analyzes various algorithms using the tool of analysis, namely, cloud-based Analytics. A comparison of load distribution algorithms is also made.

Analysis of Motion and Internal Loading in Redundantly Actuated Human Eyeball

The 3-DOF rotational motion of the human eyeball is created by using six extraocular muscles. For the force-redundant system of the human eyeball, a load distribution algorithm is proposed to investigate the dynamics and intrinsic load distribution of the eyeball. Initially, the role of each extraocular muscle is explained by describing the anatomy of the human eye. Furthermore, activity of each muscle group is analyzed to create six primitive motions of the human eye. Moreover, the dynamic model of the human eye is developed to simulate the human eye motion. Finally, a load distribution algorithm is newly developed and it is found that asymmetric arrangement of six extraocular muscles with respect to the eye axis enables the human eye not only to create the motion using minimum number of extraocular muscles, but also to ensure stability in other directions by providing antagonistic internal loading. Surprisingly, it is also found that all six primitive motions of the eyeball require three independent muscles, which is different from clinical observation so far.

Research on Load Distribution Algorithm of Central Heating Network

Hydraulic and thermal imbalance is very common in central heating system, resulting in energy loss and poor heating experience of heat users. In order to solve the problem of hydrothermal imbalance, a control method based on Modeling and Simulation of central heating system and PSO particle swarm optimization algorithm is proposed. Firstly, the mathematical modeling and analysis of the hydraulic and thermal conditions of the central heating system are carried out, and the actual operation of the system is simulated by using MATLAB/Simulink to build and simulate the model of the central heating system. Then, the valves of each heat exchanger station are analyzed by using particle swarm optimization (PSO) with the variance of return water temperature as the control objective, and the appropriate valve openings are calculated iteratively, so as to solve the problem of hydro-thermal imbalance in the central heating system. The traditional PID control method is used to carry out comparative experiments. The experiment shows that the particle swarm optimization method performs better than the PID control method. The return water temperature of the heat exchanger station is similar, and it can meet the heating demand better.

Joint QoS-control and handover optimization in backhaul aware SDN-based LTE networks

Future cellular networks will be dense and require key traffic management technologies for fine-grained network control. The problem gets more complicated in the presence of different network segments with bottleneck links limiting the desired quality of service (QoS) delivery to the last mile user. In this work, we first design a framework for software-defined cellular networks (SDCN) and then propose new mechanisms for management of QoS and non-QoS users traffic considering both access and backhaul networks, jointly. The overall SDN-LTE system and related approaches are developed and tested using network simulator (ns-3) in different network environments. Especially, when the users are non-uniformly distributed, the results shows that compared to other approaches, the proposed load distribution algorithm enables at least 6\% and 23\% increase in the average QoS user downlink (DL) throughput for all network users and 40\%-ile edge users, respectively. Also, the proposed system efficiently achieves desired QoS and handles the network congestion without incurring significant overhead.

Способ согласования нагрузок электроприводов горизонтальных валков клети толстолистового прокатного стана

This paper overviews recent advancements in research into the emergence of frontal upward bends; it also covers papers on the distribution of load between the electric drives of upper and lower rolls in horizontal platemill stands. The bulk of research lacks appropriate emphasis on the alignment of these systems. The paper dwells structuring a speed regulator for Mill 5000, which is a platemill; the regulator runs load distribution and frontal upward bending algorithms. The paper substantiates the need to research their parameters for the purpose of better alignment. It presents oscillographs of upper- and lower-roll torques that prove the load is non-uniform in any roughing pass. The paper also analyzes the oscillographs of speeds and torques in a single pass. The existing speed configuration is shown to cause the lower-roll torque to reach its limits, whereas the upper-roll drive switches to the generator mode. The authors propose and validate a set of solutions to address these challenges. They herein present a load regulation method based on forced alignment of upper- and lower-roll drive speeds by disabling the integral part of the load distribution controller. An algorithm based on this method has been implemented in the APCS of Mill 5000; the resultant oscillographs prove better accuracy and shorter time to align the torques. It is herein recommended to apply the research results in the real-world setting.

Programming Algorithms of load balancing with HA-Proxy in HTTP services

The access to the public and private services through the web gains daily protagonism, and sometimes they must support amounts of requests that a team can not process, so there are solutions that use algorithms that allow to distribute the load of requests of a web application in several equipment; the objective of this work is to perform an analysis of load balancing scheduling algorithms through the HA-Proxy tool, and deliver an instrument that identifies the load distribution algorithm to be used and the technological infrastructure, to largely cover implementation. The information used for this work is based on a bibliographic analysis, eld study and implementation of the different load balancing algorithms in equipment, where the distribution and its performance will be analyzed. The incorporation of this technology to the management of services on the web, improves availability, helps business continuity and through the different forms of distribution of the requests of the algorithms that can be implemented in HA-Proxy to provide those responsible for information technology systems with a view of their advantages and disadvantages.

Optimum Extraction of Micro Grid, Using the Load Transmission from the Demand Side Management Program

One of the important problems in optimum extraction of power system, is the micro grid optimum extraction, considering the demand side management. Demand Side Management performance reduces the extraction cost of power system and on the other hand these kind of programs need the financial encouraging policies. In this paper, the optimum extraction problem from micro grids has been formulated in addition to demand side management. Load transmission has been considered as an effective solution in demand side management. Objective function of this problem is the reduction of extraction costs, the problem criteria contain the extraction criteria and performance limitations for the load transmission. In this problem, the amount of load transmission per hour has been considered as the problem variables and for this problem, the Genetic Algorithm and optimum load distribution algorithm have been used in combination to each other. The suggested method performed on a sample micro grid and results showed that with demand side management it is possible to reduce the micro grid total extraction costs.

Load distribution algorithm of process control system in tandem cold rolling

To improve the online performance of the process control computer of tandem cold rolling mills, a new multi-objective load distribution optimisation model is presented, which is based on the cost function, and takes into account the limit rolling force, the rolling force balance, the front and back tension, the reduction ratio, the power balance and strip shape control. Then, with less strict restriction on initial iterative calculation values for convergence, the Nelder–Mead simplex algorithm (NMS) is adopted to accomplish these membership functions optimisation during operation, which can obtain a good optimal solution set. In comparison with the empirical load distribution solution, the optimal solution can achieve a better performance, which demonstrates the effectiveness and robustness of the multi-objective load distribution optimisation model. The actual application result shows that the level-2 process control system with the new multi-objective load distribution optimisation model has stable operation and high accuracy, and the performance of the optimal rolling schedule given by the proposed approach is reasonable and satisfactory.

Multi-Cloud Provisioning and Load Distribution for Three-Tier Applications

Cloud data centers are becoming the preferred deployment environment for a wide range of business applications because they provide many benefits compared to private in-house infrastructure. However, the traditional approach of using a single cloud has several limitations in terms of availability, avoiding vendor lock-in, and providing legislation-compliant services with suitable Quality of Experience (QoE) to users worldwide. One way for cloud clients to mitigate these issues is to use multiple clouds (i.e., a Multi-Cloud). In this article, we introduce an approach for deploying three-tier applications across multiple clouds in order to satisfy their key nonfunctional requirements. We propose adaptive, dynamic, and reactive resource provisioning and load distribution algorithms that heuristically optimize overall cost and response delays without violating essential legislative and regulatory requirements. Our simulation with realistic workload, network, and cloud characteristics shows that our method improves the state of the art in terms of availability, regulatory compliance, and QoE with acceptable sacrifice in cost and latency.

A STUDY OF LOAD DISTRIBUTION ALGORITHMS IN DISTRIBUTED SCHEDULING

As we know that in distributed systems several autonomous computers are interconnected to provide a single coherent view of a powerful system and these autonomous computers work independently in a team-like fashion such that the domain of tasks is shared between all of them. Now to take full advantage of this distributed scenario, we need good resource allocation schemes. Load distribution algorithm’s work is to deliverately distributed and re-distributes the tasks (loads) among all the participating nodes so that the overall performance of the entire system is maximized. in this paper we study the details of the load distribution algorithms and their suitableness in various load scenerios.