Multi-agent Technique Research Articles

Electric Taxi Charging Guidance Strategy Based on Electric Vehicle Agent-based Simulation

Electric vehicles connected to the electricity grid will have a great impact on the power system, especially with the high penetration of electric vehicles, the safety and stability of the power system could be threatened. In order to accurately simulate the electric taxi operation behavior and load characteristic, this paper proposes a mothed based on multi-agent technique and reinforcement learning algorithm to study the operation behavior of electric taxis. Different charging strategies on the operation of electric taxi are studied. Based on the charging strategy of shortest path, a charging guidance strategy model is proposed, which considers the charging distance, the charging queue time and the charging equilibrium degree of the charging equipment. The simulation results show that the electric taxi adopting the charging guidance strategy will not only decrease the charging queue time, improve the operation time and income of the electric taxi, but also help improve the equilibrium degree and utilization rate of the charging equipment, reduce the power grid loss and voltage offset.

Multi-agent learning technique inspired from software engineering model for permutation coded GA

Hybrid genetic algorithms (HGAs) have recognized significant attention in recent years and being progressively more used to solve real-world problems. HGA is the forms of assimilation between genetic algorithm and other search optimization techniques to improve the overall performance of the genetic algorithm (GA). GA can be hybridized with many other bio-inspired heuristic algorithms such as particle swarm optimization, cuckoo search genetic algorithm, firefly algorithm-genetic algorithm, real coded genetic algorithm-artificial fish swarm algorithm, etc., multi-agent system (MAS) is a new paradigm for conceptualizing, designing and optimizing the solution models. Multi-agent learning concept improves the outcome of the MAS and the type of learning process involved in it plays a vital role. Incremental model is a well-known software development process in which the system yields better effect at the end of every cycle. In this paper, software engineering inspired incremental model based multi-agent learning model for permutation coded genetic algorithms has been proposed. One of the famous combinatorial hard problems of traveling salesman problem (TSP) is being chosen as the test bed and the experiments are performed on large sized benchmark TSP instances obtained from standard TSPLIB. The experimental results support that the proposed model perform better than existing best working initialization methods in terms of convergence rate, error rate and computation time.

Simulating the origins of life: The dual role of RNA replicases as an obstacle to evolution.

Despite years of study, it is still not clear how life emerged from inanimate matter and evolved into the complex forms that we observe today. One of the most recognized hypotheses for the origins of life, the RNA World hypothesis, assumes that life was sparked by prebiotic replicating RNA chains. In this paper, we address the problems caused by the interplay between hypothetical prebiotic RNA replicases and RNA parasitic species. We consider the coexistence of parasite RNAs and RNA replicases as well as the impact of parasites on the further evolution of replicases. For these purposes, we used multi-agent modeling techniques that allow for realistic assumptions regarding the movement and spatial interactions of modeled species. The general model used in this study is based on work by Takeuchi and Hogeweg. Our results confirm that the coexistence of parasite RNAs and replicases is possible in a spatially extended system, even if we take into consideration more realistic assumptions than Takeuchi and Hogeweg. However, we also showed that the presence of trade-off that takes into the account an RNA folding process could still pose a serious obstacle to the evolution of replication. We conclude that this might be a cause for one of the greatest transitions in life that took place early in evolution—the separation of the function between DNA templates and protein enzymes, with a central role for RNA species.

Integrating Reinforcement Learning with Multi-Agent Techniques for Adaptive Service Composition

Service-oriented architecture is a widely used software engineering paradigm to cope with complexity and dynamics in enterprise applications. Service composition, which provides a cost-effective way to implement software systems, has attracted significant attention from both industry and research communities. As online services may keep evolving over time and thus lead to a highly dynamic environment, service composition must be self-adaptive to tackle uninformed behavior during the evolution of services. In addition, service composition should also maintain high efficiency for large-scale services, which are common for enterprise applications. This article presents a new model for large-scale adaptive service composition based on multi-agent reinforcement learning. The model integrates reinforcement learning and game theory, where the former is to achieve adaptation in a highly dynamic environment and the latter is to enable agents to work for a common task (i.e., composition). In particular, we propose a multi-agent Q-learning algorithm for service composition, which is expected to achieve better performance when compared with the single-agent Q-learning method and multi-agent SARSA (State-Action-Reward-State-Action) method. Our experimental results demonstrate the effectiveness and efficiency of our approach.

Agent-based modeling of availability for complex multiple units systems

PurposeThe purpose of this paper is to propose an availability modeling method of complex multiple units system (CMUS) based on the multi-agent technique.Design/methodology/approachBased on the multi-agent technique, this paper describes the availability model structure for CMUS and develops agent-based models of components, maintenance policies, maintenance tools, maintenance fields, and maintenance staff, as well as the communication method among the different agents. On the basis of the agent-based availability modeling theory, the availability simulation scheme of CMUS is given using MATLAB. Thus, the availability modeling theory of CMUS and its simulation method are developed. To demonstrate the applicability of the proposed availability modeling method, a numerical example is given.FindingsThe proposed agent-based modeling method is applicable to availability modeling of CMUS, including the modeling of component failure, maintenance tools/fields/staff, maintenance policy, and structural/economic dependence among components.Practical implicationsAs a bottom-top, modular, expandable, and reusable modeling theory, the agent-based modeling method might be useful for availability modeling of different CMUSs in reality.Originality/valueThe multi-agent technique is introduced into availability modeling of multi-component systems in this paper. Thus, it is possible to model failure of many components, maintenance policies, maintenance tools, maintenance fields, and maintenance staff together for availability analysis of complex systems of equipment.

Development of User-friendly Tool for Energy Behavioral Change of Consumers

Abstract This paper purposes to provide an user-friendly intelligent tool, integrating fuzzy controllers and multi-agent techniques, able to motivate and to support behavioral change of energy end-users, having as main objective to re-define the role of energy consumer in “prosumer” in the context of a reorganized decentralized energy market, now reported to intelligent grids (smart grids). Integration of interactive technologies in a decision support system for microgrids energy management optimizes: functioning from an economical point of view, active control of distributed generation, controlled consumption, loading the storage equipment. The added value of the proposed tool consists of integrating decision theory and artificial intelligence concepts in monitoring and control actions, allowing “prosumers”: to make energy usage data accessible and to demonstrate that energy savings can be achieved without compromising comfort levels.

Integrated Ecological Assessment of Engineering Projects Based on Emergy Analysis

For a long time, the problems of complex system mechanism of major engineering, such as lack of acknowledge, inconsistence of scale, insufficient quantification and lack of valid direct viewing evaluation tools lead to decision failures of major engineering projects. Under the view of engineering ecology, based on system theory and system ecology, employs system analysis method and ecological network analysis method, activates engineering. Given emergy as the uniform scale, adopting emergy analysis methods, building up emergy evaluation index system of major engineering can realize quantitative assessment of major engineering. Employing the integration of computational experiments methods and emergy analysis methods realizes the numerical simulation of complex system mechanism of major engineering; getting help from the integration of BIM, GIS and Multi-agent technique makes the linguistic expressions of space and analog simulation come true, to emerge ecological evolution. The study of this project, with theoretical significance and using value, converting comprehensive assessment to ecological assessment, provides brand-new theory, methods and decision tools for the evaluation of major engineering projects.

Fusing data in adaptive agent control systems for electrical grids

This paper reports a Monte Carlo analysis of a novel multi-agent technique for network-centric control in a microgrid scenario. Agents monitor a feeder line shared by n microgrids and collectively assess changes in the direction and magnitude of power system dynamic stability. Every agent samples voltage variation every few milliseconds, classifies observations, and votes to express and communicate their individual inferences about the state of system stability. Monte Carlo simulations are used to investigate the probability that rules for representing and fusing information reliably produce error-resilient collective outcomes (ERCOs) in centralised and decentralised networks. ERCOs overcome communications or decision-making errors to provide a window of opportunity for adapting to correct emergent instability or to minimise harm. Voting systems provide a semantics and syntax for relating low-level data to high-level inferences about network situations. Our results provide a basis for optimising the design of communications infrastructure to control electrical grid stability.

Software for partitioning and protecting a water supply network

ABSTRACTWater network partitioning (WNP) concerns the implementation of the paradigm of ‘divide and conquer’ in the water supply systems consisting in dividing a water network into k smaller subsystems by gate valves and flow meters. WNP allows improving the management of water distribution systems by transforming into Smart WAter Networks (SWANs) that represent key subsystems of Smart Cities. WNP is possible if water utilities start to use isolating valves (also with control devices) and flow meters. These instruments open new perspectives for the management of water supply systems both in terms of water saving and water protection. Recently, starting from the advantages offered by computing power and network analysis tools, some techniques based on graph partitioning algorithms have been developed by the authors to improve water management and protection, implementing the paradigm of ‘divide and conquer’. This paper presents the second release of SWANP 2.0 (Smart WAter Network Partitioning and Protection) software that integrates two different algorithms, based on multilevel and multi-agent techniques, for WNP and a novel algorithm, based on a multi-objective function, for water network protection from intentional contamination. The SWANP 2.0 software, developed in Python v2.7.6 language, provides the decision-maker different solutions comparing network layouts with some hydraulic and protection performance indices.

Structural Modelling and Deceleration Algorithm for a Follow Aircraft on Performance-Based Navigation Airway Based on Multi-Agent Technique

Abstract Considering the operation characteristics of the high-speed PBN airway, we propose an aircraft agent structural model and a basic algorithm flow of decision-making by Multi-agent technique. According to the constraint of safe separation and speed with the aircrafts, making use of the car-following theory, the deceleration constraint model is built for a flight management system. When the front aircraft decelerates, the model can offer a speed adjustment proposal for the following aircraft. The model is built based on the minimal safe separation and speed interval constraint; each variable, influencing the deceleration of the following aircraft can be analyzed. Simulation analysis is carried out for different combinations of aircraft types, initial speed, safe separation and deceleration. The follow aircraft deceleration was calculated under different conditions and the results coincided with reality. It is proved that the model can provide safe separation between the two aircrafts.

Emergency response nurse scheduling with medical support robot by multi-agent and fuzzy technique.

In this paper, a new co-operative re-scheduling method corresponding the medical support tasks that the time of occurrence can not be predicted is described, assuming robot can co-operate medical activities with the nurse. Here, Multi-Agent-System (MAS) is used for the co-operative re-scheduling, in which Fuzzy-Contract-Net (FCN) is applied to the robots task assignment for the emergency tasks. As the simulation results, it is confirmed that the re-scheduling results by the proposed method can keep the patients satisfaction and decrease the work load of the nurse.

A Multi-Agent Control for Energy Management in PV/Wind/Fuel Cell/Battery Hybrid Power System

The usage of renewable energy systems increases worldwide due to extinction of conventional sources and also the absence of some serious environmental effects such as global warming, ozone layer depletion etc. These renewable power systems are not able to satisfy the load continuously due to seasonal availability of the resources. A Hybrid Power System (HPS) formed with renewable energy sources are a solution to provide power for stand-alone electrical loads. However, the energy management in HPS is quite complex as it relies on a central controller. This paper proposes a distributed Energy Management System (EMS) to control the energy flow in the PV/Wind/Fuel Cell/Battery HPS based on multi-agent system (MAS) technology. With this concept, a HPS is seen as a collection of different elements called agents, collaborates to reach a global coordination to satisfy the demand in the system. The Algorithm of the Multi-Agent System technique for HPS has been implemented using MATLAB/Simulink environment. The results show that the algorithm is effectively working for a HPS to provide power to the load and control power flow between various elements of the system.

Taekwondo Athletes Physical Fitness Evaluation System Based on Multi-Agent

Aiming at project characteristics of taekwondo and combining with multi-Agent technique, this paper has put forward a taekwondo athlete physical fitness evaluation system based on multi-Agent. Moreover, it has made elaborate about the system module.

Study for the Distributed Power Grid Faults Diagnose System Based on Mas

The setup structure for the power grid faults diagnose system is analysed, the Multi-Agent System technique is used to the system. The functional modular of the system is transformed into Multi-Agent System, which has the same function as the entity system. The modular of the system can be in reconfiguration state when trouble appears by using Agent technique. The system running mechanism is also given.

Fault Diagnosis System Based on Multiagent Technique for Ship Power System

Fault diagnosis system of ship power system can assist the crew to deal with faults, shorten the processing time, and prevent faults expanding. Multiagent technique is adopted for the fault diagnosis system. Ship power system is divided into several feeder units. Each one is abstracted as a regional feeder agent (FED-Agent). A multiagent fault diagnosis system is established with FED-Agent and other functional agents. Considering of the characteristics of agent, the multiagent system processes both autonomy and interactivity. It can solve fault diagnosis problem of ship power system effectively.

A study of pricing strategy in platform business: a multi-agent simulation approach

The platform business has attracted an increasing amount of attention from industry professionals and academics alike. Although a low pricing strategy is effective for increasing the number of users in the platform business, it remains unclear if a low pricing strategy increases profits for platform providers. To address this issue, we employed multi-agent simulation techniques to analyse the influence of pricing strategy on platform provider’s profit. First, we constructed a user behavioural model which incorporates both cross-side network effects and same-side network effects. In this model, we treated consumers, suppliers, and advertisers as platform users. Next, the simulations demonstrated that a low pricing strategy generates greater profit than a high pricing strategy when the suppliers’ and advertisers’ same-side network effects are negative. Taken together, the results of this study suggest that platform providers must choose a pricing strategy on the basis of the impact of same-side network effects.

Multi-agent Technique and Its Application for Economic Load Dispatch

Multi-agent Technique and Its Application for Economic Load Dispatch

Study of Remote Monitoring and Diagnostic System for Transformers Based on Multi-Agent Techniques

The development direction of transformer monitoring and diagnosis is remote and intelligent. But the existing systems have the following problems: lack of diagnostic knowledge and methods, poor flexibility etc. To solve these problems, the architecture of a remote monitoring and diagnostic system for transformers based on multi-agent techniques is presented. On the basis of ultra high frequency (UHF) partial discharge (PD), core earth current and dissolved gas analysis (DGA), the hierarchical decomposition model is established. The tasks, functions and structure involved in the collaboration agents are defined. Then, the fusion strategy from multi-experts conclusions is proposed based on diagnostic confidence and weights. In final, the system implementation is described. Some functions of the system have been put into service and worked well.

Study for Power Grid Fault Diagnosis System Based on Hierarchical Distributed MAS

The setup structure for the power grid faults diagnose system is analysed, the Multi-Agent System technique is used to the system. The functional modular of the system is transformed into Multi-Agent System, which has the same function as the entity system. The modular of the system can be in reconfiguration state when trouble appears by using Agent technique. The system running mechanism is also given.

Learning in Unknown Reward Games: Application to Sensor Networks

This paper demonstrates a decentralised method for optimisation using game-theoretic multi-agent techniques, applied to a sensor network management problem. Our first major contribution is to show how the marginal contribution utility design is used to construct a unknown-reward potential game formulation of the problem. This formulation exploits the sparse structure of sensor network problems, and allows us to apply a bound to the price of anarchy of the Nash equilibria of the induced game. Furthermore, since the game is a potential game, solutions can be found using multiagent learning techniques. The techniques we derive use Q-learning to estimate an agent’s rewards, while an action adaptation process responds to an agent’s opponents’ behaviour. However, there are many different algorithmic configurations that could be used to solve these games. Thus, our second major contribution is an extensive evaluation of several action adaptation processes. Specifically, we compare six algorithms across a variety of parameter settings to ascertain the quality of the solutions they produce, their speed of convergence, and their robustness to pre-specified parameter choices. Our results show that they each perform similarly across a wide range of parameters. There is, however, a significant effect from moving to a learning policy with sampling probabilities that go to zero too quickly for rewards to be accurately estimated.