This study was conducted during summer and winter of 2018- 2019 in the agricultural research field of Shahid Chamran University. Experimental design was split- plot based on RCBD with three replications. The main plot was the type of agricultural system in three levels including conventional (Conv), organic (Org) and sustainable (Sust) (integrated between Conv and Org) and sup- plot was the type of pre- cultivated crop in sequence with wheat including cultivation of mung bean (M- W), corn (C- W), sesame (S- W) and fallow (F- W). Yield quantity (yield and its component) and quality (grain protein), an estimate of photosynthesis matter transfer index of wheat and soil organic carbon (SOC) after one double-cropping were measured. The result showed that the highest (545.04 g/m2) and the lowest (409.28 g/m2) seed yields were obtained in Conv and Org respectively. In contract, with the changing type of system from Conv to Org, grain protein was increased significantly (from 8.3 to 9.6 %). In addition, the highest (535.47 g/m2) yield of wheat was obtained from M- W double cropping. On the other hands the highest remobilization and current photosynthesis matter were obtained in the organic agricultural system with M- W and conventional with M- W double cropping. The situation of SOC showed that the highest (33.18 mg/g) SOC was obtained in the organic agricultural system with C- W double cropping. The reason for improving SOC in the organic and sustainable agricultural system was application of organic matter (compost and vermicompost) and crop residue management. Totally, from the crop ecology point of view, sustainable agricultural method with a sequence of M- W was the most desirable system.

Agents are software entities that act continuously and autonomously in a special environment. It is very essential for the agents to have the ability to learn how to act in the special environment for which they are designed to act in, to show reflexes to their environment actions, to choose their way and pursue it autonomously, and to be able to adapt and learn. In multi-agent systems, many intelligent agents that can interact with each other cooperate to achieve a set of goals. Because of the inherent complexity that exists in dynamic and changeable multi-agent environments, there is always a need to machine learning in such environments. As a model for learning, learning automata act in a stochastic environment and are able to update their action probabilities considering the inputs from their environment, so optimizing their functionality as a result. Learning automata are abstract models that can perform some numbers of actions. Each selected action is evaluated by a stochastic environment and a response is given back to the automata. Learning automata use this response to choose its next action. In this paper, the goal is to investigate and evaluate the application of learning automata to cooperation in multi-agent systems, using soccer server simulation as a test-bed. Because of the large state space of a complex Multi-agent domains, it is vital to have a method for environmental states’ generalization. An appropriate selection of such a method can have a great role in determining agent states and actions. In this paper we have also introduced and designed a new technique called “The best corner in State Square” for generalizing the vast number of states in the environment to a few number of states by building a virtual grid in agent’s domain environment. The efficiency of this technique in a cooperative multi-agent domain is investigated.

Agents, in a multi agent system, communicate with each other through the process of exchanging messages which is called dialogue. Multi agent organization is generally usedto optimize agents’ communications. Holonic organization demonstrates a self-similar recursive and hierarchical structure in which each holon may include some other holons. In a holonic system, lateral communication occurs between members of a determined holon and vertical communications are inter-level ones between different holons. When agents start a dialogue, according to their beliefs, they follow some rules that define the permissive speech acts called dialogue protocol. The dialogue strategy is the policy of agents to choose a particular speech act among the allowed ones by the protocol in order to achieve the common goals of holon. In this paper a formal model for dialogue strategy for lateral communication in a holon is proposed. This model tries to choose the most preferable speech acts considering at the same time local beliefs and goals along with public knowledge obtained from holonic organization. Moreover, the argumentation theory is applied to rank and define the values of speech acts. The proposed model finds the most preferable option to utter and it also decreases the number of exchanging messages. The proposed model of dialogue strategy is illustrated via a deliberation dialogue example in a holon. The example showed a significant efficiency in decreasing the number of exchanged messages and the effectiveness of deliberation.

In previous papers authors have considered agents as inertia less self driven particles and designed a flocking algorithm. Application of this algorithm to agents with considerable inertial characteristics needs a behavioural controller. The controller uses the local information and helps every agent to imitate the desired behaviour as a member of the flocking frame which covers the main issue in this paper. All agents are assumed to possess limited identical influencing/sensing radius. The sliding-mode control technique is used, hence; effect of bounded disturbances and uncertainties can be omitted too. Once inertial agents are equipped with the behavioral controller, the multi-agent system behaves similar to a group of self-driven inertia-less particles which; coordination control algorithms and cohesion analyses are previously designed for.

The objective of the current paper is to present an intelligent system for complex process monitoring, based on artificial intelligence technologies. This system aims to realize with success all the complex process monitoring tasks that are: detection, diagnosis, identification and reconfiguration. For this purpose, the development of a multi-agent system that combines multiple intelligences such as: multivariate control charts, neural networks, Bayesian networks and expert systems has became a necessity. The proposed system is evaluated in the monitoring of the complex process Tennessee Eastman process.

This paper describes how multi-agent system technology can be used as the underpinning platform for voltage control in power systems. In this study, some FACTS (flexible AC transmission systems) devices are properly designed to coordinate their decisions and actions in order to provide a coordinated secondary voltage control mechanism based on multi-agent theory. Each device here is modeled as an agent being able to cooperate and communicate with other devices. In this system, individual autonomous agents and intelligent decision makers learn to perform optimal actions through proper interactions with their environments. The SARSA Q-learning, which is an on-policy algorithm in reinforcement learning (RL) is then used and tested successfully in voltage control problem. In this research, the Java Agent Development (JADE) platform is used to implement the agents and to simulate their communications. The power system is also fully implemented in Java. The proposed intelligent MA based method is finally applied to IEEE 39-buses New England power system. The results of simulation better highlight the merit of the method and its ability in coordinating FACTS devices for removing voltage disturbances.

Due to their extended use, nowadays, Multi-Agent Systems have attracted the attention of many researchers. Bipartite formation is one of the interesting fields of Multi-Agent Systems that has been raised within a decade. In this research, the distributed bipartite formation of Multi-Agent Systems was investigated by a leader-follower approach. Heterogeneous agents in this approach have second-order nonlinear dynamics, and the communication graph between the agents is also a structurally balanced signed directed graph. Because of the distributed approach of the controller and the lack of existing communication between the leader and all of the followers, a finite-time observer is used to estimate the leader's dynamic in finite time. Also, because a finite-time approach increases performance and efficiency in many practical applications, a terminal sliding mode controller provides finite-time formation. Finally, the validity of the theoretical results is illustrated by simulation examples.

This paper studies the problem of fault detection and isolation (FDI) for multi-agent systems (MAS) via complex Laplacian subject to actuator faults. Using simple and linear interaction rules related to complex Laplacian, a planar formation of agents in the plane is achieved. The communication network is a directed, and yet connected graph with a fixed topology. The loss of symmetry in the digraph Laplacian matrix is also considered. Both the partial actuator effectiveness and the actuator bias faults are taken into account. For this purpose, a virtual agent whose dynamics structure is identical to that of the leader agent is introduced to determine the center of the planar formation. The FDI scheme requires no additional fault isolation model which is an essential part in the traditional FDI scheme. Finally, numerical example results are presented to show the effectiveness of the proposed scheme.

The problem of consensus in fractional order single-integrator multi-agent systems has been studied in this paper. The effect of memory is considered using the Riemann-Liouville fractional derivative in the dynamics of the agents. In order to achieve convergence among the agents, a fractional order control protocol based on the error signal between neighboring agents is proposed. Using Lyapunov's stability theorem, a Lyapunov function is introduced that shows that the agents converge over a specified settling time and the upper bound of the settling time is obtained. The merit of the proposed bound for the settling time is that it is independent of the initial conditions. Finally, some simulations are provided to confirm the introduced method.