Multi-agent Principles Research Articles

Learning-based multi-agent MPC for irrigation scheduling

Amid concerns about freshwater scarcity, the agricultural sector faces challenges in water conservation and optimizing crop yields, highlighting the limitations of traditional irrigation scheduling methods. To overcome these challenges, this paper introduces a unified, learning-based predictive irrigation scheduler that integrates machine learning and Model Predictive Control (MPC), while also incorporating multi-agent principles. The proposed framework incorporates a three-stage management zone delineation process, utilizing k-means clustering and hydraulic parameters estimates for optimized agro-hydrological modeling. Long Short-Term Memory (LSTM) networks are employed for accurate and computationally efficient root zone soil moisture modeling. The scheduler, formulated as a mixed-integer MPC with zone control, utilizes the identified LSTM networks to maximize root water uptake while minimizing overall water consumption and fixed irrigation costs. Additionally, the learning-based scheduler adopts a multi-agent MPC paradigm, where decentralized hybrid actor–critic agents and the concept of a limiting irrigation management zone are employed to enhance computational efficiency. Evaluating the performance on a 26.4-hectare field in Lethbridge for the 2015 and 2022 growing seasons demonstrates the superiority of the proposed scheduler over the widely-used triggered scheduling approach in terms of Irrigation Water Use Efficiency (IWUE) and total prescribed irrigation. Notably, the proposed approach achieves water savings between 7 to 23%, coupled with IWUE increases ranging from 10 to 35%.

Моделирование процессов социальной самоорганизации интеллектуальных агентов

The relevance of the task of modeling human behavior posed in the article is associated with the need for active development of the economy, ensuring the involvement of an increasing proportion of the young population with higher and secondary specialized education. As a result of state incentives for business, more and more people are ready to receive higher education or continue to study at the next levels. When studying the processes of managing the social behavior of subjects, the “system of systems” (SoS) approach was used, within which various methods of modeling, simulation and analysis are developed and studied. The simulation is based on the multi-agent principle, the mechanism of which allows analyzing the behavior of the self-organization of an intelligent agent (social subject) and, if necessary, changing its behavior. The ideal approach for implementing the modeling of a multi-agent system (MAS) of the behavior of an agent is the evolutionary simulation methodology (ESM), which allows developing a set of interconnected optimization simulation models that implements the property of self-organization of intelligent agents. The basic principles of self-organization control are formulated, which is based on the theory of equilibrium random processes (RSP), which provides the possibility of influencing any available parameters and in any combination of them using ESM. The ways of adapting ESM in relation to modeling the process of social self-organization of a young person are considered, and a graphical interpretation of social development is proposed, two parameters are used as phase coordinates: social status and income level. Models of indirect methods of management, choice of the direction of development of a person’s career growth in the production management system based on dynamic programming have been developed. Examples of ESM implementation are given.

ASSESSMENT OF CONSUMERS POWER CONSUMPTION OPTIMIZATION BASED ON DEMAND SIDE MANAGEMENT

To ensure the functioning of the energy system, coordination and increase the efficiency of its parts need new control mechanisms. Generation, transmission and consumption of electricity needed control mechanisms that include integration of self-organizing power and heat supply systems, built on multi-agent principle. Also they must correspond intellectual basis, monitoring and accumulation. This includes effectiveness assessment of the state and analysis of technical, technological and organizational management mechanisms. One of the main parts is interaction principles of energy systems in accordance with European Community policy at various levels at liberalized electricity market.
 In most developed countries, demand management programs are widely used as a means of harmonizing the modes of generation and consumption in the power supply system. The main direct methods are set in the form of electricity tariffs. Indirect methods are set in the form of programs to manage electricity demand and the possibility of their application to manage electricity demand. Methods for estimating the unevenness of the daily schedule of electricity consumption and the factors influencing the technological environment are presented.
 The work aims at scientific and applied problem – finding methods of estimation and features of managing the demand for electricity.
 The use of the proposed estimation methods of electricity consumption influence non-uniformity on the level of power supplies system losses based on Frize QF power and optimization of consumers’ operation modes in the power supply system is considered.
 Approaches and optimization mechanisms of the daily electricity consumption on the example of a residential complex with the possibility of energy accumulation are offered

Adaptive Clustering through Multi-Agent Technology: Development and Perspectives

The paper is devoted to an overview of multi-agent principles, methods, and technologies intended to adaptive real-time data clustering. The proposed methods provide new principles of self-organization of records and clusters, represented by software agents, making it possible to increase the adaptability of different clustering processes significantly. The paper also presents a comparative review of the methods and results recently developed in this area and their industrial applications. An ability of self-organization of items and clusters suggests a new perspective to form groups in a bottom-up online fashion together with continuous adaption previously obtained decisions. Multi-agent technology allows implementing this methodology in a parallel and asynchronous multi-thread manner, providing highly flexible, scalable, and reliable solutions. Industrial applications of the intended for solving too complex engineering problems are discussed together with several practical examples of data clustering in manufacturing applications, such as the pre-analysis of customer datasets in the sales process, pattern discovery, and ongoing forecasting and consolidation of orders and resources in logistics, clustering semantic networks in insurance document processing. Future research is outlined in the areas such as capturing the semantics of problem domains and guided self-organization on the virtual market.

Energy Hub Function Optimization Models During Ukrainian Energy Resources Market Liberalization

Analysis of energy supply systems that provide integration of self-organizing electricity and heat supply systems is conducted. The study considers the possibility of a model of energy hubs that combines disparate heat and electrical energy generation sources to meet the energy demand of consumers. The proposed models will allow to optimize energy consumption modes and integration of self-organizing electricity and heat systems built on the multiagent principle on the basis of smart technologies.