Towards developing a cyber-physical multi-agent system for managing precise farms with digital twins of plants

Abstract

The paper presents the multi-agent approach for developing cyber-physical system for managing precise farms with digital twins of plants. It discusses complexity of the problem caused by a priori incompleteness of knowledge about factors of plant growth and development, high uncertainty of crops cultivation, variety of weather, business and technical requirements, etc. The approach proposes knowledge bases and multi-agent technology in combination with machine learning methods for designing considered systems. Digital twin of plant is specified as an agent based on ontology model of objects relevant for plant cultivation (specific sort of plant, soil, etc) associated with history of operations and environment conditions. The architecture and functions of system components are designed. The expected results of system implementation and the benefits for farmers are discussed.

Digital Twins: Review and Challenges

“…Regarding the level of integration, Kritzinger in his work [50], get as most used level the Digital Shadow (35 percent), followed by Digital Model (28 percent) and with a lower percentage the Digital Twin (18 percent), having a 19 percent of publications of indeterminate level of integration. The publications that present data exchange do so through the main communication trends, addressed in a previous section, however, only the publications [71,15,86,92,20,5,66,52,44,4,51,35,75,23] present communication between DTs of the same system. The results of the categorization can be seen in Fig.…”

“…The authors use international standards for their platform, called uDiT (universal Digital Twin platform), and presents the next elements: a middleware supported by OMG (Object Management Group) and DDS (Data Distribution Service) tools; besides allows co-simulation through FMI, and presents gateway methods. Others examples that belong to the informatics area and that have been previously described can be seen in [81,3,66,44,52,75,23].…”

“…Although in the analyzed case studies the use of Big Data only has been necessary for one of them, which has a large amount of data to handle. Laryukhin in his work [52], develops a MAS perspective for farm managing, using the digital twin concept. The big data of the farm include: actions, effects and responses, and also parameters describing the context of the current season and the specific situation of each day (temperature, accumulated precipitation, etc.…”

“…Laryukhin [52] develops a multi-agent approach based on CPS and DT technologies, for managing precise farms. The approach is knowledge driven, digital twins of plants are created, each DT is a smart agent created from a set of relevant information to optimize plant cultivation (plant type, crop, etc), also contains historical data about environmental conditions and activities.…”

System engineering view on multi-agent technology for industrial applications: barriers and prospects

“…One of the new promising application is cyber-physical MAS with digital twins of controlled objects, which can be also synchronized with real objects. Examples of such objects could be not only machines or enterprises, but also living organisms, for example, in wheat production digital twin of plant can represent main phases of plant developments with ongoing re-forecasting of the harvest and generating advices for farmers [Laryukhin et al, 2019]. The next step could cover the whole biocoenosis of the field -according to modern research, plants can detect insect attacks by 'sniffing' each other's aromas [King, 2020].…”