The objective of this study was to perform a three-dimensional mapping model for the study of temperature and humidity behavior in the data center.The above consists of the installation of hardware and software components that carry out processes to control the environmental conditions of the racks.In addition, a sensor positioning model was defined to design and implement a monitoring system taking into account the costs.It was verified that the temperature and humidity levels of the servers are below the 27° C threshold according to international standards.This is done through data mining techniques, to contribute to decision making and generate a strategic maintenance plan by the administrator.Keyword -Monitoring, sensor, rack, control system, data mining.I. INTRODUCTION Data centers are rooms that contain servers for storage and processing [1].They are made up of buildings, facilities, telecommunications equipment, refrigeration and energy, which rapidly develop as an important part of the IT industry [2].The growing multidisciplinary demand requires that this type of facilities that house highperformance computational machines have an appropriate balance and control of temperature and humidity levels, which is essential for operational efficiency in the protection of the equipment involved [3].In the data centers an essential part to maintain stable environmental conditions are the cooling infrastructure, because it contributes significantly to energy consumption.With the above, the balance of temperature and humidity levels is achieved [4], however, in most cases, these high-performance computing facilities are not capable enough to handle additional cooling requirements as: recirculation or mixing of hot and cold air, in addition to little controlled humidity levels [5].The coordination of the air conditioning units of the computer room (CRAC) and the supply of air temperature (SAT), represents a challenge of the logistics for the maintenance of the data centers; In aspects such as the speed of the fans, the energy consumption between the CRACs and the chillers decreases, while the temperature of the racks remains below the established thresholds.In addition, one of the biggest obstacles to overcome is the lack of simplified and computationally suitable models [6].Among the works related to the development of the modeling of influential factors in the performance, maintenance and useful life of the data centers, is that of [7], who in their study used simulations to achieve the prediction of the behavior of heat flows in data centers with a sensitivity analysis, focused on the search for precision in the three-dimensional profile, and in which, with the help of a reduced-order modeling method, they manage to drastically reduce the execution time of the simulation (up to 600 times faster), maintaining the model's accuracy in an acceptable manner.In addition, [6] proposed models that determine the efficiency of refrigeration processes, in order to improve the quality of these computing facilities and their thermal environment.A data center management and analysis scheme based on the dynamic model of rack entry temperature is used.The procedures for identifying the parameters of the model and its reduction are analyzed.An improved approach to thermal zone mapping is introduced through the grouping by the temperature of the model-based rack input.Another associated study is carried out by [5], in which they executed computer simulations based on a modeling of differential equations, in order to achieve a lower energy consumption and establish adequate flows of hot and cold air, to achieve greater use of refrigeration equipment.Likewise, works such as that of [8] suggest the need to formulate administrative policies depending on the properties of each data center based on simple models that detail the thermal behavior.