▷ Enhancing Energy Efficiency with Learning-based Consumption Prediction

✅ Keywords:

➡️ #EnergyConsumptionPrediction #Energy #ESP32 #PZMT004 #OpenSource #OpenHardware #RegressionLearner #SustainableEnergyInformation #DataCenter #NodeRed #EmbeddedSystems #MIcrocontroller #Phyton #MQTT #MySQL #Telegram

✅ Introduction:

In this edition, we explore a groundbreaking research study titled "Learning-based Energy Consumption Prediction" conducted by our team of experts. We delve into the challenges posed by the increasing influx of data into cloud-fog infrastructures and the pressing need for sustainable energy consumption management. Our researchers have developed an energy consumption prediction model, focusing on hardware design, data pre-processing, and machine learning techniques. Join us on this journey as we discuss the methodology, findings, and future prospects of this pioneering study.

✅ Content:

In our study, titled "Learning-based Energy Consumption Prediction," we address the critical issue of managing energy consumption in servers, fog devices, and cloud computing platforms. The growing demand for cloud-fog infrastructure has intensified the challenges associated with Green IT. To tackle this, we propose an innovative energy consumption prediction model. This model comprises hardware design, data pre-processing, and characteristic extraction, aiming to create a non-invasive meter utilizing a network of sensors. These sensors, equipped with microcontrollers and the MQTT communication protocol, measure various parameters such as voltage, current, power, frequency, energy, and power factor. The real-time energy measurements are then displayed on a dashboard, empowering users to optimize their IT equipment and reduce maintenance costs.
During our research, we evaluated different linear regression models to select the most suitable one. These models enable us to predict energy consumption on an hourly and daily basis, providing valuable insights for effective energy management strategies. Our supervised machine learning algorithms have paved the way for accurate predictions, guiding businesses and individuals in optimizing their energy usage patterns.

✅ Conclusions:

In our study, we introduced a hardware-based prototype capable of recording extensive measurements from workstations. We employed a Robust Linear Regression Model, selected based on the Root Mean Square Error (RMSE) of predicted values. Our hourly predictions exhibited a low RMSE of 0.025712 [kWh], signifying the model's effectiveness in short-term predictions. However, the daily predictions revealed a higher RMSE of 3.25029 [kWh], indicating underfitting within this time window.
As a part of our future endeavors, we plan to conduct additional experiments with extended data acquisition periods, allowing us to train the prediction model for more extended time windows, such as weeks and months. Furthermore, we aim to design an FPGA-based gateway to aggregate data from multiple energy consumption sensors connected to data center servers. This approach will enhance the accuracy of our dataset and validation of the energy consumption prediction model, contributing to more reliable and efficient energy management solutions.

✅ References:

Estrada, R., Torres, D., Bazurto, A., & Valeriano, I. (2022). Learning-based Energy Consumption Prediction. Procedia Computer Science, 203, 272-279.
✅The Matlab code used for data processing are available in: https://github.com/vasanza/Matlab_Code/tree/EnergyConsumptionPredictionDatacenter
✅The dataset used for data processing are available in: https://ieee-dataport.org/open-access/data-server-energy-consumption-dataset
Read More

Comments

▷ The Social Cognitive Theory #SCT applied to reduce sedentarism in citizens

➡️ #SCT #SocialCognitiveTheory #Sedentarism Sedentarism is a growing concern in today's society due to its negative effects on health and well-being. However, the Social Cognitive Theory offers a solution to reduce it through a series of strategies based on human behavior. ➡️ According to this theory, human behavior is influenced by social perception, that is, how we perceive others and how they perceive us. In the case of sedentarism, one way to reduce it is through the creation of a social culture that values and promotes physical activity. ➡️ One way to achieve this is through education and awareness about sedentarism, physical activity, nutrition, quality of life, among other health-related aspects. Creating awareness campaigns about the importance of maintaining an active lifestyle can help influence social perception and motivate people to change their sedentary behavior. ➡️ Another strategy is the creation of programs and physical activities that are accessible and attracti

▷ Display of last 24 hours of Temperature, Humidity and Temp. CPU

For this post, two sensors have been deployed for real-time data collection, currently operational in the city of Guayaquil: one for humidity and another for temperature. Both sensors utilize LoRA technology to transmit collected information to a Gateway. This Gateway serves as a central connection point, receiving data from the sensors and forwarding it to the Google Cloud platform via LTE cellular connectivity. Leaflet viewer with OpenStreetMap Leaflet viewer with OpenStreetMap Once the data is stored on the Google Cloud platform, a customized web interface has been developed. This interface facilitates the visualization and analysis of the sensor-collected data, offering users a clear and easily accessible representation. In today's interconnected world, the ability to gather and visualize real-time data is essential for understanding and making informed decisions. On this occasion, we will explore how to visualize the data from the last 24 h

▷ The Importance of Energy Consumption Prediction in Data Centers

➡️ #EnergyConsumption #EnergyPrediction #DataCenter In the digital age, data centers are a key piece of the technological infrastructure that drives the global economy. From managing large databases to cloud services, these centers consume large amounts of energy, making it crucial to have a good energy consumption prediction. Here we will explain why it is important to have a good energy consumption prediction in data centers. ➡️ Reducing Costs Energy consumption in data centers can be a significant cost for companies. Therefore, it is important to have a good energy consumption prediction to be able to plan and control costs efficiently. A good energy consumption prediction will allow companies to allocate budgets and plan appropriately, which will help reduce long-term costs. ➡️ Reducing Environmental Impact In addition to costs, data centers also have a significant impact on the environment. Generating energy for data centers often involves burning fossil fuels, contributing to gr

▷ Data visualization: of Temperature, Humidity, and CPU Temp.

For this post, two sensors have been deployed for real-time data collection, currently operational in the city of Guayaquil: one for humidity and another for temperature. Both sensors utilize LoRA technology to transmit collected information to a Gateway. This Gateway serves as a central connection point, receiving data from the sensors and forwarding it to the Google Cloud platform via LTE cellular connectivity. Leaflet viewer with OpenStreetMap Leaflet viewer with OpenStreetMap Once the data is stored on the Google Cloud platform, a customized web interface has been developed. This interface facilitates the visualization and analysis of the sensor-collected data, offering users a clear and easily accessible representation. In this post, we'll explore how to visualize real-time data from Google Cloud using JavaScript and the powerful charting library, Chart.js. The goal is to create an interactive environment that visually

▷ Advancements in Device-Free Indoor Localization Using Machine Learning and 28 GHz Band Technology

✅ Keywords : ➡️ #MillimeterWave #MMwave #28GHz #IndoorLocation #WirelessInSite #Remcom #Matlab #ML #MachineLearning #AI #ArtificialIntelligence #RegressionLearner #Classification ✅ Introduction: In this edition of our newsletter, we delve into groundbreaking research exploring the realms of device-free indoor localization techniques. Utilizing the power fluctuations in a communication link due to the presence of a human body, our researchers have employed advanced machine learning methods in the 28 GHz band. This innovative approach aims to redefine indoor positioning, offering unprecedented accuracy and efficiency. ✅ Content: In our quest to enhance indoor localization technology, our research team conducted comprehensive studies. Through meticulous simulations and experiments, we evaluated the potential of machine learning algorithms in the 28 GHz band, focusing on the effects of human presence within an enclosed space. 1. Database Construction and Simulation: Our researchers meti

▷ The Importance of Soft Processors in #FPGAs for Customized Digital Circuits

➡️ #FPGA #VHDL #SoC # System-on-Chip #Processor #SoftProcessors #DigitalCircuits #DigitalSystems FPGAs (Field-Programmable Gate Arrays) are programmable electronic devices that allow for the creation of customized digital circuits. Unlike ASICs (Application-Specific Integrated Circuits), which are integrated circuits specifically designed for one application, FPGAs can be programmed and reprogrammed to perform different tasks. ➡️ One of the most important advantages of FPGAs is their ability to implement soft processors, which are processors that are implemented in the FPGA using a hardware description language (HDL). Soft processors allow designers of integrated systems to create more complex and flexible systems than would be possible with conventional integrated circuits. ➡️ The importance of using soft processors in FPGAs lies in the ability to create highly customized integrated systems, tailored to specific user needs. Soft processors can be optimized for a specific task, whi

▷ Adafruit #HUZZAH32 - #ESP32 Feather

➡️ #ESP32 #HUZZAH32 #Feather #dafruit El #HUZZAH32 es módulo de desarrollo basado en #ESP32, hecha con el módulo oficial WROOM32. Este hardware contiene: convertidor USB a serie incorporado, reinicio automático del cargador de arranque, cargador de iones de litio / polímero, y casi todos los GPIO que sacaste para que puedas usarlo con cualquiera de nuestras alas de plumas. El ESP32 es una actualización perfecta del ESP8266 que ha sido tan popular. En comparación, el ESP32 tiene mucho más GPIO, muchas entradas analógicas, dos salidas analógicas, múltiples periféricos adicionales (como un UART de repuesto), dos núcleos para que no tenga que ceder ante el administrador de WiFi, procesador de mayor velocidad, ¡etcétera etcétera! Creemos que a medida que el ESP32 obtenga tracción, veremos a más personas moverse a este chip exclusivamente, ya que tiene todas las funciones. ✅ Overview : 240 MHz dual core Tensilica LX6 microcontroller with 600 DMIPS Integrated 520 KB SRAM Integrated 8

▷ #SoCs in Digital System Designs

➡️ #SoC # System-on-Chip #Processor #FPGA In the world of digital electronics, the use of #SoCs or System-on-Chip is becoming increasingly common in digital system designs. These integrated circuits contain everything needed to implement a complete system on a single chip, greatly simplifying the design process and reducing the size, cost, and power consumption of the final system. A typical SoC includes multiple functional blocks such as a processor, memory, peripheral controllers, communication interfaces, and other specialized circuits. Depending on the system's needs, the designer can choose from a wide range of SoCs available in the market, which vary in size, processing capability, and features. The advantages of using SoCs in digital system designs include: ➡️ Integration of multiple functions in a single chip: SoCs allow integration of everything needed to implement a complete system on a single chip, reducing the size and cost of the final system. ➡️ Simplified design: B

ASNZ SYSTEMS

Search This Blog