35 docs tagged with "size:small"

Building an ML model takes significant computing resources that need to be optimized for efficient utilization.

User tracking, user data collection and targeting in things like advertisements are responsible for significant energy use in many digital products, and services.

From an energy-efficiency perspective, it's better to reduce network traffic by reading the data locally through a cache rather than accessing it remotely over the network. Shortening the distance a network packet travels means that less energy is required to transmit it. Similarly, from an embodied carbon perspective, we are more efficient with hardware when a network packet traverses through less computing equipment.

From an energy-efficiency perspective, it's better to shorten the distance a network packet travels so that less energy is required to transmit it. Similarly, from an embodied-carbon perspective, when a network packet traverses through less computing equipment, we are more efficient with hardware.

From an energy-efficiency perspective, it's better to minimise the size of the data transmitted so that less energy is required because the network traffic is reduced.

Web pages offer a lot of images that aren't displayed on the first loaded screen and can thus be loaded dynamically.

From an embodied carbon perspective, it's better to delete unused storage resources so we are efficient with hardware and so that the storage layer is optimised for the task.

One direct replacement of the GIF is the MP4 video format which provides much smaller file sizes and higher quality at the same time.

Web browsers often communicate with web servers in a human readable format. These can be HTML, JavaScript and/or CSS files and REST requests which can return a response in JSON. This human readable communication is redundant and, as such, can be compressed to save bandwidth.

Applications are built with a software architecture that best fits the business need they are serving. Cloud providers make it easy to evaluate other CPU types

As part of your AI/ML process, you should evaluate using a pre-trained model and use transfer learning to avoid training a new model from scratch.

It's better to have one VM running at a higher utilization than two running at low utilization rates, not only in terms of energy proportionality but also in terms of embodied carbon. Two servers running at low utilization rates will consume more energy than one running at a high utilization rate. In addition, the unused capacity on the underutilized server could be more efficiently used for another task or process.

It's better to have one VM running at a higher utilization than two running at low utilization rates, not only in terms of energy proportionality but also in terms of embodied carbon. Two servers running at low utilization rates will consume more energy than one running at a high utilization rate. In addition, the unused capacity on the underutilized server could be more efficiently used for another task or process.

Minification removes unnecessary or redundant data without affecting how the resource is processed by the web browser.

Description

It's better to maximise storage utilisation so the storage layer is optimised for the task, not only in terms of energy proportionality but also in terms of embodied carbon. Two storage units running at low utilization rates will consume more energy than one running at a high utilization rate. In addition, the unused capacity on the underutilised storage unit could be more efficiently used for another task or process.

Description

Large-scale AI/ML models require significant storage space and take more resources to run as compared to optimized models.

All systems have periods of peak and low load. From a hardware-efficiency perspective, we are more efficient with hardware if we minimise the impact of request spikes with an implementation that allows an even utilization of components. From an energy-efficiency perspective, we are more efficient with energy if we ensure that idle resources are kept to a minimum.

From an energy-efficiency perspective, it's better to minimize the size of the data transmitted so that less energy is required because the network traffic is reduced.

Description

CSS files are very complex and need energy intensive parsing and processing. Each added CSS definition increases the amount of time and processing power needed in this process.

Data computation for ML workloads and ML inference is a significant contributor to the carbon footprint of the ML application. Also, if the ML model is running on the cloud, the data needs to be transferred and processed on the cloud to the required format that can be used by the ML model for inference.

Applications consume CPU even when they are not actively in use. For example, background timers, garbage collection, health checks, etc. Even when the application is shut down, the underlying hardware is consuming idle power.

In order to reduce carbon emissions and costs, Dev&Test Kubernetes clusters can turn off nodes out of office hours. Thereby, optimization is implemented at the cluster level. For production clusters, where nodes need to stay up and running, optimization needs to be implemented at the application level.

Training an AI model implies a significant carbon footprint. The underlying framework used for the development, training, and deployment of AI/ML needs to be evaluated and considered to ensure the process is as energy efficient as possible.

Selecting the right hardware/VM instance types for training is one of the choices you should make as part of your energy-efficient AI/ML process.

Modern image formats can help to reduce bandwidth, storage and computing requirements on the displaying device.

From an embodied carbon perspective, it's better to have an automated mechanism to delete unused storage resources so we are efficient with hardware and so that the storage layer is optimised for the task.

Description

Distributed denial of service (DDoS) attacks are used to increase the server load so that it is unable to respond to any legitimate requests. This is usually done to harm the owner of the service or hardware.

Efficient storage of the model becomes extremely important to manage the data used for ML model development.

Evaluate and use alternative, more energy efficient, models that provide similar functionality.

Description

Depending on the model parameters and training iterations, training an AI/ML model consumes a lot of power and requires many servers which contribute to embodied emissions.