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 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.
If service downtimes are acceptable it's better to not strive for highest availability but to design the solution according to real business needs. Lower availability guarantees can help reduce energy consumption by using less infrastructure components.
Software that demands frequent hardware upgrades increases embodied carbon from device manufacturing; designing for backwards compatibility extends device lifetimes and reduces the carbon footprint of customer equipment.
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.
Unused cloud resources such as databases, storage buckets, and compute instances continue to consume energy and generate embodied carbon; identifying and decommissioning them eliminates unnecessary waste.
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.
When making calls across process boundaries to either databases or file systems or REST APIs, relying on synchronous calls can cause the calling thread to become blocked, putting additional load on the CPU
Modern applications need to communicate with other applications on a regular basis. Since these other applications have their own deployment schedule, downtimes and availability, the network connection to these application might have problems. If the other application is not reachable, all network requests against this other application will fail and future network requests are futile.
Interpreted languages re-parse and compile code on every execution, consuming more energy than pre-compiled binaries, which perform compilation once and run more efficiently at runtime.