ETAP PS vs. Pytorch

ETAP is highly recommended for evaluating static conditions in electrical power systems, whether in high or medium complexity networks. For example, study of load flow, analysis of frequency harmonics.

On the other hand, I would not recommend ETAP for the simulation of highly complex control systems that require a dynamic analysis of the variables.

They have created Pytorch Lightening on top of Pytorch to make the life of Data Scientists easy so that they can use complex models they need with just a few lines of code, so it's becoming popular. As compared to TensorFlow(Keras), where we can create custom neural networks by just adding layers, it's slightly complicated in Pytorch.

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info

• Excellent facility for the design of electrical systems, since it has multiple options and configuration.
• Truly intuitive, it is easy to adapt to the user interface, so the learning curve is very fast.
• It offers a wide variety of electrical studies that can be carried out, therefore it is very versatile for multiple applications.

• flexibility
• Clean code, close to the algorithm.
• Fast
• Handles GPUs, multiple GPUs on a single machine, CPUs, and Mac.
• Versatile, can work efficiently on text/audio/image/tabular datasets.

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info

• Perhaps the interface is somewhat confusing the first time you use the program.
• It offers a wide configuration, which can be overwhelming.
• Sometimes the program can freeze depending on the size of the electrical grid that is being simulated. This also depends on the software requirements.

• Since pythonic if developing an app with pytorch as backend the response can be substantially slow and support is less compares to Tensorflow

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info

ETAP PS is really easy to use. When recreating the power system to be simulated, it is easy to obtain a result close to reality due to the multiple components offered in the interface. As for the electrical studies available, they are simple to execute and require really little configuration to make them work, always offering a wide variety of options to adjust the program to the simulation of the desired condition.

The big advantage of PyTorch is how close it is to the algorithm. Oftentimes, it is easier to read Pytorch code than a given paper directly. I particularly like the object-oriented approach in model definition; it makes things very clean and easy to teach to software engineers.

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info

Sometimes when the program crashes for a random reason, it is difficult to find a direct solution to the problem. I think better documentation is needed for this type of case. Still, more and more people are sharing their work on the web, making it easier to orient yourself when these issues occur.

Simulink allows to analyze and simulate different variables with respect to time in an electric power system, but it is more focused on visual programming On the other hand, ETAP is better designed for static simulation of power systems, offering options and studies in a very more direct and easier to execute.

Pytorch is very, very simple compared to TensorFlow. Simple to install, less dependency issues, and very small learning curve. TensorFlow is very much optimised for robust deployment but very complicated to train simple models and play around with the loss functions. It needs a lot of juggling around with the documentation. The research community also prefers PyTorch, so it becomes easy to find solutions to most of the problems. Keras is very simple and good for learning ML / DL. But when going deep into research or building some product that requires a lot of tweaks and experimentation, Keras is not suitable for that. May be good for proving some hypotheses but not good for rigorous experimentation with complex models.

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info

• Improves the reliability of the electrical system.
• Study of the system operations, allowing a better adjustment of the facilities that are in production.
• Provides results that allow you to select solutions for energy saving.

• The ability to make models as never before
• Being able to control the bias of models was not done before the arrival of Pytorch in our company

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info