Electrika | Devpost

Inspiration

As Dean Kumar stated, the factors enabling clean energy are dropping in cost with every passing year. Clean energy is the future, but using the technology already available today we are able to save costs for consumers.

What it does

The overall objective of our project is to develop a cleaner, more reliable, resilient, and affordable electric system. The greatest challenge facing electric distribution is responding to rapidly changing customer needs for electricity. For example, having the ability to monitor and influence each customer’s usage, in real time, could enable distribution operators to better match supply with demand, thus boosting asset utilization, improving service quality, and lowering costs. More complete integration of distributed energy and demand-side management resources into the distribution system could enable customers to implement their own tailored solutions, thus boosting profitability and quality of life.

Customer activities, needs, wants, and desires, as well as the weather, shape patterns of electricity use, which vary by the time of day and season of the year. These patterns typically result in high concentrations of electricity use in “peak periods.” The larger the peak period, the greater the amount of electric resources that will be needed to meet it, including distribution, transmission, and generation assets. The national average load factor (the degree to which physical facilities are being utilized) is about 55%. This means that electric system assets, on average, are used about half the time. As a result, steps taken by customers to reduce their consumption of electricity during peak periods can measurably improve overall electric system efficiency and economics.

The price of electricity in any given area is governed by complex dynamics, driven by many factors including day-to-day and seasonal variation in demand, seasonal variation in temperature, availability of electricity from surrounding regions, and cascade effects when plants are shut down. Electrika takes into account all of these complex variables to model generation and load data and using a predictive artificial neural nets algoraithm determines the future condition of the electric grid. This empowers the consumers to make more informed decisions in using electricity ( turning on their washers/dryers for an example) may be at times when the grid is not stressed and this in turn makes the electric grid more resilient and robust.

How we built it

In our model, which we refer to as a dynamic supply-demand model, we simultaneously capture electricity price and usage time series.

This model is built on the basic economic principle that on each day, the price and quantity in a competitive market can be determined as the intersection of supply and demand curves.

The model incorporates temperature, seasonality effects and gas-availability as factors by expressing the supply and demand curves as explicit functions of these factors.

Since the model is nonlinear and non-Gaussian, and the supply and demand curves are not directly observable, traditional methods for parameter estimation and forecasting are not applicable.

Hence, we are using artificial neural networks in this context. We have chosen MATLAB as our platform of choice. The final model is very accurate, with the artificial neural network handling power system analysis and modelling.

Challenges we ran into

MATLAB is trickier to integrate than Python, so communicating through Node proved difficult.

Accomplishments that I'm proud of

The model requires quite a significant amount of data to regularly train on, and as such cannot be loaded onto user phones. Instead, the MATLAB model lives on a remote Windows server and responds to requests from the application handled via a Node.js server.

We are proud to have figured out this solution.

What we learned

We learned quite a bit about app development and inter-service communication by integrating MATLAB with Node.js.

What's next for Electrika

Well sky is the limit for Elektrika. In future we plan to fully integrate the app with the usage pattern of all 50 states of United States and come up with our pricing algorithm by working with all the regional stakeholders who supply electricity. We also have an idea to integrate the PV systems with the app. For example, the app should be also able to tell how an user can install PV arrays on his house based on his location and may be help the grid by supplying some amount of surplus electricity and for doing so the user must be given some incentive which again the app should be able to predict to encourage two way communication between the user and the grid. We plan to work on all these stuffs in the near future and make this an all inclusive go to app for electricity.

Using predictive capabilities would enable functionality similar to the Amazon AWS model of “spot instance” bidding, for electricity. For periods where usage is predicted to be low, electricity would be permitted to be drawn.