deep-daya Goto Github PK

analysis_foodsafetyscores

Project 1- Data 100- Analysis of Restaurant Food Safety Scores

batch-reinforcement-learning

This project finds the best policy for three different Markov decision processes given sampled transitions, each consisting of a state, action, reward, and next state without exploration

bayesian-structure-learning

Project to find Bayesian Network Structures that best fit given some data based on the Bayesian Score of the graph.

data-science-projects

Data Science Projects covering Spam Ham Email Classification, Analysis of Donald Trump's Tweets, EDA, Sampling Error, Gradient Descent, PCA, Logistic Regression and More

dcfc_battery_optimization

docs

Source code for the Streamlit Python library documentation

eleng134-uc-berkeley

energy-conversion-principles-projects

Projects related to modeling Solar Hybrid Power, Wind Turbines, Solar Collector Systems, and Gas Turbine Evaluaiton

energy_systems_and_control-projects

Projects related to Energy Systems and Control covering Flight Path Optimization, Battery Modeling, State Estimation, Optimal Economic Dispatch of Distribution, Forecasting Electricity Power Consumption, Optimal PHEV Energy Management

grid_scale_energy_storage_q_learning

Final Project for AA 228: Decision-Making under Uncertainty Abstract: Grid-scale energy storage systems (ESSs) are capable of participating in multiple grid applications, with the potential for multiple value streams for a single system, termed "value-stacking". This paper introduces a framework for decision making, using reinforcement learning to analyze the financial advantage of value-stacking grid-scale energy storage, as applied to a single residential home with energy storage. A policy is developed via Q-learning to dispatch the energy storage between two grid applications: time-of-use (TOU) bill reduction and energy arbitrage on locational marginal price (LMP). The performance of the dispatch resulting from this learned policy is then compared to several other dispatch cases: a baseline of no dispatch, a naively-determined dispatch, and the optimal dispatches for TOU and LMP separately. The policy obtained via Q-learning successfully led to the lowest cost, demonstrating the financial advantage of value-stacking.

java-projects

keras

Deep Learning for humans

ml_electricity_demand_us_covid19

tetrahedral_occupation_li_inorganic_crystals

Final Project for Data100: Providing insight for tendency of elements to occupy a given tetrahedral site in inorganic crystals

wind-temperature-modeling

CS 231N Project