VidyutVanika21: An Autonomous Intelligent Broker for Smart-grids
Authors: Sanjay Chandlekar, Bala Suraj Pedasingu, Easwar Subramanian, Sanjay Bhat, Praveen Paruchuri, Sujit Gujar
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this paper, we describe the design of one such intelligent energy broker called Vidyut Vanika21 (VV21) and analyze its performance using a simulation platform called Power TAC (Power Trading Agent Competition)... We further demonstrate the efficacy of the retail and wholesale strategies of VV21 in Power TAC 2021 finals and through several controlled experiments. |
| Researcher Affiliation | Collaboration | Sanjay Chandlekar1 , Bala Suraj Pedasingu2 , Easwar Subramanian2 , Sanjay Bhat2 , Praveen Paruchuri1 and Sujit Gujar1 1International Institute of Information Technology (IIIT), Hyderabad, India 2TCS Innovation Labs, Hyderabad, India |
| Pseudocode | Yes | Algorithm 1 shows the working of VV21 RM. Below We detail TE and TD. [...] Algorithm 2 shows the working of TE [...] Algorithm 3 Tariff Designer(avg Price, power Type) [...] The wholesale module of VV21 (VV21 WM), as explained in Algorithm 4 [...] Algorithm 5 outlines the details of SCF. [...] Algorithm 6 describes the working of BG. |
| Open Source Code | No | The paper does not provide an explicit statement or link for open-sourcing the code. |
| Open Datasets | No | The Power Trading Agent Competition (Power TAC) [Ketter et al., 2020] provides an efficient simulation of real-world smart grids... before starting a game, a two-week bootstrap simulation exercise is arranged in which the DU acts as the default broker. The output of this boot period, which includes identities and consumption data of all retail customers, average clearing prices in the wholesale market, weather and calendar information, is made known to the brokers. |
| Dataset Splits | No | The paper describes the simulation setup and data generation within the Power TAC environment, but does not provide specific train/validation/test dataset splits of a fixed, publicly accessible dataset. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory) used for running experiments. |
| Software Dependencies | No | With the help of Gambit [Mc Kelveya et al., 2014], we found that the above game has a unique Nash equilibrium |
| Experiment Setup | Yes | we decided to keep HB around 45% for 7 and 5 player configurations and 60% for 3 player configurations. The values of MB and LB are set to 60% and 40% of the HB. |