Bidding in Smart Grid PDAs: Theory, Analysis and Strategy
Authors: Susobhan Ghosh, Sujit Gujar, Praveen Paruchuri, Easwar Subramanian, Sanjay Bhat1974-1981
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically show that MDPLCPBS follows the equilibrium strategy for double auctions that we previously analyze. In addition, we benchmark our strategy against the baseline and the state-of-the-art bidding strategies for the Power TAC wholesale market PDAs, and show that MDPLCPBS outperforms most of them consistently. Experimental Analysis We first analyze if our proposed bidding strategy, MDPLCPBS, follows the Nash Equilibrium derived above, and then benchmark it against the baseline and competing stateof-the-art strategies. |
| Researcher Affiliation | Collaboration | 1Machine Learning Lab, IIIT Hyderabad, India susobhan.ghosh@research.iiit.ac.in, {sujit.gujar, praveen.p}@iiit.ac.in 2Tata Consultancy Services, TCS Innovation Labs, Hyderabad, India {easwar.subramanian, sanjay.bhat}@tcs.com |
| Pseudocode | Yes | Algorithm 1 MDPLCPBS |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code, nor does it include a link to a code repository. |
| Open Datasets | No | The paper utilizes the Power TAC simulator and generates data within it for experiments (e.g., 'We draw θB U[40, 80] and θS U[40, 80]'), but it does not refer to or provide access information for a publicly available or open dataset used for training. |
| Dataset Splits | No | The paper describes its experimental setup including batches and sets of games for simulation ('We run two batches of experiments, with 30 games in each set of the batch, for 5 sets per batch.'), but it does not specify explicit train/validation/test dataset splits with percentages or sample counts. |
| Hardware Specification | No | The paper describes experiments run in the Power TAC simulation environment, but it does not specify any hardware details such as GPU or CPU models, or other computer specifications used for these experiments. |
| Software Dependencies | No | The paper mentions various software components and agents like 'Power TAC', 'REPTree', 'Tac Tex', 'MCTS', 'ZI', and 'ZIP', but it does not provide specific version numbers for any of these or other ancillary software dependencies. |
| Experiment Setup | Yes | We draw θB U[40, 80] and θS U[40, 80]", "energy demand to be the previous slot s tariff market net demand", "MCTS-dyn-C2 version with 10000 iterations", "The fraction set is given by {0.25, 0.5, 0.75, 1}", "The mean μ taken from the limit price predicted by the MDP in Tac Tex. The profit margin m is set to 1% of μ, resulting in the initial bid price to be p = μ 1.01. If the bid fails, the next bid price is incremented by 10% of μ. |