v0.5.0 - (10th December 2024)

New Features:

• Learning rate and noise scheduling: Added the possibility to schedule the learning rate and action noise in the learning process. This feature
  enables streamlining the learning progress. Currently, only "linear" decay available by setting the learning_rate_schedule and
  action_noise_schedule in the learning config to "linear". Defaults to no decay if not provided. It decays learning_rate/ noise_dt
  linearly from starting value to 0 over given training_episodes which can be adjusted by the user. The schedule parameters (e.g. end value
  and end fraction) are not adjustable in the config file, but can be set in the code.
• Hydrogen Plant: A new demand side unit representing a hydrogen plant has been added. The hydrogen plant consists of an
  electrolyzer and a seasonal hydrogen storage unit. The electrolyzer converts electricity into hydrogen, which can be
  stored in the hydrogen storage unit and later used.
• Seasonal Hydrogen Storage: A new storage unit representing a seasonal hydrogen storage has been added. The seasonal hydrogen
  storage unit can store hydrogen over long periods and release it when needed. It has specific constraints to avoid charging or
  discharging during off-season or on-season time as well as a target level to be reached at the end of the season.

Improvements:

• Timeseries Performance Optimization: Switched to a custom FastIndex and FastSeries class, which is based on the pandas Series
  but utilizes NumPy arrays for internal data storage and indexing. This change significantly improves the
  performance of read and write operations, achieving an average speedup of 2x to 3x compared to standard
  pandas Series. The FastSeries class retains a close resemblance to the pandas Series, including core
  functionalities like indexing, slicing, and arithmetic operations. This ensures seamless integration,
  allowing users to work with the new class without requiring significant code adaptation.
• Outputs Role Performance Optimization: Output role handles dict data directly and only converts to DataFrame on Database write.
• Overall Performance Optimization: The overall performance of the framework has been improved by a factor of 5x to 12x
  depending on the size of the simulation (number of units, markets, and time steps).

Bugfixes:

• Tutorials: General fixes of the tutorials, to align with updated functionalitites of Assume
• Tutorial 07: Aligned Amiris loader with changes in format in Amiris compare (https://gitlab.com/fame-framework/fame-io/-/issues/203 and https://gitlab.com/fame-framework/fame-io/-/issues/208)
• Powerplant: Remove duplicate Powerplant.set_dispatch_plan() which broke multi-market bidding
• CSV scenario loader: Fixed issue when one extra day was being added to the index, which lead to an error in the simulation when additional data was not available in the input data.
• Market opening schedule: Fixed issue where the market opening was scheduled even though the simulation was ending before the required products. Now the market opening is only scheduled
  if the total duration of the market products plus first delivery time fits before the simulation end.
• Loader fixes: Fixes for PyPSA, OEDS and AMIRIS loaders

v0.4.3 (11th November 2024)

Improvements:

• Documentation: added codespell hook to pre-commit which checks for spelling errors in documentation and code

Bugfixes:

• Simulation: Delete simulation results for same simulation prior to run (as before v0.4.2)

Full Changelog: v0.4.2...v0.4.3

v0.4.2

New Features:

• Residential Components: Added new residential DST components including PV, EV, Heat Pump, and Boiler, now with enhanced docstrings for better usability.
• Modular DST Components: DST components have been converted from functions to classes, improving modularity and reusability.
• Generic Storage Class: Introduced a GenericStorage class for storage components. Specific classes, such as EV and Hydrogen Storage, now inherit from it.
• Storage Learning Strategy: Added a new DRL-based learning strategy for storage units. To use it, set storage_learning in the bidding_EOM column of storage_units.csv. Refer to the StorageRLStrategy documentation for more details.
• Mango 2.x Update: Upgraded to mango 2.x, enabling synchronous world creation. To upgrade an existing environment, run:

  pip uninstall -y mango-agents mango-agents-assume && pip install assume-framework --upgrade
  

• Distributed Simulation Enhancements: Improved distributed simulation for TCP and MQTT, allowing containers to wait for each other during simulations.
• Integrated Optimization with Pyomo and HIGHS Solver: The Pyomo library and HIGHS solver are now installed by default, removing the need to install assume-framework[optimization] separately. The HIGHS solver is used as the default, replacing the older GLPK solver for improved optimization performance and efficiency.

Improvements:

• Documentation: Refined tutorial notebooks and added bug fixes.
• Saving Frequency Logic: Refactored the saving frequency in the WriteOutput class for improved efficiency.

Bug Fixes:

• Solver Compatibility: Addressed undefined solver_options when using solvers other than Gurobi or HIGHS.
• Cashflow Calculation: Corrected cashflow calculations for single-digit orders.
• Simulation Execution: Enabled simulations to synchronize and wait for each other.
• Edge Case Handling: Fixed edge cases in pay_as_clear and pay_as_bid.

New Contributor:

• @HafnerMichael made their first contribution with improvements to cashflow calculations and development of residential DST components.

Full Changelog: v0.4.1...v0.4.2

v0.4.1

v0.4.1 - latest release (8th October 2024)

New Features:

• improve LSTM learning strategy (#382)
• add python 3.12 compatibility (#334)
• manual strategy for interactive market simulation (#403)

Improvements:

• add the ability to define the solver for the optimization-based market clearing inside the param_dict of the config file (#432)
• shallow clone in Jupyter notebooks so that cloning is faster (#433)
• fixes in storage operation bidding (#417)
• update GitHub Actions versions (#402)

Bug Fixes:

• add compatibility with pyyaml-include (#421)
• make complex clearing compatible to RL (#430)
• pin PyPSA to remove DeprecationWarnings for now (#431)

v0.4.0

New Features:

• Market Coupling: Users can now perform market clearing for different market zones with given transmission capacities. This feature
  allows for more realistic simulation of market conditions across multiple interconnected regions, enhancing the accuracy of market
  analysis and decision-making processes. A tutorial on how to use this feature is coming soon.

• Adjust the Framework to Schedule Storing to the Learning Role: This enhancement enables Learning agents to participate in sequential
  markets, such as day-ahead and intraday markets. The rewards are now written after the last market, ensuring that the learning process
  accurately reflects the outcomes of all market interactions. This improvement supports more sophisticated and realistic agent training scenarios.
  A tutorial on how to use this feature is coming soon.

• Multiprocessing: Using a command line option, it is now possible to use run each simulation agent in its own process to speed up larger simulations.
  You can read more about it in :doc:distributed_simulation

• Steel Plant Demand Side Management Unit: A new unit type has been added to the framework, enabling users to model the demand side management
  of a steel plant. This feature allows for more detailed and accurate simulations of industrial energy consumption patterns and market interactions.
  This unit can be configured with different components, such as the electric arc furnace, electrolyzer, and hot storage, to reflect the specific
  characteristics of steel production processes. The process can be optimized to minimize costs or to maximize the available flexibility, depending
  on the user's requirements. A tutorial and detailed documentation on how to use this feature are coming soon.

Improvements:

• Significant speed up of the framework and especially of the learning process
• Separated scenario loader function to improve speed and reduce unrequired operations
• Refactored unit operator by adding a seperate unit operator for learning units
• Enhanced learning output and path handling
• Updated dashboard for better storage view
• Improved clearing with shuffling of bids, to avoid bias in clearing of units early in order book
• Introduced a mechanism to clear the market according to defined market zones while maintaining information about
  individual nodes, enabling the establishment of specific market zones within the energy market and subsequent
  nodal-based markets such as redispatch.
• Added zones_identifier to the configuration file and zone_id to the buses.csv, and refactored the complex market
  clearing algorithm to incorporate zone information, ensuring that bids submitted with a specific node are
  matched to the corresponding market zone.
• If any values in the availability_df.csv file are larger than 1, the framework will now warn the user
  and run a method to normalize the values to [0, 1].
• Examples have been restructed to easier orientation and understanding: example_01.. cover all feature demonstration examples,
  example_02.. cover all learning examples, example_03.. cover all full year examples

Bug Fixes:

• Fix learning when action dimension equals one
• Fixed Tutorial 5
• Correctly calculated timezone offsets
• Improved handling of rejected bids
• Fix the error that exploration mode is used during evaluation
• Fix double dispatch writing
• Fixed complex clearing with pyomo>=6.7
• Resolved various issues with learning and policy saving
• Fixed missing market dispatch values in day-ahead markets
• Added a check for availability_df.csv file to check for any values larger than 1

Other Changes:

• Added closing word and final dashboard link to interoperability tutorial

v0.3.7

What's Changed

• Edit how pyomo markets are imported by @nick-harder in #310
• Add ARM docker platform by @maurerle in #312
• Contract Market with feed in policy and market premium by @maurerle in #248
• Add basic grid visualization by @maurerle in #305
• Pypsa loader by @maurerle in #311
• update grafana docker version to latest by @maurerle in #316
• adjustments to scenario loaders by @maurerle in #317
• set correct compose.yml mount for docker by @maurerle in #320
• This commit prepares assume to integrate proper nodal pricing by @nick-harder in #304
• fix bugs in tutorial 6 by @adamsjohanna in #324
• Add fixed pyomo version to avoid warning by @adamsjohanna in #325
• Add Code of Conduct by @maurerle in #313
• Interoperability tutorial by @maurerle in #323
• increase version to 0.3.7 for latest release by @maurerle in #327

Full Changelog: v0.3.6...v0.3.7

v0.3.6

What's Changed

• update github actions by @maurerle in #296
• use latest github actions versions for codecov too by @maurerle in #297
• Fix tutorial 2 by @nick-harder in #299
• silence output of gurobipy by specifying an env which does not log by @maurerle in #300
• fixes writing market_dispatch and dispatch for other product_types by @maurerle in #301
• Fix datetime warning by @maurerle in #302
• Add a tutorial for the advanced order types and documentation for the complex clearing by @adamsjohanna in #303
• Fixes string conversion of paths by @kim-mskw in #307
• move dmas bidding strategies into try since pyomo is not a required d… by @nick-harder in #308

Full Changelog: v0.3.5...v0.3.6

v0.3.5

Release Notes - v0.3.5

We are thrilled to announce the release of v0.3.5 of ASSUME Framework. This release marks the introduction of the redispatch module, a tool for congestion management, alongside several bug fixes and improvements. Let's delve into the details of the changes:

Redispatch Module Introduction

Congestion Management

In v0.3.5, the introduction of the redispatch module significantly enhances the framework's capabilities in addressing congestion management challenges. This module is equipped to support both cost-based and market-based redispatch strategies, leveraging the PyPSA network to detect and resolve congestion effectively.

To explore its functionality, users can engage with the Example 01d, wherein a Day-Ahead Energy Market and a subsequent Redispatch Market are employed. Initially, the market is cleared using a single bidding zone, followed by a congestion management process. Furthermore, a detailed Jupyter-based tutorial will be made available to facilitate a deeper understanding of the module's application.

Cost-Based and Market-Based Redispatch

The redispatch module offers support for both cost-based and market-based redispatch strategies. This includes the implementation of "pay as bid" and "pay as clear" market methods, empowering users with versatile tools for congestion management.

Detailed Changes

Redispatch v1

Implemented by @nick-harder. @paragpatil39 and @rqussous in PR #279, this significant update introduces the initial version of the redispatch feature, laying the foundation for advanced congestion management.

New Strategies Allocation

@nick-harder's contribution in PR #289 brings about a crucial change in strategy allocation, now utilizing market names instead of product types, enhancing the overall clarity and usability of the framework.

Bug Fixes and Refinements

• Storage Operation Fixes: @adamsjohanna addressed some bugs in storage operations, ensuring smoother functionality (PR #291).
• Removal of Empty Bid Method: In PR #293, @nick-harder eliminated the use of empty bid as a method of bidding strategy, streamlining the bidding process.
• EOM References Cleanup: @nick-harder's contribution in PR #294 involved the removal of hard-coded EOM references from the code base, ensuring a more flexible and maintainable code structure.
• Overall scenario loading and other quality improvements by @maurerle

For a comprehensive list of changes, please refer to the Full Changelog.

We encourage all users to upgrade to v0.3.5 to leverage the latest enhancements and bug fixes. Your feedback is invaluable, and we look forward to hearing about your experiences with these new features.

v0.3

Release Notes - Version 0.3

What's Changed

Features

• Added reuse compliance by @maurerle
• Added Data Request mechanism by @maurerle (#247)
• Added "Open in Collab" to notebooks by @nick-harder (#258)
• Added block order and linked order and respective market clearing mechanism by @adamsjohanna (#269)
• Added MASTR based OEDS loader by @maurerle
• Added AMIRIS Scenario loader by @maurerle

Fixes

• Fixed calculation of marginal cost and output_before by @maurerle (#250)
• Changed buffer add function call by @kim-mskw (#255)
• Adjusted query of reward during training by @nick-harder (#256)
• Fixed calculation of flexible storage bids by @maurerle (#260)
• Fixed RL evaluations by @kim-mskw (#280)
• Fixed usage of license references by @maurerle (#246)

Documentation

• [Tutorial] Added basic tutorial 01 and 02 by @nick-harder (#257)
• [Tutorial] Added Custom Unit and Custom Strategy tutorial by @Manish-Khanra (#262)
• [Tutorial] Added tutorial of EOM and LTM comparison by @maurerle (#265)
• Updated dependencies and installation instructions by @nick-harder (#282)
• Added additional clearing and strategy docs by @maurerle (#283)

Other

• Moved scenario loaders to separate folder by @maurerle (#264)
• Added an automatic assignment of RL units to one RL unit operator by @kim-mskw (#276)
• Improved data_dict usage by @maurerle (#274)

Full Changelog

Full Changelog

v0.2.1

What's Changed

• fix loading learned strategies by @nick-harder in #219
• Workshop dach by @kim-mskw in #218
• distribute current time correctly to agents running in shadow container in different process by @maurerle in #199
• RL Documentation by @kim-mskw in #221
• Add shields badges to readme by @maurerle in #223
• add amiris scenario loader by @maurerle in #224
• fixes for running distributed scenario with mqtt by @maurerle in #222

Full Changelog: v0.2.0...v0.2.1