From trading strategies to outage planing, we optimize you plant to peak efficiency.

Power Generation

From optimizing trading strategies in deregulated energy markets to synchronizing outage planning with operational data, BKO helps power and utilities sectors create more value.

Wholesale Power Generation Dispatch

Dispatching power plant generation optimally enables wholesale generators to maximize their revenue. Machine learning models of power plant performance enable optimized trading strategies in deregulated energy markets.

Icon - Elements Webflow Library - BRIX Templates

Synchronizing Outage Planning with Operational Data

Using Aveva PI operational data greatly improves outage planning. Plant managers can use machine learning applications to better forecast asset outage spend and duration. Engine degradation and equipment events can be predicted and monitored by using both supervised and unsupervised machine learning techniques.

Icon - Elements Webflow Library - BRIX Templates

Renewable Resources Optimization

Forecasting power generation from renewable assets including wind, solar and storage can get complicated. We can help renewable operators optimize their asset dispatch by building deep learning and deep reinforcement learning algorithms that outperform traditional methods.

Icon - Elements Webflow Library - BRIX Templates


Particularly useful for generation asset owners who don’t want to hire control engineers, have limited access to them, or cannot justify the cost, based on the asset size. One of our engineers can monitor multiple assets from multiple owners, achieving significant benefits of scale.Services fall into three broad categories:

- Monitoring for anomaly detection.
- Monitoring for maintenance optimization.
- Monitoring for performance improvement and cost reduction.

BKO Services will work with any client-side hardware or software, bringing you the benefits that come from monitoring by skilled engineers, analysis using Machine Learning, and reporting from data stored in Modern Real-Time databases, and Cloud technologies.

Icon - Elements Webflow Library - BRIX Templates

Monitoring for Anomaly detection

Our engineers perform anomaly detection using in-house trained predictive models to provide early warning alerts and diagnostic guidance to our customers. In a complex industry setting such as power plants, aviation etc. Anomaly detection is critical to raise alarms beforehand to prevent significant damages and mishaps. Here, we propose a novel approach of using a multimodal neural network-based autoencoder. These detected anomalies generally tend to be more accurate and robust than anomalies detected by a single data source as latent representations capture inter-dependencies between different parts of the system through those multiple data sources.

Icon - Elements Webflow Library - BRIX Templates
Case Study


Customer Overview

TexGen provides approximately 2,300 megawatts of efficient and dependable gas-powered electricity, enough to power over 2 million Texan homes. With four power plants operating near Houston and Dallas, TexGen offers electricity that can be fine-tuned to match grid needs, guaranteeing a stable and robust power grid throughout the year.

Customer Challenge

TexGen was experiencing less than optimal results in four main areas:

  • Data from various equipment and systems was not integrated causing inefficient flow of information.
  • Machine maintenance schedules needed updating and data was needed to choose optimal servicing times and assess post-maintenance performance.
  • TexGen’s personnel lacked the knowledge and experience to effectively use dashboards and interpret results.
  • A lack of monitoring data led to leadership’s uncertainty in accurately gauging trends over the past year and predicting long-term patterns of performance.
  • TexGen expressed the need for comprehensive monitoring of fuel consumption and NOx emissions. This requirement reflects their commitment to environmental responsibility and efficient fuel utilization.


BKO took a holistic approach in meeting the four challenges expressed by TexGen. Using Seeq was ideal due to its ability to solve multiple problems with some core implementations.

We set up online dashboard monitoring and parameter control in Seeq. Then we implemented a live health score dashboard that assesses the daily and weekly performance of gas turbines, steam turbines, and condensers. 

Additionally, our service extended to one power plant, where we implemented NOx monitoring and established an automated email notification system. Using Seeq’s advanced capabilities BKO created online dashboard monitoring displays which included and are not limited to NOx monitoring.

This comprehensive approach offered real-time insights into equipment performance and enabled optimal operational efficiency leading to accelerated outcomes. The data also enabled proactive maintenance and provided real data to inform leadership decisions.

As a final step, BKO spent time training the engineers and other relevant personnel to be proficient in the use of Seeq in TexGen’s operations.

"Using Seeq’s advanced capabilities BKO created online dashboard monitoring displays which included and are not limited to NOx monitoring. In order to ensure that plant operators are informed about elevated NOx emissions automated email notifications were established in addition to the dashboard monitoring. BKO recognizes the need for real time data but also the necessity of notification when performing plant operations which was made possible with Seeq."


An examination of three years of data enabled us to identify problems with two units, enabling TexGen to enhance operational efficiency and  recover an additional 10 MW at base load.TexGen engineers are fully aware and trained in the awesome power of Seeq software.Ongoing monthly reports maintain plant optimization by providing the latest data on plant performance and equipment functionality.Leadership decisions are now based on up-to-date and accurate data leading to greater insights on performance.

"TexGen now ensures swift alerting for the operations team in case of elevated NOx emissions enabling rapid response and compliance with environmental regulations. NOx monitoring dashboards and notifications ensured TexGen the ability to adhere to environmental standards. Seeq provided a platform to deliver actionable insights in pursuit of cleaner operations."

In solving TexGen’s challenges, BKO continues to utilize Seeq as a powerful tool, enabling seamless data analysis and predictive maintenance. This continuous service not only reinforces TexGen's commitment to operational excellence but also ensures that their operations remain optimized and efficient, guaranteeing a reliable and resilient power grid for Texas.

Case Study

Forecasting & Optimal Power Generation
in Deregulated Markets


A large independent power producer wanted to improve its strategy of power generation with regards to the dynamic market where energy commodities are bought and sold. The energy commodity market includes the process of investing in or speculating on the price direction of energy markets such as oil, gas and renewables. Optimizing forecasts leads to better strategies that increase future commercial value of their power plants. A typical plant can have around 300 different generation points, each with its own profit margin. Those 300 daily offers are tied to the operational profile of the equipment and vary with weather and equipment changes. Until now our client was relying on no more than outdated plot curves on a spreadsheet. There was a clear opportunity to vastly improve the overall profit from power generation by closely monitoring the complicated, but observable, system of generation points while quickly reacting to external market behavior.


Deregulated markets are extremely efficient at providing value and robustness. They achieve this by offering more flexibility for smaller energy producers, increasing competition, which then leads to improved efficiency and lower costs. Another benefit of deregulated energy markets is that they typically emerge as a distributed network of power generation. The distribution increases market robustness in handling failure and shutdowns.Modern power plants themselves are also impressive marvels of engineering, extremely efficient at achieving a determined goal. In a deregulated power market, plants can offer both their generation capabilities and costs to a clearing house called Day Ahead Market (DAM). To address the inherent complexity, we created a power generation marketing and planning system for each unique plant.

The solution centered around a powerful machine learning model:

machine learning model that learned actionable representations of each plant to forecast into the next day. The end result was a robust process that improved the enterprise financial goals through optimized power plant dispatching and generation planning.

This consisted of building:

  • A machine learning + thermodynamics simulation to create a digital twin representation of each plant's capabilities.
  • An interface for plant operators to forecast future generation capabilities based on local weather forecasts.

Forecast results are then shared with energy dispatchers to monetize predicted capabilities.