Energy Supply Chain Optimization and Prescriptive Analytics

The ever-increasing complexity of the global marketplace is making optimization even more important to organizations. With easier access to such powerful tools, more companies are turning to optimization models to help make crucial decisions including tasks such as hedging strategies, storage management, allocating inventory, selecting transportation routes, product optionality, blending and optimizing portfolios.

All the functions in a company are usually aimed at a single goal – to make more money by selling more products at a higher price than what the products cost. However, this goal is often forgotten because the way they operate is so myopic and siloed.

Each portion of the business has its own metrics and, all too often, narrowly pursues them to the detriment of the company. Supply chain strives for increasing demand forecast accuracy or reducing lead-times. Storage and processing aims to maximize its capacity utilization. Procurement wants to reduce the cost of raw materials. 

Unfortunately, much optimization is done in excel and focused on solving a simple set of decision variables within a single functional silo. None of the models are integrated despite the fact that these critical planning decisions are most certainly inter-related in the real-world. After enough practice it is easy enough for an Excel expert to get one optimization model working but maintaining the model over time with all the changing variables becomes too costly. Any high level optimization requires a compilation of output from various spreadsheets and applications across the enterprise.

…This is a sample of how natural gas supply chain is currently optimized

The Growing Necessity for Advanced Analytics in the Energy Supply Chain

The science of business analytics has and will continue to evolve at exponential speeds. This evolution is due to: (1) the availability of more and more data, and (2) the increasing strength and computing power of the various tools and capabilities. Advanced analytics will differentiate companies in the marketplace. “Those who do not integrate advanced analytics in their everyday operations run the risk of falling behind their competition.

The driving forces behind analytics in the energy supply chain have to do with:

 ·       Unprecedented data availability

·       Intense competition

·       Technological advancements

·       Constant search for cost reduction and revenue growth

·       Changing customer dynamics

·       Expanding customer expectations

·       Stringent regulatory requirements

·       Geopolitical factors

Analytics are increasingly becoming necessary not only report on past performance but also digest large quantities of information to predict the future and recommend actions in order to help analysts see the forest for the trees and avoid being locked into current dogma.

 Analytics capabilities

Energy Supply Chain Optimization and Prescriptive Analytics

Prescriptive analytics not only anticipates what will happen and when it will happen, but also why it will happen

Gartner defines prescriptive analytics as “the combination of optimization, rules and data that enhances analytics by suggesting the optimal way to handle a future situation and can be applied to strategic, tactical and operational decisions.” In other words, while all analytics approaches aim to improve decision making, only prescriptive analytics recommends (i.e. “prescribes”) the best path. [1]

Prescriptive analytics uses metaheuristic optimization solver algorithms to minimize or maximize some objective while meeting global business constraints.

Prescriptive analytics technologies transform the trading and supply chain management function by providing forward-looking insights; aligning the enterprise to the optimal course of action; quantifying trade-offs fast and with a low cost of ownership; and increasing the ability to communicate and collaborate across functions. These transformative characteristics lead to significant performance improvements.

Most businesses are a complex set of nonlinear relationships with constraints across demand, supply and financials. Senior management’s job is to gain clarity and determine the actions to be taken at all levels. They must determine where to allocate capital; decide which products to fund and cut; establish policies across the business; and create operational schedules. These actions all have the same purpose — to maximize the company’s primary objective.

Prescriptive analytics is not statistical modeling; it is deterministic. The purpose is to quantify trade-offs and understand the impact of various positions before action is taken. With the ability to apply optimization to these scenarios, trading executives can discover significant value.

Prescriptive analytics automatically synthesizes big data, multiple disciplines of mathematical sciences and computational sciences, and business rules, to make predictions and then suggests decision options to take advantage of the predictions. It can continually take in new data to re-predict and re-prescribe, thus automatically improving prediction accuracy and prescribing better decision options

Companies gain tremendous value when applying prescriptive analytics to make better decisions. First, users gain accuracy by modeling business processes and constraints in greater detail. Second, the decisions improve as the software will deal with complexity to find a better answer and support what-if analyses. Finally, the business gains agility by spending time analyzing only the best scenarios and through deeper organizational learning. These themes — accuracy by modeling, software to handle business complexities and business gains by analyzing best scenarios — are central to an organization’s finance function. Other departments often look to the trading function for its expertise in these areas.

Prescriptive analytics automatically synthesizes big data, mathematical sciences, business rules, and machine learning to make predictions and then suggests decision options to take advantage of the predictions. 

Prescriptive analytics goes beyond predicting future outcomes by also suggesting actions to benefit from the predictions and showing the decision maker the implications of each decision option.[2]

Prescriptive analytics not only anticipates what will happen and when it will happen, but also why it will happen. 

Further, prescriptive analytics can suggest decision options on how to take advantage of a future opportunity or mitigate a future risk and illustrate the implication of each decision option. In practice, prescriptive analytics can continually and automatically process new data to improve prediction accuracy and provide better decision options.

Prescriptive analytics synergistically combines data, business rules, and mathematical models. The data inputs to prescriptive analytics may come from multiple sources, internal (inside the organization) and external (social media, et al.). The data may also be structured, which includes numerical and categorical data, as well as unstructured data, such as text, images, audio, and video data, including big data. Business rules define the business process and include constraints, preferences, policies, best practices, and boundaries. Mathematical models are techniques derived from mathematical sciences and related disciplines including applied statistics, machine learning, operations research, and natural language processing. 

Power and natural gas prices fluctuate dramatically depending on supply, demand, geo-politics and weather conditions. Natural gas producers have a keen interest in more accurately predicting gas prices so that they can lock in favorable terms while hedging downside risk. Prescriptive analytics can accurately predict prices by modeling internal and external variables simultaneously and also provide decision options and show the impact of each decision option.

For example, prescriptive analytics can benefit energy supply chain strategic planning by using analytics to leverage operational and supply and consumption data combined with data of external factors such as market prices, supply and demand, congestion, weather, exchange rates and volatility.

Another example is energy and utilities. Natural gas prices fluctuate dramatically depending upon supply, demand, econometrics, geo-politics, and weather conditions. Gas producers, transmission (pipeline) companies and utility firms have a keen interest in more accurately predicting gas prices so that they can lock in favorable terms while hedging downside risk. Prescriptive analytics can accurately predict prices by modeling internal and external variables simultaneously and also provide decision options and show the impact of each decision option.